Merge tag 'pull-loongarch-20230506' of https://gitlab.com/gaosong/qemu into staging

Add LoongArch LSX instructions.

# -----BEGIN PGP SIGNATURE-----
#
# iLMEAAEIAB0WIQS4/x2g0v3LLaCcbCxAov/yOSY+3wUCZFXxGwAKCRBAov/yOSY+
# 39EoA/0Uy2DPz6g7J5+9tcIRk9jLrp36aYQJ9J8zRJd226YFvHSfiBWSIteMFOEX
# Z0Jx1bL6N97KK/HA74Nx++x0kVuplEGp1s5cO/odL3gYy8RaJm23p9iaDa0D/UaB
# ygLvXtuzN4unDFP5EF/wa9zRkDb7qX2iBBvc8OIal7eT4dDX+g==
# =gyVU
# -----END PGP SIGNATURE-----
# gpg: Signature made Sat 06 May 2023 07:18:03 AM BST
# gpg:                using RSA key B8FF1DA0D2FDCB2DA09C6C2C40A2FFF239263EDF
# gpg: Good signature from "Song Gao <m17746591750@163.com>" [unknown]
# gpg: WARNING: This key is not certified with a trusted signature!
# gpg:          There is no indication that the signature belongs to the owner.
# Primary key fingerprint: B8FF 1DA0 D2FD CB2D A09C  6C2C 40A2 FFF2 3926 3EDF

* tag 'pull-loongarch-20230506' of https://gitlab.com/gaosong/qemu: (45 commits)
  hw/intc: don't use target_ulong for LoongArch ipi
  target/loongarch: CPUCFG support LSX
  target/loongarch: Use {set/get}_gpr replace to cpu_fpr
  target/loongarch: Implement vldi
  target/loongarch: Implement vld vst
  target/loongarch: Implement vilvl vilvh vextrins vshuf
  target/loongarch: Implement vreplve vpack vpick
  target/loongarch: Implement vinsgr2vr vpickve2gr vreplgr2vr
  target/loongarch: Implement vbitsel vset
  target/loongarch: Implement vfcmp
  target/loongarch: Implement vseq vsle vslt
  target/loongarch: Implement LSX fpu fcvt instructions
  target/loongarch: Implement LSX fpu arith instructions
  target/loongarch: Implement vfrstp
  target/loongarch: Implement vbitclr vbitset vbitrev
  target/loongarch: Implement vpcnt
  target/loongarch: Implement vclo vclz
  target/loongarch: Implement vssrlrn vssrarn
  target/loongarch: Implement vssrln vssran
  target/loongarch: Implement vsrlrn vsrarn
  ...

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

hw/intc/loongarch_ipi.c

@@ -50,7 +50,7 @@ static uint64_t loongarch_ipi_readl(void *opaque, hwaddr addr, unsigned size)
     return ret;
 }
 
-static void send_ipi_data(CPULoongArchState *env, target_ulong val, target_ulong addr)
+static void send_ipi_data(CPULoongArchState *env, uint64_t val, hwaddr addr)
 {
     int i, mask = 0, data = 0;
 

linux-user/loongarch64/signal.c

@@ -128,7 +128,7 @@ static void setup_sigframe(CPULoongArchState *env,
 
     fpu_ctx = (struct target_fpu_context *)(info + 1);
     for (i = 0; i < 32; ++i) {
-        __put_user(env->fpr[i], &fpu_ctx->regs[i]);
+        __put_user(env->fpr[i].vreg.D(0), &fpu_ctx->regs[i]);
     }
     __put_user(read_fcc(env), &fpu_ctx->fcc);
     __put_user(env->fcsr0, &fpu_ctx->fcsr);
@@ -193,7 +193,7 @@ static void restore_sigframe(CPULoongArchState *env,
         uint64_t fcc;
 
         for (i = 0; i < 32; ++i) {
-            __get_user(env->fpr[i], &fpu_ctx->regs[i]);
+            __get_user(env->fpr[i].vreg.D(0), &fpu_ctx->regs[i]);
         }
         __get_user(fcc, &fpu_ctx->fcc);
         write_fcc(env, fcc);

target/loongarch/cpu.c

@@ -52,6 +52,7 @@ static const char * const excp_names[] = {
     [EXCCODE_FPE] = "Floating Point Exception",
     [EXCCODE_DBP] = "Debug breakpoint",
     [EXCCODE_BCE] = "Bound Check Exception",
+    [EXCCODE_SXD] = "128 bit vector instructions Disable exception",
 };
 
 const char *loongarch_exception_name(int32_t exception)
@@ -187,6 +188,7 @@ static void loongarch_cpu_do_interrupt(CPUState *cs)
     case EXCCODE_FPD:
     case EXCCODE_FPE:
     case EXCCODE_BCE:
+    case EXCCODE_SXD:
         env->CSR_BADV = env->pc;
         QEMU_FALLTHROUGH;
     case EXCCODE_ADEM:
@@ -386,6 +388,7 @@ static void loongarch_la464_initfn(Object *obj)
     data = FIELD_DP32(data, CPUCFG2, FP_SP, 1);
     data = FIELD_DP32(data, CPUCFG2, FP_DP, 1);
     data = FIELD_DP32(data, CPUCFG2, FP_VER, 1);
+    data = FIELD_DP32(data, CPUCFG2, LSX, 1),
     data = FIELD_DP32(data, CPUCFG2, LLFTP, 1);
     data = FIELD_DP32(data, CPUCFG2, LLFTP_VER, 1);
     data = FIELD_DP32(data, CPUCFG2, LAM, 1);
@@ -656,7 +659,7 @@ void loongarch_cpu_dump_state(CPUState *cs, FILE *f, int flags)
     /* fpr */
     if (flags & CPU_DUMP_FPU) {
         for (i = 0; i < 32; i++) {
-            qemu_fprintf(f, " %s %016" PRIx64, fregnames[i], env->fpr[i]);
+            qemu_fprintf(f, " %s %016" PRIx64, fregnames[i], env->fpr[i].vreg.D(0));
             if ((i & 3) == 3) {
                 qemu_fprintf(f, "\n");
             }

target/loongarch/cpu.h

@@ -8,6 +8,7 @@
 #ifndef LOONGARCH_CPU_H
 #define LOONGARCH_CPU_H
 
+#include "qemu/int128.h"
 #include "exec/cpu-defs.h"
 #include "fpu/softfloat-types.h"
 #include "hw/registerfields.h"
@@ -54,6 +55,10 @@ FIELD(FCSR0, CAUSE, 24, 5)
     do { \
         (REG) = FIELD_DP32(REG, FCSR0, CAUSE, V); \
     } while (0)
+#define UPDATE_FP_CAUSE(REG, V) \
+    do { \
+        (REG) |= FIELD_DP32(0, FCSR0, CAUSE, V); \
+    } while (0)
 
 #define GET_FP_ENABLES(REG)    FIELD_EX32(REG, FCSR0, ENABLES)
 #define SET_FP_ENABLES(REG, V) \
@@ -241,6 +246,24 @@ FIELD(TLB_MISC, ASID, 1, 10)
 FIELD(TLB_MISC, VPPN, 13, 35)
 FIELD(TLB_MISC, PS, 48, 6)
 
+#define LSX_LEN   (128)
+typedef union VReg {
+    int8_t   B[LSX_LEN / 8];
+    int16_t  H[LSX_LEN / 16];
+    int32_t  W[LSX_LEN / 32];
+    int64_t  D[LSX_LEN / 64];
+    uint8_t  UB[LSX_LEN / 8];
+    uint16_t UH[LSX_LEN / 16];
+    uint32_t UW[LSX_LEN / 32];
+    uint64_t UD[LSX_LEN / 64];
+    Int128   Q[LSX_LEN / 128];
+}VReg;
+
+typedef union fpr_t fpr_t;
+union fpr_t {
+    VReg  vreg;
+};
+
 struct LoongArchTLB {
     uint64_t tlb_misc;
     /* Fields corresponding to CSR_TLBELO0/1 */
@@ -253,7 +276,7 @@ typedef struct CPUArchState {
     uint64_t gpr[32];
     uint64_t pc;
 
-    uint64_t fpr[32];
+    fpr_t fpr[32];
     float_status fp_status;
     bool cf[8];
 
@@ -400,6 +423,7 @@ static inline int cpu_mmu_index(CPULoongArchState *env, bool ifetch)
 #define HW_FLAGS_PLV_MASK   R_CSR_CRMD_PLV_MASK  /* 0x03 */
 #define HW_FLAGS_CRMD_PG    R_CSR_CRMD_PG_MASK   /* 0x10 */
 #define HW_FLAGS_EUEN_FPE   0x04
+#define HW_FLAGS_EUEN_SXE   0x08
 
 static inline void cpu_get_tb_cpu_state(CPULoongArchState *env,
                                         target_ulong *pc,
@@ -410,6 +434,7 @@ static inline void cpu_get_tb_cpu_state(CPULoongArchState *env,
     *cs_base = 0;
     *flags = env->CSR_CRMD & (R_CSR_CRMD_PLV_MASK | R_CSR_CRMD_PG_MASK);
     *flags |= FIELD_EX64(env->CSR_EUEN, CSR_EUEN, FPE) * HW_FLAGS_EUEN_FPE;
+    *flags |= FIELD_EX64(env->CSR_EUEN, CSR_EUEN, SXE) * HW_FLAGS_EUEN_SXE;
 }
 
 void loongarch_cpu_list(void);

target/loongarch/disas.c

@@ -21,11 +21,21 @@ static inline int plus_1(DisasContext *ctx, int x)
     return x + 1;
 }
 
+static inline int shl_1(DisasContext *ctx, int x)
+{
+    return x << 1;
+}
+
 static inline int shl_2(DisasContext *ctx, int x)
 {
     return x << 2;
 }
 
+static inline int shl_3(DisasContext *ctx, int x)
+{
+    return x << 3;
+}
+
 #define CSR_NAME(REG) \
     [LOONGARCH_CSR_##REG] = (#REG)
 
@@ -784,3 +794,904 @@ PCADD_INSN(pcaddi)
 PCADD_INSN(pcalau12i)
 PCADD_INSN(pcaddu12i)
 PCADD_INSN(pcaddu18i)
+
+#define INSN_LSX(insn, type)                                \
+static bool trans_##insn(DisasContext *ctx, arg_##type * a) \
+{                                                           \
+    output_##type(ctx, a, #insn);                           \
+    return true;                                            \
+}
+
+static void output_cv(DisasContext *ctx, arg_cv *a,
+                        const char *mnemonic)
+{
+    output(ctx, mnemonic, "fcc%d, v%d", a->cd, a->vj);
+}
+
+static void output_vvv(DisasContext *ctx, arg_vvv *a, const char *mnemonic)
+{
+    output(ctx, mnemonic, "v%d, v%d, v%d", a->vd, a->vj, a->vk);
+}
+
+static void output_vv_i(DisasContext *ctx, arg_vv_i *a, const char *mnemonic)
+{
+    output(ctx, mnemonic, "v%d, v%d, 0x%x", a->vd, a->vj, a->imm);
+}
+
+static void output_vv(DisasContext *ctx, arg_vv *a, const char *mnemonic)
+{
+    output(ctx, mnemonic, "v%d, v%d", a->vd, a->vj);
+}
+
+static void output_vvvv(DisasContext *ctx, arg_vvvv *a, const char *mnemonic)
+{
+    output(ctx, mnemonic, "v%d, v%d, v%d, v%d", a->vd, a->vj, a->vk, a->va);
+}
+
+static void output_vr_i(DisasContext *ctx, arg_vr_i *a, const char *mnemonic)
+{
+    output(ctx, mnemonic, "v%d, r%d, 0x%x", a->vd, a->rj, a->imm);
+}
+
+static void output_vr_ii(DisasContext *ctx, arg_vr_ii *a, const char *mnemonic)
+{
+    output(ctx, mnemonic, "v%d, r%d, 0x%x, 0x%x", a->vd, a->rj, a->imm, a->imm2);
+}
+
+static void output_rv_i(DisasContext *ctx, arg_rv_i *a, const char *mnemonic)
+{
+    output(ctx, mnemonic, "r%d, v%d, 0x%x", a->rd, a->vj,  a->imm);
+}
+
+static void output_vr(DisasContext *ctx, arg_vr *a, const char *mnemonic)
+{
+    output(ctx, mnemonic, "v%d, r%d", a->vd, a->rj);
+}
+
+static void output_vvr(DisasContext *ctx, arg_vvr *a, const char *mnemonic)
+{
+    output(ctx, mnemonic, "v%d, v%d, r%d", a->vd, a->vj, a->rk);
+}
+
+static void output_vrr(DisasContext *ctx, arg_vrr *a, const char *mnemonic)
+{
+    output(ctx, mnemonic, "v%d, r%d, r%d", a->vd, a->rj, a->rk);
+}
+
+static void output_v_i(DisasContext *ctx, arg_v_i *a, const char *mnemonic)
+{
+    output(ctx, mnemonic, "v%d, 0x%x", a->vd, a->imm);
+}
+
+INSN_LSX(vadd_b,           vvv)
+INSN_LSX(vadd_h,           vvv)
+INSN_LSX(vadd_w,           vvv)
+INSN_LSX(vadd_d,           vvv)
+INSN_LSX(vadd_q,           vvv)
+INSN_LSX(vsub_b,           vvv)
+INSN_LSX(vsub_h,           vvv)
+INSN_LSX(vsub_w,           vvv)
+INSN_LSX(vsub_d,           vvv)
+INSN_LSX(vsub_q,           vvv)
+
+INSN_LSX(vaddi_bu,         vv_i)
+INSN_LSX(vaddi_hu,         vv_i)
+INSN_LSX(vaddi_wu,         vv_i)
+INSN_LSX(vaddi_du,         vv_i)
+INSN_LSX(vsubi_bu,         vv_i)
+INSN_LSX(vsubi_hu,         vv_i)
+INSN_LSX(vsubi_wu,         vv_i)
+INSN_LSX(vsubi_du,         vv_i)
+
+INSN_LSX(vneg_b,           vv)
+INSN_LSX(vneg_h,           vv)
+INSN_LSX(vneg_w,           vv)
+INSN_LSX(vneg_d,           vv)
+
+INSN_LSX(vsadd_b,          vvv)
+INSN_LSX(vsadd_h,          vvv)
+INSN_LSX(vsadd_w,          vvv)
+INSN_LSX(vsadd_d,          vvv)
+INSN_LSX(vsadd_bu,         vvv)
+INSN_LSX(vsadd_hu,         vvv)
+INSN_LSX(vsadd_wu,         vvv)
+INSN_LSX(vsadd_du,         vvv)
+INSN_LSX(vssub_b,          vvv)
+INSN_LSX(vssub_h,          vvv)
+INSN_LSX(vssub_w,          vvv)
+INSN_LSX(vssub_d,          vvv)
+INSN_LSX(vssub_bu,         vvv)
+INSN_LSX(vssub_hu,         vvv)
+INSN_LSX(vssub_wu,         vvv)
+INSN_LSX(vssub_du,         vvv)
+
+INSN_LSX(vhaddw_h_b,       vvv)
+INSN_LSX(vhaddw_w_h,       vvv)
+INSN_LSX(vhaddw_d_w,       vvv)
+INSN_LSX(vhaddw_q_d,       vvv)
+INSN_LSX(vhaddw_hu_bu,     vvv)
+INSN_LSX(vhaddw_wu_hu,     vvv)
+INSN_LSX(vhaddw_du_wu,     vvv)
+INSN_LSX(vhaddw_qu_du,     vvv)
+INSN_LSX(vhsubw_h_b,       vvv)
+INSN_LSX(vhsubw_w_h,       vvv)
+INSN_LSX(vhsubw_d_w,       vvv)
+INSN_LSX(vhsubw_q_d,       vvv)
+INSN_LSX(vhsubw_hu_bu,     vvv)
+INSN_LSX(vhsubw_wu_hu,     vvv)
+INSN_LSX(vhsubw_du_wu,     vvv)
+INSN_LSX(vhsubw_qu_du,     vvv)
+
+INSN_LSX(vaddwev_h_b,      vvv)
+INSN_LSX(vaddwev_w_h,      vvv)
+INSN_LSX(vaddwev_d_w,      vvv)
+INSN_LSX(vaddwev_q_d,      vvv)
+INSN_LSX(vaddwod_h_b,      vvv)
+INSN_LSX(vaddwod_w_h,      vvv)
+INSN_LSX(vaddwod_d_w,      vvv)
+INSN_LSX(vaddwod_q_d,      vvv)
+INSN_LSX(vsubwev_h_b,      vvv)
+INSN_LSX(vsubwev_w_h,      vvv)
+INSN_LSX(vsubwev_d_w,      vvv)
+INSN_LSX(vsubwev_q_d,      vvv)
+INSN_LSX(vsubwod_h_b,      vvv)
+INSN_LSX(vsubwod_w_h,      vvv)
+INSN_LSX(vsubwod_d_w,      vvv)
+INSN_LSX(vsubwod_q_d,      vvv)
+
+INSN_LSX(vaddwev_h_bu,     vvv)
+INSN_LSX(vaddwev_w_hu,     vvv)
+INSN_LSX(vaddwev_d_wu,     vvv)
+INSN_LSX(vaddwev_q_du,     vvv)
+INSN_LSX(vaddwod_h_bu,     vvv)
+INSN_LSX(vaddwod_w_hu,     vvv)
+INSN_LSX(vaddwod_d_wu,     vvv)
+INSN_LSX(vaddwod_q_du,     vvv)
+INSN_LSX(vsubwev_h_bu,     vvv)
+INSN_LSX(vsubwev_w_hu,     vvv)
+INSN_LSX(vsubwev_d_wu,     vvv)
+INSN_LSX(vsubwev_q_du,     vvv)
+INSN_LSX(vsubwod_h_bu,     vvv)
+INSN_LSX(vsubwod_w_hu,     vvv)
+INSN_LSX(vsubwod_d_wu,     vvv)
+INSN_LSX(vsubwod_q_du,     vvv)
+
+INSN_LSX(vaddwev_h_bu_b,   vvv)
+INSN_LSX(vaddwev_w_hu_h,   vvv)
+INSN_LSX(vaddwev_d_wu_w,   vvv)
+INSN_LSX(vaddwev_q_du_d,   vvv)
+INSN_LSX(vaddwod_h_bu_b,   vvv)
+INSN_LSX(vaddwod_w_hu_h,   vvv)
+INSN_LSX(vaddwod_d_wu_w,   vvv)
+INSN_LSX(vaddwod_q_du_d,   vvv)
+
+INSN_LSX(vavg_b,           vvv)
+INSN_LSX(vavg_h,           vvv)
+INSN_LSX(vavg_w,           vvv)
+INSN_LSX(vavg_d,           vvv)
+INSN_LSX(vavg_bu,          vvv)
+INSN_LSX(vavg_hu,          vvv)
+INSN_LSX(vavg_wu,          vvv)
+INSN_LSX(vavg_du,          vvv)
+INSN_LSX(vavgr_b,          vvv)
+INSN_LSX(vavgr_h,          vvv)
+INSN_LSX(vavgr_w,          vvv)
+INSN_LSX(vavgr_d,          vvv)
+INSN_LSX(vavgr_bu,         vvv)
+INSN_LSX(vavgr_hu,         vvv)
+INSN_LSX(vavgr_wu,         vvv)
+INSN_LSX(vavgr_du,         vvv)
+
+INSN_LSX(vabsd_b,          vvv)
+INSN_LSX(vabsd_h,          vvv)
+INSN_LSX(vabsd_w,          vvv)
+INSN_LSX(vabsd_d,          vvv)
+INSN_LSX(vabsd_bu,         vvv)
+INSN_LSX(vabsd_hu,         vvv)
+INSN_LSX(vabsd_wu,         vvv)
+INSN_LSX(vabsd_du,         vvv)
+
+INSN_LSX(vadda_b,          vvv)
+INSN_LSX(vadda_h,          vvv)
+INSN_LSX(vadda_w,          vvv)
+INSN_LSX(vadda_d,          vvv)
+
+INSN_LSX(vmax_b,           vvv)
+INSN_LSX(vmax_h,           vvv)
+INSN_LSX(vmax_w,           vvv)
+INSN_LSX(vmax_d,           vvv)
+INSN_LSX(vmin_b,           vvv)
+INSN_LSX(vmin_h,           vvv)
+INSN_LSX(vmin_w,           vvv)
+INSN_LSX(vmin_d,           vvv)
+INSN_LSX(vmax_bu,          vvv)
+INSN_LSX(vmax_hu,          vvv)
+INSN_LSX(vmax_wu,          vvv)
+INSN_LSX(vmax_du,          vvv)
+INSN_LSX(vmin_bu,          vvv)
+INSN_LSX(vmin_hu,          vvv)
+INSN_LSX(vmin_wu,          vvv)
+INSN_LSX(vmin_du,          vvv)
+INSN_LSX(vmaxi_b,          vv_i)
+INSN_LSX(vmaxi_h,          vv_i)
+INSN_LSX(vmaxi_w,          vv_i)
+INSN_LSX(vmaxi_d,          vv_i)
+INSN_LSX(vmini_b,          vv_i)
+INSN_LSX(vmini_h,          vv_i)
+INSN_LSX(vmini_w,          vv_i)
+INSN_LSX(vmini_d,          vv_i)
+INSN_LSX(vmaxi_bu,         vv_i)
+INSN_LSX(vmaxi_hu,         vv_i)
+INSN_LSX(vmaxi_wu,         vv_i)
+INSN_LSX(vmaxi_du,         vv_i)
+INSN_LSX(vmini_bu,         vv_i)
+INSN_LSX(vmini_hu,         vv_i)
+INSN_LSX(vmini_wu,         vv_i)
+INSN_LSX(vmini_du,         vv_i)
+
+INSN_LSX(vmul_b,           vvv)
+INSN_LSX(vmul_h,           vvv)
+INSN_LSX(vmul_w,           vvv)
+INSN_LSX(vmul_d,           vvv)
+INSN_LSX(vmuh_b,           vvv)
+INSN_LSX(vmuh_h,           vvv)
+INSN_LSX(vmuh_w,           vvv)
+INSN_LSX(vmuh_d,           vvv)
+INSN_LSX(vmuh_bu,          vvv)
+INSN_LSX(vmuh_hu,          vvv)
+INSN_LSX(vmuh_wu,          vvv)
+INSN_LSX(vmuh_du,          vvv)
+
+INSN_LSX(vmulwev_h_b,      vvv)
+INSN_LSX(vmulwev_w_h,      vvv)
+INSN_LSX(vmulwev_d_w,      vvv)
+INSN_LSX(vmulwev_q_d,      vvv)
+INSN_LSX(vmulwod_h_b,      vvv)
+INSN_LSX(vmulwod_w_h,      vvv)
+INSN_LSX(vmulwod_d_w,      vvv)
+INSN_LSX(vmulwod_q_d,      vvv)
+INSN_LSX(vmulwev_h_bu,     vvv)
+INSN_LSX(vmulwev_w_hu,     vvv)
+INSN_LSX(vmulwev_d_wu,     vvv)
+INSN_LSX(vmulwev_q_du,     vvv)
+INSN_LSX(vmulwod_h_bu,     vvv)
+INSN_LSX(vmulwod_w_hu,     vvv)
+INSN_LSX(vmulwod_d_wu,     vvv)
+INSN_LSX(vmulwod_q_du,     vvv)
+INSN_LSX(vmulwev_h_bu_b,   vvv)
+INSN_LSX(vmulwev_w_hu_h,   vvv)
+INSN_LSX(vmulwev_d_wu_w,   vvv)
+INSN_LSX(vmulwev_q_du_d,   vvv)
+INSN_LSX(vmulwod_h_bu_b,   vvv)
+INSN_LSX(vmulwod_w_hu_h,   vvv)
+INSN_LSX(vmulwod_d_wu_w,   vvv)
+INSN_LSX(vmulwod_q_du_d,   vvv)
+
+INSN_LSX(vmadd_b,          vvv)
+INSN_LSX(vmadd_h,          vvv)
+INSN_LSX(vmadd_w,          vvv)
+INSN_LSX(vmadd_d,          vvv)
+INSN_LSX(vmsub_b,          vvv)
+INSN_LSX(vmsub_h,          vvv)
+INSN_LSX(vmsub_w,          vvv)
+INSN_LSX(vmsub_d,          vvv)
+
+INSN_LSX(vmaddwev_h_b,     vvv)
+INSN_LSX(vmaddwev_w_h,     vvv)
+INSN_LSX(vmaddwev_d_w,     vvv)
+INSN_LSX(vmaddwev_q_d,     vvv)
+INSN_LSX(vmaddwod_h_b,     vvv)
+INSN_LSX(vmaddwod_w_h,     vvv)
+INSN_LSX(vmaddwod_d_w,     vvv)
+INSN_LSX(vmaddwod_q_d,     vvv)
+INSN_LSX(vmaddwev_h_bu,    vvv)
+INSN_LSX(vmaddwev_w_hu,    vvv)
+INSN_LSX(vmaddwev_d_wu,    vvv)
+INSN_LSX(vmaddwev_q_du,    vvv)
+INSN_LSX(vmaddwod_h_bu,    vvv)
+INSN_LSX(vmaddwod_w_hu,    vvv)
+INSN_LSX(vmaddwod_d_wu,    vvv)
+INSN_LSX(vmaddwod_q_du,    vvv)
+INSN_LSX(vmaddwev_h_bu_b,  vvv)
+INSN_LSX(vmaddwev_w_hu_h,  vvv)
+INSN_LSX(vmaddwev_d_wu_w,  vvv)
+INSN_LSX(vmaddwev_q_du_d,  vvv)
+INSN_LSX(vmaddwod_h_bu_b,  vvv)
+INSN_LSX(vmaddwod_w_hu_h,  vvv)
+INSN_LSX(vmaddwod_d_wu_w,  vvv)
+INSN_LSX(vmaddwod_q_du_d,  vvv)
+
+INSN_LSX(vdiv_b,           vvv)
+INSN_LSX(vdiv_h,           vvv)
+INSN_LSX(vdiv_w,           vvv)
+INSN_LSX(vdiv_d,           vvv)
+INSN_LSX(vdiv_bu,          vvv)
+INSN_LSX(vdiv_hu,          vvv)
+INSN_LSX(vdiv_wu,          vvv)
+INSN_LSX(vdiv_du,          vvv)
+INSN_LSX(vmod_b,           vvv)
+INSN_LSX(vmod_h,           vvv)
+INSN_LSX(vmod_w,           vvv)
+INSN_LSX(vmod_d,           vvv)
+INSN_LSX(vmod_bu,          vvv)
+INSN_LSX(vmod_hu,          vvv)
+INSN_LSX(vmod_wu,          vvv)
+INSN_LSX(vmod_du,          vvv)
+
+INSN_LSX(vsat_b,           vv_i)
+INSN_LSX(vsat_h,           vv_i)
+INSN_LSX(vsat_w,           vv_i)
+INSN_LSX(vsat_d,           vv_i)
+INSN_LSX(vsat_bu,          vv_i)
+INSN_LSX(vsat_hu,          vv_i)
+INSN_LSX(vsat_wu,          vv_i)
+INSN_LSX(vsat_du,          vv_i)
+
+INSN_LSX(vexth_h_b,        vv)
+INSN_LSX(vexth_w_h,        vv)
+INSN_LSX(vexth_d_w,        vv)
+INSN_LSX(vexth_q_d,        vv)
+INSN_LSX(vexth_hu_bu,      vv)
+INSN_LSX(vexth_wu_hu,      vv)
+INSN_LSX(vexth_du_wu,      vv)
+INSN_LSX(vexth_qu_du,      vv)
+
+INSN_LSX(vsigncov_b,       vvv)
+INSN_LSX(vsigncov_h,       vvv)
+INSN_LSX(vsigncov_w,       vvv)
+INSN_LSX(vsigncov_d,       vvv)
+
+INSN_LSX(vmskltz_b,        vv)
+INSN_LSX(vmskltz_h,        vv)
+INSN_LSX(vmskltz_w,        vv)
+INSN_LSX(vmskltz_d,        vv)
+INSN_LSX(vmskgez_b,        vv)
+INSN_LSX(vmsknz_b,         vv)
+
+INSN_LSX(vldi,             v_i)
+
+INSN_LSX(vand_v,           vvv)
+INSN_LSX(vor_v,            vvv)
+INSN_LSX(vxor_v,           vvv)
+INSN_LSX(vnor_v,           vvv)
+INSN_LSX(vandn_v,          vvv)
+INSN_LSX(vorn_v,           vvv)
+
+INSN_LSX(vandi_b,          vv_i)
+INSN_LSX(vori_b,           vv_i)
+INSN_LSX(vxori_b,          vv_i)
+INSN_LSX(vnori_b,          vv_i)
+
+INSN_LSX(vsll_b,           vvv)
+INSN_LSX(vsll_h,           vvv)
+INSN_LSX(vsll_w,           vvv)
+INSN_LSX(vsll_d,           vvv)
+INSN_LSX(vslli_b,          vv_i)
+INSN_LSX(vslli_h,          vv_i)
+INSN_LSX(vslli_w,          vv_i)
+INSN_LSX(vslli_d,          vv_i)
+
+INSN_LSX(vsrl_b,           vvv)
+INSN_LSX(vsrl_h,           vvv)
+INSN_LSX(vsrl_w,           vvv)
+INSN_LSX(vsrl_d,           vvv)
+INSN_LSX(vsrli_b,          vv_i)
+INSN_LSX(vsrli_h,          vv_i)
+INSN_LSX(vsrli_w,          vv_i)
+INSN_LSX(vsrli_d,          vv_i)
+
+INSN_LSX(vsra_b,           vvv)
+INSN_LSX(vsra_h,           vvv)
+INSN_LSX(vsra_w,           vvv)
+INSN_LSX(vsra_d,           vvv)
+INSN_LSX(vsrai_b,          vv_i)
+INSN_LSX(vsrai_h,          vv_i)
+INSN_LSX(vsrai_w,          vv_i)
+INSN_LSX(vsrai_d,          vv_i)
+
+INSN_LSX(vrotr_b,          vvv)
+INSN_LSX(vrotr_h,          vvv)
+INSN_LSX(vrotr_w,          vvv)
+INSN_LSX(vrotr_d,          vvv)
+INSN_LSX(vrotri_b,         vv_i)
+INSN_LSX(vrotri_h,         vv_i)
+INSN_LSX(vrotri_w,         vv_i)
+INSN_LSX(vrotri_d,         vv_i)
+
+INSN_LSX(vsllwil_h_b,      vv_i)
+INSN_LSX(vsllwil_w_h,      vv_i)
+INSN_LSX(vsllwil_d_w,      vv_i)
+INSN_LSX(vextl_q_d,        vv)
+INSN_LSX(vsllwil_hu_bu,    vv_i)
+INSN_LSX(vsllwil_wu_hu,    vv_i)
+INSN_LSX(vsllwil_du_wu,    vv_i)
+INSN_LSX(vextl_qu_du,      vv)
+
+INSN_LSX(vsrlr_b,          vvv)
+INSN_LSX(vsrlr_h,          vvv)
+INSN_LSX(vsrlr_w,          vvv)
+INSN_LSX(vsrlr_d,          vvv)
+INSN_LSX(vsrlri_b,         vv_i)
+INSN_LSX(vsrlri_h,         vv_i)
+INSN_LSX(vsrlri_w,         vv_i)
+INSN_LSX(vsrlri_d,         vv_i)
+
+INSN_LSX(vsrar_b,          vvv)
+INSN_LSX(vsrar_h,          vvv)
+INSN_LSX(vsrar_w,          vvv)
+INSN_LSX(vsrar_d,          vvv)
+INSN_LSX(vsrari_b,         vv_i)
+INSN_LSX(vsrari_h,         vv_i)
+INSN_LSX(vsrari_w,         vv_i)
+INSN_LSX(vsrari_d,         vv_i)
+
+INSN_LSX(vsrln_b_h,       vvv)
+INSN_LSX(vsrln_h_w,       vvv)
+INSN_LSX(vsrln_w_d,       vvv)
+INSN_LSX(vsran_b_h,       vvv)
+INSN_LSX(vsran_h_w,       vvv)
+INSN_LSX(vsran_w_d,       vvv)
+
+INSN_LSX(vsrlni_b_h,       vv_i)
+INSN_LSX(vsrlni_h_w,       vv_i)
+INSN_LSX(vsrlni_w_d,       vv_i)
+INSN_LSX(vsrlni_d_q,       vv_i)
+INSN_LSX(vsrani_b_h,       vv_i)
+INSN_LSX(vsrani_h_w,       vv_i)
+INSN_LSX(vsrani_w_d,       vv_i)
+INSN_LSX(vsrani_d_q,       vv_i)
+
+INSN_LSX(vsrlrn_b_h,       vvv)
+INSN_LSX(vsrlrn_h_w,       vvv)
+INSN_LSX(vsrlrn_w_d,       vvv)
+INSN_LSX(vsrarn_b_h,       vvv)
+INSN_LSX(vsrarn_h_w,       vvv)
+INSN_LSX(vsrarn_w_d,       vvv)
+
+INSN_LSX(vsrlrni_b_h,      vv_i)
+INSN_LSX(vsrlrni_h_w,      vv_i)
+INSN_LSX(vsrlrni_w_d,      vv_i)
+INSN_LSX(vsrlrni_d_q,      vv_i)
+INSN_LSX(vsrarni_b_h,      vv_i)
+INSN_LSX(vsrarni_h_w,      vv_i)
+INSN_LSX(vsrarni_w_d,      vv_i)
+INSN_LSX(vsrarni_d_q,      vv_i)
+
+INSN_LSX(vssrln_b_h,       vvv)
+INSN_LSX(vssrln_h_w,       vvv)
+INSN_LSX(vssrln_w_d,       vvv)
+INSN_LSX(vssran_b_h,       vvv)
+INSN_LSX(vssran_h_w,       vvv)
+INSN_LSX(vssran_w_d,       vvv)
+INSN_LSX(vssrln_bu_h,      vvv)
+INSN_LSX(vssrln_hu_w,      vvv)
+INSN_LSX(vssrln_wu_d,      vvv)
+INSN_LSX(vssran_bu_h,      vvv)
+INSN_LSX(vssran_hu_w,      vvv)
+INSN_LSX(vssran_wu_d,      vvv)
+
+INSN_LSX(vssrlni_b_h,      vv_i)
+INSN_LSX(vssrlni_h_w,      vv_i)
+INSN_LSX(vssrlni_w_d,      vv_i)
+INSN_LSX(vssrlni_d_q,      vv_i)
+INSN_LSX(vssrani_b_h,      vv_i)
+INSN_LSX(vssrani_h_w,      vv_i)
+INSN_LSX(vssrani_w_d,      vv_i)
+INSN_LSX(vssrani_d_q,      vv_i)
+INSN_LSX(vssrlni_bu_h,     vv_i)
+INSN_LSX(vssrlni_hu_w,     vv_i)
+INSN_LSX(vssrlni_wu_d,     vv_i)
+INSN_LSX(vssrlni_du_q,     vv_i)
+INSN_LSX(vssrani_bu_h,     vv_i)
+INSN_LSX(vssrani_hu_w,     vv_i)
+INSN_LSX(vssrani_wu_d,     vv_i)
+INSN_LSX(vssrani_du_q,     vv_i)
+
+INSN_LSX(vssrlrn_b_h,      vvv)
+INSN_LSX(vssrlrn_h_w,      vvv)
+INSN_LSX(vssrlrn_w_d,      vvv)
+INSN_LSX(vssrarn_b_h,      vvv)
+INSN_LSX(vssrarn_h_w,      vvv)
+INSN_LSX(vssrarn_w_d,      vvv)
+INSN_LSX(vssrlrn_bu_h,     vvv)
+INSN_LSX(vssrlrn_hu_w,     vvv)
+INSN_LSX(vssrlrn_wu_d,     vvv)
+INSN_LSX(vssrarn_bu_h,     vvv)
+INSN_LSX(vssrarn_hu_w,     vvv)
+INSN_LSX(vssrarn_wu_d,     vvv)
+
+INSN_LSX(vssrlrni_b_h,     vv_i)
+INSN_LSX(vssrlrni_h_w,     vv_i)
+INSN_LSX(vssrlrni_w_d,     vv_i)
+INSN_LSX(vssrlrni_d_q,     vv_i)
+INSN_LSX(vssrlrni_bu_h,    vv_i)
+INSN_LSX(vssrlrni_hu_w,    vv_i)
+INSN_LSX(vssrlrni_wu_d,    vv_i)
+INSN_LSX(vssrlrni_du_q,    vv_i)
+INSN_LSX(vssrarni_b_h,     vv_i)
+INSN_LSX(vssrarni_h_w,     vv_i)
+INSN_LSX(vssrarni_w_d,     vv_i)
+INSN_LSX(vssrarni_d_q,     vv_i)
+INSN_LSX(vssrarni_bu_h,    vv_i)
+INSN_LSX(vssrarni_hu_w,    vv_i)
+INSN_LSX(vssrarni_wu_d,    vv_i)
+INSN_LSX(vssrarni_du_q,    vv_i)
+
+INSN_LSX(vclo_b,           vv)
+INSN_LSX(vclo_h,           vv)
+INSN_LSX(vclo_w,           vv)
+INSN_LSX(vclo_d,           vv)
+INSN_LSX(vclz_b,           vv)
+INSN_LSX(vclz_h,           vv)
+INSN_LSX(vclz_w,           vv)
+INSN_LSX(vclz_d,           vv)
+
+INSN_LSX(vpcnt_b,          vv)
+INSN_LSX(vpcnt_h,          vv)
+INSN_LSX(vpcnt_w,          vv)
+INSN_LSX(vpcnt_d,          vv)
+
+INSN_LSX(vbitclr_b,        vvv)
+INSN_LSX(vbitclr_h,        vvv)
+INSN_LSX(vbitclr_w,        vvv)
+INSN_LSX(vbitclr_d,        vvv)
+INSN_LSX(vbitclri_b,       vv_i)
+INSN_LSX(vbitclri_h,       vv_i)
+INSN_LSX(vbitclri_w,       vv_i)
+INSN_LSX(vbitclri_d,       vv_i)
+INSN_LSX(vbitset_b,        vvv)
+INSN_LSX(vbitset_h,        vvv)
+INSN_LSX(vbitset_w,        vvv)
+INSN_LSX(vbitset_d,        vvv)
+INSN_LSX(vbitseti_b,       vv_i)
+INSN_LSX(vbitseti_h,       vv_i)
+INSN_LSX(vbitseti_w,       vv_i)
+INSN_LSX(vbitseti_d,       vv_i)
+INSN_LSX(vbitrev_b,        vvv)
+INSN_LSX(vbitrev_h,        vvv)
+INSN_LSX(vbitrev_w,        vvv)
+INSN_LSX(vbitrev_d,        vvv)
+INSN_LSX(vbitrevi_b,       vv_i)
+INSN_LSX(vbitrevi_h,       vv_i)
+INSN_LSX(vbitrevi_w,       vv_i)
+INSN_LSX(vbitrevi_d,       vv_i)
+
+INSN_LSX(vfrstp_b,         vvv)
+INSN_LSX(vfrstp_h,         vvv)
+INSN_LSX(vfrstpi_b,        vv_i)
+INSN_LSX(vfrstpi_h,        vv_i)
+
+INSN_LSX(vfadd_s,          vvv)
+INSN_LSX(vfadd_d,          vvv)
+INSN_LSX(vfsub_s,          vvv)
+INSN_LSX(vfsub_d,          vvv)
+INSN_LSX(vfmul_s,          vvv)
+INSN_LSX(vfmul_d,          vvv)
+INSN_LSX(vfdiv_s,          vvv)
+INSN_LSX(vfdiv_d,          vvv)
+
+INSN_LSX(vfmadd_s,         vvvv)
+INSN_LSX(vfmadd_d,         vvvv)
+INSN_LSX(vfmsub_s,         vvvv)
+INSN_LSX(vfmsub_d,         vvvv)
+INSN_LSX(vfnmadd_s,        vvvv)
+INSN_LSX(vfnmadd_d,        vvvv)
+INSN_LSX(vfnmsub_s,        vvvv)
+INSN_LSX(vfnmsub_d,        vvvv)
+
+INSN_LSX(vfmax_s,          vvv)
+INSN_LSX(vfmax_d,          vvv)
+INSN_LSX(vfmin_s,          vvv)
+INSN_LSX(vfmin_d,          vvv)
+
+INSN_LSX(vfmaxa_s,         vvv)
+INSN_LSX(vfmaxa_d,         vvv)
+INSN_LSX(vfmina_s,         vvv)
+INSN_LSX(vfmina_d,         vvv)
+
+INSN_LSX(vflogb_s,         vv)
+INSN_LSX(vflogb_d,         vv)
+
+INSN_LSX(vfclass_s,        vv)
+INSN_LSX(vfclass_d,        vv)
+
+INSN_LSX(vfsqrt_s,         vv)
+INSN_LSX(vfsqrt_d,         vv)
+INSN_LSX(vfrecip_s,        vv)
+INSN_LSX(vfrecip_d,        vv)
+INSN_LSX(vfrsqrt_s,        vv)
+INSN_LSX(vfrsqrt_d,        vv)
+
+INSN_LSX(vfcvtl_s_h,       vv)
+INSN_LSX(vfcvth_s_h,       vv)
+INSN_LSX(vfcvtl_d_s,       vv)
+INSN_LSX(vfcvth_d_s,       vv)
+INSN_LSX(vfcvt_h_s,        vvv)
+INSN_LSX(vfcvt_s_d,        vvv)
+
+INSN_LSX(vfrint_s,         vv)
+INSN_LSX(vfrint_d,         vv)
+INSN_LSX(vfrintrm_s,       vv)
+INSN_LSX(vfrintrm_d,       vv)
+INSN_LSX(vfrintrp_s,       vv)
+INSN_LSX(vfrintrp_d,       vv)
+INSN_LSX(vfrintrz_s,       vv)
+INSN_LSX(vfrintrz_d,       vv)
+INSN_LSX(vfrintrne_s,      vv)
+INSN_LSX(vfrintrne_d,      vv)
+
+INSN_LSX(vftint_w_s,       vv)
+INSN_LSX(vftint_l_d,       vv)
+INSN_LSX(vftintrm_w_s,     vv)
+INSN_LSX(vftintrm_l_d,     vv)
+INSN_LSX(vftintrp_w_s,     vv)
+INSN_LSX(vftintrp_l_d,     vv)
+INSN_LSX(vftintrz_w_s,     vv)
+INSN_LSX(vftintrz_l_d,     vv)
+INSN_LSX(vftintrne_w_s,    vv)
+INSN_LSX(vftintrne_l_d,    vv)
+INSN_LSX(vftint_wu_s,      vv)
+INSN_LSX(vftint_lu_d,      vv)
+INSN_LSX(vftintrz_wu_s,    vv)
+INSN_LSX(vftintrz_lu_d,    vv)
+INSN_LSX(vftint_w_d,       vvv)
+INSN_LSX(vftintrm_w_d,     vvv)
+INSN_LSX(vftintrp_w_d,     vvv)
+INSN_LSX(vftintrz_w_d,     vvv)
+INSN_LSX(vftintrne_w_d,    vvv)
+INSN_LSX(vftintl_l_s,      vv)
+INSN_LSX(vftinth_l_s,      vv)
+INSN_LSX(vftintrml_l_s,    vv)
+INSN_LSX(vftintrmh_l_s,    vv)
+INSN_LSX(vftintrpl_l_s,    vv)
+INSN_LSX(vftintrph_l_s,    vv)
+INSN_LSX(vftintrzl_l_s,    vv)
+INSN_LSX(vftintrzh_l_s,    vv)
+INSN_LSX(vftintrnel_l_s,   vv)
+INSN_LSX(vftintrneh_l_s,   vv)
+
+INSN_LSX(vffint_s_w,       vv)
+INSN_LSX(vffint_s_wu,      vv)
+INSN_LSX(vffint_d_l,       vv)
+INSN_LSX(vffint_d_lu,      vv)
+INSN_LSX(vffintl_d_w,      vv)
+INSN_LSX(vffinth_d_w,      vv)
+INSN_LSX(vffint_s_l,       vvv)
+
+INSN_LSX(vseq_b,           vvv)
+INSN_LSX(vseq_h,           vvv)
+INSN_LSX(vseq_w,           vvv)
+INSN_LSX(vseq_d,           vvv)
+INSN_LSX(vseqi_b,          vv_i)
+INSN_LSX(vseqi_h,          vv_i)
+INSN_LSX(vseqi_w,          vv_i)
+INSN_LSX(vseqi_d,          vv_i)
+
+INSN_LSX(vsle_b,           vvv)
+INSN_LSX(vsle_h,           vvv)
+INSN_LSX(vsle_w,           vvv)
+INSN_LSX(vsle_d,           vvv)
+INSN_LSX(vslei_b,          vv_i)
+INSN_LSX(vslei_h,          vv_i)
+INSN_LSX(vslei_w,          vv_i)
+INSN_LSX(vslei_d,          vv_i)
+INSN_LSX(vsle_bu,          vvv)
+INSN_LSX(vsle_hu,          vvv)
+INSN_LSX(vsle_wu,          vvv)
+INSN_LSX(vsle_du,          vvv)
+INSN_LSX(vslei_bu,         vv_i)
+INSN_LSX(vslei_hu,         vv_i)
+INSN_LSX(vslei_wu,         vv_i)
+INSN_LSX(vslei_du,         vv_i)
+
+INSN_LSX(vslt_b,           vvv)
+INSN_LSX(vslt_h,           vvv)
+INSN_LSX(vslt_w,           vvv)
+INSN_LSX(vslt_d,           vvv)
+INSN_LSX(vslti_b,          vv_i)
+INSN_LSX(vslti_h,          vv_i)
+INSN_LSX(vslti_w,          vv_i)
+INSN_LSX(vslti_d,          vv_i)
+INSN_LSX(vslt_bu,          vvv)
+INSN_LSX(vslt_hu,          vvv)
+INSN_LSX(vslt_wu,          vvv)
+INSN_LSX(vslt_du,          vvv)
+INSN_LSX(vslti_bu,         vv_i)
+INSN_LSX(vslti_hu,         vv_i)
+INSN_LSX(vslti_wu,         vv_i)
+INSN_LSX(vslti_du,         vv_i)
+
+#define output_vfcmp(C, PREFIX, SUFFIX)                                     \
+{                                                                           \
+    (C)->info->fprintf_func((C)->info->stream, "%08x   %s%s\t%d, f%d, f%d", \
+                            (C)->insn, PREFIX, SUFFIX, a->vd,               \
+                            a->vj, a->vk);                                  \
+}
+
+static bool output_vvv_fcond(DisasContext *ctx, arg_vvv_fcond * a,
+                             const char *suffix)
+{
+    bool ret = true;
+    switch (a->fcond) {
+    case 0x0:
+        output_vfcmp(ctx, "vfcmp_caf_", suffix);
+        break;
+    case 0x1:
+        output_vfcmp(ctx, "vfcmp_saf_", suffix);
+        break;
+    case 0x2:
+        output_vfcmp(ctx, "vfcmp_clt_", suffix);
+        break;
+    case 0x3:
+        output_vfcmp(ctx, "vfcmp_slt_", suffix);
+        break;
+    case 0x4:
+        output_vfcmp(ctx, "vfcmp_ceq_", suffix);
+        break;
+    case 0x5:
+        output_vfcmp(ctx, "vfcmp_seq_", suffix);
+        break;
+    case 0x6:
+        output_vfcmp(ctx, "vfcmp_cle_", suffix);
+        break;
+    case 0x7:
+        output_vfcmp(ctx, "vfcmp_sle_", suffix);
+        break;
+    case 0x8:
+        output_vfcmp(ctx, "vfcmp_cun_", suffix);
+        break;
+    case 0x9:
+        output_vfcmp(ctx, "vfcmp_sun_", suffix);
+        break;
+    case 0xA:
+        output_vfcmp(ctx, "vfcmp_cult_", suffix);
+        break;
+    case 0xB:
+        output_vfcmp(ctx, "vfcmp_sult_", suffix);
+        break;
+    case 0xC:
+        output_vfcmp(ctx, "vfcmp_cueq_", suffix);
+        break;
+    case 0xD:
+        output_vfcmp(ctx, "vfcmp_sueq_", suffix);
+        break;
+    case 0xE:
+        output_vfcmp(ctx, "vfcmp_cule_", suffix);
+        break;
+    case 0xF:
+        output_vfcmp(ctx, "vfcmp_sule_", suffix);
+        break;
+    case 0x10:
+        output_vfcmp(ctx, "vfcmp_cne_", suffix);
+        break;
+    case 0x11:
+        output_vfcmp(ctx, "vfcmp_sne_", suffix);
+        break;
+    case 0x14:
+        output_vfcmp(ctx, "vfcmp_cor_", suffix);
+        break;
+    case 0x15:
+        output_vfcmp(ctx, "vfcmp_sor_", suffix);
+        break;
+    case 0x18:
+        output_vfcmp(ctx, "vfcmp_cune_", suffix);
+        break;
+    case 0x19:
+        output_vfcmp(ctx, "vfcmp_sune_", suffix);
+        break;
+    default:
+        ret = false;
+    }
+    return ret;
+}
+
+#define LSX_FCMP_INSN(suffix)                            \
+static bool trans_vfcmp_cond_##suffix(DisasContext *ctx, \
+                                     arg_vvv_fcond * a)  \
+{                                                        \
+    return output_vvv_fcond(ctx, a, #suffix);            \
+}
+
+LSX_FCMP_INSN(s)
+LSX_FCMP_INSN(d)
+
+INSN_LSX(vbitsel_v,        vvvv)
+INSN_LSX(vbitseli_b,       vv_i)
+
+INSN_LSX(vseteqz_v,        cv)
+INSN_LSX(vsetnez_v,        cv)
+INSN_LSX(vsetanyeqz_b,     cv)
+INSN_LSX(vsetanyeqz_h,     cv)
+INSN_LSX(vsetanyeqz_w,     cv)
+INSN_LSX(vsetanyeqz_d,     cv)
+INSN_LSX(vsetallnez_b,     cv)
+INSN_LSX(vsetallnez_h,     cv)
+INSN_LSX(vsetallnez_w,     cv)
+INSN_LSX(vsetallnez_d,     cv)
+
+INSN_LSX(vinsgr2vr_b,      vr_i)
+INSN_LSX(vinsgr2vr_h,      vr_i)
+INSN_LSX(vinsgr2vr_w,      vr_i)
+INSN_LSX(vinsgr2vr_d,      vr_i)
+INSN_LSX(vpickve2gr_b,     rv_i)
+INSN_LSX(vpickve2gr_h,     rv_i)
+INSN_LSX(vpickve2gr_w,     rv_i)
+INSN_LSX(vpickve2gr_d,     rv_i)
+INSN_LSX(vpickve2gr_bu,    rv_i)
+INSN_LSX(vpickve2gr_hu,    rv_i)
+INSN_LSX(vpickve2gr_wu,    rv_i)
+INSN_LSX(vpickve2gr_du,    rv_i)
+
+INSN_LSX(vreplgr2vr_b,     vr)
+INSN_LSX(vreplgr2vr_h,     vr)
+INSN_LSX(vreplgr2vr_w,     vr)
+INSN_LSX(vreplgr2vr_d,     vr)
+
+INSN_LSX(vreplve_b,        vvr)
+INSN_LSX(vreplve_h,        vvr)
+INSN_LSX(vreplve_w,        vvr)
+INSN_LSX(vreplve_d,        vvr)
+INSN_LSX(vreplvei_b,       vv_i)
+INSN_LSX(vreplvei_h,       vv_i)
+INSN_LSX(vreplvei_w,       vv_i)
+INSN_LSX(vreplvei_d,       vv_i)
+
+INSN_LSX(vbsll_v,          vv_i)
+INSN_LSX(vbsrl_v,          vv_i)
+
+INSN_LSX(vpackev_b,        vvv)
+INSN_LSX(vpackev_h,        vvv)
+INSN_LSX(vpackev_w,        vvv)
+INSN_LSX(vpackev_d,        vvv)
+INSN_LSX(vpackod_b,        vvv)
+INSN_LSX(vpackod_h,        vvv)
+INSN_LSX(vpackod_w,        vvv)
+INSN_LSX(vpackod_d,        vvv)
+
+INSN_LSX(vpickev_b,        vvv)
+INSN_LSX(vpickev_h,        vvv)
+INSN_LSX(vpickev_w,        vvv)
+INSN_LSX(vpickev_d,        vvv)
+INSN_LSX(vpickod_b,        vvv)
+INSN_LSX(vpickod_h,        vvv)
+INSN_LSX(vpickod_w,        vvv)
+INSN_LSX(vpickod_d,        vvv)
+
+INSN_LSX(vilvl_b,          vvv)
+INSN_LSX(vilvl_h,          vvv)
+INSN_LSX(vilvl_w,          vvv)
+INSN_LSX(vilvl_d,          vvv)
+INSN_LSX(vilvh_b,          vvv)
+INSN_LSX(vilvh_h,          vvv)
+INSN_LSX(vilvh_w,          vvv)
+INSN_LSX(vilvh_d,          vvv)
+
+INSN_LSX(vshuf_b,          vvvv)
+INSN_LSX(vshuf_h,          vvv)
+INSN_LSX(vshuf_w,          vvv)
+INSN_LSX(vshuf_d,          vvv)
+INSN_LSX(vshuf4i_b,        vv_i)
+INSN_LSX(vshuf4i_h,        vv_i)
+INSN_LSX(vshuf4i_w,        vv_i)
+INSN_LSX(vshuf4i_d,        vv_i)
+
+INSN_LSX(vpermi_w,         vv_i)
+
+INSN_LSX(vextrins_d,       vv_i)
+INSN_LSX(vextrins_w,       vv_i)
+INSN_LSX(vextrins_h,       vv_i)
+INSN_LSX(vextrins_b,       vv_i)
+
+INSN_LSX(vld,              vr_i)
+INSN_LSX(vst,              vr_i)
+INSN_LSX(vldx,             vrr)
+INSN_LSX(vstx,             vrr)
+
+INSN_LSX(vldrepl_d,        vr_i)
+INSN_LSX(vldrepl_w,        vr_i)
+INSN_LSX(vldrepl_h,        vr_i)
+INSN_LSX(vldrepl_b,        vr_i)
+INSN_LSX(vstelm_d,         vr_ii)
+INSN_LSX(vstelm_w,         vr_ii)
+INSN_LSX(vstelm_h,         vr_ii)
+INSN_LSX(vstelm_b,         vr_ii)

target/loongarch/fpu_helper.c

@@ -33,7 +33,7 @@ void restore_fp_status(CPULoongArchState *env)
     set_flush_to_zero(0, &env->fp_status);
 }
 
-static int ieee_ex_to_loongarch(int xcpt)
+int ieee_ex_to_loongarch(int xcpt)
 {
     int ret = 0;
     if (xcpt & float_flag_invalid) {

target/loongarch/gdbstub.c

@@ -69,7 +69,7 @@ static int loongarch_gdb_get_fpu(CPULoongArchState *env,
                                  GByteArray *mem_buf, int n)
 {
     if (0 <= n && n < 32) {
-        return gdb_get_reg64(mem_buf, env->fpr[n]);
+        return gdb_get_reg64(mem_buf, env->fpr[n].vreg.D(0));
     } else if (n == 32) {
         uint64_t val = read_fcc(env);
         return gdb_get_reg64(mem_buf, val);
@@ -85,7 +85,7 @@ static int loongarch_gdb_set_fpu(CPULoongArchState *env,
     int length = 0;
 
     if (0 <= n && n < 32) {
-        env->fpr[n] = ldq_p(mem_buf);
+        env->fpr[n].vreg.D(0) = ldq_p(mem_buf);
         length = 8;
     } else if (n == 32) {
         uint64_t val = ldq_p(mem_buf);

target/loongarch/helper.h

@@ -130,3 +130,569 @@ DEF_HELPER_4(ldpte, void, env, tl, tl, i32)
 DEF_HELPER_1(ertn, void, env)
 DEF_HELPER_1(idle, void, env)
 #endif
+
+/* LoongArch LSX  */
+DEF_HELPER_4(vhaddw_h_b, void, env, i32, i32, i32)
+DEF_HELPER_4(vhaddw_w_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vhaddw_d_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vhaddw_q_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vhaddw_hu_bu, void, env, i32, i32, i32)
+DEF_HELPER_4(vhaddw_wu_hu, void, env, i32, i32, i32)
+DEF_HELPER_4(vhaddw_du_wu, void, env, i32, i32, i32)
+DEF_HELPER_4(vhaddw_qu_du, void, env, i32, i32, i32)
+DEF_HELPER_4(vhsubw_h_b, void, env, i32, i32, i32)
+DEF_HELPER_4(vhsubw_w_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vhsubw_d_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vhsubw_q_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vhsubw_hu_bu, void, env, i32, i32, i32)
+DEF_HELPER_4(vhsubw_wu_hu, void, env, i32, i32, i32)
+DEF_HELPER_4(vhsubw_du_wu, void, env, i32, i32, i32)
+DEF_HELPER_4(vhsubw_qu_du, void, env, i32, i32, i32)
+
+DEF_HELPER_FLAGS_4(vaddwev_h_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vaddwev_w_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vaddwev_d_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vaddwev_q_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vaddwod_h_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vaddwod_w_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vaddwod_d_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vaddwod_q_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(vsubwev_h_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vsubwev_w_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vsubwev_d_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vsubwev_q_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vsubwod_h_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vsubwod_w_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vsubwod_d_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vsubwod_q_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(vaddwev_h_bu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vaddwev_w_hu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vaddwev_d_wu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vaddwev_q_du, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vaddwod_h_bu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vaddwod_w_hu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vaddwod_d_wu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vaddwod_q_du, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(vsubwev_h_bu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vsubwev_w_hu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vsubwev_d_wu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vsubwev_q_du, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vsubwod_h_bu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vsubwod_w_hu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vsubwod_d_wu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vsubwod_q_du, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(vaddwev_h_bu_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vaddwev_w_hu_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vaddwev_d_wu_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vaddwev_q_du_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vaddwod_h_bu_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vaddwod_w_hu_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vaddwod_d_wu_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vaddwod_q_du_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(vavg_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vavg_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vavg_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vavg_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vavg_bu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vavg_hu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vavg_wu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vavg_du, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(vavgr_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vavgr_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vavgr_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vavgr_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vavgr_bu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vavgr_hu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vavgr_wu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vavgr_du, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(vabsd_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vabsd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vabsd_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vabsd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vabsd_bu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vabsd_hu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vabsd_wu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vabsd_du, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(vadda_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vadda_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vadda_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vadda_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(vmini_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vmini_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vmini_w, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vmini_d, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vmini_bu, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vmini_hu, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vmini_wu, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vmini_du, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+
+DEF_HELPER_FLAGS_4(vmaxi_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vmaxi_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vmaxi_w, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vmaxi_d, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vmaxi_bu, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vmaxi_hu, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vmaxi_wu, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vmaxi_du, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+
+DEF_HELPER_FLAGS_4(vmuh_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmuh_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmuh_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmuh_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmuh_bu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmuh_hu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmuh_wu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmuh_du, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(vmulwev_h_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmulwev_w_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmulwev_d_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmulwod_h_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmulwod_w_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmulwod_d_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(vmulwev_h_bu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmulwev_w_hu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmulwev_d_wu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmulwod_h_bu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmulwod_w_hu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmulwod_d_wu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(vmulwev_h_bu_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmulwev_w_hu_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmulwev_d_wu_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmulwod_h_bu_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmulwod_w_hu_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmulwod_d_wu_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(vmadd_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmadd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmadd_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmadd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmsub_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmsub_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmsub_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmsub_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(vmaddwev_h_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmaddwev_w_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmaddwev_d_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmaddwod_h_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmaddwod_w_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmaddwod_d_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(vmaddwev_h_bu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmaddwev_w_hu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmaddwev_d_wu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmaddwod_h_bu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmaddwod_w_hu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmaddwod_d_wu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(vmaddwev_h_bu_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmaddwev_w_hu_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmaddwev_d_wu_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmaddwod_h_bu_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmaddwod_w_hu_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vmaddwod_d_wu_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_4(vdiv_b, void, env, i32, i32, i32)
+DEF_HELPER_4(vdiv_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vdiv_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vdiv_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vdiv_bu, void, env, i32, i32, i32)
+DEF_HELPER_4(vdiv_hu, void, env, i32, i32, i32)
+DEF_HELPER_4(vdiv_wu, void, env, i32, i32, i32)
+DEF_HELPER_4(vdiv_du, void, env, i32, i32, i32)
+DEF_HELPER_4(vmod_b, void, env, i32, i32, i32)
+DEF_HELPER_4(vmod_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vmod_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vmod_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vmod_bu, void, env, i32, i32, i32)
+DEF_HELPER_4(vmod_hu, void, env, i32, i32, i32)
+DEF_HELPER_4(vmod_wu, void, env, i32, i32, i32)
+DEF_HELPER_4(vmod_du, void, env, i32, i32, i32)
+
+DEF_HELPER_FLAGS_4(vsat_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vsat_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vsat_w, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vsat_d, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vsat_bu, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vsat_hu, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vsat_wu, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vsat_du, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+
+DEF_HELPER_3(vexth_h_b, void, env, i32, i32)
+DEF_HELPER_3(vexth_w_h, void, env, i32, i32)
+DEF_HELPER_3(vexth_d_w, void, env, i32, i32)
+DEF_HELPER_3(vexth_q_d, void, env, i32, i32)
+DEF_HELPER_3(vexth_hu_bu, void, env, i32, i32)
+DEF_HELPER_3(vexth_wu_hu, void, env, i32, i32)
+DEF_HELPER_3(vexth_du_wu, void, env, i32, i32)
+DEF_HELPER_3(vexth_qu_du, void, env, i32, i32)
+
+DEF_HELPER_FLAGS_4(vsigncov_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vsigncov_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vsigncov_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vsigncov_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_3(vmskltz_b, void, env, i32, i32)
+DEF_HELPER_3(vmskltz_h, void, env, i32, i32)
+DEF_HELPER_3(vmskltz_w, void, env, i32, i32)
+DEF_HELPER_3(vmskltz_d, void, env, i32, i32)
+DEF_HELPER_3(vmskgez_b, void, env, i32, i32)
+DEF_HELPER_3(vmsknz_b, void, env, i32,i32)
+
+DEF_HELPER_FLAGS_4(vnori_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+
+DEF_HELPER_4(vsllwil_h_b, void, env, i32, i32, i32)
+DEF_HELPER_4(vsllwil_w_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vsllwil_d_w, void, env, i32, i32, i32)
+DEF_HELPER_3(vextl_q_d, void, env, i32, i32)
+DEF_HELPER_4(vsllwil_hu_bu, void, env, i32, i32, i32)
+DEF_HELPER_4(vsllwil_wu_hu, void, env, i32, i32, i32)
+DEF_HELPER_4(vsllwil_du_wu, void, env, i32, i32, i32)
+DEF_HELPER_3(vextl_qu_du, void, env, i32, i32)
+
+DEF_HELPER_4(vsrlr_b, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrlr_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrlr_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrlr_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrlri_b, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrlri_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrlri_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrlri_d, void, env, i32, i32, i32)
+
+DEF_HELPER_4(vsrar_b, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrar_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrar_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrar_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrari_b, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrari_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrari_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrari_d, void, env, i32, i32, i32)
+
+DEF_HELPER_4(vsrln_b_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrln_h_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrln_w_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vsran_b_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vsran_h_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vsran_w_d, void, env, i32, i32, i32)
+
+DEF_HELPER_4(vsrlni_b_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrlni_h_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrlni_w_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrlni_d_q, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrani_b_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrani_h_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrani_w_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrani_d_q, void, env, i32, i32, i32)
+
+DEF_HELPER_4(vsrlrn_b_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrlrn_h_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrlrn_w_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrarn_b_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrarn_h_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrarn_w_d, void, env, i32, i32, i32)
+
+DEF_HELPER_4(vsrlrni_b_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrlrni_h_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrlrni_w_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrlrni_d_q, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrarni_b_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrarni_h_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrarni_w_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vsrarni_d_q, void, env, i32, i32, i32)
+
+DEF_HELPER_4(vssrln_b_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrln_h_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrln_w_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vssran_b_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vssran_h_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vssran_w_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrln_bu_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrln_hu_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrln_wu_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vssran_bu_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vssran_hu_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vssran_wu_d, void, env, i32, i32, i32)
+
+DEF_HELPER_4(vssrlni_b_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrlni_h_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrlni_w_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrlni_d_q, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrani_b_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrani_h_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrani_w_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrani_d_q, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrlni_bu_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrlni_hu_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrlni_wu_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrlni_du_q, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrani_bu_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrani_hu_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrani_wu_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrani_du_q, void, env, i32, i32, i32)
+
+DEF_HELPER_4(vssrlrn_b_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrlrn_h_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrlrn_w_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrarn_b_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrarn_h_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrarn_w_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrlrn_bu_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrlrn_hu_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrlrn_wu_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrarn_bu_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrarn_hu_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrarn_wu_d, void, env, i32, i32, i32)
+
+DEF_HELPER_4(vssrlrni_b_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrlrni_h_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrlrni_w_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrlrni_d_q, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrarni_b_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrarni_h_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrarni_w_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrarni_d_q, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrlrni_bu_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrlrni_hu_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrlrni_wu_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrlrni_du_q, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrarni_bu_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrarni_hu_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrarni_wu_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vssrarni_du_q, void, env, i32, i32, i32)
+
+DEF_HELPER_3(vclo_b, void, env, i32, i32)
+DEF_HELPER_3(vclo_h, void, env, i32, i32)
+DEF_HELPER_3(vclo_w, void, env, i32, i32)
+DEF_HELPER_3(vclo_d, void, env, i32, i32)
+DEF_HELPER_3(vclz_b, void, env, i32, i32)
+DEF_HELPER_3(vclz_h, void, env, i32, i32)
+DEF_HELPER_3(vclz_w, void, env, i32, i32)
+DEF_HELPER_3(vclz_d, void, env, i32, i32)
+
+DEF_HELPER_3(vpcnt_b, void, env, i32, i32)
+DEF_HELPER_3(vpcnt_h, void, env, i32, i32)
+DEF_HELPER_3(vpcnt_w, void, env, i32, i32)
+DEF_HELPER_3(vpcnt_d, void, env, i32, i32)
+
+DEF_HELPER_FLAGS_4(vbitclr_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vbitclr_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vbitclr_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vbitclr_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vbitclri_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vbitclri_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vbitclri_w, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vbitclri_d, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+
+DEF_HELPER_FLAGS_4(vbitset_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vbitset_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vbitset_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vbitset_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vbitseti_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vbitseti_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vbitseti_w, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vbitseti_d, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+
+DEF_HELPER_FLAGS_4(vbitrev_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vbitrev_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vbitrev_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vbitrev_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vbitrevi_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vbitrevi_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vbitrevi_w, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vbitrevi_d, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+
+DEF_HELPER_4(vfrstp_b, void, env, i32, i32, i32)
+DEF_HELPER_4(vfrstp_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vfrstpi_b, void, env, i32, i32, i32)
+DEF_HELPER_4(vfrstpi_h, void, env, i32, i32, i32)
+
+DEF_HELPER_4(vfadd_s, void, env, i32, i32, i32)
+DEF_HELPER_4(vfadd_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vfsub_s, void, env, i32, i32, i32)
+DEF_HELPER_4(vfsub_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vfmul_s, void, env, i32, i32, i32)
+DEF_HELPER_4(vfmul_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vfdiv_s, void, env, i32, i32, i32)
+DEF_HELPER_4(vfdiv_d, void, env, i32, i32, i32)
+
+DEF_HELPER_5(vfmadd_s, void, env, i32, i32, i32, i32)
+DEF_HELPER_5(vfmadd_d, void, env, i32, i32, i32, i32)
+DEF_HELPER_5(vfmsub_s, void, env, i32, i32, i32, i32)
+DEF_HELPER_5(vfmsub_d, void, env, i32, i32, i32, i32)
+DEF_HELPER_5(vfnmadd_s, void, env, i32, i32, i32, i32)
+DEF_HELPER_5(vfnmadd_d, void, env, i32, i32, i32, i32)
+DEF_HELPER_5(vfnmsub_s, void, env, i32, i32, i32, i32)
+DEF_HELPER_5(vfnmsub_d, void, env, i32, i32, i32, i32)
+
+DEF_HELPER_4(vfmax_s, void, env, i32, i32, i32)
+DEF_HELPER_4(vfmax_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vfmin_s, void, env, i32, i32, i32)
+DEF_HELPER_4(vfmin_d, void, env, i32, i32, i32)
+
+DEF_HELPER_4(vfmaxa_s, void, env, i32, i32, i32)
+DEF_HELPER_4(vfmaxa_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vfmina_s, void, env, i32, i32, i32)
+DEF_HELPER_4(vfmina_d, void, env, i32, i32, i32)
+
+DEF_HELPER_3(vflogb_s, void, env, i32, i32)
+DEF_HELPER_3(vflogb_d, void, env, i32, i32)
+
+DEF_HELPER_3(vfclass_s, void, env, i32, i32)
+DEF_HELPER_3(vfclass_d, void, env, i32, i32)
+
+DEF_HELPER_3(vfsqrt_s, void, env, i32, i32)
+DEF_HELPER_3(vfsqrt_d, void, env, i32, i32)
+DEF_HELPER_3(vfrecip_s, void, env, i32, i32)
+DEF_HELPER_3(vfrecip_d, void, env, i32, i32)
+DEF_HELPER_3(vfrsqrt_s, void, env, i32, i32)
+DEF_HELPER_3(vfrsqrt_d, void, env, i32, i32)
+
+DEF_HELPER_3(vfcvtl_s_h, void, env, i32, i32)
+DEF_HELPER_3(vfcvth_s_h, void, env, i32, i32)
+DEF_HELPER_3(vfcvtl_d_s, void, env, i32, i32)
+DEF_HELPER_3(vfcvth_d_s, void, env, i32, i32)
+DEF_HELPER_4(vfcvt_h_s, void, env, i32, i32, i32)
+DEF_HELPER_4(vfcvt_s_d, void, env, i32, i32, i32)
+
+DEF_HELPER_3(vfrintrne_s, void, env, i32, i32)
+DEF_HELPER_3(vfrintrne_d, void, env, i32, i32)
+DEF_HELPER_3(vfrintrz_s, void, env, i32, i32)
+DEF_HELPER_3(vfrintrz_d, void, env, i32, i32)
+DEF_HELPER_3(vfrintrp_s, void, env, i32, i32)
+DEF_HELPER_3(vfrintrp_d, void, env, i32, i32)
+DEF_HELPER_3(vfrintrm_s, void, env, i32, i32)
+DEF_HELPER_3(vfrintrm_d, void, env, i32, i32)
+DEF_HELPER_3(vfrint_s, void, env, i32, i32)
+DEF_HELPER_3(vfrint_d, void, env, i32, i32)
+
+DEF_HELPER_3(vftintrne_w_s, void, env, i32, i32)
+DEF_HELPER_3(vftintrne_l_d, void, env, i32, i32)
+DEF_HELPER_3(vftintrz_w_s, void, env, i32, i32)
+DEF_HELPER_3(vftintrz_l_d, void, env, i32, i32)
+DEF_HELPER_3(vftintrp_w_s, void, env, i32, i32)
+DEF_HELPER_3(vftintrp_l_d, void, env, i32, i32)
+DEF_HELPER_3(vftintrm_w_s, void, env, i32, i32)
+DEF_HELPER_3(vftintrm_l_d, void, env, i32, i32)
+DEF_HELPER_3(vftint_w_s, void, env, i32, i32)
+DEF_HELPER_3(vftint_l_d, void, env, i32, i32)
+DEF_HELPER_3(vftintrz_wu_s, void, env, i32, i32)
+DEF_HELPER_3(vftintrz_lu_d, void, env, i32, i32)
+DEF_HELPER_3(vftint_wu_s, void, env, i32, i32)
+DEF_HELPER_3(vftint_lu_d, void, env, i32, i32)
+DEF_HELPER_4(vftintrne_w_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vftintrz_w_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vftintrp_w_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vftintrm_w_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vftint_w_d, void, env, i32, i32, i32)
+DEF_HELPER_3(vftintrnel_l_s, void, env, i32, i32)
+DEF_HELPER_3(vftintrneh_l_s, void, env, i32, i32)
+DEF_HELPER_3(vftintrzl_l_s, void, env, i32, i32)
+DEF_HELPER_3(vftintrzh_l_s, void, env, i32, i32)
+DEF_HELPER_3(vftintrpl_l_s, void, env, i32, i32)
+DEF_HELPER_3(vftintrph_l_s, void, env, i32, i32)
+DEF_HELPER_3(vftintrml_l_s, void, env, i32, i32)
+DEF_HELPER_3(vftintrmh_l_s, void, env, i32, i32)
+DEF_HELPER_3(vftintl_l_s, void, env, i32, i32)
+DEF_HELPER_3(vftinth_l_s, void, env, i32, i32)
+
+DEF_HELPER_3(vffint_s_w, void, env, i32, i32)
+DEF_HELPER_3(vffint_d_l, void, env, i32, i32)
+DEF_HELPER_3(vffint_s_wu, void, env, i32, i32)
+DEF_HELPER_3(vffint_d_lu, void, env, i32, i32)
+DEF_HELPER_3(vffintl_d_w, void, env, i32, i32)
+DEF_HELPER_3(vffinth_d_w, void, env, i32, i32)
+DEF_HELPER_4(vffint_s_l, void, env, i32, i32, i32)
+
+DEF_HELPER_FLAGS_4(vseqi_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vseqi_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vseqi_w, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vseqi_d, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+
+DEF_HELPER_FLAGS_4(vslei_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vslei_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vslei_w, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vslei_d, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vslei_bu, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vslei_hu, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vslei_wu, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vslei_du, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+
+DEF_HELPER_FLAGS_4(vslti_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vslti_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vslti_w, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vslti_d, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vslti_bu, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vslti_hu, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vslti_wu, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vslti_du, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+
+DEF_HELPER_5(vfcmp_c_s, void, env, i32, i32, i32, i32)
+DEF_HELPER_5(vfcmp_s_s, void, env, i32, i32, i32, i32)
+DEF_HELPER_5(vfcmp_c_d, void, env, i32, i32, i32, i32)
+DEF_HELPER_5(vfcmp_s_d, void, env, i32, i32, i32, i32)
+
+DEF_HELPER_FLAGS_4(vbitseli_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+
+DEF_HELPER_3(vsetanyeqz_b, void, env, i32, i32)
+DEF_HELPER_3(vsetanyeqz_h, void, env, i32, i32)
+DEF_HELPER_3(vsetanyeqz_w, void, env, i32, i32)
+DEF_HELPER_3(vsetanyeqz_d, void, env, i32, i32)
+DEF_HELPER_3(vsetallnez_b, void, env, i32, i32)
+DEF_HELPER_3(vsetallnez_h, void, env, i32, i32)
+DEF_HELPER_3(vsetallnez_w, void, env, i32, i32)
+DEF_HELPER_3(vsetallnez_d, void, env, i32, i32)
+
+DEF_HELPER_4(vpackev_b, void, env, i32, i32, i32)
+DEF_HELPER_4(vpackev_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vpackev_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vpackev_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vpackod_b, void, env, i32, i32, i32)
+DEF_HELPER_4(vpackod_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vpackod_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vpackod_d, void, env, i32, i32, i32)
+
+DEF_HELPER_4(vpickev_b, void, env, i32, i32, i32)
+DEF_HELPER_4(vpickev_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vpickev_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vpickev_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vpickod_b, void, env, i32, i32, i32)
+DEF_HELPER_4(vpickod_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vpickod_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vpickod_d, void, env, i32, i32, i32)
+
+DEF_HELPER_4(vilvl_b, void, env, i32, i32, i32)
+DEF_HELPER_4(vilvl_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vilvl_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vilvl_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vilvh_b, void, env, i32, i32, i32)
+DEF_HELPER_4(vilvh_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vilvh_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vilvh_d, void, env, i32, i32, i32)
+
+DEF_HELPER_5(vshuf_b, void, env, i32, i32, i32, i32)
+DEF_HELPER_4(vshuf_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vshuf_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vshuf_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vshuf4i_b, void, env, i32, i32, i32)
+DEF_HELPER_4(vshuf4i_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vshuf4i_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vshuf4i_d, void, env, i32, i32, i32)
+
+DEF_HELPER_4(vpermi_w, void, env, i32, i32, i32)
+
+DEF_HELPER_4(vextrins_b, void, env, i32, i32, i32)
+DEF_HELPER_4(vextrins_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vextrins_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vextrins_d, void, env, i32, i32, i32)

target/loongarch/insn_trans/trans_farith.c.inc

@@ -17,18 +17,29 @@
 static bool gen_fff(DisasContext *ctx, arg_fff *a,
                     void (*func)(TCGv, TCGv_env, TCGv, TCGv))
 {
+    TCGv dest = get_fpr(ctx, a->fd);
+    TCGv src1 = get_fpr(ctx, a->fj);
+    TCGv src2 = get_fpr(ctx, a->fk);
+
     CHECK_FPE;
 
-    func(cpu_fpr[a->fd], cpu_env, cpu_fpr[a->fj], cpu_fpr[a->fk]);
+    func(dest, cpu_env, src1, src2);
+    set_fpr(a->fd, dest);
+
     return true;
 }
 
 static bool gen_ff(DisasContext *ctx, arg_ff *a,
                    void (*func)(TCGv, TCGv_env, TCGv))
 {
+    TCGv dest = get_fpr(ctx, a->fd);
+    TCGv src = get_fpr(ctx, a->fj);
+
     CHECK_FPE;
 
-    func(cpu_fpr[a->fd], cpu_env, cpu_fpr[a->fj]);
+    func(dest, cpu_env, src);
+    set_fpr(a->fd, dest);
+
     return true;
 }
 
@@ -37,61 +48,98 @@ static bool gen_muladd(DisasContext *ctx, arg_ffff *a,
                        int flag)
 {
     TCGv_i32 tflag = tcg_constant_i32(flag);
+    TCGv dest = get_fpr(ctx, a->fd);
+    TCGv src1 = get_fpr(ctx, a->fj);
+    TCGv src2 = get_fpr(ctx, a->fk);
+    TCGv src3 = get_fpr(ctx, a->fa);
 
     CHECK_FPE;
 
-    func(cpu_fpr[a->fd], cpu_env, cpu_fpr[a->fj],
-         cpu_fpr[a->fk], cpu_fpr[a->fa], tflag);
+    func(dest, cpu_env, src1, src2, src3, tflag);
+    set_fpr(a->fd, dest);
+
     return true;
 }
 
 static bool trans_fcopysign_s(DisasContext *ctx, arg_fcopysign_s *a)
 {
+    TCGv dest = get_fpr(ctx, a->fd);
+    TCGv src1 = get_fpr(ctx, a->fk);
+    TCGv src2 = get_fpr(ctx, a->fj);
+
     CHECK_FPE;
 
-    tcg_gen_deposit_i64(cpu_fpr[a->fd], cpu_fpr[a->fk], cpu_fpr[a->fj], 0, 31);
+    tcg_gen_deposit_i64(dest, src1, src2, 0, 31);
+    set_fpr(a->fd, dest);
+
     return true;
 }
 
 static bool trans_fcopysign_d(DisasContext *ctx, arg_fcopysign_d *a)
 {
+    TCGv dest = get_fpr(ctx, a->fd);
+    TCGv src1 = get_fpr(ctx, a->fk);
+    TCGv src2 = get_fpr(ctx, a->fj);
+
     CHECK_FPE;
 
-    tcg_gen_deposit_i64(cpu_fpr[a->fd], cpu_fpr[a->fk], cpu_fpr[a->fj], 0, 63);
+    tcg_gen_deposit_i64(dest, src1, src2, 0, 63);
+    set_fpr(a->fd, dest);
+
     return true;
 }
 
 static bool trans_fabs_s(DisasContext *ctx, arg_fabs_s *a)
 {
+    TCGv dest = get_fpr(ctx, a->fd);
+    TCGv src = get_fpr(ctx, a->fj);
+
     CHECK_FPE;
 
-    tcg_gen_andi_i64(cpu_fpr[a->fd], cpu_fpr[a->fj], MAKE_64BIT_MASK(0, 31));
-    gen_nanbox_s(cpu_fpr[a->fd], cpu_fpr[a->fd]);
+    tcg_gen_andi_i64(dest, src, MAKE_64BIT_MASK(0, 31));
+    gen_nanbox_s(dest, dest);
+    set_fpr(a->fd, dest);
+
     return true;
 }
 
 static bool trans_fabs_d(DisasContext *ctx, arg_fabs_d *a)
 {
+    TCGv dest = get_fpr(ctx, a->fd);
+    TCGv src = get_fpr(ctx, a->fj);
+
     CHECK_FPE;
 
-    tcg_gen_andi_i64(cpu_fpr[a->fd], cpu_fpr[a->fj], MAKE_64BIT_MASK(0, 63));
+    tcg_gen_andi_i64(dest, src, MAKE_64BIT_MASK(0, 63));
+    set_fpr(a->fd, dest);
+
     return true;
 }
 
 static bool trans_fneg_s(DisasContext *ctx, arg_fneg_s *a)
 {
+    TCGv dest = get_fpr(ctx, a->fd);
+    TCGv src = get_fpr(ctx, a->fj);
+
     CHECK_FPE;
 
-    tcg_gen_xori_i64(cpu_fpr[a->fd], cpu_fpr[a->fj], 0x80000000);
-    gen_nanbox_s(cpu_fpr[a->fd], cpu_fpr[a->fd]);
+    tcg_gen_xori_i64(dest, src, 0x80000000);
+    gen_nanbox_s(dest, dest);
+    set_fpr(a->fd, dest);
+
     return true;
 }
 
 static bool trans_fneg_d(DisasContext *ctx, arg_fneg_d *a)
 {
+    TCGv dest = get_fpr(ctx, a->fd);
+    TCGv src = get_fpr(ctx, a->fj);
+
     CHECK_FPE;
 
-    tcg_gen_xori_i64(cpu_fpr[a->fd], cpu_fpr[a->fj], 0x8000000000000000LL);
+    tcg_gen_xori_i64(dest, src, 0x8000000000000000LL);
+    set_fpr(a->fd, dest);
+
     return true;
 }
 

target/loongarch/insn_trans/trans_fcmp.c.inc

@@ -25,17 +25,19 @@ static uint32_t get_fcmp_flags(int cond)
 
 static bool trans_fcmp_cond_s(DisasContext *ctx, arg_fcmp_cond_s *a)
 {
-    TCGv var;
+    TCGv var, src1, src2;
     uint32_t flags;
     void (*fn)(TCGv, TCGv_env, TCGv, TCGv, TCGv_i32);
 
     CHECK_FPE;
 
     var = tcg_temp_new();
+    src1 = get_fpr(ctx, a->fj);
+    src2 = get_fpr(ctx, a->fk);
     fn = (a->fcond & 1 ? gen_helper_fcmp_s_s : gen_helper_fcmp_c_s);
     flags = get_fcmp_flags(a->fcond >> 1);
 
-    fn(var, cpu_env, cpu_fpr[a->fj], cpu_fpr[a->fk], tcg_constant_i32(flags));
+    fn(var, cpu_env, src1, src2, tcg_constant_i32(flags));
 
     tcg_gen_st8_tl(var, cpu_env, offsetof(CPULoongArchState, cf[a->cd]));
     return true;
@@ -43,17 +45,19 @@ static bool trans_fcmp_cond_s(DisasContext *ctx, arg_fcmp_cond_s *a)
 
 static bool trans_fcmp_cond_d(DisasContext *ctx, arg_fcmp_cond_d *a)
 {
-    TCGv var;
+    TCGv var, src1, src2;
     uint32_t flags;
     void (*fn)(TCGv, TCGv_env, TCGv, TCGv, TCGv_i32);
 
     CHECK_FPE;
 
     var = tcg_temp_new();
+    src1 = get_fpr(ctx, a->fj);
+    src2 = get_fpr(ctx, a->fk);
     fn = (a->fcond & 1 ? gen_helper_fcmp_s_d : gen_helper_fcmp_c_d);
     flags = get_fcmp_flags(a->fcond >> 1);
 
-    fn(var, cpu_env, cpu_fpr[a->fj], cpu_fpr[a->fk], tcg_constant_i32(flags));
+    fn(var, cpu_env, src1, src2, tcg_constant_i32(flags));
 
     tcg_gen_st8_tl(var, cpu_env, offsetof(CPULoongArchState, cf[a->cd]));
     return true;

target/loongarch/insn_trans/trans_fmemory.c.inc

@@ -13,6 +13,7 @@ static void maybe_nanbox_load(TCGv freg, MemOp mop)
 static bool gen_fload_i(DisasContext *ctx, arg_fr_i *a, MemOp mop)
 {
     TCGv addr = gpr_src(ctx, a->rj, EXT_NONE);
+    TCGv dest = get_fpr(ctx, a->fd);
 
     CHECK_FPE;
 
@@ -22,8 +23,9 @@ static bool gen_fload_i(DisasContext *ctx, arg_fr_i *a, MemOp mop)
         addr = temp;
     }
 
-    tcg_gen_qemu_ld_tl(cpu_fpr[a->fd], addr, ctx->mem_idx, mop);
-    maybe_nanbox_load(cpu_fpr[a->fd], mop);
+    tcg_gen_qemu_ld_tl(dest, addr, ctx->mem_idx, mop);
+    maybe_nanbox_load(dest, mop);
+    set_fpr(a->fd, dest);
 
     return true;
 }
@@ -31,6 +33,7 @@ static bool gen_fload_i(DisasContext *ctx, arg_fr_i *a, MemOp mop)
 static bool gen_fstore_i(DisasContext *ctx, arg_fr_i *a, MemOp mop)
 {
     TCGv addr = gpr_src(ctx, a->rj, EXT_NONE);
+    TCGv src = get_fpr(ctx, a->fd);
 
     CHECK_FPE;
 
@@ -40,7 +43,8 @@ static bool gen_fstore_i(DisasContext *ctx, arg_fr_i *a, MemOp mop)
         addr = temp;
     }
 
-    tcg_gen_qemu_st_tl(cpu_fpr[a->fd], addr, ctx->mem_idx, mop);
+    tcg_gen_qemu_st_tl(src, addr, ctx->mem_idx, mop);
+
     return true;
 }
 
@@ -48,14 +52,16 @@ static bool gen_floadx(DisasContext *ctx, arg_frr *a, MemOp mop)
 {
     TCGv src1 = gpr_src(ctx, a->rj, EXT_NONE);
     TCGv src2 = gpr_src(ctx, a->rk, EXT_NONE);
+    TCGv dest = get_fpr(ctx, a->fd);
     TCGv addr;
 
     CHECK_FPE;
 
     addr = tcg_temp_new();
     tcg_gen_add_tl(addr, src1, src2);
-    tcg_gen_qemu_ld_tl(cpu_fpr[a->fd], addr, ctx->mem_idx, mop);
-    maybe_nanbox_load(cpu_fpr[a->fd], mop);
+    tcg_gen_qemu_ld_tl(dest, addr, ctx->mem_idx, mop);
+    maybe_nanbox_load(dest, mop);
+    set_fpr(a->fd, dest);
 
     return true;
 }
@@ -64,13 +70,14 @@ static bool gen_fstorex(DisasContext *ctx, arg_frr *a, MemOp mop)
 {
     TCGv src1 = gpr_src(ctx, a->rj, EXT_NONE);
     TCGv src2 = gpr_src(ctx, a->rk, EXT_NONE);
+    TCGv src3 = get_fpr(ctx, a->fd);
     TCGv addr;
 
     CHECK_FPE;
 
     addr = tcg_temp_new();
     tcg_gen_add_tl(addr, src1, src2);
-    tcg_gen_qemu_st_tl(cpu_fpr[a->fd], addr, ctx->mem_idx, mop);
+    tcg_gen_qemu_st_tl(src3, addr, ctx->mem_idx, mop);
 
     return true;
 }
@@ -79,6 +86,7 @@ static bool gen_fload_gt(DisasContext *ctx, arg_frr *a, MemOp mop)
 {
     TCGv src1 = gpr_src(ctx, a->rj, EXT_NONE);
     TCGv src2 = gpr_src(ctx, a->rk, EXT_NONE);
+    TCGv dest = get_fpr(ctx, a->fd);
     TCGv addr;
 
     CHECK_FPE;
@@ -86,8 +94,9 @@ static bool gen_fload_gt(DisasContext *ctx, arg_frr *a, MemOp mop)
     addr = tcg_temp_new();
     gen_helper_asrtgt_d(cpu_env, src1, src2);
     tcg_gen_add_tl(addr, src1, src2);
-    tcg_gen_qemu_ld_tl(cpu_fpr[a->fd], addr, ctx->mem_idx, mop);
-    maybe_nanbox_load(cpu_fpr[a->fd], mop);
+    tcg_gen_qemu_ld_tl(dest, addr, ctx->mem_idx, mop);
+    maybe_nanbox_load(dest, mop);
+    set_fpr(a->fd, dest);
 
     return true;
 }
@@ -96,6 +105,7 @@ static bool gen_fstore_gt(DisasContext *ctx, arg_frr *a, MemOp mop)
 {
     TCGv src1 = gpr_src(ctx, a->rj, EXT_NONE);
     TCGv src2 = gpr_src(ctx, a->rk, EXT_NONE);
+    TCGv src3 = get_fpr(ctx, a->fd);
     TCGv addr;
 
     CHECK_FPE;
@@ -103,7 +113,7 @@ static bool gen_fstore_gt(DisasContext *ctx, arg_frr *a, MemOp mop)
     addr = tcg_temp_new();
     gen_helper_asrtgt_d(cpu_env, src1, src2);
     tcg_gen_add_tl(addr, src1, src2);
-    tcg_gen_qemu_st_tl(cpu_fpr[a->fd], addr, ctx->mem_idx, mop);
+    tcg_gen_qemu_st_tl(src3, addr, ctx->mem_idx, mop);
 
     return true;
 }
@@ -112,6 +122,7 @@ static bool gen_fload_le(DisasContext *ctx, arg_frr *a, MemOp mop)
 {
     TCGv src1 = gpr_src(ctx, a->rj, EXT_NONE);
     TCGv src2 = gpr_src(ctx, a->rk, EXT_NONE);
+    TCGv dest = get_fpr(ctx, a->fd);
     TCGv addr;
 
     CHECK_FPE;
@@ -119,8 +130,9 @@ static bool gen_fload_le(DisasContext *ctx, arg_frr *a, MemOp mop)
     addr = tcg_temp_new();
     gen_helper_asrtle_d(cpu_env, src1, src2);
     tcg_gen_add_tl(addr, src1, src2);
-    tcg_gen_qemu_ld_tl(cpu_fpr[a->fd], addr, ctx->mem_idx, mop);
-    maybe_nanbox_load(cpu_fpr[a->fd], mop);
+    tcg_gen_qemu_ld_tl(dest, addr, ctx->mem_idx, mop);
+    maybe_nanbox_load(dest, mop);
+    set_fpr(a->fd, dest);
 
     return true;
 }
@@ -129,6 +141,7 @@ static bool gen_fstore_le(DisasContext *ctx, arg_frr *a, MemOp mop)
 {
     TCGv src1 = gpr_src(ctx, a->rj, EXT_NONE);
     TCGv src2 = gpr_src(ctx, a->rk, EXT_NONE);
+    TCGv src3 = get_fpr(ctx, a->fd);
     TCGv addr;
 
     CHECK_FPE;
@@ -136,7 +149,7 @@ static bool gen_fstore_le(DisasContext *ctx, arg_frr *a, MemOp mop)
     addr = tcg_temp_new();
     gen_helper_asrtle_d(cpu_env, src1, src2);
     tcg_gen_add_tl(addr, src1, src2);
-    tcg_gen_qemu_st_tl(cpu_fpr[a->fd], addr, ctx->mem_idx, mop);
+    tcg_gen_qemu_st_tl(src3, addr, ctx->mem_idx, mop);
 
     return true;
 }

target/loongarch/insn_trans/trans_fmov.c.inc

@@ -10,14 +10,17 @@ static const uint32_t fcsr_mask[4] = {
 static bool trans_fsel(DisasContext *ctx, arg_fsel *a)
 {
     TCGv zero = tcg_constant_tl(0);
+    TCGv dest = get_fpr(ctx, a->fd);
+    TCGv src1 = get_fpr(ctx, a->fj);
+    TCGv src2 = get_fpr(ctx, a->fk);
     TCGv cond;
 
     CHECK_FPE;
 
     cond = tcg_temp_new();
     tcg_gen_ld8u_tl(cond, cpu_env, offsetof(CPULoongArchState, cf[a->ca]));
-    tcg_gen_movcond_tl(TCG_COND_EQ, cpu_fpr[a->fd], cond, zero,
-                       cpu_fpr[a->fj], cpu_fpr[a->fk]);
+    tcg_gen_movcond_tl(TCG_COND_EQ, dest, cond, zero, src1, src2);
+    set_fpr(a->fd, dest);
 
     return true;
 }
@@ -25,15 +28,16 @@ static bool trans_fsel(DisasContext *ctx, arg_fsel *a)
 static bool gen_f2f(DisasContext *ctx, arg_ff *a,
                     void (*func)(TCGv, TCGv), bool nanbox)
 {
-    TCGv dest = cpu_fpr[a->fd];
-    TCGv src = cpu_fpr[a->fj];
+    TCGv dest = get_fpr(ctx, a->fd);
+    TCGv src = get_fpr(ctx, a->fj);
 
     CHECK_FPE;
 
     func(dest, src);
     if (nanbox) {
-        gen_nanbox_s(cpu_fpr[a->fd], cpu_fpr[a->fd]);
+        gen_nanbox_s(dest, dest);
     }
+    set_fpr(a->fd, dest);
 
     return true;
 }
@@ -42,10 +46,13 @@ static bool gen_r2f(DisasContext *ctx, arg_fr *a,
                     void (*func)(TCGv, TCGv))
 {
     TCGv src = gpr_src(ctx, a->rj, EXT_NONE);
+    TCGv dest = get_fpr(ctx, a->fd);
 
     CHECK_FPE;
 
-    func(cpu_fpr[a->fd], src);
+    func(dest, src);
+    set_fpr(a->fd, dest);
+
     return true;
 }
 
@@ -53,10 +60,11 @@ static bool gen_f2r(DisasContext *ctx, arg_rf *a,
                     void (*func)(TCGv, TCGv))
 {
     TCGv dest = gpr_dst(ctx, a->rd, EXT_NONE);
+    TCGv src = get_fpr(ctx, a->fj);
 
     CHECK_FPE;
 
-    func(dest, cpu_fpr[a->fj]);
+    func(dest, src);
     gen_set_gpr(a->rd, dest, EXT_NONE);
 
     return true;
@@ -124,11 +132,12 @@ static void gen_movfrh2gr_s(TCGv dest, TCGv src)
 static bool trans_movfr2cf(DisasContext *ctx, arg_movfr2cf *a)
 {
     TCGv t0;
+    TCGv src = get_fpr(ctx, a->fj);
 
     CHECK_FPE;
 
     t0 = tcg_temp_new();
-    tcg_gen_andi_tl(t0, cpu_fpr[a->fj], 0x1);
+    tcg_gen_andi_tl(t0, src, 0x1);
     tcg_gen_st8_tl(t0, cpu_env, offsetof(CPULoongArchState, cf[a->cd & 0x7]));
 
     return true;
@@ -136,10 +145,14 @@ static bool trans_movfr2cf(DisasContext *ctx, arg_movfr2cf *a)
 
 static bool trans_movcf2fr(DisasContext *ctx, arg_movcf2fr *a)
 {
+    TCGv dest = get_fpr(ctx, a->fd);
+
     CHECK_FPE;
 
-    tcg_gen_ld8u_tl(cpu_fpr[a->fd], cpu_env,
+    tcg_gen_ld8u_tl(dest, cpu_env,
                     offsetof(CPULoongArchState, cf[a->cj & 0x7]));
+    set_fpr(a->fd, dest);
+
     return true;
 }
 

target/loongarch/insn_trans/trans_lsx.c.inc

@@ -0,0 +1,4400 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * LSX translate functions
+ * Copyright (c) 2022-2023 Loongson Technology Corporation Limited
+ */
+
+#ifndef CONFIG_USER_ONLY
+#define CHECK_SXE do { \
+    if ((ctx->base.tb->flags & HW_FLAGS_EUEN_SXE) == 0) { \
+        generate_exception(ctx, EXCCODE_SXD); \
+        return true; \
+    } \
+} while (0)
+#else
+#define CHECK_SXE
+#endif
+
+static bool gen_vvvv(DisasContext *ctx, arg_vvvv *a,
+                     void (*func)(TCGv_ptr, TCGv_i32, TCGv_i32,
+                                  TCGv_i32, TCGv_i32))
+{
+    TCGv_i32 vd = tcg_constant_i32(a->vd);
+    TCGv_i32 vj = tcg_constant_i32(a->vj);
+    TCGv_i32 vk = tcg_constant_i32(a->vk);
+    TCGv_i32 va = tcg_constant_i32(a->va);
+
+    CHECK_SXE;
+    func(cpu_env, vd, vj, vk, va);
+    return true;
+}
+
+static bool gen_vvv(DisasContext *ctx, arg_vvv *a,
+                    void (*func)(TCGv_ptr, TCGv_i32, TCGv_i32, TCGv_i32))
+{
+    TCGv_i32 vd = tcg_constant_i32(a->vd);
+    TCGv_i32 vj = tcg_constant_i32(a->vj);
+    TCGv_i32 vk = tcg_constant_i32(a->vk);
+
+    CHECK_SXE;
+
+    func(cpu_env, vd, vj, vk);
+    return true;
+}
+
+static bool gen_vv(DisasContext *ctx, arg_vv *a,
+                   void (*func)(TCGv_ptr, TCGv_i32, TCGv_i32))
+{
+    TCGv_i32 vd = tcg_constant_i32(a->vd);
+    TCGv_i32 vj = tcg_constant_i32(a->vj);
+
+    CHECK_SXE;
+    func(cpu_env, vd, vj);
+    return true;
+}
+
+static bool gen_vv_i(DisasContext *ctx, arg_vv_i *a,
+                     void (*func)(TCGv_ptr, TCGv_i32, TCGv_i32, TCGv_i32))
+{
+    TCGv_i32 vd = tcg_constant_i32(a->vd);
+    TCGv_i32 vj = tcg_constant_i32(a->vj);
+    TCGv_i32 imm = tcg_constant_i32(a->imm);
+
+    CHECK_SXE;
+    func(cpu_env, vd, vj, imm);
+    return true;
+}
+
+static bool gen_cv(DisasContext *ctx, arg_cv *a,
+                    void (*func)(TCGv_ptr, TCGv_i32, TCGv_i32))
+{
+    TCGv_i32 vj = tcg_constant_i32(a->vj);
+    TCGv_i32 cd = tcg_constant_i32(a->cd);
+
+    CHECK_SXE;
+    func(cpu_env, cd, vj);
+    return true;
+}
+
+static bool gvec_vvv(DisasContext *ctx, arg_vvv *a, MemOp mop,
+                     void (*func)(unsigned, uint32_t, uint32_t,
+                                  uint32_t, uint32_t, uint32_t))
+{
+    uint32_t vd_ofs, vj_ofs, vk_ofs;
+
+    CHECK_SXE;
+
+    vd_ofs = vec_full_offset(a->vd);
+    vj_ofs = vec_full_offset(a->vj);
+    vk_ofs = vec_full_offset(a->vk);
+
+    func(mop, vd_ofs, vj_ofs, vk_ofs, 16, ctx->vl/8);
+    return true;
+}
+
+static bool gvec_vv(DisasContext *ctx, arg_vv *a, MemOp mop,
+                    void (*func)(unsigned, uint32_t, uint32_t,
+                                 uint32_t, uint32_t))
+{
+    uint32_t vd_ofs, vj_ofs;
+
+    CHECK_SXE;
+
+    vd_ofs = vec_full_offset(a->vd);
+    vj_ofs = vec_full_offset(a->vj);
+
+    func(mop, vd_ofs, vj_ofs, 16, ctx->vl/8);
+    return true;
+}
+
+static bool gvec_vv_i(DisasContext *ctx, arg_vv_i *a, MemOp mop,
+                      void (*func)(unsigned, uint32_t, uint32_t,
+                                   int64_t, uint32_t, uint32_t))
+{
+    uint32_t vd_ofs, vj_ofs;
+
+    CHECK_SXE;
+
+    vd_ofs = vec_full_offset(a->vd);
+    vj_ofs = vec_full_offset(a->vj);
+
+    func(mop, vd_ofs, vj_ofs, a->imm , 16, ctx->vl/8);
+    return true;
+}
+
+static bool gvec_subi(DisasContext *ctx, arg_vv_i *a, MemOp mop)
+{
+    uint32_t vd_ofs, vj_ofs;
+
+    CHECK_SXE;
+
+    vd_ofs = vec_full_offset(a->vd);
+    vj_ofs = vec_full_offset(a->vj);
+
+    tcg_gen_gvec_addi(mop, vd_ofs, vj_ofs, -a->imm, 16, ctx->vl/8);
+    return true;
+}
+
+TRANS(vadd_b, gvec_vvv, MO_8, tcg_gen_gvec_add)
+TRANS(vadd_h, gvec_vvv, MO_16, tcg_gen_gvec_add)
+TRANS(vadd_w, gvec_vvv, MO_32, tcg_gen_gvec_add)
+TRANS(vadd_d, gvec_vvv, MO_64, tcg_gen_gvec_add)
+
+#define VADDSUB_Q(NAME)                                        \
+static bool trans_v## NAME ##_q(DisasContext *ctx, arg_vvv *a) \
+{                                                              \
+    TCGv_i64 rh, rl, ah, al, bh, bl;                           \
+                                                               \
+    CHECK_SXE;                                                 \
+                                                               \
+    rh = tcg_temp_new_i64();                                   \
+    rl = tcg_temp_new_i64();                                   \
+    ah = tcg_temp_new_i64();                                   \
+    al = tcg_temp_new_i64();                                   \
+    bh = tcg_temp_new_i64();                                   \
+    bl = tcg_temp_new_i64();                                   \
+                                                               \
+    get_vreg64(ah, a->vj, 1);                                  \
+    get_vreg64(al, a->vj, 0);                                  \
+    get_vreg64(bh, a->vk, 1);                                  \
+    get_vreg64(bl, a->vk, 0);                                  \
+                                                               \
+    tcg_gen_## NAME ##2_i64(rl, rh, al, ah, bl, bh);           \
+                                                               \
+    set_vreg64(rh, a->vd, 1);                                  \
+    set_vreg64(rl, a->vd, 0);                                  \
+                                                               \
+    return true;                                               \
+}
+
+VADDSUB_Q(add)
+VADDSUB_Q(sub)
+
+TRANS(vsub_b, gvec_vvv, MO_8, tcg_gen_gvec_sub)
+TRANS(vsub_h, gvec_vvv, MO_16, tcg_gen_gvec_sub)
+TRANS(vsub_w, gvec_vvv, MO_32, tcg_gen_gvec_sub)
+TRANS(vsub_d, gvec_vvv, MO_64, tcg_gen_gvec_sub)
+
+TRANS(vaddi_bu, gvec_vv_i, MO_8, tcg_gen_gvec_addi)
+TRANS(vaddi_hu, gvec_vv_i, MO_16, tcg_gen_gvec_addi)
+TRANS(vaddi_wu, gvec_vv_i, MO_32, tcg_gen_gvec_addi)
+TRANS(vaddi_du, gvec_vv_i, MO_64, tcg_gen_gvec_addi)
+TRANS(vsubi_bu, gvec_subi, MO_8)
+TRANS(vsubi_hu, gvec_subi, MO_16)
+TRANS(vsubi_wu, gvec_subi, MO_32)
+TRANS(vsubi_du, gvec_subi, MO_64)
+
+TRANS(vneg_b, gvec_vv, MO_8, tcg_gen_gvec_neg)
+TRANS(vneg_h, gvec_vv, MO_16, tcg_gen_gvec_neg)
+TRANS(vneg_w, gvec_vv, MO_32, tcg_gen_gvec_neg)
+TRANS(vneg_d, gvec_vv, MO_64, tcg_gen_gvec_neg)
+
+TRANS(vsadd_b, gvec_vvv, MO_8, tcg_gen_gvec_ssadd)
+TRANS(vsadd_h, gvec_vvv, MO_16, tcg_gen_gvec_ssadd)
+TRANS(vsadd_w, gvec_vvv, MO_32, tcg_gen_gvec_ssadd)
+TRANS(vsadd_d, gvec_vvv, MO_64, tcg_gen_gvec_ssadd)
+TRANS(vsadd_bu, gvec_vvv, MO_8, tcg_gen_gvec_usadd)
+TRANS(vsadd_hu, gvec_vvv, MO_16, tcg_gen_gvec_usadd)
+TRANS(vsadd_wu, gvec_vvv, MO_32, tcg_gen_gvec_usadd)
+TRANS(vsadd_du, gvec_vvv, MO_64, tcg_gen_gvec_usadd)
+TRANS(vssub_b, gvec_vvv, MO_8, tcg_gen_gvec_sssub)
+TRANS(vssub_h, gvec_vvv, MO_16, tcg_gen_gvec_sssub)
+TRANS(vssub_w, gvec_vvv, MO_32, tcg_gen_gvec_sssub)
+TRANS(vssub_d, gvec_vvv, MO_64, tcg_gen_gvec_sssub)
+TRANS(vssub_bu, gvec_vvv, MO_8, tcg_gen_gvec_ussub)
+TRANS(vssub_hu, gvec_vvv, MO_16, tcg_gen_gvec_ussub)
+TRANS(vssub_wu, gvec_vvv, MO_32, tcg_gen_gvec_ussub)
+TRANS(vssub_du, gvec_vvv, MO_64, tcg_gen_gvec_ussub)
+
+TRANS(vhaddw_h_b, gen_vvv, gen_helper_vhaddw_h_b)
+TRANS(vhaddw_w_h, gen_vvv, gen_helper_vhaddw_w_h)
+TRANS(vhaddw_d_w, gen_vvv, gen_helper_vhaddw_d_w)
+TRANS(vhaddw_q_d, gen_vvv, gen_helper_vhaddw_q_d)
+TRANS(vhaddw_hu_bu, gen_vvv, gen_helper_vhaddw_hu_bu)
+TRANS(vhaddw_wu_hu, gen_vvv, gen_helper_vhaddw_wu_hu)
+TRANS(vhaddw_du_wu, gen_vvv, gen_helper_vhaddw_du_wu)
+TRANS(vhaddw_qu_du, gen_vvv, gen_helper_vhaddw_qu_du)
+TRANS(vhsubw_h_b, gen_vvv, gen_helper_vhsubw_h_b)
+TRANS(vhsubw_w_h, gen_vvv, gen_helper_vhsubw_w_h)
+TRANS(vhsubw_d_w, gen_vvv, gen_helper_vhsubw_d_w)
+TRANS(vhsubw_q_d, gen_vvv, gen_helper_vhsubw_q_d)
+TRANS(vhsubw_hu_bu, gen_vvv, gen_helper_vhsubw_hu_bu)
+TRANS(vhsubw_wu_hu, gen_vvv, gen_helper_vhsubw_wu_hu)
+TRANS(vhsubw_du_wu, gen_vvv, gen_helper_vhsubw_du_wu)
+TRANS(vhsubw_qu_du, gen_vvv, gen_helper_vhsubw_qu_du)
+
+static void gen_vaddwev_s(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    TCGv_vec t1, t2;
+
+    int halfbits = 4 << vece;
+
+    t1 = tcg_temp_new_vec_matching(a);
+    t2 = tcg_temp_new_vec_matching(b);
+
+    /* Sign-extend the even elements from a */
+    tcg_gen_shli_vec(vece, t1, a, halfbits);
+    tcg_gen_sari_vec(vece, t1, t1, halfbits);
+
+    /* Sign-extend the even elements from b */
+    tcg_gen_shli_vec(vece, t2, b, halfbits);
+    tcg_gen_sari_vec(vece, t2, t2, halfbits);
+
+    tcg_gen_add_vec(vece, t, t1, t2);
+}
+
+static void gen_vaddwev_w_h(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 t1, t2;
+
+    t1 = tcg_temp_new_i32();
+    t2 = tcg_temp_new_i32();
+    tcg_gen_ext16s_i32(t1, a);
+    tcg_gen_ext16s_i32(t2, b);
+    tcg_gen_add_i32(t, t1, t2);
+}
+
+static void gen_vaddwev_d_w(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b)
+{
+    TCGv_i64 t1, t2;
+
+    t1 = tcg_temp_new_i64();
+    t2 = tcg_temp_new_i64();
+    tcg_gen_ext32s_i64(t1, a);
+    tcg_gen_ext32s_i64(t2, b);
+    tcg_gen_add_i64(t, t1, t2);
+}
+
+static void do_vaddwev_s(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                         uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_shli_vec, INDEX_op_sari_vec, INDEX_op_add_vec, 0
+        };
+    static const GVecGen3 op[4] = {
+        {
+            .fniv = gen_vaddwev_s,
+            .fno = gen_helper_vaddwev_h_b,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fni4 = gen_vaddwev_w_h,
+            .fniv = gen_vaddwev_s,
+            .fno = gen_helper_vaddwev_w_h,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fni8 = gen_vaddwev_d_w,
+            .fniv = gen_vaddwev_s,
+            .fno = gen_helper_vaddwev_d_w,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+        {
+            .fno = gen_helper_vaddwev_q_d,
+            .vece = MO_128
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vaddwev_h_b, gvec_vvv, MO_8, do_vaddwev_s)
+TRANS(vaddwev_w_h, gvec_vvv, MO_16, do_vaddwev_s)
+TRANS(vaddwev_d_w, gvec_vvv, MO_32, do_vaddwev_s)
+TRANS(vaddwev_q_d, gvec_vvv, MO_64, do_vaddwev_s)
+
+static void gen_vaddwod_w_h(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 t1, t2;
+
+    t1 = tcg_temp_new_i32();
+    t2 = tcg_temp_new_i32();
+    tcg_gen_sari_i32(t1, a, 16);
+    tcg_gen_sari_i32(t2, b, 16);
+    tcg_gen_add_i32(t, t1, t2);
+}
+
+static void gen_vaddwod_d_w(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b)
+{
+    TCGv_i64 t1, t2;
+
+    t1 = tcg_temp_new_i64();
+    t2 = tcg_temp_new_i64();
+    tcg_gen_sari_i64(t1, a, 32);
+    tcg_gen_sari_i64(t2, b, 32);
+    tcg_gen_add_i64(t, t1, t2);
+}
+
+static void gen_vaddwod_s(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    TCGv_vec t1, t2;
+
+    int halfbits = 4 << vece;
+
+    t1 = tcg_temp_new_vec_matching(a);
+    t2 = tcg_temp_new_vec_matching(b);
+
+    /* Sign-extend the odd elements for vector */
+    tcg_gen_sari_vec(vece, t1, a, halfbits);
+    tcg_gen_sari_vec(vece, t2, b, halfbits);
+
+    tcg_gen_add_vec(vece, t, t1, t2);
+}
+
+static void do_vaddwod_s(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                         uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_sari_vec, INDEX_op_add_vec, 0
+        };
+    static const GVecGen3 op[4] = {
+        {
+            .fniv = gen_vaddwod_s,
+            .fno = gen_helper_vaddwod_h_b,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fni4 = gen_vaddwod_w_h,
+            .fniv = gen_vaddwod_s,
+            .fno = gen_helper_vaddwod_w_h,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fni8 = gen_vaddwod_d_w,
+            .fniv = gen_vaddwod_s,
+            .fno = gen_helper_vaddwod_d_w,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+        {
+            .fno = gen_helper_vaddwod_q_d,
+            .vece = MO_128
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vaddwod_h_b, gvec_vvv, MO_8, do_vaddwod_s)
+TRANS(vaddwod_w_h, gvec_vvv, MO_16, do_vaddwod_s)
+TRANS(vaddwod_d_w, gvec_vvv, MO_32, do_vaddwod_s)
+TRANS(vaddwod_q_d, gvec_vvv, MO_64, do_vaddwod_s)
+
+static void gen_vsubwev_s(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    TCGv_vec t1, t2;
+
+    int halfbits = 4 << vece;
+
+    t1 = tcg_temp_new_vec_matching(a);
+    t2 = tcg_temp_new_vec_matching(b);
+
+    /* Sign-extend the even elements from a */
+    tcg_gen_shli_vec(vece, t1, a, halfbits);
+    tcg_gen_sari_vec(vece, t1, t1, halfbits);
+
+    /* Sign-extend the even elements from b */
+    tcg_gen_shli_vec(vece, t2, b, halfbits);
+    tcg_gen_sari_vec(vece, t2, t2, halfbits);
+
+    tcg_gen_sub_vec(vece, t, t1, t2);
+}
+
+static void gen_vsubwev_w_h(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 t1, t2;
+
+    t1 = tcg_temp_new_i32();
+    t2 = tcg_temp_new_i32();
+    tcg_gen_ext16s_i32(t1, a);
+    tcg_gen_ext16s_i32(t2, b);
+    tcg_gen_sub_i32(t, t1, t2);
+}
+
+static void gen_vsubwev_d_w(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b)
+{
+    TCGv_i64 t1, t2;
+
+    t1 = tcg_temp_new_i64();
+    t2 = tcg_temp_new_i64();
+    tcg_gen_ext32s_i64(t1, a);
+    tcg_gen_ext32s_i64(t2, b);
+    tcg_gen_sub_i64(t, t1, t2);
+}
+
+static void do_vsubwev_s(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                         uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_shli_vec, INDEX_op_sari_vec, INDEX_op_sub_vec, 0
+        };
+    static const GVecGen3 op[4] = {
+        {
+            .fniv = gen_vsubwev_s,
+            .fno = gen_helper_vsubwev_h_b,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fni4 = gen_vsubwev_w_h,
+            .fniv = gen_vsubwev_s,
+            .fno = gen_helper_vsubwev_w_h,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fni8 = gen_vsubwev_d_w,
+            .fniv = gen_vsubwev_s,
+            .fno = gen_helper_vsubwev_d_w,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+        {
+            .fno = gen_helper_vsubwev_q_d,
+            .vece = MO_128
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vsubwev_h_b, gvec_vvv, MO_8, do_vsubwev_s)
+TRANS(vsubwev_w_h, gvec_vvv, MO_16, do_vsubwev_s)
+TRANS(vsubwev_d_w, gvec_vvv, MO_32, do_vsubwev_s)
+TRANS(vsubwev_q_d, gvec_vvv, MO_64, do_vsubwev_s)
+
+static void gen_vsubwod_s(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    TCGv_vec t1, t2;
+
+    int halfbits = 4 << vece;
+
+    t1 = tcg_temp_new_vec_matching(a);
+    t2 = tcg_temp_new_vec_matching(b);
+
+    /* Sign-extend the odd elements for vector */
+    tcg_gen_sari_vec(vece, t1, a, halfbits);
+    tcg_gen_sari_vec(vece, t2, b, halfbits);
+
+    tcg_gen_sub_vec(vece, t, t1, t2);
+}
+
+static void gen_vsubwod_w_h(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 t1, t2;
+
+    t1 = tcg_temp_new_i32();
+    t2 = tcg_temp_new_i32();
+    tcg_gen_sari_i32(t1, a, 16);
+    tcg_gen_sari_i32(t2, b, 16);
+    tcg_gen_sub_i32(t, t1, t2);
+}
+
+static void gen_vsubwod_d_w(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b)
+{
+    TCGv_i64 t1, t2;
+
+    t1 = tcg_temp_new_i64();
+    t2 = tcg_temp_new_i64();
+    tcg_gen_sari_i64(t1, a, 32);
+    tcg_gen_sari_i64(t2, b, 32);
+    tcg_gen_sub_i64(t, t1, t2);
+}
+
+static void do_vsubwod_s(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                         uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_sari_vec, INDEX_op_sub_vec, 0
+        };
+    static const GVecGen3 op[4] = {
+        {
+            .fniv = gen_vsubwod_s,
+            .fno = gen_helper_vsubwod_h_b,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fni4 = gen_vsubwod_w_h,
+            .fniv = gen_vsubwod_s,
+            .fno = gen_helper_vsubwod_w_h,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fni8 = gen_vsubwod_d_w,
+            .fniv = gen_vsubwod_s,
+            .fno = gen_helper_vsubwod_d_w,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+        {
+            .fno = gen_helper_vsubwod_q_d,
+            .vece = MO_128
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vsubwod_h_b, gvec_vvv, MO_8, do_vsubwod_s)
+TRANS(vsubwod_w_h, gvec_vvv, MO_16, do_vsubwod_s)
+TRANS(vsubwod_d_w, gvec_vvv, MO_32, do_vsubwod_s)
+TRANS(vsubwod_q_d, gvec_vvv, MO_64, do_vsubwod_s)
+
+static void gen_vaddwev_u(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    TCGv_vec t1, t2, t3;
+
+    t1 = tcg_temp_new_vec_matching(a);
+    t2 = tcg_temp_new_vec_matching(b);
+    t3 = tcg_constant_vec_matching(t, vece, MAKE_64BIT_MASK(0, 4 << vece));
+    tcg_gen_and_vec(vece, t1, a, t3);
+    tcg_gen_and_vec(vece, t2, b, t3);
+    tcg_gen_add_vec(vece, t, t1, t2);
+}
+
+static void gen_vaddwev_w_hu(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 t1, t2;
+
+    t1 = tcg_temp_new_i32();
+    t2 = tcg_temp_new_i32();
+    tcg_gen_ext16u_i32(t1, a);
+    tcg_gen_ext16u_i32(t2, b);
+    tcg_gen_add_i32(t, t1, t2);
+}
+
+static void gen_vaddwev_d_wu(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b)
+{
+    TCGv_i64 t1, t2;
+
+    t1 = tcg_temp_new_i64();
+    t2 = tcg_temp_new_i64();
+    tcg_gen_ext32u_i64(t1, a);
+    tcg_gen_ext32u_i64(t2, b);
+    tcg_gen_add_i64(t, t1, t2);
+}
+
+static void do_vaddwev_u(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                         uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_add_vec, 0
+        };
+    static const GVecGen3 op[4] = {
+        {
+            .fniv = gen_vaddwev_u,
+            .fno = gen_helper_vaddwev_h_bu,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fni4 = gen_vaddwev_w_hu,
+            .fniv = gen_vaddwev_u,
+            .fno = gen_helper_vaddwev_w_hu,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fni8 = gen_vaddwev_d_wu,
+            .fniv = gen_vaddwev_u,
+            .fno = gen_helper_vaddwev_d_wu,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+        {
+            .fno = gen_helper_vaddwev_q_du,
+            .vece = MO_128
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vaddwev_h_bu, gvec_vvv, MO_8, do_vaddwev_u)
+TRANS(vaddwev_w_hu, gvec_vvv, MO_16, do_vaddwev_u)
+TRANS(vaddwev_d_wu, gvec_vvv, MO_32, do_vaddwev_u)
+TRANS(vaddwev_q_du, gvec_vvv, MO_64, do_vaddwev_u)
+
+static void gen_vaddwod_u(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    TCGv_vec t1, t2;
+
+    int halfbits = 4 << vece;
+
+    t1 = tcg_temp_new_vec_matching(a);
+    t2 = tcg_temp_new_vec_matching(b);
+
+    /* Zero-extend the odd elements for vector */
+    tcg_gen_shri_vec(vece, t1, a, halfbits);
+    tcg_gen_shri_vec(vece, t2, b, halfbits);
+
+    tcg_gen_add_vec(vece, t, t1, t2);
+}
+
+static void gen_vaddwod_w_hu(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 t1, t2;
+
+    t1 = tcg_temp_new_i32();
+    t2 = tcg_temp_new_i32();
+    tcg_gen_shri_i32(t1, a, 16);
+    tcg_gen_shri_i32(t2, b, 16);
+    tcg_gen_add_i32(t, t1, t2);
+}
+
+static void gen_vaddwod_d_wu(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b)
+{
+    TCGv_i64 t1, t2;
+
+    t1 = tcg_temp_new_i64();
+    t2 = tcg_temp_new_i64();
+    tcg_gen_shri_i64(t1, a, 32);
+    tcg_gen_shri_i64(t2, b, 32);
+    tcg_gen_add_i64(t, t1, t2);
+}
+
+static void do_vaddwod_u(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                         uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_shri_vec, INDEX_op_add_vec, 0
+        };
+    static const GVecGen3 op[4] = {
+        {
+            .fniv = gen_vaddwod_u,
+            .fno = gen_helper_vaddwod_h_bu,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fni4 = gen_vaddwod_w_hu,
+            .fniv = gen_vaddwod_u,
+            .fno = gen_helper_vaddwod_w_hu,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fni8 = gen_vaddwod_d_wu,
+            .fniv = gen_vaddwod_u,
+            .fno = gen_helper_vaddwod_d_wu,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+        {
+            .fno = gen_helper_vaddwod_q_du,
+            .vece = MO_128
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vaddwod_h_bu, gvec_vvv, MO_8, do_vaddwod_u)
+TRANS(vaddwod_w_hu, gvec_vvv, MO_16, do_vaddwod_u)
+TRANS(vaddwod_d_wu, gvec_vvv, MO_32, do_vaddwod_u)
+TRANS(vaddwod_q_du, gvec_vvv, MO_64, do_vaddwod_u)
+
+static void gen_vsubwev_u(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    TCGv_vec t1, t2, t3;
+
+    t1 = tcg_temp_new_vec_matching(a);
+    t2 = tcg_temp_new_vec_matching(b);
+    t3 = tcg_constant_vec_matching(t, vece, MAKE_64BIT_MASK(0, 4 << vece));
+    tcg_gen_and_vec(vece, t1, a, t3);
+    tcg_gen_and_vec(vece, t2, b, t3);
+    tcg_gen_sub_vec(vece, t, t1, t2);
+}
+
+static void gen_vsubwev_w_hu(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 t1, t2;
+
+    t1 = tcg_temp_new_i32();
+    t2 = tcg_temp_new_i32();
+    tcg_gen_ext16u_i32(t1, a);
+    tcg_gen_ext16u_i32(t2, b);
+    tcg_gen_sub_i32(t, t1, t2);
+}
+
+static void gen_vsubwev_d_wu(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b)
+{
+    TCGv_i64 t1, t2;
+
+    t1 = tcg_temp_new_i64();
+    t2 = tcg_temp_new_i64();
+    tcg_gen_ext32u_i64(t1, a);
+    tcg_gen_ext32u_i64(t2, b);
+    tcg_gen_sub_i64(t, t1, t2);
+}
+
+static void do_vsubwev_u(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                         uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_sub_vec, 0
+        };
+    static const GVecGen3 op[4] = {
+        {
+            .fniv = gen_vsubwev_u,
+            .fno = gen_helper_vsubwev_h_bu,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fni4 = gen_vsubwev_w_hu,
+            .fniv = gen_vsubwev_u,
+            .fno = gen_helper_vsubwev_w_hu,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fni8 = gen_vsubwev_d_wu,
+            .fniv = gen_vsubwev_u,
+            .fno = gen_helper_vsubwev_d_wu,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+        {
+            .fno = gen_helper_vsubwev_q_du,
+            .vece = MO_128
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vsubwev_h_bu, gvec_vvv, MO_8, do_vsubwev_u)
+TRANS(vsubwev_w_hu, gvec_vvv, MO_16, do_vsubwev_u)
+TRANS(vsubwev_d_wu, gvec_vvv, MO_32, do_vsubwev_u)
+TRANS(vsubwev_q_du, gvec_vvv, MO_64, do_vsubwev_u)
+
+static void gen_vsubwod_u(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    TCGv_vec t1, t2;
+
+    int halfbits = 4 << vece;
+
+    t1 = tcg_temp_new_vec_matching(a);
+    t2 = tcg_temp_new_vec_matching(b);
+
+    /* Zero-extend the odd elements for vector */
+    tcg_gen_shri_vec(vece, t1, a, halfbits);
+    tcg_gen_shri_vec(vece, t2, b, halfbits);
+
+    tcg_gen_sub_vec(vece, t, t1, t2);
+}
+
+static void gen_vsubwod_w_hu(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 t1, t2;
+
+    t1 = tcg_temp_new_i32();
+    t2 = tcg_temp_new_i32();
+    tcg_gen_shri_i32(t1, a, 16);
+    tcg_gen_shri_i32(t2, b, 16);
+    tcg_gen_sub_i32(t, t1, t2);
+}
+
+static void gen_vsubwod_d_wu(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b)
+{
+    TCGv_i64 t1, t2;
+
+    t1 = tcg_temp_new_i64();
+    t2 = tcg_temp_new_i64();
+    tcg_gen_shri_i64(t1, a, 32);
+    tcg_gen_shri_i64(t2, b, 32);
+    tcg_gen_sub_i64(t, t1, t2);
+}
+
+static void do_vsubwod_u(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                         uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_shri_vec, INDEX_op_sub_vec, 0
+        };
+    static const GVecGen3 op[4] = {
+        {
+            .fniv = gen_vsubwod_u,
+            .fno = gen_helper_vsubwod_h_bu,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fni4 = gen_vsubwod_w_hu,
+            .fniv = gen_vsubwod_u,
+            .fno = gen_helper_vsubwod_w_hu,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fni8 = gen_vsubwod_d_wu,
+            .fniv = gen_vsubwod_u,
+            .fno = gen_helper_vsubwod_d_wu,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+        {
+            .fno = gen_helper_vsubwod_q_du,
+            .vece = MO_128
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vsubwod_h_bu, gvec_vvv, MO_8, do_vsubwod_u)
+TRANS(vsubwod_w_hu, gvec_vvv, MO_16, do_vsubwod_u)
+TRANS(vsubwod_d_wu, gvec_vvv, MO_32, do_vsubwod_u)
+TRANS(vsubwod_q_du, gvec_vvv, MO_64, do_vsubwod_u)
+
+static void gen_vaddwev_u_s(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    TCGv_vec t1, t2, t3;
+
+    int halfbits = 4 << vece;
+
+    t1 = tcg_temp_new_vec_matching(a);
+    t2 = tcg_temp_new_vec_matching(b);
+    t3 = tcg_constant_vec_matching(t, vece, MAKE_64BIT_MASK(0, halfbits));
+
+    /* Zero-extend the even elements from a */
+    tcg_gen_and_vec(vece, t1, a, t3);
+
+    /* Sign-extend the even elements from b */
+    tcg_gen_shli_vec(vece, t2, b, halfbits);
+    tcg_gen_sari_vec(vece, t2, t2, halfbits);
+
+    tcg_gen_add_vec(vece, t, t1, t2);
+}
+
+static void gen_vaddwev_w_hu_h(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 t1, t2;
+
+    t1 = tcg_temp_new_i32();
+    t2 = tcg_temp_new_i32();
+    tcg_gen_ext16u_i32(t1, a);
+    tcg_gen_ext16s_i32(t2, b);
+    tcg_gen_add_i32(t, t1, t2);
+}
+
+static void gen_vaddwev_d_wu_w(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b)
+{
+    TCGv_i64 t1, t2;
+
+    t1 = tcg_temp_new_i64();
+    t2 = tcg_temp_new_i64();
+    tcg_gen_ext32u_i64(t1, a);
+    tcg_gen_ext32s_i64(t2, b);
+    tcg_gen_add_i64(t, t1, t2);
+}
+
+static void do_vaddwev_u_s(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                           uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_shli_vec, INDEX_op_sari_vec, INDEX_op_add_vec, 0
+        };
+    static const GVecGen3 op[4] = {
+        {
+            .fniv = gen_vaddwev_u_s,
+            .fno = gen_helper_vaddwev_h_bu_b,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fni4 = gen_vaddwev_w_hu_h,
+            .fniv = gen_vaddwev_u_s,
+            .fno = gen_helper_vaddwev_w_hu_h,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fni8 = gen_vaddwev_d_wu_w,
+            .fniv = gen_vaddwev_u_s,
+            .fno = gen_helper_vaddwev_d_wu_w,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+        {
+            .fno = gen_helper_vaddwev_q_du_d,
+            .vece = MO_128
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vaddwev_h_bu_b, gvec_vvv, MO_8, do_vaddwev_u_s)
+TRANS(vaddwev_w_hu_h, gvec_vvv, MO_16, do_vaddwev_u_s)
+TRANS(vaddwev_d_wu_w, gvec_vvv, MO_32, do_vaddwev_u_s)
+TRANS(vaddwev_q_du_d, gvec_vvv, MO_64, do_vaddwev_u_s)
+
+static void gen_vaddwod_u_s(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    TCGv_vec t1, t2;
+
+    int halfbits = 4 << vece;
+
+    t1 = tcg_temp_new_vec_matching(a);
+    t2 = tcg_temp_new_vec_matching(b);
+
+    /* Zero-extend the odd elements from a */
+    tcg_gen_shri_vec(vece, t1, a, halfbits);
+    /* Sign-extend the odd elements from b */
+    tcg_gen_sari_vec(vece, t2, b, halfbits);
+
+    tcg_gen_add_vec(vece, t, t1, t2);
+}
+
+static void gen_vaddwod_w_hu_h(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 t1, t2;
+
+    t1 = tcg_temp_new_i32();
+    t2 = tcg_temp_new_i32();
+    tcg_gen_shri_i32(t1, a, 16);
+    tcg_gen_sari_i32(t2, b, 16);
+    tcg_gen_add_i32(t, t1, t2);
+}
+
+static void gen_vaddwod_d_wu_w(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b)
+{
+    TCGv_i64 t1, t2;
+
+    t1 = tcg_temp_new_i64();
+    t2 = tcg_temp_new_i64();
+    tcg_gen_shri_i64(t1, a, 32);
+    tcg_gen_sari_i64(t2, b, 32);
+    tcg_gen_add_i64(t, t1, t2);
+}
+
+static void do_vaddwod_u_s(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                           uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_shri_vec, INDEX_op_sari_vec,  INDEX_op_add_vec, 0
+        };
+    static const GVecGen3 op[4] = {
+        {
+            .fniv = gen_vaddwod_u_s,
+            .fno = gen_helper_vaddwod_h_bu_b,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fni4 = gen_vaddwod_w_hu_h,
+            .fniv = gen_vaddwod_u_s,
+            .fno = gen_helper_vaddwod_w_hu_h,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fni8 = gen_vaddwod_d_wu_w,
+            .fniv = gen_vaddwod_u_s,
+            .fno = gen_helper_vaddwod_d_wu_w,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+        {
+            .fno = gen_helper_vaddwod_q_du_d,
+            .vece = MO_128
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vaddwod_h_bu_b, gvec_vvv, MO_8, do_vaddwod_u_s)
+TRANS(vaddwod_w_hu_h, gvec_vvv, MO_16, do_vaddwod_u_s)
+TRANS(vaddwod_d_wu_w, gvec_vvv, MO_32, do_vaddwod_u_s)
+TRANS(vaddwod_q_du_d, gvec_vvv, MO_64, do_vaddwod_u_s)
+
+static void do_vavg(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b,
+                    void (*gen_shr_vec)(unsigned, TCGv_vec,
+                                        TCGv_vec, int64_t),
+                    void (*gen_round_vec)(unsigned, TCGv_vec,
+                                          TCGv_vec, TCGv_vec))
+{
+    TCGv_vec tmp = tcg_temp_new_vec_matching(t);
+    gen_round_vec(vece, tmp, a, b);
+    tcg_gen_and_vec(vece, tmp, tmp, tcg_constant_vec_matching(t, vece, 1));
+    gen_shr_vec(vece, a, a, 1);
+    gen_shr_vec(vece, b, b, 1);
+    tcg_gen_add_vec(vece, t, a, b);
+    tcg_gen_add_vec(vece, t, t, tmp);
+}
+
+static void gen_vavg_s(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    do_vavg(vece, t, a, b, tcg_gen_sari_vec, tcg_gen_and_vec);
+}
+
+static void gen_vavg_u(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    do_vavg(vece, t, a, b, tcg_gen_shri_vec, tcg_gen_and_vec);
+}
+
+static void gen_vavgr_s(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    do_vavg(vece, t, a, b, tcg_gen_sari_vec, tcg_gen_or_vec);
+}
+
+static void gen_vavgr_u(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    do_vavg(vece, t, a, b, tcg_gen_shri_vec, tcg_gen_or_vec);
+}
+
+static void do_vavg_s(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                      uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_sari_vec, INDEX_op_add_vec, 0
+        };
+    static const GVecGen3 op[4] = {
+        {
+            .fniv = gen_vavg_s,
+            .fno = gen_helper_vavg_b,
+            .opt_opc = vecop_list,
+            .vece = MO_8
+        },
+        {
+            .fniv = gen_vavg_s,
+            .fno = gen_helper_vavg_h,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fniv = gen_vavg_s,
+            .fno = gen_helper_vavg_w,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fniv = gen_vavg_s,
+            .fno = gen_helper_vavg_d,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+static void do_vavg_u(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                      uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_shri_vec, INDEX_op_add_vec, 0
+        };
+    static const GVecGen3 op[4] = {
+        {
+            .fniv = gen_vavg_u,
+            .fno = gen_helper_vavg_bu,
+            .opt_opc = vecop_list,
+            .vece = MO_8
+        },
+        {
+            .fniv = gen_vavg_u,
+            .fno = gen_helper_vavg_hu,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fniv = gen_vavg_u,
+            .fno = gen_helper_vavg_wu,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fniv = gen_vavg_u,
+            .fno = gen_helper_vavg_du,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vavg_b, gvec_vvv, MO_8, do_vavg_s)
+TRANS(vavg_h, gvec_vvv, MO_16, do_vavg_s)
+TRANS(vavg_w, gvec_vvv, MO_32, do_vavg_s)
+TRANS(vavg_d, gvec_vvv, MO_64, do_vavg_s)
+TRANS(vavg_bu, gvec_vvv, MO_8, do_vavg_u)
+TRANS(vavg_hu, gvec_vvv, MO_16, do_vavg_u)
+TRANS(vavg_wu, gvec_vvv, MO_32, do_vavg_u)
+TRANS(vavg_du, gvec_vvv, MO_64, do_vavg_u)
+
+static void do_vavgr_s(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                       uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_sari_vec, INDEX_op_add_vec, 0
+        };
+    static const GVecGen3 op[4] = {
+        {
+            .fniv = gen_vavgr_s,
+            .fno = gen_helper_vavgr_b,
+            .opt_opc = vecop_list,
+            .vece = MO_8
+        },
+        {
+            .fniv = gen_vavgr_s,
+            .fno = gen_helper_vavgr_h,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fniv = gen_vavgr_s,
+            .fno = gen_helper_vavgr_w,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fniv = gen_vavgr_s,
+            .fno = gen_helper_vavgr_d,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+static void do_vavgr_u(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                       uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_shri_vec, INDEX_op_add_vec, 0
+        };
+    static const GVecGen3 op[4] = {
+        {
+            .fniv = gen_vavgr_u,
+            .fno = gen_helper_vavgr_bu,
+            .opt_opc = vecop_list,
+            .vece = MO_8
+        },
+        {
+            .fniv = gen_vavgr_u,
+            .fno = gen_helper_vavgr_hu,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fniv = gen_vavgr_u,
+            .fno = gen_helper_vavgr_wu,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fniv = gen_vavgr_u,
+            .fno = gen_helper_vavgr_du,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vavgr_b, gvec_vvv, MO_8, do_vavgr_s)
+TRANS(vavgr_h, gvec_vvv, MO_16, do_vavgr_s)
+TRANS(vavgr_w, gvec_vvv, MO_32, do_vavgr_s)
+TRANS(vavgr_d, gvec_vvv, MO_64, do_vavgr_s)
+TRANS(vavgr_bu, gvec_vvv, MO_8, do_vavgr_u)
+TRANS(vavgr_hu, gvec_vvv, MO_16, do_vavgr_u)
+TRANS(vavgr_wu, gvec_vvv, MO_32, do_vavgr_u)
+TRANS(vavgr_du, gvec_vvv, MO_64, do_vavgr_u)
+
+static void gen_vabsd_s(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    tcg_gen_smax_vec(vece, t, a, b);
+    tcg_gen_smin_vec(vece, a, a, b);
+    tcg_gen_sub_vec(vece, t, t, a);
+}
+
+static void do_vabsd_s(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                       uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_smax_vec, INDEX_op_smin_vec, INDEX_op_sub_vec, 0
+        };
+    static const GVecGen3 op[4] = {
+        {
+            .fniv = gen_vabsd_s,
+            .fno = gen_helper_vabsd_b,
+            .opt_opc = vecop_list,
+            .vece = MO_8
+        },
+        {
+            .fniv = gen_vabsd_s,
+            .fno = gen_helper_vabsd_h,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fniv = gen_vabsd_s,
+            .fno = gen_helper_vabsd_w,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fniv = gen_vabsd_s,
+            .fno = gen_helper_vabsd_d,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+static void gen_vabsd_u(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    tcg_gen_umax_vec(vece, t, a, b);
+    tcg_gen_umin_vec(vece, a, a, b);
+    tcg_gen_sub_vec(vece, t, t, a);
+}
+
+static void do_vabsd_u(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                       uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_umax_vec, INDEX_op_umin_vec, INDEX_op_sub_vec, 0
+        };
+    static const GVecGen3 op[4] = {
+        {
+            .fniv = gen_vabsd_u,
+            .fno = gen_helper_vabsd_bu,
+            .opt_opc = vecop_list,
+            .vece = MO_8
+        },
+        {
+            .fniv = gen_vabsd_u,
+            .fno = gen_helper_vabsd_hu,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fniv = gen_vabsd_u,
+            .fno = gen_helper_vabsd_wu,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fniv = gen_vabsd_u,
+            .fno = gen_helper_vabsd_du,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vabsd_b, gvec_vvv, MO_8, do_vabsd_s)
+TRANS(vabsd_h, gvec_vvv, MO_16, do_vabsd_s)
+TRANS(vabsd_w, gvec_vvv, MO_32, do_vabsd_s)
+TRANS(vabsd_d, gvec_vvv, MO_64, do_vabsd_s)
+TRANS(vabsd_bu, gvec_vvv, MO_8, do_vabsd_u)
+TRANS(vabsd_hu, gvec_vvv, MO_16, do_vabsd_u)
+TRANS(vabsd_wu, gvec_vvv, MO_32, do_vabsd_u)
+TRANS(vabsd_du, gvec_vvv, MO_64, do_vabsd_u)
+
+static void gen_vadda(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    TCGv_vec t1, t2;
+
+    t1 = tcg_temp_new_vec_matching(a);
+    t2 = tcg_temp_new_vec_matching(b);
+
+    tcg_gen_abs_vec(vece, t1, a);
+    tcg_gen_abs_vec(vece, t2, b);
+    tcg_gen_add_vec(vece, t, t1, t2);
+}
+
+static void do_vadda(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                     uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_abs_vec, INDEX_op_add_vec, 0
+        };
+    static const GVecGen3 op[4] = {
+        {
+            .fniv = gen_vadda,
+            .fno = gen_helper_vadda_b,
+            .opt_opc = vecop_list,
+            .vece = MO_8
+        },
+        {
+            .fniv = gen_vadda,
+            .fno = gen_helper_vadda_h,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fniv = gen_vadda,
+            .fno = gen_helper_vadda_w,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fniv = gen_vadda,
+            .fno = gen_helper_vadda_d,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vadda_b, gvec_vvv, MO_8, do_vadda)
+TRANS(vadda_h, gvec_vvv, MO_16, do_vadda)
+TRANS(vadda_w, gvec_vvv, MO_32, do_vadda)
+TRANS(vadda_d, gvec_vvv, MO_64, do_vadda)
+
+TRANS(vmax_b, gvec_vvv, MO_8, tcg_gen_gvec_smax)
+TRANS(vmax_h, gvec_vvv, MO_16, tcg_gen_gvec_smax)
+TRANS(vmax_w, gvec_vvv, MO_32, tcg_gen_gvec_smax)
+TRANS(vmax_d, gvec_vvv, MO_64, tcg_gen_gvec_smax)
+TRANS(vmax_bu, gvec_vvv, MO_8, tcg_gen_gvec_umax)
+TRANS(vmax_hu, gvec_vvv, MO_16, tcg_gen_gvec_umax)
+TRANS(vmax_wu, gvec_vvv, MO_32, tcg_gen_gvec_umax)
+TRANS(vmax_du, gvec_vvv, MO_64, tcg_gen_gvec_umax)
+
+TRANS(vmin_b, gvec_vvv, MO_8, tcg_gen_gvec_smin)
+TRANS(vmin_h, gvec_vvv, MO_16, tcg_gen_gvec_smin)
+TRANS(vmin_w, gvec_vvv, MO_32, tcg_gen_gvec_smin)
+TRANS(vmin_d, gvec_vvv, MO_64, tcg_gen_gvec_smin)
+TRANS(vmin_bu, gvec_vvv, MO_8, tcg_gen_gvec_umin)
+TRANS(vmin_hu, gvec_vvv, MO_16, tcg_gen_gvec_umin)
+TRANS(vmin_wu, gvec_vvv, MO_32, tcg_gen_gvec_umin)
+TRANS(vmin_du, gvec_vvv, MO_64, tcg_gen_gvec_umin)
+
+static void gen_vmini_s(unsigned vece, TCGv_vec t, TCGv_vec a, int64_t imm)
+{
+    tcg_gen_smin_vec(vece, t, a, tcg_constant_vec_matching(t, vece, imm));
+}
+
+static void gen_vmini_u(unsigned vece, TCGv_vec t, TCGv_vec a, int64_t imm)
+{
+    tcg_gen_umin_vec(vece, t, a, tcg_constant_vec_matching(t, vece, imm));
+}
+
+static void gen_vmaxi_s(unsigned vece, TCGv_vec t, TCGv_vec a, int64_t imm)
+{
+    tcg_gen_smax_vec(vece, t, a, tcg_constant_vec_matching(t, vece, imm));
+}
+
+static void gen_vmaxi_u(unsigned vece, TCGv_vec t, TCGv_vec a, int64_t imm)
+{
+    tcg_gen_umax_vec(vece, t, a, tcg_constant_vec_matching(t, vece, imm));
+}
+
+static void do_vmini_s(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                       int64_t imm, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_smin_vec, 0
+        };
+    static const GVecGen2i op[4] = {
+        {
+            .fniv = gen_vmini_s,
+            .fnoi = gen_helper_vmini_b,
+            .opt_opc = vecop_list,
+            .vece = MO_8
+        },
+        {
+            .fniv = gen_vmini_s,
+            .fnoi = gen_helper_vmini_h,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fniv = gen_vmini_s,
+            .fnoi = gen_helper_vmini_w,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fniv = gen_vmini_s,
+            .fnoi = gen_helper_vmini_d,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_2i(vd_ofs, vj_ofs, oprsz, maxsz, imm, &op[vece]);
+}
+
+static void do_vmini_u(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                       int64_t imm, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_umin_vec, 0
+        };
+    static const GVecGen2i op[4] = {
+        {
+            .fniv = gen_vmini_u,
+            .fnoi = gen_helper_vmini_bu,
+            .opt_opc = vecop_list,
+            .vece = MO_8
+        },
+        {
+            .fniv = gen_vmini_u,
+            .fnoi = gen_helper_vmini_hu,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fniv = gen_vmini_u,
+            .fnoi = gen_helper_vmini_wu,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fniv = gen_vmini_u,
+            .fnoi = gen_helper_vmini_du,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_2i(vd_ofs, vj_ofs, oprsz, maxsz, imm, &op[vece]);
+}
+
+TRANS(vmini_b, gvec_vv_i, MO_8, do_vmini_s)
+TRANS(vmini_h, gvec_vv_i, MO_16, do_vmini_s)
+TRANS(vmini_w, gvec_vv_i, MO_32, do_vmini_s)
+TRANS(vmini_d, gvec_vv_i, MO_64, do_vmini_s)
+TRANS(vmini_bu, gvec_vv_i, MO_8, do_vmini_u)
+TRANS(vmini_hu, gvec_vv_i, MO_16, do_vmini_u)
+TRANS(vmini_wu, gvec_vv_i, MO_32, do_vmini_u)
+TRANS(vmini_du, gvec_vv_i, MO_64, do_vmini_u)
+
+static void do_vmaxi_s(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                       int64_t imm, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_smax_vec, 0
+        };
+    static const GVecGen2i op[4] = {
+        {
+            .fniv = gen_vmaxi_s,
+            .fnoi = gen_helper_vmaxi_b,
+            .opt_opc = vecop_list,
+            .vece = MO_8
+        },
+        {
+            .fniv = gen_vmaxi_s,
+            .fnoi = gen_helper_vmaxi_h,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fniv = gen_vmaxi_s,
+            .fnoi = gen_helper_vmaxi_w,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fniv = gen_vmaxi_s,
+            .fnoi = gen_helper_vmaxi_d,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_2i(vd_ofs, vj_ofs, oprsz, maxsz, imm, &op[vece]);
+}
+
+static void do_vmaxi_u(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                       int64_t imm, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_umax_vec, 0
+        };
+    static const GVecGen2i op[4] = {
+        {
+            .fniv = gen_vmaxi_u,
+            .fnoi = gen_helper_vmaxi_bu,
+            .opt_opc = vecop_list,
+            .vece = MO_8
+        },
+        {
+            .fniv = gen_vmaxi_u,
+            .fnoi = gen_helper_vmaxi_hu,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fniv = gen_vmaxi_u,
+            .fnoi = gen_helper_vmaxi_wu,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fniv = gen_vmaxi_u,
+            .fnoi = gen_helper_vmaxi_du,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_2i(vd_ofs, vj_ofs, oprsz, maxsz, imm, &op[vece]);
+}
+
+TRANS(vmaxi_b, gvec_vv_i, MO_8, do_vmaxi_s)
+TRANS(vmaxi_h, gvec_vv_i, MO_16, do_vmaxi_s)
+TRANS(vmaxi_w, gvec_vv_i, MO_32, do_vmaxi_s)
+TRANS(vmaxi_d, gvec_vv_i, MO_64, do_vmaxi_s)
+TRANS(vmaxi_bu, gvec_vv_i, MO_8, do_vmaxi_u)
+TRANS(vmaxi_hu, gvec_vv_i, MO_16, do_vmaxi_u)
+TRANS(vmaxi_wu, gvec_vv_i, MO_32, do_vmaxi_u)
+TRANS(vmaxi_du, gvec_vv_i, MO_64, do_vmaxi_u)
+
+TRANS(vmul_b, gvec_vvv, MO_8, tcg_gen_gvec_mul)
+TRANS(vmul_h, gvec_vvv, MO_16, tcg_gen_gvec_mul)
+TRANS(vmul_w, gvec_vvv, MO_32, tcg_gen_gvec_mul)
+TRANS(vmul_d, gvec_vvv, MO_64, tcg_gen_gvec_mul)
+
+static void gen_vmuh_w(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 discard = tcg_temp_new_i32();
+    tcg_gen_muls2_i32(discard, t, a, b);
+}
+
+static void gen_vmuh_d(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b)
+{
+    TCGv_i64 discard = tcg_temp_new_i64();
+    tcg_gen_muls2_i64(discard, t, a, b);
+}
+
+static void do_vmuh_s(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                      uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const GVecGen3 op[4] = {
+        {
+            .fno = gen_helper_vmuh_b,
+            .vece = MO_8
+        },
+        {
+            .fno = gen_helper_vmuh_h,
+            .vece = MO_16
+        },
+        {
+            .fni4 = gen_vmuh_w,
+            .fno = gen_helper_vmuh_w,
+            .vece = MO_32
+        },
+        {
+            .fni8 = gen_vmuh_d,
+            .fno = gen_helper_vmuh_d,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vmuh_b, gvec_vvv, MO_8, do_vmuh_s)
+TRANS(vmuh_h, gvec_vvv, MO_16, do_vmuh_s)
+TRANS(vmuh_w, gvec_vvv, MO_32, do_vmuh_s)
+TRANS(vmuh_d, gvec_vvv, MO_64, do_vmuh_s)
+
+static void gen_vmuh_wu(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 discard = tcg_temp_new_i32();
+    tcg_gen_mulu2_i32(discard, t, a, b);
+}
+
+static void gen_vmuh_du(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b)
+{
+    TCGv_i64 discard = tcg_temp_new_i64();
+    tcg_gen_mulu2_i64(discard, t, a, b);
+}
+
+static void do_vmuh_u(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                      uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const GVecGen3 op[4] = {
+        {
+            .fno = gen_helper_vmuh_bu,
+            .vece = MO_8
+        },
+        {
+            .fno = gen_helper_vmuh_hu,
+            .vece = MO_16
+        },
+        {
+            .fni4 = gen_vmuh_wu,
+            .fno = gen_helper_vmuh_wu,
+            .vece = MO_32
+        },
+        {
+            .fni8 = gen_vmuh_du,
+            .fno = gen_helper_vmuh_du,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vmuh_bu, gvec_vvv, MO_8,  do_vmuh_u)
+TRANS(vmuh_hu, gvec_vvv, MO_16, do_vmuh_u)
+TRANS(vmuh_wu, gvec_vvv, MO_32, do_vmuh_u)
+TRANS(vmuh_du, gvec_vvv, MO_64, do_vmuh_u)
+
+static void gen_vmulwev_s(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    TCGv_vec t1, t2;
+    int halfbits = 4 << vece;
+
+    t1 = tcg_temp_new_vec_matching(a);
+    t2 = tcg_temp_new_vec_matching(b);
+    tcg_gen_shli_vec(vece, t1, a, halfbits);
+    tcg_gen_sari_vec(vece, t1, t1, halfbits);
+    tcg_gen_shli_vec(vece, t2, b, halfbits);
+    tcg_gen_sari_vec(vece, t2, t2, halfbits);
+    tcg_gen_mul_vec(vece, t, t1, t2);
+}
+
+static void gen_vmulwev_w_h(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 t1, t2;
+
+    t1 = tcg_temp_new_i32();
+    t2 = tcg_temp_new_i32();
+    tcg_gen_ext16s_i32(t1, a);
+    tcg_gen_ext16s_i32(t2, b);
+    tcg_gen_mul_i32(t, t1, t2);
+}
+
+static void gen_vmulwev_d_w(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b)
+{
+    TCGv_i64 t1, t2;
+
+    t1 = tcg_temp_new_i64();
+    t2 = tcg_temp_new_i64();
+    tcg_gen_ext32s_i64(t1, a);
+    tcg_gen_ext32s_i64(t2, b);
+    tcg_gen_mul_i64(t, t1, t2);
+}
+
+static void do_vmulwev_s(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                         uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_shli_vec, INDEX_op_sari_vec, INDEX_op_mul_vec, 0
+        };
+    static const GVecGen3 op[3] = {
+        {
+            .fniv = gen_vmulwev_s,
+            .fno = gen_helper_vmulwev_h_b,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fni4 = gen_vmulwev_w_h,
+            .fniv = gen_vmulwev_s,
+            .fno = gen_helper_vmulwev_w_h,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fni8 = gen_vmulwev_d_w,
+            .fniv = gen_vmulwev_s,
+            .fno = gen_helper_vmulwev_d_w,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vmulwev_h_b, gvec_vvv, MO_8, do_vmulwev_s)
+TRANS(vmulwev_w_h, gvec_vvv, MO_16, do_vmulwev_s)
+TRANS(vmulwev_d_w, gvec_vvv, MO_32, do_vmulwev_s)
+
+static void tcg_gen_mulus2_i64(TCGv_i64 rl, TCGv_i64 rh,
+                               TCGv_i64 arg1, TCGv_i64 arg2)
+{
+    tcg_gen_mulsu2_i64(rl, rh, arg2, arg1);
+}
+
+#define VMUL_Q(NAME, FN, idx1, idx2)                      \
+static bool trans_## NAME (DisasContext *ctx, arg_vvv *a) \
+{                                                         \
+    TCGv_i64 rh, rl, arg1, arg2;                          \
+                                                          \
+    rh = tcg_temp_new_i64();                              \
+    rl = tcg_temp_new_i64();                              \
+    arg1 = tcg_temp_new_i64();                            \
+    arg2 = tcg_temp_new_i64();                            \
+                                                          \
+    get_vreg64(arg1, a->vj, idx1);                        \
+    get_vreg64(arg2, a->vk, idx2);                        \
+                                                          \
+    tcg_gen_## FN ##_i64(rl, rh, arg1, arg2);             \
+                                                          \
+    set_vreg64(rh, a->vd, 1);                             \
+    set_vreg64(rl, a->vd, 0);                             \
+                                                          \
+    return true;                                          \
+}
+
+VMUL_Q(vmulwev_q_d, muls2, 0, 0)
+VMUL_Q(vmulwod_q_d, muls2, 1, 1)
+VMUL_Q(vmulwev_q_du, mulu2, 0, 0)
+VMUL_Q(vmulwod_q_du, mulu2, 1, 1)
+VMUL_Q(vmulwev_q_du_d, mulus2, 0, 0)
+VMUL_Q(vmulwod_q_du_d, mulus2, 1, 1)
+
+static void gen_vmulwod_s(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    TCGv_vec t1, t2;
+    int halfbits = 4 << vece;
+
+    t1 = tcg_temp_new_vec_matching(a);
+    t2 = tcg_temp_new_vec_matching(b);
+    tcg_gen_sari_vec(vece, t1, a, halfbits);
+    tcg_gen_sari_vec(vece, t2, b, halfbits);
+    tcg_gen_mul_vec(vece, t, t1, t2);
+}
+
+static void gen_vmulwod_w_h(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 t1, t2;
+
+    t1 = tcg_temp_new_i32();
+    t2 = tcg_temp_new_i32();
+    tcg_gen_sari_i32(t1, a, 16);
+    tcg_gen_sari_i32(t2, b, 16);
+    tcg_gen_mul_i32(t, t1, t2);
+}
+
+static void gen_vmulwod_d_w(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b)
+{
+    TCGv_i64 t1, t2;
+
+    t1 = tcg_temp_new_i64();
+    t2 = tcg_temp_new_i64();
+    tcg_gen_sari_i64(t1, a, 32);
+    tcg_gen_sari_i64(t2, b, 32);
+    tcg_gen_mul_i64(t, t1, t2);
+}
+
+static void do_vmulwod_s(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                         uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_sari_vec, INDEX_op_mul_vec, 0
+        };
+    static const GVecGen3 op[3] = {
+        {
+            .fniv = gen_vmulwod_s,
+            .fno = gen_helper_vmulwod_h_b,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fni4 = gen_vmulwod_w_h,
+            .fniv = gen_vmulwod_s,
+            .fno = gen_helper_vmulwod_w_h,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fni8 = gen_vmulwod_d_w,
+            .fniv = gen_vmulwod_s,
+            .fno = gen_helper_vmulwod_d_w,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vmulwod_h_b, gvec_vvv, MO_8, do_vmulwod_s)
+TRANS(vmulwod_w_h, gvec_vvv, MO_16, do_vmulwod_s)
+TRANS(vmulwod_d_w, gvec_vvv, MO_32, do_vmulwod_s)
+
+static void gen_vmulwev_u(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    TCGv_vec t1, t2, mask;
+
+    t1 = tcg_temp_new_vec_matching(a);
+    t2 = tcg_temp_new_vec_matching(b);
+    mask = tcg_constant_vec_matching(t, vece, MAKE_64BIT_MASK(0, 4 << vece));
+    tcg_gen_and_vec(vece, t1, a, mask);
+    tcg_gen_and_vec(vece, t2, b, mask);
+    tcg_gen_mul_vec(vece, t, t1, t2);
+}
+
+static void gen_vmulwev_w_hu(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 t1, t2;
+
+    t1 = tcg_temp_new_i32();
+    t2 = tcg_temp_new_i32();
+    tcg_gen_ext16u_i32(t1, a);
+    tcg_gen_ext16u_i32(t2, b);
+    tcg_gen_mul_i32(t, t1, t2);
+}
+
+static void gen_vmulwev_d_wu(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b)
+{
+    TCGv_i64 t1, t2;
+
+    t1 = tcg_temp_new_i64();
+    t2 = tcg_temp_new_i64();
+    tcg_gen_ext32u_i64(t1, a);
+    tcg_gen_ext32u_i64(t2, b);
+    tcg_gen_mul_i64(t, t1, t2);
+}
+
+static void do_vmulwev_u(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                         uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_mul_vec, 0
+        };
+    static const GVecGen3 op[3] = {
+        {
+            .fniv = gen_vmulwev_u,
+            .fno = gen_helper_vmulwev_h_bu,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fni4 = gen_vmulwev_w_hu,
+            .fniv = gen_vmulwev_u,
+            .fno = gen_helper_vmulwev_w_hu,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fni8 = gen_vmulwev_d_wu,
+            .fniv = gen_vmulwev_u,
+            .fno = gen_helper_vmulwev_d_wu,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vmulwev_h_bu, gvec_vvv, MO_8, do_vmulwev_u)
+TRANS(vmulwev_w_hu, gvec_vvv, MO_16, do_vmulwev_u)
+TRANS(vmulwev_d_wu, gvec_vvv, MO_32, do_vmulwev_u)
+
+static void gen_vmulwod_u(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    TCGv_vec t1, t2;
+    int halfbits = 4 << vece;
+
+    t1 = tcg_temp_new_vec_matching(a);
+    t2 = tcg_temp_new_vec_matching(b);
+    tcg_gen_shri_vec(vece, t1, a, halfbits);
+    tcg_gen_shri_vec(vece, t2, b, halfbits);
+    tcg_gen_mul_vec(vece, t, t1, t2);
+}
+
+static void gen_vmulwod_w_hu(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 t1, t2;
+
+    t1 = tcg_temp_new_i32();
+    t2 = tcg_temp_new_i32();
+    tcg_gen_shri_i32(t1, a, 16);
+    tcg_gen_shri_i32(t2, b, 16);
+    tcg_gen_mul_i32(t, t1, t2);
+}
+
+static void gen_vmulwod_d_wu(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b)
+{
+    TCGv_i64 t1, t2;
+
+    t1 = tcg_temp_new_i64();
+    t2 = tcg_temp_new_i64();
+    tcg_gen_shri_i64(t1, a, 32);
+    tcg_gen_shri_i64(t2, b, 32);
+    tcg_gen_mul_i64(t, t1, t2);
+}
+
+static void do_vmulwod_u(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                         uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_shri_vec, INDEX_op_mul_vec, 0
+        };
+    static const GVecGen3 op[3] = {
+        {
+            .fniv = gen_vmulwod_u,
+            .fno = gen_helper_vmulwod_h_bu,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fni4 = gen_vmulwod_w_hu,
+            .fniv = gen_vmulwod_u,
+            .fno = gen_helper_vmulwod_w_hu,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fni8 = gen_vmulwod_d_wu,
+            .fniv = gen_vmulwod_u,
+            .fno = gen_helper_vmulwod_d_wu,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vmulwod_h_bu, gvec_vvv, MO_8, do_vmulwod_u)
+TRANS(vmulwod_w_hu, gvec_vvv, MO_16, do_vmulwod_u)
+TRANS(vmulwod_d_wu, gvec_vvv, MO_32, do_vmulwod_u)
+
+static void gen_vmulwev_u_s(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    TCGv_vec t1, t2, mask;
+    int halfbits = 4 << vece;
+
+    t1 = tcg_temp_new_vec_matching(a);
+    t2 = tcg_temp_new_vec_matching(b);
+    mask = tcg_constant_vec_matching(t, vece, MAKE_64BIT_MASK(0, 4 << vece));
+    tcg_gen_and_vec(vece, t1, a, mask);
+    tcg_gen_shli_vec(vece, t2, b, halfbits);
+    tcg_gen_sari_vec(vece, t2, t2, halfbits);
+    tcg_gen_mul_vec(vece, t, t1, t2);
+}
+
+static void gen_vmulwev_w_hu_h(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 t1, t2;
+
+    t1 = tcg_temp_new_i32();
+    t2 = tcg_temp_new_i32();
+    tcg_gen_ext16u_i32(t1, a);
+    tcg_gen_ext16s_i32(t2, b);
+    tcg_gen_mul_i32(t, t1, t2);
+}
+
+static void gen_vmulwev_d_wu_w(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b)
+{
+    TCGv_i64 t1, t2;
+
+    t1 = tcg_temp_new_i64();
+    t2 = tcg_temp_new_i64();
+    tcg_gen_ext32u_i64(t1, a);
+    tcg_gen_ext32s_i64(t2, b);
+    tcg_gen_mul_i64(t, t1, t2);
+}
+
+static void do_vmulwev_u_s(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                           uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_shli_vec, INDEX_op_sari_vec, INDEX_op_mul_vec, 0
+        };
+    static const GVecGen3 op[3] = {
+        {
+            .fniv = gen_vmulwev_u_s,
+            .fno = gen_helper_vmulwev_h_bu_b,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fni4 = gen_vmulwev_w_hu_h,
+            .fniv = gen_vmulwev_u_s,
+            .fno = gen_helper_vmulwev_w_hu_h,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fni8 = gen_vmulwev_d_wu_w,
+            .fniv = gen_vmulwev_u_s,
+            .fno = gen_helper_vmulwev_d_wu_w,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vmulwev_h_bu_b, gvec_vvv, MO_8, do_vmulwev_u_s)
+TRANS(vmulwev_w_hu_h, gvec_vvv, MO_16, do_vmulwev_u_s)
+TRANS(vmulwev_d_wu_w, gvec_vvv, MO_32, do_vmulwev_u_s)
+
+static void gen_vmulwod_u_s(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    TCGv_vec t1, t2;
+    int halfbits = 4 << vece;
+
+    t1 = tcg_temp_new_vec_matching(a);
+    t2 = tcg_temp_new_vec_matching(b);
+    tcg_gen_shri_vec(vece, t1, a, halfbits);
+    tcg_gen_sari_vec(vece, t2, b, halfbits);
+    tcg_gen_mul_vec(vece, t, t1, t2);
+}
+
+static void gen_vmulwod_w_hu_h(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 t1, t2;
+
+    t1 = tcg_temp_new_i32();
+    t2 = tcg_temp_new_i32();
+    tcg_gen_shri_i32(t1, a, 16);
+    tcg_gen_sari_i32(t2, b, 16);
+    tcg_gen_mul_i32(t, t1, t2);
+}
+static void gen_vmulwod_d_wu_w(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b)
+{
+    TCGv_i64 t1, t2;
+
+    t1 = tcg_temp_new_i64();
+    t2 = tcg_temp_new_i64();
+    tcg_gen_shri_i64(t1, a, 32);
+    tcg_gen_sari_i64(t2, b, 32);
+    tcg_gen_mul_i64(t, t1, t2);
+}
+
+static void do_vmulwod_u_s(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                           uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_shri_vec, INDEX_op_sari_vec, INDEX_op_mul_vec, 0
+        };
+    static const GVecGen3 op[3] = {
+        {
+            .fniv = gen_vmulwod_u_s,
+            .fno = gen_helper_vmulwod_h_bu_b,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fni4 = gen_vmulwod_w_hu_h,
+            .fniv = gen_vmulwod_u_s,
+            .fno = gen_helper_vmulwod_w_hu_h,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fni8 = gen_vmulwod_d_wu_w,
+            .fniv = gen_vmulwod_u_s,
+            .fno = gen_helper_vmulwod_d_wu_w,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vmulwod_h_bu_b, gvec_vvv, MO_8, do_vmulwod_u_s)
+TRANS(vmulwod_w_hu_h, gvec_vvv, MO_16, do_vmulwod_u_s)
+TRANS(vmulwod_d_wu_w, gvec_vvv, MO_32, do_vmulwod_u_s)
+
+static void gen_vmadd(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    TCGv_vec t1;
+
+    t1 = tcg_temp_new_vec_matching(t);
+    tcg_gen_mul_vec(vece, t1, a, b);
+    tcg_gen_add_vec(vece, t, t, t1);
+}
+
+static void gen_vmadd_w(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 t1;
+
+    t1 = tcg_temp_new_i32();
+    tcg_gen_mul_i32(t1, a, b);
+    tcg_gen_add_i32(t, t, t1);
+}
+
+static void gen_vmadd_d(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b)
+{
+    TCGv_i64 t1;
+
+    t1 = tcg_temp_new_i64();
+    tcg_gen_mul_i64(t1, a, b);
+    tcg_gen_add_i64(t, t, t1);
+}
+
+static void do_vmadd(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                     uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_mul_vec, INDEX_op_add_vec, 0
+        };
+    static const GVecGen3 op[4] = {
+        {
+            .fniv = gen_vmadd,
+            .fno = gen_helper_vmadd_b,
+            .load_dest = true,
+            .opt_opc = vecop_list,
+            .vece = MO_8
+        },
+        {
+            .fniv = gen_vmadd,
+            .fno = gen_helper_vmadd_h,
+            .load_dest = true,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fni4 = gen_vmadd_w,
+            .fniv = gen_vmadd,
+            .fno = gen_helper_vmadd_w,
+            .load_dest = true,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fni8 = gen_vmadd_d,
+            .fniv = gen_vmadd,
+            .fno = gen_helper_vmadd_d,
+            .load_dest = true,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vmadd_b, gvec_vvv, MO_8, do_vmadd)
+TRANS(vmadd_h, gvec_vvv, MO_16, do_vmadd)
+TRANS(vmadd_w, gvec_vvv, MO_32, do_vmadd)
+TRANS(vmadd_d, gvec_vvv, MO_64, do_vmadd)
+
+static void gen_vmsub(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    TCGv_vec t1;
+
+    t1 = tcg_temp_new_vec_matching(t);
+    tcg_gen_mul_vec(vece, t1, a, b);
+    tcg_gen_sub_vec(vece, t, t, t1);
+}
+
+static void gen_vmsub_w(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 t1;
+
+    t1 = tcg_temp_new_i32();
+    tcg_gen_mul_i32(t1, a, b);
+    tcg_gen_sub_i32(t, t, t1);
+}
+
+static void gen_vmsub_d(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b)
+{
+    TCGv_i64 t1;
+
+    t1 = tcg_temp_new_i64();
+    tcg_gen_mul_i64(t1, a, b);
+    tcg_gen_sub_i64(t, t, t1);
+}
+
+static void do_vmsub(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                     uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_mul_vec, INDEX_op_sub_vec, 0
+        };
+    static const GVecGen3 op[4] = {
+        {
+            .fniv = gen_vmsub,
+            .fno = gen_helper_vmsub_b,
+            .load_dest = true,
+            .opt_opc = vecop_list,
+            .vece = MO_8
+        },
+        {
+            .fniv = gen_vmsub,
+            .fno = gen_helper_vmsub_h,
+            .load_dest = true,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fni4 = gen_vmsub_w,
+            .fniv = gen_vmsub,
+            .fno = gen_helper_vmsub_w,
+            .load_dest = true,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fni8 = gen_vmsub_d,
+            .fniv = gen_vmsub,
+            .fno = gen_helper_vmsub_d,
+            .load_dest = true,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vmsub_b, gvec_vvv, MO_8, do_vmsub)
+TRANS(vmsub_h, gvec_vvv, MO_16, do_vmsub)
+TRANS(vmsub_w, gvec_vvv, MO_32, do_vmsub)
+TRANS(vmsub_d, gvec_vvv, MO_64, do_vmsub)
+
+static void gen_vmaddwev_s(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    TCGv_vec t1, t2, t3;
+    int halfbits = 4 << vece;
+
+    t1 = tcg_temp_new_vec_matching(a);
+    t2 = tcg_temp_new_vec_matching(b);
+    t3 = tcg_temp_new_vec_matching(t);
+    tcg_gen_shli_vec(vece, t1, a, halfbits);
+    tcg_gen_sari_vec(vece, t1, t1, halfbits);
+    tcg_gen_shli_vec(vece, t2, b, halfbits);
+    tcg_gen_sari_vec(vece, t2, t2, halfbits);
+    tcg_gen_mul_vec(vece, t3, t1, t2);
+    tcg_gen_add_vec(vece, t, t, t3);
+}
+
+static void gen_vmaddwev_w_h(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 t1;
+
+    t1 = tcg_temp_new_i32();
+    gen_vmulwev_w_h(t1, a, b);
+    tcg_gen_add_i32(t, t, t1);
+}
+
+static void gen_vmaddwev_d_w(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b)
+{
+    TCGv_i64 t1;
+
+    t1 = tcg_temp_new_i64();
+    gen_vmulwev_d_w(t1, a, b);
+    tcg_gen_add_i64(t, t, t1);
+}
+
+static void do_vmaddwev_s(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                          uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_shli_vec, INDEX_op_sari_vec,
+        INDEX_op_mul_vec, INDEX_op_add_vec, 0
+        };
+    static const GVecGen3 op[3] = {
+        {
+            .fniv = gen_vmaddwev_s,
+            .fno = gen_helper_vmaddwev_h_b,
+            .load_dest = true,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fni4 = gen_vmaddwev_w_h,
+            .fniv = gen_vmaddwev_s,
+            .fno = gen_helper_vmaddwev_w_h,
+            .load_dest = true,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fni8 = gen_vmaddwev_d_w,
+            .fniv = gen_vmaddwev_s,
+            .fno = gen_helper_vmaddwev_d_w,
+            .load_dest = true,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vmaddwev_h_b, gvec_vvv, MO_8, do_vmaddwev_s)
+TRANS(vmaddwev_w_h, gvec_vvv, MO_16, do_vmaddwev_s)
+TRANS(vmaddwev_d_w, gvec_vvv, MO_32, do_vmaddwev_s)
+
+#define VMADD_Q(NAME, FN, idx1, idx2)                     \
+static bool trans_## NAME (DisasContext *ctx, arg_vvv *a) \
+{                                                         \
+    TCGv_i64 rh, rl, arg1, arg2, th, tl;                  \
+                                                          \
+    rh = tcg_temp_new_i64();                              \
+    rl = tcg_temp_new_i64();                              \
+    arg1 = tcg_temp_new_i64();                            \
+    arg2 = tcg_temp_new_i64();                            \
+    th = tcg_temp_new_i64();                              \
+    tl = tcg_temp_new_i64();                              \
+                                                          \
+    get_vreg64(arg1, a->vj, idx1);                        \
+    get_vreg64(arg2, a->vk, idx2);                        \
+    get_vreg64(rh, a->vd, 1);                             \
+    get_vreg64(rl, a->vd, 0);                             \
+                                                          \
+    tcg_gen_## FN ##_i64(tl, th, arg1, arg2);             \
+    tcg_gen_add2_i64(rl, rh, rl, rh, tl, th);             \
+                                                          \
+    set_vreg64(rh, a->vd, 1);                             \
+    set_vreg64(rl, a->vd, 0);                             \
+                                                          \
+    return true;                                          \
+}
+
+VMADD_Q(vmaddwev_q_d, muls2, 0, 0)
+VMADD_Q(vmaddwod_q_d, muls2, 1, 1)
+VMADD_Q(vmaddwev_q_du, mulu2, 0, 0)
+VMADD_Q(vmaddwod_q_du, mulu2, 1, 1)
+VMADD_Q(vmaddwev_q_du_d, mulus2, 0, 0)
+VMADD_Q(vmaddwod_q_du_d, mulus2, 1, 1)
+
+static void gen_vmaddwod_s(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    TCGv_vec t1, t2, t3;
+    int halfbits = 4 << vece;
+
+    t1 = tcg_temp_new_vec_matching(a);
+    t2 = tcg_temp_new_vec_matching(b);
+    t3 = tcg_temp_new_vec_matching(t);
+    tcg_gen_sari_vec(vece, t1, a, halfbits);
+    tcg_gen_sari_vec(vece, t2, b, halfbits);
+    tcg_gen_mul_vec(vece, t3, t1, t2);
+    tcg_gen_add_vec(vece, t, t, t3);
+}
+
+static void gen_vmaddwod_w_h(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 t1;
+
+    t1 = tcg_temp_new_i32();
+    gen_vmulwod_w_h(t1, a, b);
+    tcg_gen_add_i32(t, t, t1);
+}
+
+static void gen_vmaddwod_d_w(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b)
+{
+    TCGv_i64 t1;
+
+    t1 = tcg_temp_new_i64();
+    gen_vmulwod_d_w(t1, a, b);
+    tcg_gen_add_i64(t, t, t1);
+}
+
+static void do_vmaddwod_s(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                          uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_sari_vec, INDEX_op_mul_vec, INDEX_op_add_vec, 0
+        };
+    static const GVecGen3 op[3] = {
+        {
+            .fniv = gen_vmaddwod_s,
+            .fno = gen_helper_vmaddwod_h_b,
+            .load_dest = true,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fni4 = gen_vmaddwod_w_h,
+            .fniv = gen_vmaddwod_s,
+            .fno = gen_helper_vmaddwod_w_h,
+            .load_dest = true,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fni8 = gen_vmaddwod_d_w,
+            .fniv = gen_vmaddwod_s,
+            .fno = gen_helper_vmaddwod_d_w,
+            .load_dest = true,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vmaddwod_h_b, gvec_vvv, MO_8, do_vmaddwod_s)
+TRANS(vmaddwod_w_h, gvec_vvv, MO_16, do_vmaddwod_s)
+TRANS(vmaddwod_d_w, gvec_vvv, MO_32, do_vmaddwod_s)
+
+static void gen_vmaddwev_u(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    TCGv_vec t1, t2, mask;
+
+    t1 = tcg_temp_new_vec_matching(t);
+    t2 = tcg_temp_new_vec_matching(b);
+    mask = tcg_constant_vec_matching(t, vece, MAKE_64BIT_MASK(0, 4 << vece));
+    tcg_gen_and_vec(vece, t1, a, mask);
+    tcg_gen_and_vec(vece, t2, b, mask);
+    tcg_gen_mul_vec(vece, t1, t1, t2);
+    tcg_gen_add_vec(vece, t, t, t1);
+}
+
+static void gen_vmaddwev_w_hu(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 t1;
+
+    t1 = tcg_temp_new_i32();
+    gen_vmulwev_w_hu(t1, a, b);
+    tcg_gen_add_i32(t, t, t1);
+}
+
+static void gen_vmaddwev_d_wu(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b)
+{
+    TCGv_i64 t1;
+
+    t1 = tcg_temp_new_i64();
+    gen_vmulwev_d_wu(t1, a, b);
+    tcg_gen_add_i64(t, t, t1);
+}
+
+static void do_vmaddwev_u(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                          uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_mul_vec, INDEX_op_add_vec, 0
+        };
+    static const GVecGen3 op[3] = {
+        {
+            .fniv = gen_vmaddwev_u,
+            .fno = gen_helper_vmaddwev_h_bu,
+            .load_dest = true,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fni4 = gen_vmaddwev_w_hu,
+            .fniv = gen_vmaddwev_u,
+            .fno = gen_helper_vmaddwev_w_hu,
+            .load_dest = true,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fni8 = gen_vmaddwev_d_wu,
+            .fniv = gen_vmaddwev_u,
+            .fno = gen_helper_vmaddwev_d_wu,
+            .load_dest = true,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vmaddwev_h_bu, gvec_vvv, MO_8, do_vmaddwev_u)
+TRANS(vmaddwev_w_hu, gvec_vvv, MO_16, do_vmaddwev_u)
+TRANS(vmaddwev_d_wu, gvec_vvv, MO_32, do_vmaddwev_u)
+
+static void gen_vmaddwod_u(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    TCGv_vec t1, t2, t3;
+    int halfbits = 4 << vece;
+
+    t1 = tcg_temp_new_vec_matching(a);
+    t2 = tcg_temp_new_vec_matching(b);
+    t3 = tcg_temp_new_vec_matching(t);
+    tcg_gen_shri_vec(vece, t1, a, halfbits);
+    tcg_gen_shri_vec(vece, t2, b, halfbits);
+    tcg_gen_mul_vec(vece, t3, t1, t2);
+    tcg_gen_add_vec(vece, t, t, t3);
+}
+
+static void gen_vmaddwod_w_hu(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 t1;
+
+    t1 = tcg_temp_new_i32();
+    gen_vmulwod_w_hu(t1, a, b);
+    tcg_gen_add_i32(t, t, t1);
+}
+
+static void gen_vmaddwod_d_wu(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b)
+{
+    TCGv_i64 t1;
+
+    t1 = tcg_temp_new_i64();
+    gen_vmulwod_d_wu(t1, a, b);
+    tcg_gen_add_i64(t, t, t1);
+}
+
+static void do_vmaddwod_u(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                          uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_shri_vec, INDEX_op_mul_vec, INDEX_op_add_vec, 0
+        };
+    static const GVecGen3 op[3] = {
+        {
+            .fniv = gen_vmaddwod_u,
+            .fno = gen_helper_vmaddwod_h_bu,
+            .load_dest = true,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fni4 = gen_vmaddwod_w_hu,
+            .fniv = gen_vmaddwod_u,
+            .fno = gen_helper_vmaddwod_w_hu,
+            .load_dest = true,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fni8 = gen_vmaddwod_d_wu,
+            .fniv = gen_vmaddwod_u,
+            .fno = gen_helper_vmaddwod_d_wu,
+            .load_dest = true,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vmaddwod_h_bu, gvec_vvv, MO_8, do_vmaddwod_u)
+TRANS(vmaddwod_w_hu, gvec_vvv, MO_16, do_vmaddwod_u)
+TRANS(vmaddwod_d_wu, gvec_vvv, MO_32, do_vmaddwod_u)
+
+static void gen_vmaddwev_u_s(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    TCGv_vec t1, t2, mask;
+    int halfbits = 4 << vece;
+
+    t1 = tcg_temp_new_vec_matching(a);
+    t2 = tcg_temp_new_vec_matching(b);
+    mask = tcg_constant_vec_matching(t, vece, MAKE_64BIT_MASK(0, 4 << vece));
+    tcg_gen_and_vec(vece, t1, a, mask);
+    tcg_gen_shli_vec(vece, t2, b, halfbits);
+    tcg_gen_sari_vec(vece, t2, t2, halfbits);
+    tcg_gen_mul_vec(vece, t1, t1, t2);
+    tcg_gen_add_vec(vece, t, t, t1);
+}
+
+static void gen_vmaddwev_w_hu_h(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 t1;
+
+    t1 = tcg_temp_new_i32();
+    gen_vmulwev_w_hu_h(t1, a, b);
+    tcg_gen_add_i32(t, t, t1);
+}
+
+static void gen_vmaddwev_d_wu_w(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b)
+{
+    TCGv_i64 t1;
+
+    t1 = tcg_temp_new_i64();
+    gen_vmulwev_d_wu_w(t1, a, b);
+    tcg_gen_add_i64(t, t, t1);
+}
+
+static void do_vmaddwev_u_s(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                            uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_shli_vec, INDEX_op_sari_vec,
+        INDEX_op_mul_vec, INDEX_op_add_vec, 0
+        };
+    static const GVecGen3 op[3] = {
+        {
+            .fniv = gen_vmaddwev_u_s,
+            .fno = gen_helper_vmaddwev_h_bu_b,
+            .load_dest = true,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fni4 = gen_vmaddwev_w_hu_h,
+            .fniv = gen_vmaddwev_u_s,
+            .fno = gen_helper_vmaddwev_w_hu_h,
+            .load_dest = true,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fni8 = gen_vmaddwev_d_wu_w,
+            .fniv = gen_vmaddwev_u_s,
+            .fno = gen_helper_vmaddwev_d_wu_w,
+            .load_dest = true,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vmaddwev_h_bu_b, gvec_vvv, MO_8, do_vmaddwev_u_s)
+TRANS(vmaddwev_w_hu_h, gvec_vvv, MO_16, do_vmaddwev_u_s)
+TRANS(vmaddwev_d_wu_w, gvec_vvv, MO_32, do_vmaddwev_u_s)
+
+static void gen_vmaddwod_u_s(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    TCGv_vec t1, t2, t3;
+    int halfbits = 4 << vece;
+
+    t1 = tcg_temp_new_vec_matching(a);
+    t2 = tcg_temp_new_vec_matching(b);
+    t3 = tcg_temp_new_vec_matching(t);
+    tcg_gen_shri_vec(vece, t1, a, halfbits);
+    tcg_gen_sari_vec(vece, t2, b, halfbits);
+    tcg_gen_mul_vec(vece, t3, t1, t2);
+    tcg_gen_add_vec(vece, t, t, t3);
+}
+
+static void gen_vmaddwod_w_hu_h(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 t1;
+
+    t1 = tcg_temp_new_i32();
+    gen_vmulwod_w_hu_h(t1, a, b);
+    tcg_gen_add_i32(t, t, t1);
+}
+
+static void gen_vmaddwod_d_wu_w(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b)
+{
+    TCGv_i64 t1;
+
+    t1 = tcg_temp_new_i64();
+    gen_vmulwod_d_wu_w(t1, a, b);
+    tcg_gen_add_i64(t, t, t1);
+}
+
+static void do_vmaddwod_u_s(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                            uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_shri_vec, INDEX_op_sari_vec,
+        INDEX_op_mul_vec, INDEX_op_add_vec, 0
+        };
+    static const GVecGen3 op[3] = {
+        {
+            .fniv = gen_vmaddwod_u_s,
+            .fno = gen_helper_vmaddwod_h_bu_b,
+            .load_dest = true,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fni4 = gen_vmaddwod_w_hu_h,
+            .fniv = gen_vmaddwod_u_s,
+            .fno = gen_helper_vmaddwod_w_hu_h,
+            .load_dest = true,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fni8 = gen_vmaddwod_d_wu_w,
+            .fniv = gen_vmaddwod_u_s,
+            .fno = gen_helper_vmaddwod_d_wu_w,
+            .load_dest = true,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vmaddwod_h_bu_b, gvec_vvv, MO_8, do_vmaddwod_u_s)
+TRANS(vmaddwod_w_hu_h, gvec_vvv, MO_16, do_vmaddwod_u_s)
+TRANS(vmaddwod_d_wu_w, gvec_vvv, MO_32, do_vmaddwod_u_s)
+
+TRANS(vdiv_b, gen_vvv, gen_helper_vdiv_b)
+TRANS(vdiv_h, gen_vvv, gen_helper_vdiv_h)
+TRANS(vdiv_w, gen_vvv, gen_helper_vdiv_w)
+TRANS(vdiv_d, gen_vvv, gen_helper_vdiv_d)
+TRANS(vdiv_bu, gen_vvv, gen_helper_vdiv_bu)
+TRANS(vdiv_hu, gen_vvv, gen_helper_vdiv_hu)
+TRANS(vdiv_wu, gen_vvv, gen_helper_vdiv_wu)
+TRANS(vdiv_du, gen_vvv, gen_helper_vdiv_du)
+TRANS(vmod_b, gen_vvv, gen_helper_vmod_b)
+TRANS(vmod_h, gen_vvv, gen_helper_vmod_h)
+TRANS(vmod_w, gen_vvv, gen_helper_vmod_w)
+TRANS(vmod_d, gen_vvv, gen_helper_vmod_d)
+TRANS(vmod_bu, gen_vvv, gen_helper_vmod_bu)
+TRANS(vmod_hu, gen_vvv, gen_helper_vmod_hu)
+TRANS(vmod_wu, gen_vvv, gen_helper_vmod_wu)
+TRANS(vmod_du, gen_vvv, gen_helper_vmod_du)
+
+static void gen_vsat_s(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec max)
+{
+    TCGv_vec min;
+
+    min = tcg_temp_new_vec_matching(t);
+    tcg_gen_not_vec(vece, min, max);
+    tcg_gen_smax_vec(vece, t, a, min);
+    tcg_gen_smin_vec(vece, t, t, max);
+}
+
+static void do_vsat_s(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                      int64_t imm, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_smax_vec, INDEX_op_smin_vec, 0
+        };
+    static const GVecGen2s op[4] = {
+        {
+            .fniv = gen_vsat_s,
+            .fno = gen_helper_vsat_b,
+            .opt_opc = vecop_list,
+            .vece = MO_8
+        },
+        {
+            .fniv = gen_vsat_s,
+            .fno = gen_helper_vsat_h,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fniv = gen_vsat_s,
+            .fno = gen_helper_vsat_w,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fniv = gen_vsat_s,
+            .fno = gen_helper_vsat_d,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_2s(vd_ofs, vj_ofs, oprsz, maxsz,
+                    tcg_constant_i64((1ll<< imm) -1), &op[vece]);
+}
+
+TRANS(vsat_b, gvec_vv_i, MO_8, do_vsat_s)
+TRANS(vsat_h, gvec_vv_i, MO_16, do_vsat_s)
+TRANS(vsat_w, gvec_vv_i, MO_32, do_vsat_s)
+TRANS(vsat_d, gvec_vv_i, MO_64, do_vsat_s)
+
+static void gen_vsat_u(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec max)
+{
+    tcg_gen_umin_vec(vece, t, a, max);
+}
+
+static void do_vsat_u(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                       int64_t imm, uint32_t oprsz, uint32_t maxsz)
+{
+    uint64_t max;
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_umin_vec, 0
+        };
+    static const GVecGen2s op[4] = {
+        {
+            .fniv = gen_vsat_u,
+            .fno = gen_helper_vsat_bu,
+            .opt_opc = vecop_list,
+            .vece = MO_8
+        },
+        {
+            .fniv = gen_vsat_u,
+            .fno = gen_helper_vsat_hu,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fniv = gen_vsat_u,
+            .fno = gen_helper_vsat_wu,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fniv = gen_vsat_u,
+            .fno = gen_helper_vsat_du,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    max = (imm == 0x3f) ? UINT64_MAX : (1ull << (imm + 1)) - 1;
+    tcg_gen_gvec_2s(vd_ofs, vj_ofs, oprsz, maxsz,
+                    tcg_constant_i64(max), &op[vece]);
+}
+
+TRANS(vsat_bu, gvec_vv_i, MO_8, do_vsat_u)
+TRANS(vsat_hu, gvec_vv_i, MO_16, do_vsat_u)
+TRANS(vsat_wu, gvec_vv_i, MO_32, do_vsat_u)
+TRANS(vsat_du, gvec_vv_i, MO_64, do_vsat_u)
+
+TRANS(vexth_h_b, gen_vv, gen_helper_vexth_h_b)
+TRANS(vexth_w_h, gen_vv, gen_helper_vexth_w_h)
+TRANS(vexth_d_w, gen_vv, gen_helper_vexth_d_w)
+TRANS(vexth_q_d, gen_vv, gen_helper_vexth_q_d)
+TRANS(vexth_hu_bu, gen_vv, gen_helper_vexth_hu_bu)
+TRANS(vexth_wu_hu, gen_vv, gen_helper_vexth_wu_hu)
+TRANS(vexth_du_wu, gen_vv, gen_helper_vexth_du_wu)
+TRANS(vexth_qu_du, gen_vv, gen_helper_vexth_qu_du)
+
+static void gen_vsigncov(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    TCGv_vec t1, zero;
+
+    t1 = tcg_temp_new_vec_matching(t);
+    zero = tcg_constant_vec_matching(t, vece, 0);
+
+    tcg_gen_neg_vec(vece, t1, b);
+    tcg_gen_cmpsel_vec(TCG_COND_LT, vece, t, a, zero, t1, b);
+    tcg_gen_cmpsel_vec(TCG_COND_EQ, vece, t, a, zero, zero, t);
+}
+
+static void do_vsigncov(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                        uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_neg_vec, INDEX_op_cmpsel_vec, 0
+        };
+    static const GVecGen3 op[4] = {
+        {
+            .fniv = gen_vsigncov,
+            .fno = gen_helper_vsigncov_b,
+            .opt_opc = vecop_list,
+            .vece = MO_8
+        },
+        {
+            .fniv = gen_vsigncov,
+            .fno = gen_helper_vsigncov_h,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fniv = gen_vsigncov,
+            .fno = gen_helper_vsigncov_w,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fniv = gen_vsigncov,
+            .fno = gen_helper_vsigncov_d,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vsigncov_b, gvec_vvv, MO_8, do_vsigncov)
+TRANS(vsigncov_h, gvec_vvv, MO_16, do_vsigncov)
+TRANS(vsigncov_w, gvec_vvv, MO_32, do_vsigncov)
+TRANS(vsigncov_d, gvec_vvv, MO_64, do_vsigncov)
+
+TRANS(vmskltz_b, gen_vv, gen_helper_vmskltz_b)
+TRANS(vmskltz_h, gen_vv, gen_helper_vmskltz_h)
+TRANS(vmskltz_w, gen_vv, gen_helper_vmskltz_w)
+TRANS(vmskltz_d, gen_vv, gen_helper_vmskltz_d)
+TRANS(vmskgez_b, gen_vv, gen_helper_vmskgez_b)
+TRANS(vmsknz_b, gen_vv, gen_helper_vmsknz_b)
+
+#define EXPAND_BYTE(bit)  ((uint64_t)(bit ? 0xff : 0))
+
+static uint64_t vldi_get_value(DisasContext *ctx, uint32_t imm)
+{
+    int mode;
+    uint64_t data, t;
+
+    /*
+     * imm bit [11:8] is mode, mode value is 0-12.
+     * other values are invalid.
+     */
+    mode = (imm >> 8) & 0xf;
+    t =  imm & 0xff;
+    switch (mode) {
+    case 0:
+        /* data: {2{24'0, imm[7:0]}} */
+        data =  (t << 32) | t ;
+        break;
+    case 1:
+        /* data: {2{16'0, imm[7:0], 8'0}} */
+        data = (t << 24) | (t << 8);
+        break;
+    case 2:
+        /* data: {2{8'0, imm[7:0], 16'0}} */
+        data = (t << 48) | (t << 16);
+        break;
+    case 3:
+        /* data: {2{imm[7:0], 24'0}} */
+        data = (t << 56) | (t << 24);
+        break;
+    case 4:
+        /* data: {4{8'0, imm[7:0]}} */
+        data = (t << 48) | (t << 32) | (t << 16) | t;
+        break;
+    case 5:
+        /* data: {4{imm[7:0], 8'0}} */
+        data = (t << 56) |(t << 40) | (t << 24) | (t << 8);
+        break;
+    case 6:
+        /* data: {2{16'0, imm[7:0], 8'1}} */
+        data = (t << 40) | ((uint64_t)0xff << 32) | (t << 8) | 0xff;
+        break;
+    case 7:
+        /* data: {2{8'0, imm[7:0], 16'1}} */
+        data = (t << 48) | ((uint64_t)0xffff << 32) | (t << 16) | 0xffff;
+        break;
+    case 8:
+        /* data: {8{imm[7:0]}} */
+        data =(t << 56) | (t << 48) | (t << 40) | (t << 32) |
+              (t << 24) | (t << 16) | (t << 8) | t;
+        break;
+    case 9:
+        /* data: {{8{imm[7]}, ..., 8{imm[0]}}} */
+        {
+            uint64_t b0,b1,b2,b3,b4,b5,b6,b7;
+            b0 = t& 0x1;
+            b1 = (t & 0x2) >> 1;
+            b2 = (t & 0x4) >> 2;
+            b3 = (t & 0x8) >> 3;
+            b4 = (t & 0x10) >> 4;
+            b5 = (t & 0x20) >> 5;
+            b6 = (t & 0x40) >> 6;
+            b7 = (t & 0x80) >> 7;
+            data = (EXPAND_BYTE(b7) << 56) |
+                   (EXPAND_BYTE(b6) << 48) |
+                   (EXPAND_BYTE(b5) << 40) |
+                   (EXPAND_BYTE(b4) << 32) |
+                   (EXPAND_BYTE(b3) << 24) |
+                   (EXPAND_BYTE(b2) << 16) |
+                   (EXPAND_BYTE(b1) <<  8) |
+                   EXPAND_BYTE(b0);
+        }
+        break;
+    case 10:
+        /* data: {2{imm[7], ~imm[6], {5{imm[6]}}, imm[5:0], 19'0}} */
+        {
+            uint64_t b6, b7;
+            uint64_t t0, t1;
+            b6 = (imm & 0x40) >> 6;
+            b7 = (imm & 0x80) >> 7;
+            t0 = (imm & 0x3f);
+            t1 = (b7 << 6) | ((1-b6) << 5) | (uint64_t)(b6 ? 0x1f : 0);
+            data  = (t1 << 57) | (t0 << 51) | (t1 << 25) | (t0 << 19);
+        }
+        break;
+    case 11:
+        /* data: {32'0, imm[7], ~{imm[6]}, 5{imm[6]}, imm[5:0], 19'0} */
+        {
+            uint64_t b6,b7;
+            uint64_t t0, t1;
+            b6 = (imm & 0x40) >> 6;
+            b7 = (imm & 0x80) >> 7;
+            t0 = (imm & 0x3f);
+            t1 = (b7 << 6) | ((1-b6) << 5) | (b6 ? 0x1f : 0);
+            data = (t1 << 25) | (t0 << 19);
+        }
+        break;
+    case 12:
+        /* data: {imm[7], ~imm[6], 8{imm[6]}, imm[5:0], 48'0} */
+        {
+            uint64_t b6,b7;
+            uint64_t t0, t1;
+            b6 = (imm & 0x40) >> 6;
+            b7 = (imm & 0x80) >> 7;
+            t0 = (imm & 0x3f);
+            t1 = (b7 << 9) | ((1-b6) << 8) | (b6 ? 0xff : 0);
+            data = (t1 << 54) | (t0 << 48);
+        }
+        break;
+    default:
+        generate_exception(ctx, EXCCODE_INE);
+        g_assert_not_reached();
+    }
+    return data;
+}
+
+static bool trans_vldi(DisasContext *ctx, arg_vldi *a)
+{
+    int sel, vece;
+    uint64_t value;
+    CHECK_SXE;
+
+    sel = (a->imm >> 12) & 0x1;
+
+    if (sel) {
+        value = vldi_get_value(ctx, a->imm);
+        vece = MO_64;
+    } else {
+        value = ((int32_t)(a->imm << 22)) >> 22;
+        vece = (a->imm >> 10) & 0x3;
+    }
+
+    tcg_gen_gvec_dup_i64(vece, vec_full_offset(a->vd), 16, ctx->vl/8,
+                         tcg_constant_i64(value));
+    return true;
+}
+
+TRANS(vand_v, gvec_vvv, MO_64, tcg_gen_gvec_and)
+TRANS(vor_v, gvec_vvv, MO_64, tcg_gen_gvec_or)
+TRANS(vxor_v, gvec_vvv, MO_64, tcg_gen_gvec_xor)
+TRANS(vnor_v, gvec_vvv, MO_64, tcg_gen_gvec_nor)
+
+static bool trans_vandn_v(DisasContext *ctx, arg_vvv *a)
+{
+    uint32_t vd_ofs, vj_ofs, vk_ofs;
+
+    CHECK_SXE;
+
+    vd_ofs = vec_full_offset(a->vd);
+    vj_ofs = vec_full_offset(a->vj);
+    vk_ofs = vec_full_offset(a->vk);
+
+    tcg_gen_gvec_andc(MO_64, vd_ofs, vk_ofs, vj_ofs, 16, ctx->vl/8);
+    return true;
+}
+TRANS(vorn_v, gvec_vvv, MO_64, tcg_gen_gvec_orc)
+TRANS(vandi_b, gvec_vv_i, MO_8, tcg_gen_gvec_andi)
+TRANS(vori_b, gvec_vv_i, MO_8, tcg_gen_gvec_ori)
+TRANS(vxori_b, gvec_vv_i, MO_8, tcg_gen_gvec_xori)
+
+static void gen_vnori(unsigned vece, TCGv_vec t, TCGv_vec a, int64_t imm)
+{
+    TCGv_vec t1;
+
+    t1 = tcg_constant_vec_matching(t, vece, imm);
+    tcg_gen_nor_vec(vece, t, a, t1);
+}
+
+static void gen_vnori_b(TCGv_i64 t, TCGv_i64 a, int64_t imm)
+{
+    tcg_gen_movi_i64(t, dup_const(MO_8, imm));
+    tcg_gen_nor_i64(t, a, t);
+}
+
+static void do_vnori_b(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                       int64_t imm, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_nor_vec, 0
+        };
+    static const GVecGen2i op = {
+       .fni8 = gen_vnori_b,
+       .fniv = gen_vnori,
+       .fnoi = gen_helper_vnori_b,
+       .opt_opc = vecop_list,
+       .vece = MO_8
+    };
+
+    tcg_gen_gvec_2i(vd_ofs, vj_ofs, oprsz, maxsz, imm, &op);
+}
+
+TRANS(vnori_b, gvec_vv_i, MO_8, do_vnori_b)
+
+TRANS(vsll_b, gvec_vvv, MO_8, tcg_gen_gvec_shlv)
+TRANS(vsll_h, gvec_vvv, MO_16, tcg_gen_gvec_shlv)
+TRANS(vsll_w, gvec_vvv, MO_32, tcg_gen_gvec_shlv)
+TRANS(vsll_d, gvec_vvv, MO_64, tcg_gen_gvec_shlv)
+TRANS(vslli_b, gvec_vv_i, MO_8, tcg_gen_gvec_shli)
+TRANS(vslli_h, gvec_vv_i, MO_16, tcg_gen_gvec_shli)
+TRANS(vslli_w, gvec_vv_i, MO_32, tcg_gen_gvec_shli)
+TRANS(vslli_d, gvec_vv_i, MO_64, tcg_gen_gvec_shli)
+
+TRANS(vsrl_b, gvec_vvv, MO_8, tcg_gen_gvec_shrv)
+TRANS(vsrl_h, gvec_vvv, MO_16, tcg_gen_gvec_shrv)
+TRANS(vsrl_w, gvec_vvv, MO_32, tcg_gen_gvec_shrv)
+TRANS(vsrl_d, gvec_vvv, MO_64, tcg_gen_gvec_shrv)
+TRANS(vsrli_b, gvec_vv_i, MO_8, tcg_gen_gvec_shri)
+TRANS(vsrli_h, gvec_vv_i, MO_16, tcg_gen_gvec_shri)
+TRANS(vsrli_w, gvec_vv_i, MO_32, tcg_gen_gvec_shri)
+TRANS(vsrli_d, gvec_vv_i, MO_64, tcg_gen_gvec_shri)
+
+TRANS(vsra_b, gvec_vvv, MO_8, tcg_gen_gvec_sarv)
+TRANS(vsra_h, gvec_vvv, MO_16, tcg_gen_gvec_sarv)
+TRANS(vsra_w, gvec_vvv, MO_32, tcg_gen_gvec_sarv)
+TRANS(vsra_d, gvec_vvv, MO_64, tcg_gen_gvec_sarv)
+TRANS(vsrai_b, gvec_vv_i, MO_8, tcg_gen_gvec_sari)
+TRANS(vsrai_h, gvec_vv_i, MO_16, tcg_gen_gvec_sari)
+TRANS(vsrai_w, gvec_vv_i, MO_32, tcg_gen_gvec_sari)
+TRANS(vsrai_d, gvec_vv_i, MO_64, tcg_gen_gvec_sari)
+
+TRANS(vrotr_b, gvec_vvv, MO_8, tcg_gen_gvec_rotrv)
+TRANS(vrotr_h, gvec_vvv, MO_16, tcg_gen_gvec_rotrv)
+TRANS(vrotr_w, gvec_vvv, MO_32, tcg_gen_gvec_rotrv)
+TRANS(vrotr_d, gvec_vvv, MO_64, tcg_gen_gvec_rotrv)
+TRANS(vrotri_b, gvec_vv_i, MO_8, tcg_gen_gvec_rotri)
+TRANS(vrotri_h, gvec_vv_i, MO_16, tcg_gen_gvec_rotri)
+TRANS(vrotri_w, gvec_vv_i, MO_32, tcg_gen_gvec_rotri)
+TRANS(vrotri_d, gvec_vv_i, MO_64, tcg_gen_gvec_rotri)
+
+TRANS(vsllwil_h_b, gen_vv_i, gen_helper_vsllwil_h_b)
+TRANS(vsllwil_w_h, gen_vv_i, gen_helper_vsllwil_w_h)
+TRANS(vsllwil_d_w, gen_vv_i, gen_helper_vsllwil_d_w)
+TRANS(vextl_q_d, gen_vv, gen_helper_vextl_q_d)
+TRANS(vsllwil_hu_bu, gen_vv_i, gen_helper_vsllwil_hu_bu)
+TRANS(vsllwil_wu_hu, gen_vv_i, gen_helper_vsllwil_wu_hu)
+TRANS(vsllwil_du_wu, gen_vv_i, gen_helper_vsllwil_du_wu)
+TRANS(vextl_qu_du, gen_vv, gen_helper_vextl_qu_du)
+
+TRANS(vsrlr_b, gen_vvv, gen_helper_vsrlr_b)
+TRANS(vsrlr_h, gen_vvv, gen_helper_vsrlr_h)
+TRANS(vsrlr_w, gen_vvv, gen_helper_vsrlr_w)
+TRANS(vsrlr_d, gen_vvv, gen_helper_vsrlr_d)
+TRANS(vsrlri_b, gen_vv_i, gen_helper_vsrlri_b)
+TRANS(vsrlri_h, gen_vv_i, gen_helper_vsrlri_h)
+TRANS(vsrlri_w, gen_vv_i, gen_helper_vsrlri_w)
+TRANS(vsrlri_d, gen_vv_i, gen_helper_vsrlri_d)
+
+TRANS(vsrar_b, gen_vvv, gen_helper_vsrar_b)
+TRANS(vsrar_h, gen_vvv, gen_helper_vsrar_h)
+TRANS(vsrar_w, gen_vvv, gen_helper_vsrar_w)
+TRANS(vsrar_d, gen_vvv, gen_helper_vsrar_d)
+TRANS(vsrari_b, gen_vv_i, gen_helper_vsrari_b)
+TRANS(vsrari_h, gen_vv_i, gen_helper_vsrari_h)
+TRANS(vsrari_w, gen_vv_i, gen_helper_vsrari_w)
+TRANS(vsrari_d, gen_vv_i, gen_helper_vsrari_d)
+
+TRANS(vsrln_b_h, gen_vvv, gen_helper_vsrln_b_h)
+TRANS(vsrln_h_w, gen_vvv, gen_helper_vsrln_h_w)
+TRANS(vsrln_w_d, gen_vvv, gen_helper_vsrln_w_d)
+TRANS(vsran_b_h, gen_vvv, gen_helper_vsran_b_h)
+TRANS(vsran_h_w, gen_vvv, gen_helper_vsran_h_w)
+TRANS(vsran_w_d, gen_vvv, gen_helper_vsran_w_d)
+
+TRANS(vsrlni_b_h, gen_vv_i, gen_helper_vsrlni_b_h)
+TRANS(vsrlni_h_w, gen_vv_i, gen_helper_vsrlni_h_w)
+TRANS(vsrlni_w_d, gen_vv_i, gen_helper_vsrlni_w_d)
+TRANS(vsrlni_d_q, gen_vv_i, gen_helper_vsrlni_d_q)
+TRANS(vsrani_b_h, gen_vv_i, gen_helper_vsrani_b_h)
+TRANS(vsrani_h_w, gen_vv_i, gen_helper_vsrani_h_w)
+TRANS(vsrani_w_d, gen_vv_i, gen_helper_vsrani_w_d)
+TRANS(vsrani_d_q, gen_vv_i, gen_helper_vsrani_d_q)
+
+TRANS(vsrlrn_b_h, gen_vvv, gen_helper_vsrlrn_b_h)
+TRANS(vsrlrn_h_w, gen_vvv, gen_helper_vsrlrn_h_w)
+TRANS(vsrlrn_w_d, gen_vvv, gen_helper_vsrlrn_w_d)
+TRANS(vsrarn_b_h, gen_vvv, gen_helper_vsrarn_b_h)
+TRANS(vsrarn_h_w, gen_vvv, gen_helper_vsrarn_h_w)
+TRANS(vsrarn_w_d, gen_vvv, gen_helper_vsrarn_w_d)
+
+TRANS(vsrlrni_b_h, gen_vv_i, gen_helper_vsrlrni_b_h)
+TRANS(vsrlrni_h_w, gen_vv_i, gen_helper_vsrlrni_h_w)
+TRANS(vsrlrni_w_d, gen_vv_i, gen_helper_vsrlrni_w_d)
+TRANS(vsrlrni_d_q, gen_vv_i, gen_helper_vsrlrni_d_q)
+TRANS(vsrarni_b_h, gen_vv_i, gen_helper_vsrarni_b_h)
+TRANS(vsrarni_h_w, gen_vv_i, gen_helper_vsrarni_h_w)
+TRANS(vsrarni_w_d, gen_vv_i, gen_helper_vsrarni_w_d)
+TRANS(vsrarni_d_q, gen_vv_i, gen_helper_vsrarni_d_q)
+
+TRANS(vssrln_b_h, gen_vvv, gen_helper_vssrln_b_h)
+TRANS(vssrln_h_w, gen_vvv, gen_helper_vssrln_h_w)
+TRANS(vssrln_w_d, gen_vvv, gen_helper_vssrln_w_d)
+TRANS(vssran_b_h, gen_vvv, gen_helper_vssran_b_h)
+TRANS(vssran_h_w, gen_vvv, gen_helper_vssran_h_w)
+TRANS(vssran_w_d, gen_vvv, gen_helper_vssran_w_d)
+TRANS(vssrln_bu_h, gen_vvv, gen_helper_vssrln_bu_h)
+TRANS(vssrln_hu_w, gen_vvv, gen_helper_vssrln_hu_w)
+TRANS(vssrln_wu_d, gen_vvv, gen_helper_vssrln_wu_d)
+TRANS(vssran_bu_h, gen_vvv, gen_helper_vssran_bu_h)
+TRANS(vssran_hu_w, gen_vvv, gen_helper_vssran_hu_w)
+TRANS(vssran_wu_d, gen_vvv, gen_helper_vssran_wu_d)
+
+TRANS(vssrlni_b_h, gen_vv_i, gen_helper_vssrlni_b_h)
+TRANS(vssrlni_h_w, gen_vv_i, gen_helper_vssrlni_h_w)
+TRANS(vssrlni_w_d, gen_vv_i, gen_helper_vssrlni_w_d)
+TRANS(vssrlni_d_q, gen_vv_i, gen_helper_vssrlni_d_q)
+TRANS(vssrani_b_h, gen_vv_i, gen_helper_vssrani_b_h)
+TRANS(vssrani_h_w, gen_vv_i, gen_helper_vssrani_h_w)
+TRANS(vssrani_w_d, gen_vv_i, gen_helper_vssrani_w_d)
+TRANS(vssrani_d_q, gen_vv_i, gen_helper_vssrani_d_q)
+TRANS(vssrlni_bu_h, gen_vv_i, gen_helper_vssrlni_bu_h)
+TRANS(vssrlni_hu_w, gen_vv_i, gen_helper_vssrlni_hu_w)
+TRANS(vssrlni_wu_d, gen_vv_i, gen_helper_vssrlni_wu_d)
+TRANS(vssrlni_du_q, gen_vv_i, gen_helper_vssrlni_du_q)
+TRANS(vssrani_bu_h, gen_vv_i, gen_helper_vssrani_bu_h)
+TRANS(vssrani_hu_w, gen_vv_i, gen_helper_vssrani_hu_w)
+TRANS(vssrani_wu_d, gen_vv_i, gen_helper_vssrani_wu_d)
+TRANS(vssrani_du_q, gen_vv_i, gen_helper_vssrani_du_q)
+
+TRANS(vssrlrn_b_h, gen_vvv, gen_helper_vssrlrn_b_h)
+TRANS(vssrlrn_h_w, gen_vvv, gen_helper_vssrlrn_h_w)
+TRANS(vssrlrn_w_d, gen_vvv, gen_helper_vssrlrn_w_d)
+TRANS(vssrarn_b_h, gen_vvv, gen_helper_vssrarn_b_h)
+TRANS(vssrarn_h_w, gen_vvv, gen_helper_vssrarn_h_w)
+TRANS(vssrarn_w_d, gen_vvv, gen_helper_vssrarn_w_d)
+TRANS(vssrlrn_bu_h, gen_vvv, gen_helper_vssrlrn_bu_h)
+TRANS(vssrlrn_hu_w, gen_vvv, gen_helper_vssrlrn_hu_w)
+TRANS(vssrlrn_wu_d, gen_vvv, gen_helper_vssrlrn_wu_d)
+TRANS(vssrarn_bu_h, gen_vvv, gen_helper_vssrarn_bu_h)
+TRANS(vssrarn_hu_w, gen_vvv, gen_helper_vssrarn_hu_w)
+TRANS(vssrarn_wu_d, gen_vvv, gen_helper_vssrarn_wu_d)
+
+TRANS(vssrlrni_b_h, gen_vv_i, gen_helper_vssrlrni_b_h)
+TRANS(vssrlrni_h_w, gen_vv_i, gen_helper_vssrlrni_h_w)
+TRANS(vssrlrni_w_d, gen_vv_i, gen_helper_vssrlrni_w_d)
+TRANS(vssrlrni_d_q, gen_vv_i, gen_helper_vssrlrni_d_q)
+TRANS(vssrarni_b_h, gen_vv_i, gen_helper_vssrarni_b_h)
+TRANS(vssrarni_h_w, gen_vv_i, gen_helper_vssrarni_h_w)
+TRANS(vssrarni_w_d, gen_vv_i, gen_helper_vssrarni_w_d)
+TRANS(vssrarni_d_q, gen_vv_i, gen_helper_vssrarni_d_q)
+TRANS(vssrlrni_bu_h, gen_vv_i, gen_helper_vssrlrni_bu_h)
+TRANS(vssrlrni_hu_w, gen_vv_i, gen_helper_vssrlrni_hu_w)
+TRANS(vssrlrni_wu_d, gen_vv_i, gen_helper_vssrlrni_wu_d)
+TRANS(vssrlrni_du_q, gen_vv_i, gen_helper_vssrlrni_du_q)
+TRANS(vssrarni_bu_h, gen_vv_i, gen_helper_vssrarni_bu_h)
+TRANS(vssrarni_hu_w, gen_vv_i, gen_helper_vssrarni_hu_w)
+TRANS(vssrarni_wu_d, gen_vv_i, gen_helper_vssrarni_wu_d)
+TRANS(vssrarni_du_q, gen_vv_i, gen_helper_vssrarni_du_q)
+
+TRANS(vclo_b, gen_vv, gen_helper_vclo_b)
+TRANS(vclo_h, gen_vv, gen_helper_vclo_h)
+TRANS(vclo_w, gen_vv, gen_helper_vclo_w)
+TRANS(vclo_d, gen_vv, gen_helper_vclo_d)
+TRANS(vclz_b, gen_vv, gen_helper_vclz_b)
+TRANS(vclz_h, gen_vv, gen_helper_vclz_h)
+TRANS(vclz_w, gen_vv, gen_helper_vclz_w)
+TRANS(vclz_d, gen_vv, gen_helper_vclz_d)
+
+TRANS(vpcnt_b, gen_vv, gen_helper_vpcnt_b)
+TRANS(vpcnt_h, gen_vv, gen_helper_vpcnt_h)
+TRANS(vpcnt_w, gen_vv, gen_helper_vpcnt_w)
+TRANS(vpcnt_d, gen_vv, gen_helper_vpcnt_d)
+
+static void do_vbit(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b,
+                    void (*func)(unsigned, TCGv_vec, TCGv_vec, TCGv_vec))
+{
+    TCGv_vec mask, lsh, t1, one;
+
+    lsh = tcg_temp_new_vec_matching(t);
+    t1 = tcg_temp_new_vec_matching(t);
+    mask = tcg_constant_vec_matching(t, vece, (8 << vece) - 1);
+    one = tcg_constant_vec_matching(t, vece, 1);
+
+    tcg_gen_and_vec(vece, lsh, b, mask);
+    tcg_gen_shlv_vec(vece, t1, one, lsh);
+    func(vece, t, a, t1);
+}
+
+static void gen_vbitclr(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    do_vbit(vece, t, a, b, tcg_gen_andc_vec);
+}
+
+static void gen_vbitset(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    do_vbit(vece, t, a, b, tcg_gen_or_vec);
+}
+
+static void gen_vbitrev(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    do_vbit(vece, t, a, b, tcg_gen_xor_vec);
+}
+
+static void do_vbitclr(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                      uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_shlv_vec, INDEX_op_andc_vec, 0
+        };
+    static const GVecGen3 op[4] = {
+        {
+            .fniv = gen_vbitclr,
+            .fno = gen_helper_vbitclr_b,
+            .opt_opc = vecop_list,
+            .vece = MO_8
+        },
+        {
+            .fniv = gen_vbitclr,
+            .fno = gen_helper_vbitclr_h,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fniv = gen_vbitclr,
+            .fno = gen_helper_vbitclr_w,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fniv = gen_vbitclr,
+            .fno = gen_helper_vbitclr_d,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vbitclr_b, gvec_vvv, MO_8, do_vbitclr)
+TRANS(vbitclr_h, gvec_vvv, MO_16, do_vbitclr)
+TRANS(vbitclr_w, gvec_vvv, MO_32, do_vbitclr)
+TRANS(vbitclr_d, gvec_vvv, MO_64, do_vbitclr)
+
+static void do_vbiti(unsigned vece, TCGv_vec t, TCGv_vec a, int64_t imm,
+                     void (*func)(unsigned, TCGv_vec, TCGv_vec, TCGv_vec))
+{
+    int lsh;
+    TCGv_vec t1, one;
+
+    lsh = imm & ((8 << vece) -1);
+    t1 = tcg_temp_new_vec_matching(t);
+    one = tcg_constant_vec_matching(t, vece, 1);
+
+    tcg_gen_shli_vec(vece, t1, one, lsh);
+    func(vece, t, a, t1);
+}
+
+static void gen_vbitclri(unsigned vece, TCGv_vec t, TCGv_vec a, int64_t imm)
+{
+    do_vbiti(vece, t, a, imm, tcg_gen_andc_vec);
+}
+
+static void gen_vbitseti(unsigned vece, TCGv_vec t, TCGv_vec a, int64_t imm)
+{
+    do_vbiti(vece, t, a, imm, tcg_gen_or_vec);
+}
+
+static void gen_vbitrevi(unsigned vece, TCGv_vec t, TCGv_vec a, int64_t imm)
+{
+    do_vbiti(vece, t, a, imm, tcg_gen_xor_vec);
+}
+
+static void do_vbitclri(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                        int64_t imm, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_shli_vec, INDEX_op_andc_vec, 0
+        };
+    static const GVecGen2i op[4] = {
+        {
+            .fniv = gen_vbitclri,
+            .fnoi = gen_helper_vbitclri_b,
+            .opt_opc = vecop_list,
+            .vece = MO_8
+        },
+        {
+            .fniv = gen_vbitclri,
+            .fnoi = gen_helper_vbitclri_h,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fniv = gen_vbitclri,
+            .fnoi = gen_helper_vbitclri_w,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fniv = gen_vbitclri,
+            .fnoi = gen_helper_vbitclri_d,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_2i(vd_ofs, vj_ofs, oprsz, maxsz, imm, &op[vece]);
+}
+
+TRANS(vbitclri_b, gvec_vv_i, MO_8, do_vbitclri)
+TRANS(vbitclri_h, gvec_vv_i, MO_16, do_vbitclri)
+TRANS(vbitclri_w, gvec_vv_i, MO_32, do_vbitclri)
+TRANS(vbitclri_d, gvec_vv_i, MO_64, do_vbitclri)
+
+static void do_vbitset(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                       uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_shlv_vec, 0
+        };
+    static const GVecGen3 op[4] = {
+        {
+            .fniv = gen_vbitset,
+            .fno = gen_helper_vbitset_b,
+            .opt_opc = vecop_list,
+            .vece = MO_8
+        },
+        {
+            .fniv = gen_vbitset,
+            .fno = gen_helper_vbitset_h,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fniv = gen_vbitset,
+            .fno = gen_helper_vbitset_w,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fniv = gen_vbitset,
+            .fno = gen_helper_vbitset_d,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vbitset_b, gvec_vvv, MO_8, do_vbitset)
+TRANS(vbitset_h, gvec_vvv, MO_16, do_vbitset)
+TRANS(vbitset_w, gvec_vvv, MO_32, do_vbitset)
+TRANS(vbitset_d, gvec_vvv, MO_64, do_vbitset)
+
+static void do_vbitseti(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                        int64_t imm, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_shli_vec, 0
+        };
+    static const GVecGen2i op[4] = {
+        {
+            .fniv = gen_vbitseti,
+            .fnoi = gen_helper_vbitseti_b,
+            .opt_opc = vecop_list,
+            .vece = MO_8
+        },
+        {
+            .fniv = gen_vbitseti,
+            .fnoi = gen_helper_vbitseti_h,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fniv = gen_vbitseti,
+            .fnoi = gen_helper_vbitseti_w,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fniv = gen_vbitseti,
+            .fnoi = gen_helper_vbitseti_d,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_2i(vd_ofs, vj_ofs, oprsz, maxsz, imm, &op[vece]);
+}
+
+TRANS(vbitseti_b, gvec_vv_i, MO_8, do_vbitseti)
+TRANS(vbitseti_h, gvec_vv_i, MO_16, do_vbitseti)
+TRANS(vbitseti_w, gvec_vv_i, MO_32, do_vbitseti)
+TRANS(vbitseti_d, gvec_vv_i, MO_64, do_vbitseti)
+
+static void do_vbitrev(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                       uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_shlv_vec, 0
+        };
+    static const GVecGen3 op[4] = {
+        {
+            .fniv = gen_vbitrev,
+            .fno = gen_helper_vbitrev_b,
+            .opt_opc = vecop_list,
+            .vece = MO_8
+        },
+        {
+            .fniv = gen_vbitrev,
+            .fno = gen_helper_vbitrev_h,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fniv = gen_vbitrev,
+            .fno = gen_helper_vbitrev_w,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fniv = gen_vbitrev,
+            .fno = gen_helper_vbitrev_d,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vbitrev_b, gvec_vvv, MO_8, do_vbitrev)
+TRANS(vbitrev_h, gvec_vvv, MO_16, do_vbitrev)
+TRANS(vbitrev_w, gvec_vvv, MO_32, do_vbitrev)
+TRANS(vbitrev_d, gvec_vvv, MO_64, do_vbitrev)
+
+static void do_vbitrevi(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                        int64_t imm, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_shli_vec, 0
+        };
+    static const GVecGen2i op[4] = {
+        {
+            .fniv = gen_vbitrevi,
+            .fnoi = gen_helper_vbitrevi_b,
+            .opt_opc = vecop_list,
+            .vece = MO_8
+        },
+        {
+            .fniv = gen_vbitrevi,
+            .fnoi = gen_helper_vbitrevi_h,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fniv = gen_vbitrevi,
+            .fnoi = gen_helper_vbitrevi_w,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fniv = gen_vbitrevi,
+            .fnoi = gen_helper_vbitrevi_d,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_2i(vd_ofs, vj_ofs, oprsz, maxsz, imm, &op[vece]);
+}
+
+TRANS(vbitrevi_b, gvec_vv_i, MO_8, do_vbitrevi)
+TRANS(vbitrevi_h, gvec_vv_i, MO_16, do_vbitrevi)
+TRANS(vbitrevi_w, gvec_vv_i, MO_32, do_vbitrevi)
+TRANS(vbitrevi_d, gvec_vv_i, MO_64, do_vbitrevi)
+
+TRANS(vfrstp_b, gen_vvv, gen_helper_vfrstp_b)
+TRANS(vfrstp_h, gen_vvv, gen_helper_vfrstp_h)
+TRANS(vfrstpi_b, gen_vv_i, gen_helper_vfrstpi_b)
+TRANS(vfrstpi_h, gen_vv_i, gen_helper_vfrstpi_h)
+
+TRANS(vfadd_s, gen_vvv, gen_helper_vfadd_s)
+TRANS(vfadd_d, gen_vvv, gen_helper_vfadd_d)
+TRANS(vfsub_s, gen_vvv, gen_helper_vfsub_s)
+TRANS(vfsub_d, gen_vvv, gen_helper_vfsub_d)
+TRANS(vfmul_s, gen_vvv, gen_helper_vfmul_s)
+TRANS(vfmul_d, gen_vvv, gen_helper_vfmul_d)
+TRANS(vfdiv_s, gen_vvv, gen_helper_vfdiv_s)
+TRANS(vfdiv_d, gen_vvv, gen_helper_vfdiv_d)
+
+TRANS(vfmadd_s, gen_vvvv, gen_helper_vfmadd_s)
+TRANS(vfmadd_d, gen_vvvv, gen_helper_vfmadd_d)
+TRANS(vfmsub_s, gen_vvvv, gen_helper_vfmsub_s)
+TRANS(vfmsub_d, gen_vvvv, gen_helper_vfmsub_d)
+TRANS(vfnmadd_s, gen_vvvv, gen_helper_vfnmadd_s)
+TRANS(vfnmadd_d, gen_vvvv, gen_helper_vfnmadd_d)
+TRANS(vfnmsub_s, gen_vvvv, gen_helper_vfnmsub_s)
+TRANS(vfnmsub_d, gen_vvvv, gen_helper_vfnmsub_d)
+
+TRANS(vfmax_s, gen_vvv, gen_helper_vfmax_s)
+TRANS(vfmax_d, gen_vvv, gen_helper_vfmax_d)
+TRANS(vfmin_s, gen_vvv, gen_helper_vfmin_s)
+TRANS(vfmin_d, gen_vvv, gen_helper_vfmin_d)
+
+TRANS(vfmaxa_s, gen_vvv, gen_helper_vfmaxa_s)
+TRANS(vfmaxa_d, gen_vvv, gen_helper_vfmaxa_d)
+TRANS(vfmina_s, gen_vvv, gen_helper_vfmina_s)
+TRANS(vfmina_d, gen_vvv, gen_helper_vfmina_d)
+
+TRANS(vflogb_s, gen_vv, gen_helper_vflogb_s)
+TRANS(vflogb_d, gen_vv, gen_helper_vflogb_d)
+
+TRANS(vfclass_s, gen_vv, gen_helper_vfclass_s)
+TRANS(vfclass_d, gen_vv, gen_helper_vfclass_d)
+
+TRANS(vfsqrt_s, gen_vv, gen_helper_vfsqrt_s)
+TRANS(vfsqrt_d, gen_vv, gen_helper_vfsqrt_d)
+TRANS(vfrecip_s, gen_vv, gen_helper_vfrecip_s)
+TRANS(vfrecip_d, gen_vv, gen_helper_vfrecip_d)
+TRANS(vfrsqrt_s, gen_vv, gen_helper_vfrsqrt_s)
+TRANS(vfrsqrt_d, gen_vv, gen_helper_vfrsqrt_d)
+
+TRANS(vfcvtl_s_h, gen_vv, gen_helper_vfcvtl_s_h)
+TRANS(vfcvth_s_h, gen_vv, gen_helper_vfcvth_s_h)
+TRANS(vfcvtl_d_s, gen_vv, gen_helper_vfcvtl_d_s)
+TRANS(vfcvth_d_s, gen_vv, gen_helper_vfcvth_d_s)
+TRANS(vfcvt_h_s, gen_vvv, gen_helper_vfcvt_h_s)
+TRANS(vfcvt_s_d, gen_vvv, gen_helper_vfcvt_s_d)
+
+TRANS(vfrintrne_s, gen_vv, gen_helper_vfrintrne_s)
+TRANS(vfrintrne_d, gen_vv, gen_helper_vfrintrne_d)
+TRANS(vfrintrz_s, gen_vv, gen_helper_vfrintrz_s)
+TRANS(vfrintrz_d, gen_vv, gen_helper_vfrintrz_d)
+TRANS(vfrintrp_s, gen_vv, gen_helper_vfrintrp_s)
+TRANS(vfrintrp_d, gen_vv, gen_helper_vfrintrp_d)
+TRANS(vfrintrm_s, gen_vv, gen_helper_vfrintrm_s)
+TRANS(vfrintrm_d, gen_vv, gen_helper_vfrintrm_d)
+TRANS(vfrint_s, gen_vv, gen_helper_vfrint_s)
+TRANS(vfrint_d, gen_vv, gen_helper_vfrint_d)
+
+TRANS(vftintrne_w_s, gen_vv, gen_helper_vftintrne_w_s)
+TRANS(vftintrne_l_d, gen_vv, gen_helper_vftintrne_l_d)
+TRANS(vftintrz_w_s, gen_vv, gen_helper_vftintrz_w_s)
+TRANS(vftintrz_l_d, gen_vv, gen_helper_vftintrz_l_d)
+TRANS(vftintrp_w_s, gen_vv, gen_helper_vftintrp_w_s)
+TRANS(vftintrp_l_d, gen_vv, gen_helper_vftintrp_l_d)
+TRANS(vftintrm_w_s, gen_vv, gen_helper_vftintrm_w_s)
+TRANS(vftintrm_l_d, gen_vv, gen_helper_vftintrm_l_d)
+TRANS(vftint_w_s, gen_vv, gen_helper_vftint_w_s)
+TRANS(vftint_l_d, gen_vv, gen_helper_vftint_l_d)
+TRANS(vftintrz_wu_s, gen_vv, gen_helper_vftintrz_wu_s)
+TRANS(vftintrz_lu_d, gen_vv, gen_helper_vftintrz_lu_d)
+TRANS(vftint_wu_s, gen_vv, gen_helper_vftint_wu_s)
+TRANS(vftint_lu_d, gen_vv, gen_helper_vftint_lu_d)
+TRANS(vftintrne_w_d, gen_vvv, gen_helper_vftintrne_w_d)
+TRANS(vftintrz_w_d, gen_vvv, gen_helper_vftintrz_w_d)
+TRANS(vftintrp_w_d, gen_vvv, gen_helper_vftintrp_w_d)
+TRANS(vftintrm_w_d, gen_vvv, gen_helper_vftintrm_w_d)
+TRANS(vftint_w_d, gen_vvv, gen_helper_vftint_w_d)
+TRANS(vftintrnel_l_s, gen_vv, gen_helper_vftintrnel_l_s)
+TRANS(vftintrneh_l_s, gen_vv, gen_helper_vftintrneh_l_s)
+TRANS(vftintrzl_l_s, gen_vv, gen_helper_vftintrzl_l_s)
+TRANS(vftintrzh_l_s, gen_vv, gen_helper_vftintrzh_l_s)
+TRANS(vftintrpl_l_s, gen_vv, gen_helper_vftintrpl_l_s)
+TRANS(vftintrph_l_s, gen_vv, gen_helper_vftintrph_l_s)
+TRANS(vftintrml_l_s, gen_vv, gen_helper_vftintrml_l_s)
+TRANS(vftintrmh_l_s, gen_vv, gen_helper_vftintrmh_l_s)
+TRANS(vftintl_l_s, gen_vv, gen_helper_vftintl_l_s)
+TRANS(vftinth_l_s, gen_vv, gen_helper_vftinth_l_s)
+
+TRANS(vffint_s_w, gen_vv, gen_helper_vffint_s_w)
+TRANS(vffint_d_l, gen_vv, gen_helper_vffint_d_l)
+TRANS(vffint_s_wu, gen_vv, gen_helper_vffint_s_wu)
+TRANS(vffint_d_lu, gen_vv, gen_helper_vffint_d_lu)
+TRANS(vffintl_d_w, gen_vv, gen_helper_vffintl_d_w)
+TRANS(vffinth_d_w, gen_vv, gen_helper_vffinth_d_w)
+TRANS(vffint_s_l, gen_vvv, gen_helper_vffint_s_l)
+
+static bool do_cmp(DisasContext *ctx, arg_vvv *a, MemOp mop, TCGCond cond)
+{
+    uint32_t vd_ofs, vj_ofs, vk_ofs;
+
+    CHECK_SXE;
+
+    vd_ofs = vec_full_offset(a->vd);
+    vj_ofs = vec_full_offset(a->vj);
+    vk_ofs = vec_full_offset(a->vk);
+
+    tcg_gen_gvec_cmp(cond, mop, vd_ofs, vj_ofs, vk_ofs, 16, ctx->vl/8);
+    return true;
+}
+
+static void do_cmpi_vec(TCGCond cond,
+                        unsigned vece, TCGv_vec t, TCGv_vec a, int64_t imm)
+{
+    tcg_gen_cmp_vec(cond, vece, t, a, tcg_constant_vec_matching(t, vece, imm));
+}
+
+static void gen_vseqi_s_vec(unsigned vece, TCGv_vec t, TCGv_vec a, int64_t imm)
+{
+    do_cmpi_vec(TCG_COND_EQ, vece, t, a, imm);
+}
+
+static void gen_vslei_s_vec(unsigned vece, TCGv_vec t, TCGv_vec a, int64_t imm)
+{
+    do_cmpi_vec(TCG_COND_LE, vece, t, a, imm);
+}
+
+static void gen_vslti_s_vec(unsigned vece, TCGv_vec t, TCGv_vec a, int64_t imm)
+{
+    do_cmpi_vec(TCG_COND_LT, vece, t, a, imm);
+}
+
+static void gen_vslei_u_vec(unsigned vece, TCGv_vec t, TCGv_vec a, int64_t imm)
+{
+    do_cmpi_vec(TCG_COND_LEU, vece, t, a, imm);
+}
+
+static void gen_vslti_u_vec(unsigned vece, TCGv_vec t, TCGv_vec a, int64_t imm)
+{
+    do_cmpi_vec(TCG_COND_LTU, vece, t, a, imm);
+}
+
+#define DO_CMPI_S(NAME)                                                \
+static bool do_## NAME ##_s(DisasContext *ctx, arg_vv_i *a, MemOp mop) \
+{                                                                      \
+    uint32_t vd_ofs, vj_ofs;                                           \
+                                                                       \
+    CHECK_SXE;                                                         \
+                                                                       \
+    static const TCGOpcode vecop_list[] = {                            \
+        INDEX_op_cmp_vec, 0                                            \
+    };                                                                 \
+    static const GVecGen2i op[4] = {                                   \
+        {                                                              \
+            .fniv = gen_## NAME ##_s_vec,                              \
+            .fnoi = gen_helper_## NAME ##_b,                           \
+            .opt_opc = vecop_list,                                     \
+            .vece = MO_8                                               \
+        },                                                             \
+        {                                                              \
+            .fniv = gen_## NAME ##_s_vec,                              \
+            .fnoi = gen_helper_## NAME ##_h,                           \
+            .opt_opc = vecop_list,                                     \
+            .vece = MO_16                                              \
+        },                                                             \
+        {                                                              \
+            .fniv = gen_## NAME ##_s_vec,                              \
+            .fnoi = gen_helper_## NAME ##_w,                           \
+            .opt_opc = vecop_list,                                     \
+            .vece = MO_32                                              \
+        },                                                             \
+        {                                                              \
+            .fniv = gen_## NAME ##_s_vec,                              \
+            .fnoi = gen_helper_## NAME ##_d,                           \
+            .opt_opc = vecop_list,                                     \
+            .vece = MO_64                                              \
+        }                                                              \
+    };                                                                 \
+                                                                       \
+    vd_ofs = vec_full_offset(a->vd);                                   \
+    vj_ofs = vec_full_offset(a->vj);                                   \
+                                                                       \
+    tcg_gen_gvec_2i(vd_ofs, vj_ofs, 16, ctx->vl/8, a->imm, &op[mop]);  \
+                                                                       \
+    return true;                                                       \
+}
+
+DO_CMPI_S(vseqi)
+DO_CMPI_S(vslei)
+DO_CMPI_S(vslti)
+
+#define DO_CMPI_U(NAME)                                                \
+static bool do_## NAME ##_u(DisasContext *ctx, arg_vv_i *a, MemOp mop) \
+{                                                                      \
+    uint32_t vd_ofs, vj_ofs;                                           \
+                                                                       \
+    CHECK_SXE;                                                         \
+                                                                       \
+    static const TCGOpcode vecop_list[] = {                            \
+        INDEX_op_cmp_vec, 0                                            \
+    };                                                                 \
+    static const GVecGen2i op[4] = {                                   \
+        {                                                              \
+            .fniv = gen_## NAME ##_u_vec,                              \
+            .fnoi = gen_helper_## NAME ##_bu,                          \
+            .opt_opc = vecop_list,                                     \
+            .vece = MO_8                                               \
+        },                                                             \
+        {                                                              \
+            .fniv = gen_## NAME ##_u_vec,                              \
+            .fnoi = gen_helper_## NAME ##_hu,                          \
+            .opt_opc = vecop_list,                                     \
+            .vece = MO_16                                              \
+        },                                                             \
+        {                                                              \
+            .fniv = gen_## NAME ##_u_vec,                              \
+            .fnoi = gen_helper_## NAME ##_wu,                          \
+            .opt_opc = vecop_list,                                     \
+            .vece = MO_32                                              \
+        },                                                             \
+        {                                                              \
+            .fniv = gen_## NAME ##_u_vec,                              \
+            .fnoi = gen_helper_## NAME ##_du,                          \
+            .opt_opc = vecop_list,                                     \
+            .vece = MO_64                                              \
+        }                                                              \
+    };                                                                 \
+                                                                       \
+    vd_ofs = vec_full_offset(a->vd);                                   \
+    vj_ofs = vec_full_offset(a->vj);                                   \
+                                                                       \
+    tcg_gen_gvec_2i(vd_ofs, vj_ofs, 16, ctx->vl/8, a->imm, &op[mop]);  \
+                                                                       \
+    return true;                                                       \
+}
+
+DO_CMPI_U(vslei)
+DO_CMPI_U(vslti)
+
+TRANS(vseq_b, do_cmp, MO_8, TCG_COND_EQ)
+TRANS(vseq_h, do_cmp, MO_16, TCG_COND_EQ)
+TRANS(vseq_w, do_cmp, MO_32, TCG_COND_EQ)
+TRANS(vseq_d, do_cmp, MO_64, TCG_COND_EQ)
+TRANS(vseqi_b, do_vseqi_s, MO_8)
+TRANS(vseqi_h, do_vseqi_s, MO_16)
+TRANS(vseqi_w, do_vseqi_s, MO_32)
+TRANS(vseqi_d, do_vseqi_s, MO_64)
+
+TRANS(vsle_b, do_cmp, MO_8, TCG_COND_LE)
+TRANS(vsle_h, do_cmp, MO_16, TCG_COND_LE)
+TRANS(vsle_w, do_cmp, MO_32, TCG_COND_LE)
+TRANS(vsle_d, do_cmp, MO_64, TCG_COND_LE)
+TRANS(vslei_b, do_vslei_s, MO_8)
+TRANS(vslei_h, do_vslei_s, MO_16)
+TRANS(vslei_w, do_vslei_s, MO_32)
+TRANS(vslei_d, do_vslei_s, MO_64)
+TRANS(vsle_bu, do_cmp, MO_8, TCG_COND_LEU)
+TRANS(vsle_hu, do_cmp, MO_16, TCG_COND_LEU)
+TRANS(vsle_wu, do_cmp, MO_32, TCG_COND_LEU)
+TRANS(vsle_du, do_cmp, MO_64, TCG_COND_LEU)
+TRANS(vslei_bu, do_vslei_u, MO_8)
+TRANS(vslei_hu, do_vslei_u, MO_16)
+TRANS(vslei_wu, do_vslei_u, MO_32)
+TRANS(vslei_du, do_vslei_u, MO_64)
+
+TRANS(vslt_b, do_cmp, MO_8, TCG_COND_LT)
+TRANS(vslt_h, do_cmp, MO_16, TCG_COND_LT)
+TRANS(vslt_w, do_cmp, MO_32, TCG_COND_LT)
+TRANS(vslt_d, do_cmp, MO_64, TCG_COND_LT)
+TRANS(vslti_b, do_vslti_s, MO_8)
+TRANS(vslti_h, do_vslti_s, MO_16)
+TRANS(vslti_w, do_vslti_s, MO_32)
+TRANS(vslti_d, do_vslti_s, MO_64)
+TRANS(vslt_bu, do_cmp, MO_8, TCG_COND_LTU)
+TRANS(vslt_hu, do_cmp, MO_16, TCG_COND_LTU)
+TRANS(vslt_wu, do_cmp, MO_32, TCG_COND_LTU)
+TRANS(vslt_du, do_cmp, MO_64, TCG_COND_LTU)
+TRANS(vslti_bu, do_vslti_u, MO_8)
+TRANS(vslti_hu, do_vslti_u, MO_16)
+TRANS(vslti_wu, do_vslti_u, MO_32)
+TRANS(vslti_du, do_vslti_u, MO_64)
+
+static bool trans_vfcmp_cond_s(DisasContext *ctx, arg_vvv_fcond *a)
+{
+    uint32_t flags;
+    void (*fn)(TCGv_env, TCGv_i32, TCGv_i32, TCGv_i32, TCGv_i32);
+    TCGv_i32 vd = tcg_constant_i32(a->vd);
+    TCGv_i32 vj = tcg_constant_i32(a->vj);
+    TCGv_i32 vk = tcg_constant_i32(a->vk);
+
+    CHECK_SXE;
+
+    fn = (a->fcond & 1 ? gen_helper_vfcmp_s_s : gen_helper_vfcmp_c_s);
+    flags = get_fcmp_flags(a->fcond >> 1);
+    fn(cpu_env, vd, vj, vk,  tcg_constant_i32(flags));
+
+    return true;
+}
+
+static bool trans_vfcmp_cond_d(DisasContext *ctx, arg_vvv_fcond *a)
+{
+    uint32_t flags;
+    void (*fn)(TCGv_env, TCGv_i32, TCGv_i32, TCGv_i32, TCGv_i32);
+    TCGv_i32 vd = tcg_constant_i32(a->vd);
+    TCGv_i32 vj = tcg_constant_i32(a->vj);
+    TCGv_i32 vk = tcg_constant_i32(a->vk);
+
+    fn = (a->fcond & 1 ? gen_helper_vfcmp_s_d : gen_helper_vfcmp_c_d);
+    flags = get_fcmp_flags(a->fcond >> 1);
+    fn(cpu_env, vd, vj, vk, tcg_constant_i32(flags));
+
+    return true;
+}
+
+static bool trans_vbitsel_v(DisasContext *ctx, arg_vvvv *a)
+{
+    CHECK_SXE;
+
+    tcg_gen_gvec_bitsel(MO_64, vec_full_offset(a->vd), vec_full_offset(a->va),
+                        vec_full_offset(a->vk), vec_full_offset(a->vj),
+                        16, ctx->vl/8);
+    return true;
+}
+
+static void gen_vbitseli(unsigned vece, TCGv_vec a, TCGv_vec b, int64_t imm)
+{
+    tcg_gen_bitsel_vec(vece, a, a, tcg_constant_vec_matching(a, vece, imm), b);
+}
+
+static bool trans_vbitseli_b(DisasContext *ctx, arg_vv_i *a)
+{
+    static const GVecGen2i op = {
+       .fniv = gen_vbitseli,
+       .fnoi = gen_helper_vbitseli_b,
+       .vece = MO_8,
+       .load_dest = true
+    };
+
+    CHECK_SXE;
+
+    tcg_gen_gvec_2i(vec_full_offset(a->vd), vec_full_offset(a->vj),
+                    16, ctx->vl/8, a->imm, &op);
+    return true;
+}
+
+#define VSET(NAME, COND)                                                       \
+static bool trans_## NAME (DisasContext *ctx, arg_cv *a)                       \
+{                                                                              \
+    TCGv_i64 t1, al, ah;                                                       \
+                                                                               \
+    al = tcg_temp_new_i64();                                                   \
+    ah = tcg_temp_new_i64();                                                   \
+    t1 = tcg_temp_new_i64();                                                   \
+                                                                               \
+    get_vreg64(ah, a->vj, 1);                                                  \
+    get_vreg64(al, a->vj, 0);                                                  \
+                                                                               \
+    CHECK_SXE;                                                                 \
+    tcg_gen_or_i64(t1, al, ah);                                                \
+    tcg_gen_setcondi_i64(COND, t1, t1, 0);                                     \
+    tcg_gen_st8_tl(t1, cpu_env, offsetof(CPULoongArchState, cf[a->cd & 0x7])); \
+                                                                               \
+    return true;                                                               \
+}
+
+VSET(vseteqz_v, TCG_COND_EQ)
+VSET(vsetnez_v, TCG_COND_NE)
+
+TRANS(vsetanyeqz_b, gen_cv, gen_helper_vsetanyeqz_b)
+TRANS(vsetanyeqz_h, gen_cv, gen_helper_vsetanyeqz_h)
+TRANS(vsetanyeqz_w, gen_cv, gen_helper_vsetanyeqz_w)
+TRANS(vsetanyeqz_d, gen_cv, gen_helper_vsetanyeqz_d)
+TRANS(vsetallnez_b, gen_cv, gen_helper_vsetallnez_b)
+TRANS(vsetallnez_h, gen_cv, gen_helper_vsetallnez_h)
+TRANS(vsetallnez_w, gen_cv, gen_helper_vsetallnez_w)
+TRANS(vsetallnez_d, gen_cv, gen_helper_vsetallnez_d)
+
+static bool trans_vinsgr2vr_b(DisasContext *ctx, arg_vr_i *a)
+{
+    CHECK_SXE;
+    tcg_gen_st8_i64(cpu_gpr[a->rj], cpu_env,
+                    offsetof(CPULoongArchState, fpr[a->vd].vreg.B(a->imm)));
+    return true;
+}
+
+static bool trans_vinsgr2vr_h(DisasContext *ctx, arg_vr_i *a)
+{
+    CHECK_SXE;
+    tcg_gen_st16_i64(cpu_gpr[a->rj], cpu_env,
+                    offsetof(CPULoongArchState, fpr[a->vd].vreg.H(a->imm)));
+    return true;
+}
+
+static bool trans_vinsgr2vr_w(DisasContext *ctx, arg_vr_i *a)
+{
+    CHECK_SXE;
+    tcg_gen_st32_i64(cpu_gpr[a->rj], cpu_env,
+                     offsetof(CPULoongArchState, fpr[a->vd].vreg.W(a->imm)));
+    return true;
+}
+
+static bool trans_vinsgr2vr_d(DisasContext *ctx, arg_vr_i *a)
+{
+    CHECK_SXE;
+    tcg_gen_st_i64(cpu_gpr[a->rj], cpu_env,
+                   offsetof(CPULoongArchState, fpr[a->vd].vreg.D(a->imm)));
+    return true;
+}
+
+static bool trans_vpickve2gr_b(DisasContext *ctx, arg_rv_i *a)
+{
+    CHECK_SXE;
+    tcg_gen_ld8s_i64(cpu_gpr[a->rd], cpu_env,
+                     offsetof(CPULoongArchState, fpr[a->vj].vreg.B(a->imm)));
+    return true;
+}
+
+static bool trans_vpickve2gr_h(DisasContext *ctx, arg_rv_i *a)
+{
+    CHECK_SXE;
+    tcg_gen_ld16s_i64(cpu_gpr[a->rd], cpu_env,
+                      offsetof(CPULoongArchState, fpr[a->vj].vreg.H(a->imm)));
+    return true;
+}
+
+static bool trans_vpickve2gr_w(DisasContext *ctx, arg_rv_i *a)
+{
+    CHECK_SXE;
+    tcg_gen_ld32s_i64(cpu_gpr[a->rd], cpu_env,
+                      offsetof(CPULoongArchState, fpr[a->vj].vreg.W(a->imm)));
+    return true;
+}
+
+static bool trans_vpickve2gr_d(DisasContext *ctx, arg_rv_i *a)
+{
+    CHECK_SXE;
+    tcg_gen_ld_i64(cpu_gpr[a->rd], cpu_env,
+                   offsetof(CPULoongArchState, fpr[a->vj].vreg.D(a->imm)));
+    return true;
+}
+
+static bool trans_vpickve2gr_bu(DisasContext *ctx, arg_rv_i *a)
+{
+    CHECK_SXE;
+    tcg_gen_ld8u_i64(cpu_gpr[a->rd], cpu_env,
+                     offsetof(CPULoongArchState, fpr[a->vj].vreg.B(a->imm)));
+    return true;
+}
+
+static bool trans_vpickve2gr_hu(DisasContext *ctx, arg_rv_i *a)
+{
+    CHECK_SXE;
+    tcg_gen_ld16u_i64(cpu_gpr[a->rd], cpu_env,
+                      offsetof(CPULoongArchState, fpr[a->vj].vreg.H(a->imm)));
+    return true;
+}
+
+static bool trans_vpickve2gr_wu(DisasContext *ctx, arg_rv_i *a)
+{
+    CHECK_SXE;
+    tcg_gen_ld32u_i64(cpu_gpr[a->rd], cpu_env,
+                      offsetof(CPULoongArchState, fpr[a->vj].vreg.W(a->imm)));
+    return true;
+}
+
+static bool trans_vpickve2gr_du(DisasContext *ctx, arg_rv_i *a)
+{
+    CHECK_SXE;
+    tcg_gen_ld_i64(cpu_gpr[a->rd], cpu_env,
+                   offsetof(CPULoongArchState, fpr[a->vj].vreg.D(a->imm)));
+    return true;
+}
+
+static bool gvec_dup(DisasContext *ctx, arg_vr *a, MemOp mop)
+{
+    CHECK_SXE;
+
+    tcg_gen_gvec_dup_i64(mop, vec_full_offset(a->vd),
+                         16, ctx->vl/8, cpu_gpr[a->rj]);
+    return true;
+}
+
+TRANS(vreplgr2vr_b, gvec_dup, MO_8)
+TRANS(vreplgr2vr_h, gvec_dup, MO_16)
+TRANS(vreplgr2vr_w, gvec_dup, MO_32)
+TRANS(vreplgr2vr_d, gvec_dup, MO_64)
+
+static bool trans_vreplvei_b(DisasContext *ctx, arg_vv_i *a)
+{
+    CHECK_SXE;
+    tcg_gen_gvec_dup_mem(MO_8,vec_full_offset(a->vd),
+                         offsetof(CPULoongArchState,
+                                  fpr[a->vj].vreg.B((a->imm))),
+                         16, ctx->vl/8);
+    return true;
+}
+
+static bool trans_vreplvei_h(DisasContext *ctx, arg_vv_i *a)
+{
+    CHECK_SXE;
+    tcg_gen_gvec_dup_mem(MO_16, vec_full_offset(a->vd),
+                         offsetof(CPULoongArchState,
+                                  fpr[a->vj].vreg.H((a->imm))),
+                         16, ctx->vl/8);
+    return true;
+}
+static bool trans_vreplvei_w(DisasContext *ctx, arg_vv_i *a)
+{
+    CHECK_SXE;
+    tcg_gen_gvec_dup_mem(MO_32, vec_full_offset(a->vd),
+                         offsetof(CPULoongArchState,
+                                  fpr[a->vj].vreg.W((a->imm))),
+                        16, ctx->vl/8);
+    return true;
+}
+static bool trans_vreplvei_d(DisasContext *ctx, arg_vv_i *a)
+{
+    CHECK_SXE;
+    tcg_gen_gvec_dup_mem(MO_64, vec_full_offset(a->vd),
+                         offsetof(CPULoongArchState,
+                                  fpr[a->vj].vreg.D((a->imm))),
+                         16, ctx->vl/8);
+    return true;
+}
+
+static bool gen_vreplve(DisasContext *ctx, arg_vvr *a, int vece, int bit,
+                        void (*func)(TCGv_i64, TCGv_ptr, tcg_target_long))
+{
+    TCGv_i64 t0 = tcg_temp_new_i64();
+    TCGv_ptr t1 = tcg_temp_new_ptr();
+    TCGv_i64 t2 = tcg_temp_new_i64();
+
+    CHECK_SXE;
+
+    tcg_gen_andi_i64(t0, gpr_src(ctx, a->rk, EXT_NONE), (LSX_LEN/bit) -1);
+    tcg_gen_shli_i64(t0, t0, vece);
+    if (HOST_BIG_ENDIAN) {
+        tcg_gen_xori_i64(t0, t0, vece << ((LSX_LEN/bit) -1));
+    }
+
+    tcg_gen_trunc_i64_ptr(t1, t0);
+    tcg_gen_add_ptr(t1, t1, cpu_env);
+    func(t2, t1, vec_full_offset(a->vj));
+    tcg_gen_gvec_dup_i64(vece, vec_full_offset(a->vd), 16, ctx->vl/8, t2);
+
+    return true;
+}
+
+TRANS(vreplve_b, gen_vreplve, MO_8,  8, tcg_gen_ld8u_i64)
+TRANS(vreplve_h, gen_vreplve, MO_16, 16, tcg_gen_ld16u_i64)
+TRANS(vreplve_w, gen_vreplve, MO_32, 32, tcg_gen_ld32u_i64)
+TRANS(vreplve_d, gen_vreplve, MO_64, 64, tcg_gen_ld_i64)
+
+static bool trans_vbsll_v(DisasContext *ctx, arg_vv_i *a)
+{
+    int ofs;
+    TCGv_i64 desthigh, destlow, high, low;
+
+    CHECK_SXE;
+
+    desthigh = tcg_temp_new_i64();
+    destlow = tcg_temp_new_i64();
+    high = tcg_temp_new_i64();
+    low = tcg_temp_new_i64();
+
+    get_vreg64(low, a->vj, 0);
+
+    ofs = ((a->imm) & 0xf) * 8;
+    if (ofs < 64) {
+        get_vreg64(high, a->vj, 1);
+        tcg_gen_extract2_i64(desthigh, low, high, 64 - ofs);
+        tcg_gen_shli_i64(destlow, low, ofs);
+    } else {
+        tcg_gen_shli_i64(desthigh, low, ofs - 64);
+        destlow = tcg_constant_i64(0);
+    }
+
+    set_vreg64(desthigh, a->vd, 1);
+    set_vreg64(destlow, a->vd, 0);
+
+    return true;
+}
+
+static bool trans_vbsrl_v(DisasContext *ctx, arg_vv_i *a)
+{
+    TCGv_i64 desthigh, destlow, high, low;
+    int ofs;
+
+    CHECK_SXE;
+
+    desthigh = tcg_temp_new_i64();
+    destlow = tcg_temp_new_i64();
+    high = tcg_temp_new_i64();
+    low = tcg_temp_new_i64();
+
+    get_vreg64(high, a->vj, 1);
+
+    ofs = ((a->imm) & 0xf) * 8;
+    if (ofs < 64) {
+        get_vreg64(low, a->vj, 0);
+        tcg_gen_extract2_i64(destlow, low, high, ofs);
+        tcg_gen_shri_i64(desthigh, high, ofs);
+    } else {
+        tcg_gen_shri_i64(destlow, high, ofs - 64);
+        desthigh = tcg_constant_i64(0);
+    }
+
+    set_vreg64(desthigh, a->vd, 1);
+    set_vreg64(destlow, a->vd, 0);
+
+    return true;
+}
+
+TRANS(vpackev_b, gen_vvv, gen_helper_vpackev_b)
+TRANS(vpackev_h, gen_vvv, gen_helper_vpackev_h)
+TRANS(vpackev_w, gen_vvv, gen_helper_vpackev_w)
+TRANS(vpackev_d, gen_vvv, gen_helper_vpackev_d)
+TRANS(vpackod_b, gen_vvv, gen_helper_vpackod_b)
+TRANS(vpackod_h, gen_vvv, gen_helper_vpackod_h)
+TRANS(vpackod_w, gen_vvv, gen_helper_vpackod_w)
+TRANS(vpackod_d, gen_vvv, gen_helper_vpackod_d)
+
+TRANS(vpickev_b, gen_vvv, gen_helper_vpickev_b)
+TRANS(vpickev_h, gen_vvv, gen_helper_vpickev_h)
+TRANS(vpickev_w, gen_vvv, gen_helper_vpickev_w)
+TRANS(vpickev_d, gen_vvv, gen_helper_vpickev_d)
+TRANS(vpickod_b, gen_vvv, gen_helper_vpickod_b)
+TRANS(vpickod_h, gen_vvv, gen_helper_vpickod_h)
+TRANS(vpickod_w, gen_vvv, gen_helper_vpickod_w)
+TRANS(vpickod_d, gen_vvv, gen_helper_vpickod_d)
+
+TRANS(vilvl_b, gen_vvv, gen_helper_vilvl_b)
+TRANS(vilvl_h, gen_vvv, gen_helper_vilvl_h)
+TRANS(vilvl_w, gen_vvv, gen_helper_vilvl_w)
+TRANS(vilvl_d, gen_vvv, gen_helper_vilvl_d)
+TRANS(vilvh_b, gen_vvv, gen_helper_vilvh_b)
+TRANS(vilvh_h, gen_vvv, gen_helper_vilvh_h)
+TRANS(vilvh_w, gen_vvv, gen_helper_vilvh_w)
+TRANS(vilvh_d, gen_vvv, gen_helper_vilvh_d)
+
+TRANS(vshuf_b, gen_vvvv, gen_helper_vshuf_b)
+TRANS(vshuf_h, gen_vvv, gen_helper_vshuf_h)
+TRANS(vshuf_w, gen_vvv, gen_helper_vshuf_w)
+TRANS(vshuf_d, gen_vvv, gen_helper_vshuf_d)
+TRANS(vshuf4i_b, gen_vv_i, gen_helper_vshuf4i_b)
+TRANS(vshuf4i_h, gen_vv_i, gen_helper_vshuf4i_h)
+TRANS(vshuf4i_w, gen_vv_i, gen_helper_vshuf4i_w)
+TRANS(vshuf4i_d, gen_vv_i, gen_helper_vshuf4i_d)
+
+TRANS(vpermi_w, gen_vv_i, gen_helper_vpermi_w)
+
+TRANS(vextrins_b, gen_vv_i, gen_helper_vextrins_b)
+TRANS(vextrins_h, gen_vv_i, gen_helper_vextrins_h)
+TRANS(vextrins_w, gen_vv_i, gen_helper_vextrins_w)
+TRANS(vextrins_d, gen_vv_i, gen_helper_vextrins_d)
+
+static bool trans_vld(DisasContext *ctx, arg_vr_i *a)
+{
+    TCGv addr, temp;
+    TCGv_i64 rl, rh;
+    TCGv_i128 val;
+
+    CHECK_SXE;
+
+    addr = gpr_src(ctx, a->rj, EXT_NONE);
+    val = tcg_temp_new_i128();
+    rl = tcg_temp_new_i64();
+    rh = tcg_temp_new_i64();
+
+    if (a->imm) {
+        temp = tcg_temp_new();
+        tcg_gen_addi_tl(temp, addr, a->imm);
+        addr = temp;
+    }
+
+    tcg_gen_qemu_ld_i128(val, addr, ctx->mem_idx, MO_128 | MO_TE);
+    tcg_gen_extr_i128_i64(rl, rh, val);
+    set_vreg64(rh, a->vd, 1);
+    set_vreg64(rl, a->vd, 0);
+
+    return true;
+}
+
+static bool trans_vst(DisasContext *ctx, arg_vr_i *a)
+{
+    TCGv addr, temp;
+    TCGv_i128 val;
+    TCGv_i64 ah, al;
+
+    CHECK_SXE;
+
+    addr = gpr_src(ctx, a->rj, EXT_NONE);
+    val = tcg_temp_new_i128();
+    ah = tcg_temp_new_i64();
+    al = tcg_temp_new_i64();
+
+    if (a->imm) {
+        temp = tcg_temp_new();
+        tcg_gen_addi_tl(temp, addr, a->imm);
+        addr = temp;
+    }
+
+    get_vreg64(ah, a->vd, 1);
+    get_vreg64(al, a->vd, 0);
+    tcg_gen_concat_i64_i128(val, al, ah);
+    tcg_gen_qemu_st_i128(val, addr, ctx->mem_idx, MO_128 | MO_TE);
+
+    return true;
+}
+
+static bool trans_vldx(DisasContext *ctx, arg_vrr *a)
+{
+    TCGv addr, src1, src2;
+    TCGv_i64 rl, rh;
+    TCGv_i128 val;
+
+    CHECK_SXE;
+
+    addr = tcg_temp_new();
+    src1 = gpr_src(ctx, a->rj, EXT_NONE);
+    src2 = gpr_src(ctx, a->rk, EXT_NONE);
+    val = tcg_temp_new_i128();
+    rl = tcg_temp_new_i64();
+    rh = tcg_temp_new_i64();
+
+    tcg_gen_add_tl(addr, src1, src2);
+    tcg_gen_qemu_ld_i128(val, addr, ctx->mem_idx, MO_128 | MO_TE);
+    tcg_gen_extr_i128_i64(rl, rh, val);
+    set_vreg64(rh, a->vd, 1);
+    set_vreg64(rl, a->vd, 0);
+
+    return true;
+}
+
+static bool trans_vstx(DisasContext *ctx, arg_vrr *a)
+{
+    TCGv addr, src1, src2;
+    TCGv_i64 ah, al;
+    TCGv_i128 val;
+
+    CHECK_SXE;
+
+    addr = tcg_temp_new();
+    src1 = gpr_src(ctx, a->rj, EXT_NONE);
+    src2 = gpr_src(ctx, a->rk, EXT_NONE);
+    val = tcg_temp_new_i128();
+    ah = tcg_temp_new_i64();
+    al = tcg_temp_new_i64();
+
+    tcg_gen_add_tl(addr, src1, src2);
+    get_vreg64(ah, a->vd, 1);
+    get_vreg64(al, a->vd, 0);
+    tcg_gen_concat_i64_i128(val, al, ah);
+    tcg_gen_qemu_st_i128(val, addr, ctx->mem_idx, MO_128 | MO_TE);
+
+    return true;
+}
+
+#define VLDREPL(NAME, MO)                                                 \
+static bool trans_## NAME (DisasContext *ctx, arg_vr_i *a)                \
+{                                                                         \
+    TCGv addr, temp;                                                      \
+    TCGv_i64 val;                                                         \
+                                                                          \
+    CHECK_SXE;                                                            \
+                                                                          \
+    addr = gpr_src(ctx, a->rj, EXT_NONE);                                 \
+    val = tcg_temp_new_i64();                                             \
+                                                                          \
+    if (a->imm) {                                                         \
+        temp = tcg_temp_new();                                            \
+        tcg_gen_addi_tl(temp, addr, a->imm);                              \
+        addr = temp;                                                      \
+    }                                                                     \
+                                                                          \
+    tcg_gen_qemu_ld_i64(val, addr, ctx->mem_idx, MO);                     \
+    tcg_gen_gvec_dup_i64(MO, vec_full_offset(a->vd), 16, ctx->vl/8, val); \
+                                                                          \
+    return true;                                                          \
+}
+
+VLDREPL(vldrepl_b, MO_8)
+VLDREPL(vldrepl_h, MO_16)
+VLDREPL(vldrepl_w, MO_32)
+VLDREPL(vldrepl_d, MO_64)
+
+#define VSTELM(NAME, MO, E)                                                  \
+static bool trans_## NAME (DisasContext *ctx, arg_vr_ii *a)                  \
+{                                                                            \
+    TCGv addr, temp;                                                         \
+    TCGv_i64 val;                                                            \
+                                                                             \
+    CHECK_SXE;                                                               \
+                                                                             \
+    addr = gpr_src(ctx, a->rj, EXT_NONE);                                    \
+    val = tcg_temp_new_i64();                                                \
+                                                                             \
+    if (a->imm) {                                                            \
+        temp = tcg_temp_new();                                               \
+        tcg_gen_addi_tl(temp, addr, a->imm);                                 \
+        addr = temp;                                                         \
+    }                                                                        \
+                                                                             \
+    tcg_gen_ld_i64(val, cpu_env,                                             \
+                   offsetof(CPULoongArchState, fpr[a->vd].vreg.E(a->imm2))); \
+    tcg_gen_qemu_st_i64(val, addr, ctx->mem_idx, MO);                        \
+                                                                             \
+    return true;                                                             \
+}
+
+VSTELM(vstelm_b, MO_8, B)
+VSTELM(vstelm_h, MO_16, H)
+VSTELM(vstelm_w, MO_32, W)
+VSTELM(vstelm_d, MO_64, D)

target/loongarch/insns.decode

@@ -485,3 +485,814 @@ ldpte            0000 01100100 01 ........ ..... 00000    @j_i
 ertn             0000 01100100 10000 01110 00000 00000    @empty
 idle             0000 01100100 10001 ...............      @i15
 dbcl             0000 00000010 10101 ...............      @i15
+
+#
+# LSX Fields
+#
+
+%i9s3     10:s9       !function=shl_3
+%i10s2    10:s10      !function=shl_2
+%i11s1    10:s11      !function=shl_1
+%i8s3     10:s8       !function=shl_3
+%i8s2     10:s8       !function=shl_2
+%i8s1     10:s8       !function=shl_1
+
+#
+# LSX Argument sets
+#
+
+&vv           vd vj
+&cv           cd vj
+&vvv          vd vj vk
+&vv_i         vd vj imm
+&vvvv         vd vj vk va
+&vvv_fcond    vd vj vk fcond
+&vr_i         vd rj imm
+&rv_i         rd vj imm
+&vr           vd rj
+&vvr          vd vj rk
+&vrr          vd rj rk
+&vr_ii        vd rj imm imm2
+&v_i          vd imm
+
+#
+# LSX Formats
+#
+@vv               .... ........ ..... ..... vj:5 vd:5    &vv
+@cv            .... ........ ..... ..... vj:5 .. cd:3    &cv
+@vvv               .... ........ ..... vk:5 vj:5 vd:5    &vvv
+@vv_ui1      .... ........ ..... .... imm:1 vj:5 vd:5    &vv_i
+@vv_ui2       .... ........ ..... ... imm:2 vj:5 vd:5    &vv_i
+@vv_ui3        .... ........ ..... .. imm:3 vj:5 vd:5    &vv_i
+@vv_ui4         .... ........ ..... . imm:4 vj:5 vd:5    &vv_i
+@vv_ui5           .... ........ ..... imm:5 vj:5 vd:5    &vv_i
+@vv_ui6            .... ........ .... imm:6 vj:5 vd:5    &vv_i
+@vv_ui7             .... ........ ... imm:7 vj:5 vd:5    &vv_i
+@vv_ui8              .... ........ .. imm:8 vj:5 vd:5    &vv_i
+@vv_i5           .... ........ ..... imm:s5 vj:5 vd:5    &vv_i
+@vvvv               .... ........ va:5 vk:5 vj:5 vd:5    &vvvv
+@vvv_fcond      .... ........ fcond:5  vk:5 vj:5 vd:5    &vvv_fcond
+@vr_ui4         .... ........ ..... . imm:4 rj:5 vd:5    &vr_i
+@vr_ui3        .... ........ ..... .. imm:3 rj:5 vd:5    &vr_i
+@vr_ui2       .... ........ ..... ... imm:2 rj:5 vd:5    &vr_i
+@vr_ui1      .... ........ ..... .... imm:1 rj:5 vd:5    &vr_i
+@rv_ui4         .... ........ ..... . imm:4 vj:5 rd:5    &rv_i
+@rv_ui3        .... ........ ..... .. imm:3 vj:5 rd:5    &rv_i
+@rv_ui2       .... ........ ..... ... imm:2 vj:5 rd:5    &rv_i
+@rv_ui1      .... ........ ..... .... imm:1 vj:5 rd:5    &rv_i
+@vr               .... ........ ..... ..... rj:5 vd:5    &vr
+@vvr               .... ........ ..... rk:5 vj:5 vd:5    &vvr
+@vr_i9            .... ........ . ......... rj:5 vd:5    &vr_i imm=%i9s3
+@vr_i10            .... ........ .......... rj:5 vd:5    &vr_i imm=%i10s2
+@vr_i11            .... ....... ........... rj:5 vd:5    &vr_i imm=%i11s1
+@vr_i12                 .... ...... imm:s12 rj:5 vd:5    &vr_i
+@vr_i8i1    .... ........ . imm2:1 ........ rj:5 vd:5    &vr_ii imm=%i8s3
+@vr_i8i2      .... ........ imm2:2 ........ rj:5 vd:5    &vr_ii imm=%i8s2
+@vr_i8i3       .... ....... imm2:3 ........ rj:5 vd:5    &vr_ii imm=%i8s1
+@vr_i8i4          .... ...... imm2:4 imm:s8 rj:5 vd:5    &vr_ii
+@vrr               .... ........ ..... rk:5 rj:5 vd:5    &vrr
+@v_i13                   .... ........ .. imm:13 vd:5    &v_i
+
+vadd_b           0111 00000000 10100 ..... ..... .....    @vvv
+vadd_h           0111 00000000 10101 ..... ..... .....    @vvv
+vadd_w           0111 00000000 10110 ..... ..... .....    @vvv
+vadd_d           0111 00000000 10111 ..... ..... .....    @vvv
+vadd_q           0111 00010010 11010 ..... ..... .....    @vvv
+vsub_b           0111 00000000 11000 ..... ..... .....    @vvv
+vsub_h           0111 00000000 11001 ..... ..... .....    @vvv
+vsub_w           0111 00000000 11010 ..... ..... .....    @vvv
+vsub_d           0111 00000000 11011 ..... ..... .....    @vvv
+vsub_q           0111 00010010 11011 ..... ..... .....    @vvv
+
+vaddi_bu         0111 00101000 10100 ..... ..... .....    @vv_ui5
+vaddi_hu         0111 00101000 10101 ..... ..... .....    @vv_ui5
+vaddi_wu         0111 00101000 10110 ..... ..... .....    @vv_ui5
+vaddi_du         0111 00101000 10111 ..... ..... .....    @vv_ui5
+vsubi_bu         0111 00101000 11000 ..... ..... .....    @vv_ui5
+vsubi_hu         0111 00101000 11001 ..... ..... .....    @vv_ui5
+vsubi_wu         0111 00101000 11010 ..... ..... .....    @vv_ui5
+vsubi_du         0111 00101000 11011 ..... ..... .....    @vv_ui5
+
+vneg_b           0111 00101001 11000 01100 ..... .....    @vv
+vneg_h           0111 00101001 11000 01101 ..... .....    @vv
+vneg_w           0111 00101001 11000 01110 ..... .....    @vv
+vneg_d           0111 00101001 11000 01111 ..... .....    @vv
+
+vsadd_b          0111 00000100 01100 ..... ..... .....    @vvv
+vsadd_h          0111 00000100 01101 ..... ..... .....    @vvv
+vsadd_w          0111 00000100 01110 ..... ..... .....    @vvv
+vsadd_d          0111 00000100 01111 ..... ..... .....    @vvv
+vsadd_bu         0111 00000100 10100 ..... ..... .....    @vvv
+vsadd_hu         0111 00000100 10101 ..... ..... .....    @vvv
+vsadd_wu         0111 00000100 10110 ..... ..... .....    @vvv
+vsadd_du         0111 00000100 10111 ..... ..... .....    @vvv
+vssub_b          0111 00000100 10000 ..... ..... .....    @vvv
+vssub_h          0111 00000100 10001 ..... ..... .....    @vvv
+vssub_w          0111 00000100 10010 ..... ..... .....    @vvv
+vssub_d          0111 00000100 10011 ..... ..... .....    @vvv
+vssub_bu         0111 00000100 11000 ..... ..... .....    @vvv
+vssub_hu         0111 00000100 11001 ..... ..... .....    @vvv
+vssub_wu         0111 00000100 11010 ..... ..... .....    @vvv
+vssub_du         0111 00000100 11011 ..... ..... .....    @vvv
+
+vhaddw_h_b       0111 00000101 01000 ..... ..... .....    @vvv
+vhaddw_w_h       0111 00000101 01001 ..... ..... .....    @vvv
+vhaddw_d_w       0111 00000101 01010 ..... ..... .....    @vvv
+vhaddw_q_d       0111 00000101 01011 ..... ..... .....    @vvv
+vhaddw_hu_bu     0111 00000101 10000 ..... ..... .....    @vvv
+vhaddw_wu_hu     0111 00000101 10001 ..... ..... .....    @vvv
+vhaddw_du_wu     0111 00000101 10010 ..... ..... .....    @vvv
+vhaddw_qu_du     0111 00000101 10011 ..... ..... .....    @vvv
+vhsubw_h_b       0111 00000101 01100 ..... ..... .....    @vvv
+vhsubw_w_h       0111 00000101 01101 ..... ..... .....    @vvv
+vhsubw_d_w       0111 00000101 01110 ..... ..... .....    @vvv
+vhsubw_q_d       0111 00000101 01111 ..... ..... .....    @vvv
+vhsubw_hu_bu     0111 00000101 10100 ..... ..... .....    @vvv
+vhsubw_wu_hu     0111 00000101 10101 ..... ..... .....    @vvv
+vhsubw_du_wu     0111 00000101 10110 ..... ..... .....    @vvv
+vhsubw_qu_du     0111 00000101 10111 ..... ..... .....    @vvv
+
+vaddwev_h_b      0111 00000001 11100 ..... ..... .....    @vvv
+vaddwev_w_h      0111 00000001 11101 ..... ..... .....    @vvv
+vaddwev_d_w      0111 00000001 11110 ..... ..... .....    @vvv
+vaddwev_q_d      0111 00000001 11111 ..... ..... .....    @vvv
+vaddwod_h_b      0111 00000010 00100 ..... ..... .....    @vvv
+vaddwod_w_h      0111 00000010 00101 ..... ..... .....    @vvv
+vaddwod_d_w      0111 00000010 00110 ..... ..... .....    @vvv
+vaddwod_q_d      0111 00000010 00111 ..... ..... .....    @vvv
+vsubwev_h_b      0111 00000010 00000 ..... ..... .....    @vvv
+vsubwev_w_h      0111 00000010 00001 ..... ..... .....    @vvv
+vsubwev_d_w      0111 00000010 00010 ..... ..... .....    @vvv
+vsubwev_q_d      0111 00000010 00011 ..... ..... .....    @vvv
+vsubwod_h_b      0111 00000010 01000 ..... ..... .....    @vvv
+vsubwod_w_h      0111 00000010 01001 ..... ..... .....    @vvv
+vsubwod_d_w      0111 00000010 01010 ..... ..... .....    @vvv
+vsubwod_q_d      0111 00000010 01011 ..... ..... .....    @vvv
+
+vaddwev_h_bu     0111 00000010 11100 ..... ..... .....    @vvv
+vaddwev_w_hu     0111 00000010 11101 ..... ..... .....    @vvv
+vaddwev_d_wu     0111 00000010 11110 ..... ..... .....    @vvv
+vaddwev_q_du     0111 00000010 11111 ..... ..... .....    @vvv
+vaddwod_h_bu     0111 00000011 00100 ..... ..... .....    @vvv
+vaddwod_w_hu     0111 00000011 00101 ..... ..... .....    @vvv
+vaddwod_d_wu     0111 00000011 00110 ..... ..... .....    @vvv
+vaddwod_q_du     0111 00000011 00111 ..... ..... .....    @vvv
+vsubwev_h_bu     0111 00000011 00000 ..... ..... .....    @vvv
+vsubwev_w_hu     0111 00000011 00001 ..... ..... .....    @vvv
+vsubwev_d_wu     0111 00000011 00010 ..... ..... .....    @vvv
+vsubwev_q_du     0111 00000011 00011 ..... ..... .....    @vvv
+vsubwod_h_bu     0111 00000011 01000 ..... ..... .....    @vvv
+vsubwod_w_hu     0111 00000011 01001 ..... ..... .....    @vvv
+vsubwod_d_wu     0111 00000011 01010 ..... ..... .....    @vvv
+vsubwod_q_du     0111 00000011 01011 ..... ..... .....    @vvv
+
+vaddwev_h_bu_b   0111 00000011 11100 ..... ..... .....    @vvv
+vaddwev_w_hu_h   0111 00000011 11101 ..... ..... .....    @vvv
+vaddwev_d_wu_w   0111 00000011 11110 ..... ..... .....    @vvv
+vaddwev_q_du_d   0111 00000011 11111 ..... ..... .....    @vvv
+vaddwod_h_bu_b   0111 00000100 00000 ..... ..... .....    @vvv
+vaddwod_w_hu_h   0111 00000100 00001 ..... ..... .....    @vvv
+vaddwod_d_wu_w   0111 00000100 00010 ..... ..... .....    @vvv
+vaddwod_q_du_d   0111 00000100 00011 ..... ..... .....    @vvv
+
+vavg_b           0111 00000110 01000 ..... ..... .....    @vvv
+vavg_h           0111 00000110 01001 ..... ..... .....    @vvv
+vavg_w           0111 00000110 01010 ..... ..... .....    @vvv
+vavg_d           0111 00000110 01011 ..... ..... .....    @vvv
+vavg_bu          0111 00000110 01100 ..... ..... .....    @vvv
+vavg_hu          0111 00000110 01101 ..... ..... .....    @vvv
+vavg_wu          0111 00000110 01110 ..... ..... .....    @vvv
+vavg_du          0111 00000110 01111 ..... ..... .....    @vvv
+vavgr_b          0111 00000110 10000 ..... ..... .....    @vvv
+vavgr_h          0111 00000110 10001 ..... ..... .....    @vvv
+vavgr_w          0111 00000110 10010 ..... ..... .....    @vvv
+vavgr_d          0111 00000110 10011 ..... ..... .....    @vvv
+vavgr_bu         0111 00000110 10100 ..... ..... .....    @vvv
+vavgr_hu         0111 00000110 10101 ..... ..... .....    @vvv
+vavgr_wu         0111 00000110 10110 ..... ..... .....    @vvv
+vavgr_du         0111 00000110 10111 ..... ..... .....    @vvv
+
+vabsd_b          0111 00000110 00000 ..... ..... .....    @vvv
+vabsd_h          0111 00000110 00001 ..... ..... .....    @vvv
+vabsd_w          0111 00000110 00010 ..... ..... .....    @vvv
+vabsd_d          0111 00000110 00011 ..... ..... .....    @vvv
+vabsd_bu         0111 00000110 00100 ..... ..... .....    @vvv
+vabsd_hu         0111 00000110 00101 ..... ..... .....    @vvv
+vabsd_wu         0111 00000110 00110 ..... ..... .....    @vvv
+vabsd_du         0111 00000110 00111 ..... ..... .....    @vvv
+
+vadda_b          0111 00000101 11000 ..... ..... .....    @vvv
+vadda_h          0111 00000101 11001 ..... ..... .....    @vvv
+vadda_w          0111 00000101 11010 ..... ..... .....    @vvv
+vadda_d          0111 00000101 11011 ..... ..... .....    @vvv
+
+vmax_b           0111 00000111 00000 ..... ..... .....    @vvv
+vmax_h           0111 00000111 00001 ..... ..... .....    @vvv
+vmax_w           0111 00000111 00010 ..... ..... .....    @vvv
+vmax_d           0111 00000111 00011 ..... ..... .....    @vvv
+vmaxi_b          0111 00101001 00000 ..... ..... .....    @vv_i5
+vmaxi_h          0111 00101001 00001 ..... ..... .....    @vv_i5
+vmaxi_w          0111 00101001 00010 ..... ..... .....    @vv_i5
+vmaxi_d          0111 00101001 00011 ..... ..... .....    @vv_i5
+vmax_bu          0111 00000111 01000 ..... ..... .....    @vvv
+vmax_hu          0111 00000111 01001 ..... ..... .....    @vvv
+vmax_wu          0111 00000111 01010 ..... ..... .....    @vvv
+vmax_du          0111 00000111 01011 ..... ..... .....    @vvv
+vmaxi_bu         0111 00101001 01000 ..... ..... .....    @vv_ui5
+vmaxi_hu         0111 00101001 01001 ..... ..... .....    @vv_ui5
+vmaxi_wu         0111 00101001 01010 ..... ..... .....    @vv_ui5
+vmaxi_du         0111 00101001 01011 ..... ..... .....    @vv_ui5
+
+vmin_b           0111 00000111 00100 ..... ..... .....    @vvv
+vmin_h           0111 00000111 00101 ..... ..... .....    @vvv
+vmin_w           0111 00000111 00110 ..... ..... .....    @vvv
+vmin_d           0111 00000111 00111 ..... ..... .....    @vvv
+vmini_b          0111 00101001 00100 ..... ..... .....    @vv_i5
+vmini_h          0111 00101001 00101 ..... ..... .....    @vv_i5
+vmini_w          0111 00101001 00110 ..... ..... .....    @vv_i5
+vmini_d          0111 00101001 00111 ..... ..... .....    @vv_i5
+vmin_bu          0111 00000111 01100 ..... ..... .....    @vvv
+vmin_hu          0111 00000111 01101 ..... ..... .....    @vvv
+vmin_wu          0111 00000111 01110 ..... ..... .....    @vvv
+vmin_du          0111 00000111 01111 ..... ..... .....    @vvv
+vmini_bu         0111 00101001 01100 ..... ..... .....    @vv_ui5
+vmini_hu         0111 00101001 01101 ..... ..... .....    @vv_ui5
+vmini_wu         0111 00101001 01110 ..... ..... .....    @vv_ui5
+vmini_du         0111 00101001 01111 ..... ..... .....    @vv_ui5
+
+vmul_b           0111 00001000 01000 ..... ..... .....    @vvv
+vmul_h           0111 00001000 01001 ..... ..... .....    @vvv
+vmul_w           0111 00001000 01010 ..... ..... .....    @vvv
+vmul_d           0111 00001000 01011 ..... ..... .....    @vvv
+vmuh_b           0111 00001000 01100 ..... ..... .....    @vvv
+vmuh_h           0111 00001000 01101 ..... ..... .....    @vvv
+vmuh_w           0111 00001000 01110 ..... ..... .....    @vvv
+vmuh_d           0111 00001000 01111 ..... ..... .....    @vvv
+vmuh_bu          0111 00001000 10000 ..... ..... .....    @vvv
+vmuh_hu          0111 00001000 10001 ..... ..... .....    @vvv
+vmuh_wu          0111 00001000 10010 ..... ..... .....    @vvv
+vmuh_du          0111 00001000 10011 ..... ..... .....    @vvv
+
+vmulwev_h_b      0111 00001001 00000 ..... ..... .....    @vvv
+vmulwev_w_h      0111 00001001 00001 ..... ..... .....    @vvv
+vmulwev_d_w      0111 00001001 00010 ..... ..... .....    @vvv
+vmulwev_q_d      0111 00001001 00011 ..... ..... .....    @vvv
+vmulwod_h_b      0111 00001001 00100 ..... ..... .....    @vvv
+vmulwod_w_h      0111 00001001 00101 ..... ..... .....    @vvv
+vmulwod_d_w      0111 00001001 00110 ..... ..... .....    @vvv
+vmulwod_q_d      0111 00001001 00111 ..... ..... .....    @vvv
+vmulwev_h_bu     0111 00001001 10000 ..... ..... .....    @vvv
+vmulwev_w_hu     0111 00001001 10001 ..... ..... .....    @vvv
+vmulwev_d_wu     0111 00001001 10010 ..... ..... .....    @vvv
+vmulwev_q_du     0111 00001001 10011 ..... ..... .....    @vvv
+vmulwod_h_bu     0111 00001001 10100 ..... ..... .....    @vvv
+vmulwod_w_hu     0111 00001001 10101 ..... ..... .....    @vvv
+vmulwod_d_wu     0111 00001001 10110 ..... ..... .....    @vvv
+vmulwod_q_du     0111 00001001 10111 ..... ..... .....    @vvv
+vmulwev_h_bu_b   0111 00001010 00000 ..... ..... .....    @vvv
+vmulwev_w_hu_h   0111 00001010 00001 ..... ..... .....    @vvv
+vmulwev_d_wu_w   0111 00001010 00010 ..... ..... .....    @vvv
+vmulwev_q_du_d   0111 00001010 00011 ..... ..... .....    @vvv
+vmulwod_h_bu_b   0111 00001010 00100 ..... ..... .....    @vvv
+vmulwod_w_hu_h   0111 00001010 00101 ..... ..... .....    @vvv
+vmulwod_d_wu_w   0111 00001010 00110 ..... ..... .....    @vvv
+vmulwod_q_du_d   0111 00001010 00111 ..... ..... .....    @vvv
+
+vmadd_b          0111 00001010 10000 ..... ..... .....    @vvv
+vmadd_h          0111 00001010 10001 ..... ..... .....    @vvv
+vmadd_w          0111 00001010 10010 ..... ..... .....    @vvv
+vmadd_d          0111 00001010 10011 ..... ..... .....    @vvv
+vmsub_b          0111 00001010 10100 ..... ..... .....    @vvv
+vmsub_h          0111 00001010 10101 ..... ..... .....    @vvv
+vmsub_w          0111 00001010 10110 ..... ..... .....    @vvv
+vmsub_d          0111 00001010 10111 ..... ..... .....    @vvv
+
+vmaddwev_h_b     0111 00001010 11000 ..... ..... .....    @vvv
+vmaddwev_w_h     0111 00001010 11001 ..... ..... .....    @vvv
+vmaddwev_d_w     0111 00001010 11010 ..... ..... .....    @vvv
+vmaddwev_q_d     0111 00001010 11011 ..... ..... .....    @vvv
+vmaddwod_h_b     0111 00001010 11100 ..... ..... .....    @vvv
+vmaddwod_w_h     0111 00001010 11101 ..... ..... .....    @vvv
+vmaddwod_d_w     0111 00001010 11110 ..... ..... .....    @vvv
+vmaddwod_q_d     0111 00001010 11111 ..... ..... .....    @vvv
+vmaddwev_h_bu    0111 00001011 01000 ..... ..... .....    @vvv
+vmaddwev_w_hu    0111 00001011 01001 ..... ..... .....    @vvv
+vmaddwev_d_wu    0111 00001011 01010 ..... ..... .....    @vvv
+vmaddwev_q_du    0111 00001011 01011 ..... ..... .....    @vvv
+vmaddwod_h_bu    0111 00001011 01100 ..... ..... .....    @vvv
+vmaddwod_w_hu    0111 00001011 01101 ..... ..... .....    @vvv
+vmaddwod_d_wu    0111 00001011 01110 ..... ..... .....    @vvv
+vmaddwod_q_du    0111 00001011 01111 ..... ..... .....    @vvv
+vmaddwev_h_bu_b  0111 00001011 11000 ..... ..... .....    @vvv
+vmaddwev_w_hu_h  0111 00001011 11001 ..... ..... .....    @vvv
+vmaddwev_d_wu_w  0111 00001011 11010 ..... ..... .....    @vvv
+vmaddwev_q_du_d  0111 00001011 11011 ..... ..... .....    @vvv
+vmaddwod_h_bu_b  0111 00001011 11100 ..... ..... .....    @vvv
+vmaddwod_w_hu_h  0111 00001011 11101 ..... ..... .....    @vvv
+vmaddwod_d_wu_w  0111 00001011 11110 ..... ..... .....    @vvv
+vmaddwod_q_du_d  0111 00001011 11111 ..... ..... .....    @vvv
+
+vdiv_b           0111 00001110 00000 ..... ..... .....    @vvv
+vdiv_h           0111 00001110 00001 ..... ..... .....    @vvv
+vdiv_w           0111 00001110 00010 ..... ..... .....    @vvv
+vdiv_d           0111 00001110 00011 ..... ..... .....    @vvv
+vdiv_bu          0111 00001110 01000 ..... ..... .....    @vvv
+vdiv_hu          0111 00001110 01001 ..... ..... .....    @vvv
+vdiv_wu          0111 00001110 01010 ..... ..... .....    @vvv
+vdiv_du          0111 00001110 01011 ..... ..... .....    @vvv
+vmod_b           0111 00001110 00100 ..... ..... .....    @vvv
+vmod_h           0111 00001110 00101 ..... ..... .....    @vvv
+vmod_w           0111 00001110 00110 ..... ..... .....    @vvv
+vmod_d           0111 00001110 00111 ..... ..... .....    @vvv
+vmod_bu          0111 00001110 01100 ..... ..... .....    @vvv
+vmod_hu          0111 00001110 01101 ..... ..... .....    @vvv
+vmod_wu          0111 00001110 01110 ..... ..... .....    @vvv
+vmod_du          0111 00001110 01111 ..... ..... .....    @vvv
+
+vsat_b           0111 00110010 01000 01 ... ..... .....   @vv_ui3
+vsat_h           0111 00110010 01000 1 .... ..... .....   @vv_ui4
+vsat_w           0111 00110010 01001 ..... ..... .....    @vv_ui5
+vsat_d           0111 00110010 0101 ...... ..... .....    @vv_ui6
+vsat_bu          0111 00110010 10000 01 ... ..... .....   @vv_ui3
+vsat_hu          0111 00110010 10000 1 .... ..... .....   @vv_ui4
+vsat_wu          0111 00110010 10001 ..... ..... .....    @vv_ui5
+vsat_du          0111 00110010 1001 ...... ..... .....    @vv_ui6
+
+vexth_h_b        0111 00101001 11101 11000 ..... .....    @vv
+vexth_w_h        0111 00101001 11101 11001 ..... .....    @vv
+vexth_d_w        0111 00101001 11101 11010 ..... .....    @vv
+vexth_q_d        0111 00101001 11101 11011 ..... .....    @vv
+vexth_hu_bu      0111 00101001 11101 11100 ..... .....    @vv
+vexth_wu_hu      0111 00101001 11101 11101 ..... .....    @vv
+vexth_du_wu      0111 00101001 11101 11110 ..... .....    @vv
+vexth_qu_du      0111 00101001 11101 11111 ..... .....    @vv
+
+vsigncov_b       0111 00010010 11100 ..... ..... .....    @vvv
+vsigncov_h       0111 00010010 11101 ..... ..... .....    @vvv
+vsigncov_w       0111 00010010 11110 ..... ..... .....    @vvv
+vsigncov_d       0111 00010010 11111 ..... ..... .....    @vvv
+
+vmskltz_b        0111 00101001 11000 10000 ..... .....    @vv
+vmskltz_h        0111 00101001 11000 10001 ..... .....    @vv
+vmskltz_w        0111 00101001 11000 10010 ..... .....    @vv
+vmskltz_d        0111 00101001 11000 10011 ..... .....    @vv
+vmskgez_b        0111 00101001 11000 10100 ..... .....    @vv
+vmsknz_b         0111 00101001 11000 11000 ..... .....    @vv
+
+vldi             0111 00111110 00 ............. .....     @v_i13
+
+vand_v           0111 00010010 01100 ..... ..... .....    @vvv
+vor_v            0111 00010010 01101 ..... ..... .....    @vvv
+vxor_v           0111 00010010 01110 ..... ..... .....    @vvv
+vnor_v           0111 00010010 01111 ..... ..... .....    @vvv
+vandn_v          0111 00010010 10000 ..... ..... .....    @vvv
+vorn_v           0111 00010010 10001 ..... ..... .....    @vvv
+
+vandi_b          0111 00111101 00 ........ ..... .....    @vv_ui8
+vori_b           0111 00111101 01 ........ ..... .....    @vv_ui8
+vxori_b          0111 00111101 10 ........ ..... .....    @vv_ui8
+vnori_b          0111 00111101 11 ........ ..... .....    @vv_ui8
+
+vsll_b           0111 00001110 10000 ..... ..... .....    @vvv
+vsll_h           0111 00001110 10001 ..... ..... .....    @vvv
+vsll_w           0111 00001110 10010 ..... ..... .....    @vvv
+vsll_d           0111 00001110 10011 ..... ..... .....    @vvv
+vslli_b          0111 00110010 11000 01 ... ..... .....   @vv_ui3
+vslli_h          0111 00110010 11000 1 .... ..... .....   @vv_ui4
+vslli_w          0111 00110010 11001 ..... ..... .....    @vv_ui5
+vslli_d          0111 00110010 1101 ...... ..... .....    @vv_ui6
+
+vsrl_b           0111 00001110 10100 ..... ..... .....    @vvv
+vsrl_h           0111 00001110 10101 ..... ..... .....    @vvv
+vsrl_w           0111 00001110 10110 ..... ..... .....    @vvv
+vsrl_d           0111 00001110 10111 ..... ..... .....    @vvv
+vsrli_b          0111 00110011 00000 01 ... ..... .....   @vv_ui3
+vsrli_h          0111 00110011 00000 1 .... ..... .....   @vv_ui4
+vsrli_w          0111 00110011 00001 ..... ..... .....    @vv_ui5
+vsrli_d          0111 00110011 0001 ...... ..... .....    @vv_ui6
+
+vsra_b           0111 00001110 11000 ..... ..... .....    @vvv
+vsra_h           0111 00001110 11001 ..... ..... .....    @vvv
+vsra_w           0111 00001110 11010 ..... ..... .....    @vvv
+vsra_d           0111 00001110 11011 ..... ..... .....    @vvv
+vsrai_b          0111 00110011 01000 01 ... ..... .....   @vv_ui3
+vsrai_h          0111 00110011 01000 1 .... ..... .....   @vv_ui4
+vsrai_w          0111 00110011 01001 ..... ..... .....    @vv_ui5
+vsrai_d          0111 00110011 0101 ...... ..... .....    @vv_ui6
+
+vrotr_b          0111 00001110 11100 ..... ..... .....    @vvv
+vrotr_h          0111 00001110 11101 ..... ..... .....    @vvv
+vrotr_w          0111 00001110 11110 ..... ..... .....    @vvv
+vrotr_d          0111 00001110 11111 ..... ..... .....    @vvv
+vrotri_b         0111 00101010 00000 01 ... ..... .....   @vv_ui3
+vrotri_h         0111 00101010 00000 1 .... ..... .....   @vv_ui4
+vrotri_w         0111 00101010 00001 ..... ..... .....    @vv_ui5
+vrotri_d         0111 00101010 0001 ...... ..... .....    @vv_ui6
+
+vsllwil_h_b      0111 00110000 10000 01 ... ..... .....   @vv_ui3
+vsllwil_w_h      0111 00110000 10000 1 .... ..... .....   @vv_ui4
+vsllwil_d_w      0111 00110000 10001 ..... ..... .....    @vv_ui5
+vextl_q_d        0111 00110000 10010 00000 ..... .....    @vv
+vsllwil_hu_bu    0111 00110000 11000 01 ... ..... .....   @vv_ui3
+vsllwil_wu_hu    0111 00110000 11000 1 .... ..... .....   @vv_ui4
+vsllwil_du_wu    0111 00110000 11001 ..... ..... .....    @vv_ui5
+vextl_qu_du      0111 00110000 11010 00000 ..... .....    @vv
+
+vsrlr_b          0111 00001111 00000 ..... ..... .....    @vvv
+vsrlr_h          0111 00001111 00001 ..... ..... .....    @vvv
+vsrlr_w          0111 00001111 00010 ..... ..... .....    @vvv
+vsrlr_d          0111 00001111 00011 ..... ..... .....    @vvv
+vsrlri_b         0111 00101010 01000 01 ... ..... .....   @vv_ui3
+vsrlri_h         0111 00101010 01000 1 .... ..... .....   @vv_ui4
+vsrlri_w         0111 00101010 01001 ..... ..... .....    @vv_ui5
+vsrlri_d         0111 00101010 0101 ...... ..... .....    @vv_ui6
+
+vsrar_b          0111 00001111 00100 ..... ..... .....    @vvv
+vsrar_h          0111 00001111 00101 ..... ..... .....    @vvv
+vsrar_w          0111 00001111 00110 ..... ..... .....    @vvv
+vsrar_d          0111 00001111 00111 ..... ..... .....    @vvv
+vsrari_b         0111 00101010 10000 01 ... ..... .....   @vv_ui3
+vsrari_h         0111 00101010 10000 1 .... ..... .....   @vv_ui4
+vsrari_w         0111 00101010 10001 ..... ..... .....    @vv_ui5
+vsrari_d         0111 00101010 1001 ...... ..... .....    @vv_ui6
+
+vsrln_b_h        0111 00001111 01001 ..... ..... .....    @vvv
+vsrln_h_w        0111 00001111 01010 ..... ..... .....    @vvv
+vsrln_w_d        0111 00001111 01011 ..... ..... .....    @vvv
+vsran_b_h        0111 00001111 01101 ..... ..... .....    @vvv
+vsran_h_w        0111 00001111 01110 ..... ..... .....    @vvv
+vsran_w_d        0111 00001111 01111 ..... ..... .....    @vvv
+
+vsrlni_b_h       0111 00110100 00000 1 .... ..... .....   @vv_ui4
+vsrlni_h_w       0111 00110100 00001 ..... ..... .....    @vv_ui5
+vsrlni_w_d       0111 00110100 0001 ...... ..... .....    @vv_ui6
+vsrlni_d_q       0111 00110100 001 ....... ..... .....    @vv_ui7
+vsrani_b_h       0111 00110101 10000 1 .... ..... .....   @vv_ui4
+vsrani_h_w       0111 00110101 10001 ..... ..... .....    @vv_ui5
+vsrani_w_d       0111 00110101 1001 ...... ..... .....    @vv_ui6
+vsrani_d_q       0111 00110101 101 ....... ..... .....    @vv_ui7
+
+vsrlrn_b_h       0111 00001111 10001 ..... ..... .....    @vvv
+vsrlrn_h_w       0111 00001111 10010 ..... ..... .....    @vvv
+vsrlrn_w_d       0111 00001111 10011 ..... ..... .....    @vvv
+vsrarn_b_h       0111 00001111 10101 ..... ..... .....    @vvv
+vsrarn_h_w       0111 00001111 10110 ..... ..... .....    @vvv
+vsrarn_w_d       0111 00001111 10111 ..... ..... .....    @vvv
+
+vsrlrni_b_h      0111 00110100 01000 1 .... ..... .....   @vv_ui4
+vsrlrni_h_w      0111 00110100 01001 ..... ..... .....    @vv_ui5
+vsrlrni_w_d      0111 00110100 0101 ...... ..... .....    @vv_ui6
+vsrlrni_d_q      0111 00110100 011 ....... ..... .....    @vv_ui7
+vsrarni_b_h      0111 00110101 11000 1 .... ..... .....   @vv_ui4
+vsrarni_h_w      0111 00110101 11001 ..... ..... .....    @vv_ui5
+vsrarni_w_d      0111 00110101 1101 ...... ..... .....    @vv_ui6
+vsrarni_d_q      0111 00110101 111 ....... ..... .....    @vv_ui7
+
+vssrln_b_h       0111 00001111 11001 ..... ..... .....    @vvv
+vssrln_h_w       0111 00001111 11010 ..... ..... .....    @vvv
+vssrln_w_d       0111 00001111 11011 ..... ..... .....    @vvv
+vssran_b_h       0111 00001111 11101 ..... ..... .....    @vvv
+vssran_h_w       0111 00001111 11110 ..... ..... .....    @vvv
+vssran_w_d       0111 00001111 11111 ..... ..... .....    @vvv
+vssrln_bu_h      0111 00010000 01001 ..... ..... .....    @vvv
+vssrln_hu_w      0111 00010000 01010 ..... ..... .....    @vvv
+vssrln_wu_d      0111 00010000 01011 ..... ..... .....    @vvv
+vssran_bu_h      0111 00010000 01101 ..... ..... .....    @vvv
+vssran_hu_w      0111 00010000 01110 ..... ..... .....    @vvv
+vssran_wu_d      0111 00010000 01111 ..... ..... .....    @vvv
+
+vssrlni_b_h      0111 00110100 10000 1 .... ..... .....   @vv_ui4
+vssrlni_h_w      0111 00110100 10001 ..... ..... .....    @vv_ui5
+vssrlni_w_d      0111 00110100 1001 ...... ..... .....    @vv_ui6
+vssrlni_d_q      0111 00110100 101 ....... ..... .....    @vv_ui7
+vssrani_b_h      0111 00110110 00000 1 .... ..... .....   @vv_ui4
+vssrani_h_w      0111 00110110 00001 ..... ..... .....    @vv_ui5
+vssrani_w_d      0111 00110110 0001 ...... ..... .....    @vv_ui6
+vssrani_d_q      0111 00110110 001 ....... ..... .....    @vv_ui7
+vssrlni_bu_h     0111 00110100 11000 1 .... ..... .....   @vv_ui4
+vssrlni_hu_w     0111 00110100 11001 ..... ..... .....    @vv_ui5
+vssrlni_wu_d     0111 00110100 1101 ...... ..... .....    @vv_ui6
+vssrlni_du_q     0111 00110100 111 ....... ..... .....    @vv_ui7
+vssrani_bu_h     0111 00110110 01000 1 .... ..... .....   @vv_ui4
+vssrani_hu_w     0111 00110110 01001 ..... ..... .....    @vv_ui5
+vssrani_wu_d     0111 00110110 0101 ...... ..... .....    @vv_ui6
+vssrani_du_q     0111 00110110 011 ....... ..... .....    @vv_ui7
+
+vssrlrn_b_h      0111 00010000 00001 ..... ..... .....    @vvv
+vssrlrn_h_w      0111 00010000 00010 ..... ..... .....    @vvv
+vssrlrn_w_d      0111 00010000 00011 ..... ..... .....    @vvv
+vssrarn_b_h      0111 00010000 00101 ..... ..... .....    @vvv
+vssrarn_h_w      0111 00010000 00110 ..... ..... .....    @vvv
+vssrarn_w_d      0111 00010000 00111 ..... ..... .....    @vvv
+vssrlrn_bu_h     0111 00010000 10001 ..... ..... .....    @vvv
+vssrlrn_hu_w     0111 00010000 10010 ..... ..... .....    @vvv
+vssrlrn_wu_d     0111 00010000 10011 ..... ..... .....    @vvv
+vssrarn_bu_h     0111 00010000 10101 ..... ..... .....    @vvv
+vssrarn_hu_w     0111 00010000 10110 ..... ..... .....    @vvv
+vssrarn_wu_d     0111 00010000 10111 ..... ..... .....    @vvv
+
+vssrlrni_b_h     0111 00110101 00000 1 .... ..... .....   @vv_ui4
+vssrlrni_h_w     0111 00110101 00001 ..... ..... .....    @vv_ui5
+vssrlrni_w_d     0111 00110101 0001 ...... ..... .....    @vv_ui6
+vssrlrni_d_q     0111 00110101 001 ....... ..... .....    @vv_ui7
+vssrarni_b_h     0111 00110110 10000 1 .... ..... .....   @vv_ui4
+vssrarni_h_w     0111 00110110 10001 ..... ..... .....    @vv_ui5
+vssrarni_w_d     0111 00110110 1001 ...... ..... .....    @vv_ui6
+vssrarni_d_q     0111 00110110 101 ....... ..... .....    @vv_ui7
+vssrlrni_bu_h    0111 00110101 01000 1 .... ..... .....   @vv_ui4
+vssrlrni_hu_w    0111 00110101 01001 ..... ..... .....    @vv_ui5
+vssrlrni_wu_d    0111 00110101 0101 ...... ..... .....    @vv_ui6
+vssrlrni_du_q    0111 00110101 011 ....... ..... .....    @vv_ui7
+vssrarni_bu_h    0111 00110110 11000 1 .... ..... .....   @vv_ui4
+vssrarni_hu_w    0111 00110110 11001 ..... ..... .....    @vv_ui5
+vssrarni_wu_d    0111 00110110 1101 ...... ..... .....    @vv_ui6
+vssrarni_du_q    0111 00110110 111 ....... ..... .....    @vv_ui7
+
+vclo_b           0111 00101001 11000 00000 ..... .....    @vv
+vclo_h           0111 00101001 11000 00001 ..... .....    @vv
+vclo_w           0111 00101001 11000 00010 ..... .....    @vv
+vclo_d           0111 00101001 11000 00011 ..... .....    @vv
+vclz_b           0111 00101001 11000 00100 ..... .....    @vv
+vclz_h           0111 00101001 11000 00101 ..... .....    @vv
+vclz_w           0111 00101001 11000 00110 ..... .....    @vv
+vclz_d           0111 00101001 11000 00111 ..... .....    @vv
+
+vpcnt_b          0111 00101001 11000 01000 ..... .....    @vv
+vpcnt_h          0111 00101001 11000 01001 ..... .....    @vv
+vpcnt_w          0111 00101001 11000 01010 ..... .....    @vv
+vpcnt_d          0111 00101001 11000 01011 ..... .....    @vv
+
+vbitclr_b        0111 00010000 11000 ..... ..... .....    @vvv
+vbitclr_h        0111 00010000 11001 ..... ..... .....    @vvv
+vbitclr_w        0111 00010000 11010 ..... ..... .....    @vvv
+vbitclr_d        0111 00010000 11011 ..... ..... .....    @vvv
+vbitclri_b       0111 00110001 00000 01 ... ..... .....   @vv_ui3
+vbitclri_h       0111 00110001 00000 1 .... ..... .....   @vv_ui4
+vbitclri_w       0111 00110001 00001 ..... ..... .....    @vv_ui5
+vbitclri_d       0111 00110001 0001 ...... ..... .....    @vv_ui6
+vbitset_b        0111 00010000 11100 ..... ..... .....    @vvv
+vbitset_h        0111 00010000 11101 ..... ..... .....    @vvv
+vbitset_w        0111 00010000 11110 ..... ..... .....    @vvv
+vbitset_d        0111 00010000 11111 ..... ..... .....    @vvv
+vbitseti_b       0111 00110001 01000 01 ... ..... .....   @vv_ui3
+vbitseti_h       0111 00110001 01000 1 .... ..... .....   @vv_ui4
+vbitseti_w       0111 00110001 01001 ..... ..... .....    @vv_ui5
+vbitseti_d       0111 00110001 0101 ...... ..... .....    @vv_ui6
+vbitrev_b        0111 00010001 00000 ..... ..... .....    @vvv
+vbitrev_h        0111 00010001 00001 ..... ..... .....    @vvv
+vbitrev_w        0111 00010001 00010 ..... ..... .....    @vvv
+vbitrev_d        0111 00010001 00011 ..... ..... .....    @vvv
+vbitrevi_b       0111 00110001 10000 01 ... ..... .....   @vv_ui3
+vbitrevi_h       0111 00110001 10000 1 .... ..... .....   @vv_ui4
+vbitrevi_w       0111 00110001 10001 ..... ..... .....    @vv_ui5
+vbitrevi_d       0111 00110001 1001 ...... ..... .....    @vv_ui6
+
+vfrstp_b         0111 00010010 10110 ..... ..... .....    @vvv
+vfrstp_h         0111 00010010 10111 ..... ..... .....    @vvv
+vfrstpi_b        0111 00101001 10100 ..... ..... .....    @vv_ui5
+vfrstpi_h        0111 00101001 10101 ..... ..... .....    @vv_ui5
+
+vfadd_s          0111 00010011 00001 ..... ..... .....    @vvv
+vfadd_d          0111 00010011 00010 ..... ..... .....    @vvv
+vfsub_s          0111 00010011 00101 ..... ..... .....    @vvv
+vfsub_d          0111 00010011 00110 ..... ..... .....    @vvv
+vfmul_s          0111 00010011 10001 ..... ..... .....    @vvv
+vfmul_d          0111 00010011 10010 ..... ..... .....    @vvv
+vfdiv_s          0111 00010011 10101 ..... ..... .....    @vvv
+vfdiv_d          0111 00010011 10110 ..... ..... .....    @vvv
+
+vfmadd_s         0000 10010001 ..... ..... ..... .....    @vvvv
+vfmadd_d         0000 10010010 ..... ..... ..... .....    @vvvv
+vfmsub_s         0000 10010101 ..... ..... ..... .....    @vvvv
+vfmsub_d         0000 10010110 ..... ..... ..... .....    @vvvv
+vfnmadd_s        0000 10011001 ..... ..... ..... .....    @vvvv
+vfnmadd_d        0000 10011010 ..... ..... ..... .....    @vvvv
+vfnmsub_s        0000 10011101 ..... ..... ..... .....    @vvvv
+vfnmsub_d        0000 10011110 ..... ..... ..... .....    @vvvv
+
+vfmax_s          0111 00010011 11001 ..... ..... .....    @vvv
+vfmax_d          0111 00010011 11010 ..... ..... .....    @vvv
+vfmin_s          0111 00010011 11101 ..... ..... .....    @vvv
+vfmin_d          0111 00010011 11110 ..... ..... .....    @vvv
+
+vfmaxa_s         0111 00010100 00001 ..... ..... .....    @vvv
+vfmaxa_d         0111 00010100 00010 ..... ..... .....    @vvv
+vfmina_s         0111 00010100 00101 ..... ..... .....    @vvv
+vfmina_d         0111 00010100 00110 ..... ..... .....    @vvv
+
+vflogb_s         0111 00101001 11001 10001 ..... .....    @vv
+vflogb_d         0111 00101001 11001 10010 ..... .....    @vv
+
+vfclass_s        0111 00101001 11001 10101 ..... .....    @vv
+vfclass_d        0111 00101001 11001 10110 ..... .....    @vv
+
+vfsqrt_s         0111 00101001 11001 11001 ..... .....    @vv
+vfsqrt_d         0111 00101001 11001 11010 ..... .....    @vv
+vfrecip_s        0111 00101001 11001 11101 ..... .....    @vv
+vfrecip_d        0111 00101001 11001 11110 ..... .....    @vv
+vfrsqrt_s        0111 00101001 11010 00001 ..... .....    @vv
+vfrsqrt_d        0111 00101001 11010 00010 ..... .....    @vv
+
+vfcvtl_s_h       0111 00101001 11011 11010 ..... .....    @vv
+vfcvth_s_h       0111 00101001 11011 11011 ..... .....    @vv
+vfcvtl_d_s       0111 00101001 11011 11100 ..... .....    @vv
+vfcvth_d_s       0111 00101001 11011 11101 ..... .....    @vv
+vfcvt_h_s        0111 00010100 01100 ..... ..... .....    @vvv
+vfcvt_s_d        0111 00010100 01101 ..... ..... .....    @vvv
+
+vfrint_s         0111 00101001 11010 01101 ..... .....    @vv
+vfrint_d         0111 00101001 11010 01110 ..... .....    @vv
+vfrintrm_s       0111 00101001 11010 10001 ..... .....    @vv
+vfrintrm_d       0111 00101001 11010 10010 ..... .....    @vv
+vfrintrp_s       0111 00101001 11010 10101 ..... .....    @vv
+vfrintrp_d       0111 00101001 11010 10110 ..... .....    @vv
+vfrintrz_s       0111 00101001 11010 11001 ..... .....    @vv
+vfrintrz_d       0111 00101001 11010 11010 ..... .....    @vv
+vfrintrne_s      0111 00101001 11010 11101 ..... .....    @vv
+vfrintrne_d      0111 00101001 11010 11110 ..... .....    @vv
+
+vftint_w_s       0111 00101001 11100 01100 ..... .....    @vv
+vftint_l_d       0111 00101001 11100 01101 ..... .....    @vv
+vftintrm_w_s     0111 00101001 11100 01110 ..... .....    @vv
+vftintrm_l_d     0111 00101001 11100 01111 ..... .....    @vv
+vftintrp_w_s     0111 00101001 11100 10000 ..... .....    @vv
+vftintrp_l_d     0111 00101001 11100 10001 ..... .....    @vv
+vftintrz_w_s     0111 00101001 11100 10010 ..... .....    @vv
+vftintrz_l_d     0111 00101001 11100 10011 ..... .....    @vv
+vftintrne_w_s    0111 00101001 11100 10100 ..... .....    @vv
+vftintrne_l_d    0111 00101001 11100 10101 ..... .....    @vv
+vftint_wu_s      0111 00101001 11100 10110 ..... .....    @vv
+vftint_lu_d      0111 00101001 11100 10111 ..... .....    @vv
+vftintrz_wu_s    0111 00101001 11100 11100 ..... .....    @vv
+vftintrz_lu_d    0111 00101001 11100 11101 ..... .....    @vv
+vftint_w_d       0111 00010100 10011 ..... ..... .....    @vvv
+vftintrm_w_d     0111 00010100 10100 ..... ..... .....    @vvv
+vftintrp_w_d     0111 00010100 10101 ..... ..... .....    @vvv
+vftintrz_w_d     0111 00010100 10110 ..... ..... .....    @vvv
+vftintrne_w_d    0111 00010100 10111 ..... ..... .....    @vvv
+vftintl_l_s      0111 00101001 11101 00000 ..... .....    @vv
+vftinth_l_s      0111 00101001 11101 00001 ..... .....    @vv
+vftintrml_l_s    0111 00101001 11101 00010 ..... .....    @vv
+vftintrmh_l_s    0111 00101001 11101 00011 ..... .....    @vv
+vftintrpl_l_s    0111 00101001 11101 00100 ..... .....    @vv
+vftintrph_l_s    0111 00101001 11101 00101 ..... .....    @vv
+vftintrzl_l_s    0111 00101001 11101 00110 ..... .....    @vv
+vftintrzh_l_s    0111 00101001 11101 00111 ..... .....    @vv
+vftintrnel_l_s   0111 00101001 11101 01000 ..... .....    @vv
+vftintrneh_l_s   0111 00101001 11101 01001 ..... .....    @vv
+
+vffint_s_w       0111 00101001 11100 00000 ..... .....    @vv
+vffint_s_wu      0111 00101001 11100 00001 ..... .....    @vv
+vffint_d_l       0111 00101001 11100 00010 ..... .....    @vv
+vffint_d_lu      0111 00101001 11100 00011 ..... .....    @vv
+vffintl_d_w      0111 00101001 11100 00100 ..... .....    @vv
+vffinth_d_w      0111 00101001 11100 00101 ..... .....    @vv
+vffint_s_l       0111 00010100 10000 ..... ..... .....    @vvv
+
+vseq_b           0111 00000000 00000 ..... ..... .....    @vvv
+vseq_h           0111 00000000 00001 ..... ..... .....    @vvv
+vseq_w           0111 00000000 00010 ..... ..... .....    @vvv
+vseq_d           0111 00000000 00011 ..... ..... .....    @vvv
+vseqi_b          0111 00101000 00000 ..... ..... .....    @vv_i5
+vseqi_h          0111 00101000 00001 ..... ..... .....    @vv_i5
+vseqi_w          0111 00101000 00010 ..... ..... .....    @vv_i5
+vseqi_d          0111 00101000 00011 ..... ..... .....    @vv_i5
+
+vsle_b           0111 00000000 00100 ..... ..... .....    @vvv
+vsle_h           0111 00000000 00101 ..... ..... .....    @vvv
+vsle_w           0111 00000000 00110 ..... ..... .....    @vvv
+vsle_d           0111 00000000 00111 ..... ..... .....    @vvv
+vslei_b          0111 00101000 00100 ..... ..... .....    @vv_i5
+vslei_h          0111 00101000 00101 ..... ..... .....    @vv_i5
+vslei_w          0111 00101000 00110 ..... ..... .....    @vv_i5
+vslei_d          0111 00101000 00111 ..... ..... .....    @vv_i5
+vsle_bu          0111 00000000 01000 ..... ..... .....    @vvv
+vsle_hu          0111 00000000 01001 ..... ..... .....    @vvv
+vsle_wu          0111 00000000 01010 ..... ..... .....    @vvv
+vsle_du          0111 00000000 01011 ..... ..... .....    @vvv
+vslei_bu         0111 00101000 01000 ..... ..... .....    @vv_ui5
+vslei_hu         0111 00101000 01001 ..... ..... .....    @vv_ui5
+vslei_wu         0111 00101000 01010 ..... ..... .....    @vv_ui5
+vslei_du         0111 00101000 01011 ..... ..... .....    @vv_ui5
+
+vslt_b           0111 00000000 01100 ..... ..... .....    @vvv
+vslt_h           0111 00000000 01101 ..... ..... .....    @vvv
+vslt_w           0111 00000000 01110 ..... ..... .....    @vvv
+vslt_d           0111 00000000 01111 ..... ..... .....    @vvv
+vslti_b          0111 00101000 01100 ..... ..... .....    @vv_i5
+vslti_h          0111 00101000 01101 ..... ..... .....    @vv_i5
+vslti_w          0111 00101000 01110 ..... ..... .....    @vv_i5
+vslti_d          0111 00101000 01111 ..... ..... .....    @vv_i5
+vslt_bu          0111 00000000 10000 ..... ..... .....    @vvv
+vslt_hu          0111 00000000 10001 ..... ..... .....    @vvv
+vslt_wu          0111 00000000 10010 ..... ..... .....    @vvv
+vslt_du          0111 00000000 10011 ..... ..... .....    @vvv
+vslti_bu         0111 00101000 10000 ..... ..... .....    @vv_ui5
+vslti_hu         0111 00101000 10001 ..... ..... .....    @vv_ui5
+vslti_wu         0111 00101000 10010 ..... ..... .....    @vv_ui5
+vslti_du         0111 00101000 10011 ..... ..... .....    @vv_ui5
+
+vfcmp_cond_s     0000 11000101 ..... ..... ..... .....    @vvv_fcond
+vfcmp_cond_d     0000 11000110 ..... ..... ..... .....    @vvv_fcond
+
+vbitsel_v        0000 11010001 ..... ..... ..... .....    @vvvv
+
+vbitseli_b       0111 00111100 01 ........ ..... .....    @vv_ui8
+
+vseteqz_v        0111 00101001 11001 00110 ..... 00 ...   @cv
+vsetnez_v        0111 00101001 11001 00111 ..... 00 ...   @cv
+vsetanyeqz_b     0111 00101001 11001 01000 ..... 00 ...   @cv
+vsetanyeqz_h     0111 00101001 11001 01001 ..... 00 ...   @cv
+vsetanyeqz_w     0111 00101001 11001 01010 ..... 00 ...   @cv
+vsetanyeqz_d     0111 00101001 11001 01011 ..... 00 ...   @cv
+vsetallnez_b     0111 00101001 11001 01100 ..... 00 ...   @cv
+vsetallnez_h     0111 00101001 11001 01101 ..... 00 ...   @cv
+vsetallnez_w     0111 00101001 11001 01110 ..... 00 ...   @cv
+vsetallnez_d     0111 00101001 11001 01111 ..... 00 ...   @cv
+
+vinsgr2vr_b      0111 00101110 10111 0 .... ..... .....   @vr_ui4
+vinsgr2vr_h      0111 00101110 10111 10 ... ..... .....   @vr_ui3
+vinsgr2vr_w      0111 00101110 10111 110 .. ..... .....   @vr_ui2
+vinsgr2vr_d      0111 00101110 10111 1110 . ..... .....   @vr_ui1
+vpickve2gr_b     0111 00101110 11111 0 .... ..... .....   @rv_ui4
+vpickve2gr_h     0111 00101110 11111 10 ... ..... .....   @rv_ui3
+vpickve2gr_w     0111 00101110 11111 110 .. ..... .....   @rv_ui2
+vpickve2gr_d     0111 00101110 11111 1110 . ..... .....   @rv_ui1
+vpickve2gr_bu    0111 00101111 00111 0 .... ..... .....   @rv_ui4
+vpickve2gr_hu    0111 00101111 00111 10 ... ..... .....   @rv_ui3
+vpickve2gr_wu    0111 00101111 00111 110 .. ..... .....   @rv_ui2
+vpickve2gr_du    0111 00101111 00111 1110 . ..... .....   @rv_ui1
+
+vreplgr2vr_b     0111 00101001 11110 00000 ..... .....    @vr
+vreplgr2vr_h     0111 00101001 11110 00001 ..... .....    @vr
+vreplgr2vr_w     0111 00101001 11110 00010 ..... .....    @vr
+vreplgr2vr_d     0111 00101001 11110 00011 ..... .....    @vr
+
+vreplve_b        0111 00010010 00100 ..... ..... .....    @vvr
+vreplve_h        0111 00010010 00101 ..... ..... .....    @vvr
+vreplve_w        0111 00010010 00110 ..... ..... .....    @vvr
+vreplve_d        0111 00010010 00111 ..... ..... .....    @vvr
+vreplvei_b       0111 00101111 01111 0 .... ..... .....   @vv_ui4
+vreplvei_h       0111 00101111 01111 10 ... ..... .....   @vv_ui3
+vreplvei_w       0111 00101111 01111 110 .. ..... .....   @vv_ui2
+vreplvei_d       0111 00101111 01111 1110 . ..... .....   @vv_ui1
+
+vbsll_v          0111 00101000 11100 ..... ..... .....    @vv_ui5
+vbsrl_v          0111 00101000 11101 ..... ..... .....    @vv_ui5
+
+vpackev_b        0111 00010001 01100 ..... ..... .....    @vvv
+vpackev_h        0111 00010001 01101 ..... ..... .....    @vvv
+vpackev_w        0111 00010001 01110 ..... ..... .....    @vvv
+vpackev_d        0111 00010001 01111 ..... ..... .....    @vvv
+vpackod_b        0111 00010001 10000 ..... ..... .....    @vvv
+vpackod_h        0111 00010001 10001 ..... ..... .....    @vvv
+vpackod_w        0111 00010001 10010 ..... ..... .....    @vvv
+vpackod_d        0111 00010001 10011 ..... ..... .....    @vvv
+
+vpickev_b        0111 00010001 11100 ..... ..... .....    @vvv
+vpickev_h        0111 00010001 11101 ..... ..... .....    @vvv
+vpickev_w        0111 00010001 11110 ..... ..... .....    @vvv
+vpickev_d        0111 00010001 11111 ..... ..... .....    @vvv
+vpickod_b        0111 00010010 00000 ..... ..... .....    @vvv
+vpickod_h        0111 00010010 00001 ..... ..... .....    @vvv
+vpickod_w        0111 00010010 00010 ..... ..... .....    @vvv
+vpickod_d        0111 00010010 00011 ..... ..... .....    @vvv
+
+vilvl_b          0111 00010001 10100 ..... ..... .....    @vvv
+vilvl_h          0111 00010001 10101 ..... ..... .....    @vvv
+vilvl_w          0111 00010001 10110 ..... ..... .....    @vvv
+vilvl_d          0111 00010001 10111 ..... ..... .....    @vvv
+vilvh_b          0111 00010001 11000 ..... ..... .....    @vvv
+vilvh_h          0111 00010001 11001 ..... ..... .....    @vvv
+vilvh_w          0111 00010001 11010 ..... ..... .....    @vvv
+vilvh_d          0111 00010001 11011 ..... ..... .....    @vvv
+
+vshuf_b          0000 11010101 ..... ..... ..... .....    @vvvv
+vshuf_h          0111 00010111 10101 ..... ..... .....    @vvv
+vshuf_w          0111 00010111 10110 ..... ..... .....    @vvv
+vshuf_d          0111 00010111 10111 ..... ..... .....    @vvv
+vshuf4i_b        0111 00111001 00 ........ ..... .....    @vv_ui8
+vshuf4i_h        0111 00111001 01 ........ ..... .....    @vv_ui8
+vshuf4i_w        0111 00111001 10 ........ ..... .....    @vv_ui8
+vshuf4i_d        0111 00111001 11 ........ ..... .....    @vv_ui8
+
+vpermi_w         0111 00111110 01 ........ ..... .....    @vv_ui8
+
+vextrins_d       0111 00111000 00 ........ ..... .....    @vv_ui8
+vextrins_w       0111 00111000 01 ........ ..... .....    @vv_ui8
+vextrins_h       0111 00111000 10 ........ ..... .....    @vv_ui8
+vextrins_b       0111 00111000 11 ........ ..... .....    @vv_ui8
+
+vld              0010 110000 ............ ..... .....     @vr_i12
+vst              0010 110001 ............ ..... .....     @vr_i12
+vldx             0011 10000100 00000 ..... ..... .....    @vrr
+vstx             0011 10000100 01000 ..... ..... .....    @vrr
+
+vldrepl_d        0011 00000001 0 ......... ..... .....    @vr_i9
+vldrepl_w        0011 00000010 .......... ..... .....     @vr_i10
+vldrepl_h        0011 0000010 ........... ..... .....     @vr_i11
+vldrepl_b        0011 000010 ............ ..... .....     @vr_i12
+vstelm_d         0011 00010001 0 . ........ ..... .....   @vr_i8i1
+vstelm_w         0011 00010010 .. ........ ..... .....    @vr_i8i2
+vstelm_h         0011 0001010 ... ........ ..... .....    @vr_i8i3
+vstelm_b         0011 000110 .... ........ ..... .....    @vr_i8i4

target/loongarch/internals.h

@@ -21,6 +21,28 @@
 /* Global bit for huge page */
 #define LOONGARCH_HGLOBAL_SHIFT     12
 
+#if  HOST_BIG_ENDIAN
+#define B(x)  B[15 - (x)]
+#define H(x)  H[7 - (x)]
+#define W(x)  W[3 - (x)]
+#define D(x)  D[1 - (x)]
+#define UB(x) UB[15 - (x)]
+#define UH(x) UH[7 - (x)]
+#define UW(x) UW[3 - (x)]
+#define UD(x) UD[1 -(x)]
+#define Q(x)  Q[x]
+#else
+#define B(x)  B[x]
+#define H(x)  H[x]
+#define W(x)  W[x]
+#define D(x)  D[x]
+#define UB(x) UB[x]
+#define UH(x) UH[x]
+#define UW(x) UW[x]
+#define UD(x) UD[x]
+#define Q(x)  Q[x]
+#endif
+
 void loongarch_translate_init(void);
 
 void loongarch_cpu_dump_state(CPUState *cpu, FILE *f, int flags);
@@ -31,6 +53,7 @@ void G_NORETURN do_raise_exception(CPULoongArchState *env,
 
 const char *loongarch_exception_name(int32_t exception);
 
+int ieee_ex_to_loongarch(int xcpt);
 void restore_fp_status(CPULoongArchState *env);
 
 #ifndef CONFIG_USER_ONLY

target/loongarch/lsx_helper.c

@@ -0,0 +1,3004 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * QEMU LoongArch LSX helper functions.
+ *
+ * Copyright (c) 2022-2023 Loongson Technology Corporation Limited
+ */
+
+#include "qemu/osdep.h"
+#include "cpu.h"
+#include "exec/exec-all.h"
+#include "exec/helper-proto.h"
+#include "fpu/softfloat.h"
+#include "internals.h"
+#include "tcg/tcg.h"
+
+#define DO_ADD(a, b)  (a + b)
+#define DO_SUB(a, b)  (a - b)
+
+#define DO_ODD_EVEN(NAME, BIT, E1, E2, DO_OP)                        \
+void HELPER(NAME)(CPULoongArchState *env,                            \
+                  uint32_t vd, uint32_t vj, uint32_t vk)             \
+{                                                                    \
+    int i;                                                           \
+    VReg *Vd = &(env->fpr[vd].vreg);                                 \
+    VReg *Vj = &(env->fpr[vj].vreg);                                 \
+    VReg *Vk = &(env->fpr[vk].vreg);                                 \
+    typedef __typeof(Vd->E1(0)) TD;                                  \
+                                                                     \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                              \
+        Vd->E1(i) = DO_OP((TD)Vj->E2(2 * i + 1), (TD)Vk->E2(2 * i)); \
+    }                                                                \
+}
+
+DO_ODD_EVEN(vhaddw_h_b, 16, H, B, DO_ADD)
+DO_ODD_EVEN(vhaddw_w_h, 32, W, H, DO_ADD)
+DO_ODD_EVEN(vhaddw_d_w, 64, D, W, DO_ADD)
+
+void HELPER(vhaddw_q_d)(CPULoongArchState *env,
+                        uint32_t vd, uint32_t vj, uint32_t vk)
+{
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+    VReg *Vk = &(env->fpr[vk].vreg);
+
+    Vd->Q(0) = int128_add(int128_makes64(Vj->D(1)), int128_makes64(Vk->D(0)));
+}
+
+DO_ODD_EVEN(vhsubw_h_b, 16, H, B, DO_SUB)
+DO_ODD_EVEN(vhsubw_w_h, 32, W, H, DO_SUB)
+DO_ODD_EVEN(vhsubw_d_w, 64, D, W, DO_SUB)
+
+void HELPER(vhsubw_q_d)(CPULoongArchState *env,
+                        uint32_t vd, uint32_t vj, uint32_t vk)
+{
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+    VReg *Vk = &(env->fpr[vk].vreg);
+
+    Vd->Q(0) = int128_sub(int128_makes64(Vj->D(1)), int128_makes64(Vk->D(0)));
+}
+
+DO_ODD_EVEN(vhaddw_hu_bu, 16, UH, UB, DO_ADD)
+DO_ODD_EVEN(vhaddw_wu_hu, 32, UW, UH, DO_ADD)
+DO_ODD_EVEN(vhaddw_du_wu, 64, UD, UW, DO_ADD)
+
+void HELPER(vhaddw_qu_du)(CPULoongArchState *env,
+                          uint32_t vd, uint32_t vj, uint32_t vk)
+{
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+    VReg *Vk = &(env->fpr[vk].vreg);
+
+    Vd->Q(0) = int128_add(int128_make64((uint64_t)Vj->D(1)),
+                          int128_make64((uint64_t)Vk->D(0)));
+}
+
+DO_ODD_EVEN(vhsubw_hu_bu, 16, UH, UB, DO_SUB)
+DO_ODD_EVEN(vhsubw_wu_hu, 32, UW, UH, DO_SUB)
+DO_ODD_EVEN(vhsubw_du_wu, 64, UD, UW, DO_SUB)
+
+void HELPER(vhsubw_qu_du)(CPULoongArchState *env,
+                          uint32_t vd, uint32_t vj, uint32_t vk)
+{
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+    VReg *Vk = &(env->fpr[vk].vreg);
+
+    Vd->Q(0) = int128_sub(int128_make64((uint64_t)Vj->D(1)),
+                          int128_make64((uint64_t)Vk->D(0)));
+}
+
+#define DO_EVEN(NAME, BIT, E1, E2, DO_OP)                        \
+void HELPER(NAME)(void *vd, void *vj, void *vk, uint32_t v)      \
+{                                                                \
+    int i;                                                       \
+    VReg *Vd = (VReg *)vd;                                       \
+    VReg *Vj = (VReg *)vj;                                       \
+    VReg *Vk = (VReg *)vk;                                       \
+    typedef __typeof(Vd->E1(0)) TD;                              \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                          \
+        Vd->E1(i) = DO_OP((TD)Vj->E2(2 * i) ,(TD)Vk->E2(2 * i)); \
+    }                                                            \
+}
+
+#define DO_ODD(NAME, BIT, E1, E2, DO_OP)                                 \
+void HELPER(NAME)(void *vd, void *vj, void *vk, uint32_t v)              \
+{                                                                        \
+    int i;                                                               \
+    VReg *Vd = (VReg *)vd;                                               \
+    VReg *Vj = (VReg *)vj;                                               \
+    VReg *Vk = (VReg *)vk;                                               \
+    typedef __typeof(Vd->E1(0)) TD;                                      \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                                  \
+        Vd->E1(i) = DO_OP((TD)Vj->E2(2 * i + 1), (TD)Vk->E2(2 * i + 1)); \
+    }                                                                    \
+}
+
+void HELPER(vaddwev_q_d)(void *vd, void *vj, void *vk, uint32_t v)
+{
+    VReg *Vd = (VReg *)vd;
+    VReg *Vj = (VReg *)vj;
+    VReg *Vk = (VReg *)vk;
+
+    Vd->Q(0) = int128_add(int128_makes64(Vj->D(0)), int128_makes64(Vk->D(0)));
+}
+
+DO_EVEN(vaddwev_h_b, 16, H, B, DO_ADD)
+DO_EVEN(vaddwev_w_h, 32, W, H, DO_ADD)
+DO_EVEN(vaddwev_d_w, 64, D, W, DO_ADD)
+
+void HELPER(vaddwod_q_d)(void *vd, void *vj, void *vk, uint32_t v)
+{
+    VReg *Vd = (VReg *)vd;
+    VReg *Vj = (VReg *)vj;
+    VReg *Vk = (VReg *)vk;
+
+    Vd->Q(0) = int128_add(int128_makes64(Vj->D(1)), int128_makes64(Vk->D(1)));
+}
+
+DO_ODD(vaddwod_h_b, 16, H, B, DO_ADD)
+DO_ODD(vaddwod_w_h, 32, W, H, DO_ADD)
+DO_ODD(vaddwod_d_w, 64, D, W, DO_ADD)
+
+void HELPER(vsubwev_q_d)(void *vd, void *vj, void *vk, uint32_t v)
+{
+    VReg *Vd = (VReg *)vd;
+    VReg *Vj = (VReg *)vj;
+    VReg *Vk = (VReg *)vk;
+
+    Vd->Q(0) = int128_sub(int128_makes64(Vj->D(0)), int128_makes64(Vk->D(0)));
+}
+
+DO_EVEN(vsubwev_h_b, 16, H, B, DO_SUB)
+DO_EVEN(vsubwev_w_h, 32, W, H, DO_SUB)
+DO_EVEN(vsubwev_d_w, 64, D, W, DO_SUB)
+
+void HELPER(vsubwod_q_d)(void *vd, void *vj, void *vk, uint32_t v)
+{
+    VReg *Vd = (VReg *)vd;
+    VReg *Vj = (VReg *)vj;
+    VReg *Vk = (VReg *)vk;
+
+    Vd->Q(0) = int128_sub(int128_makes64(Vj->D(1)), int128_makes64(Vk->D(1)));
+}
+
+DO_ODD(vsubwod_h_b, 16, H, B, DO_SUB)
+DO_ODD(vsubwod_w_h, 32, W, H, DO_SUB)
+DO_ODD(vsubwod_d_w, 64, D, W, DO_SUB)
+
+void HELPER(vaddwev_q_du)(void *vd, void *vj, void *vk, uint32_t v)
+{
+    VReg *Vd = (VReg *)vd;
+    VReg *Vj = (VReg *)vj;
+    VReg *Vk = (VReg *)vk;
+
+    Vd->Q(0) = int128_add(int128_make64((uint64_t)Vj->D(0)),
+                          int128_make64((uint64_t)Vk->D(0)));
+}
+
+DO_EVEN(vaddwev_h_bu, 16, UH, UB, DO_ADD)
+DO_EVEN(vaddwev_w_hu, 32, UW, UH, DO_ADD)
+DO_EVEN(vaddwev_d_wu, 64, UD, UW, DO_ADD)
+
+void HELPER(vaddwod_q_du)(void *vd, void *vj, void *vk, uint32_t v)
+{
+    VReg *Vd = (VReg *)vd;
+    VReg *Vj = (VReg *)vj;
+    VReg *Vk = (VReg *)vk;
+
+    Vd->Q(0) = int128_add(int128_make64((uint64_t)Vj->D(1)),
+                          int128_make64((uint64_t)Vk->D(1)));
+}
+
+DO_ODD(vaddwod_h_bu, 16, UH, UB, DO_ADD)
+DO_ODD(vaddwod_w_hu, 32, UW, UH, DO_ADD)
+DO_ODD(vaddwod_d_wu, 64, UD, UW, DO_ADD)
+
+void HELPER(vsubwev_q_du)(void *vd, void *vj, void *vk, uint32_t v)
+{
+    VReg *Vd = (VReg *)vd;
+    VReg *Vj = (VReg *)vj;
+    VReg *Vk = (VReg *)vk;
+
+    Vd->Q(0) = int128_sub(int128_make64((uint64_t)Vj->D(0)),
+                          int128_make64((uint64_t)Vk->D(0)));
+}
+
+DO_EVEN(vsubwev_h_bu, 16, UH, UB, DO_SUB)
+DO_EVEN(vsubwev_w_hu, 32, UW, UH, DO_SUB)
+DO_EVEN(vsubwev_d_wu, 64, UD, UW, DO_SUB)
+
+void HELPER(vsubwod_q_du)(void *vd, void *vj, void *vk, uint32_t v)
+{
+    VReg *Vd = (VReg *)vd;
+    VReg *Vj = (VReg *)vj;
+    VReg *Vk = (VReg *)vk;
+
+    Vd->Q(0) = int128_sub(int128_make64((uint64_t)Vj->D(1)),
+                          int128_make64((uint64_t)Vk->D(1)));
+}
+
+DO_ODD(vsubwod_h_bu, 16, UH, UB, DO_SUB)
+DO_ODD(vsubwod_w_hu, 32, UW, UH, DO_SUB)
+DO_ODD(vsubwod_d_wu, 64, UD, UW, DO_SUB)
+
+#define DO_EVEN_U_S(NAME, BIT, ES1, EU1, ES2, EU2, DO_OP)             \
+void HELPER(NAME)(void *vd, void *vj, void *vk, uint32_t v)           \
+{                                                                     \
+    int i;                                                            \
+    VReg *Vd = (VReg *)vd;                                            \
+    VReg *Vj = (VReg *)vj;                                            \
+    VReg *Vk = (VReg *)vk;                                            \
+    typedef __typeof(Vd->ES1(0)) TDS;                                 \
+    typedef __typeof(Vd->EU1(0)) TDU;                                 \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                               \
+        Vd->ES1(i) = DO_OP((TDU)Vj->EU2(2 * i) ,(TDS)Vk->ES2(2 * i)); \
+    }                                                                 \
+}
+
+#define DO_ODD_U_S(NAME, BIT, ES1, EU1, ES2, EU2, DO_OP)                      \
+void HELPER(NAME)(void *vd, void *vj, void *vk, uint32_t v)                   \
+{                                                                             \
+    int i;                                                                    \
+    VReg *Vd = (VReg *)vd;                                                    \
+    VReg *Vj = (VReg *)vj;                                                    \
+    VReg *Vk = (VReg *)vk;                                                    \
+    typedef __typeof(Vd->ES1(0)) TDS;                                         \
+    typedef __typeof(Vd->EU1(0)) TDU;                                         \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                                       \
+        Vd->ES1(i) = DO_OP((TDU)Vj->EU2(2 * i + 1), (TDS)Vk->ES2(2 * i + 1)); \
+    }                                                                         \
+}
+
+void HELPER(vaddwev_q_du_d)(void *vd, void *vj, void *vk, uint32_t v)
+{
+    VReg *Vd = (VReg *)vd;
+    VReg *Vj = (VReg *)vj;
+    VReg *Vk = (VReg *)vk;
+
+    Vd->Q(0) = int128_add(int128_make64((uint64_t)Vj->D(0)),
+                          int128_makes64(Vk->D(0)));
+}
+
+DO_EVEN_U_S(vaddwev_h_bu_b, 16, H, UH, B, UB, DO_ADD)
+DO_EVEN_U_S(vaddwev_w_hu_h, 32, W, UW, H, UH, DO_ADD)
+DO_EVEN_U_S(vaddwev_d_wu_w, 64, D, UD, W, UW, DO_ADD)
+
+void HELPER(vaddwod_q_du_d)(void *vd, void *vj, void *vk, uint32_t v)
+{
+    VReg *Vd = (VReg *)vd;
+    VReg *Vj = (VReg *)vj;
+    VReg *Vk = (VReg *)vk;
+
+    Vd->Q(0) = int128_add(int128_make64((uint64_t)Vj->D(1)),
+                          int128_makes64(Vk->D(1)));
+}
+
+DO_ODD_U_S(vaddwod_h_bu_b, 16, H, UH, B, UB, DO_ADD)
+DO_ODD_U_S(vaddwod_w_hu_h, 32, W, UW, H, UH, DO_ADD)
+DO_ODD_U_S(vaddwod_d_wu_w, 64, D, UD, W, UW, DO_ADD)
+
+#define DO_VAVG(a, b)  ((a >> 1) + (b >> 1) + (a & b & 1))
+#define DO_VAVGR(a, b) ((a >> 1) + (b >> 1) + ((a | b) & 1))
+
+#define DO_3OP(NAME, BIT, E, DO_OP)                         \
+void HELPER(NAME)(void *vd, void *vj, void *vk, uint32_t v) \
+{                                                           \
+    int i;                                                  \
+    VReg *Vd = (VReg *)vd;                                  \
+    VReg *Vj = (VReg *)vj;                                  \
+    VReg *Vk = (VReg *)vk;                                  \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                     \
+        Vd->E(i) = DO_OP(Vj->E(i), Vk->E(i));               \
+    }                                                       \
+}
+
+DO_3OP(vavg_b, 8, B, DO_VAVG)
+DO_3OP(vavg_h, 16, H, DO_VAVG)
+DO_3OP(vavg_w, 32, W, DO_VAVG)
+DO_3OP(vavg_d, 64, D, DO_VAVG)
+DO_3OP(vavgr_b, 8, B, DO_VAVGR)
+DO_3OP(vavgr_h, 16, H, DO_VAVGR)
+DO_3OP(vavgr_w, 32, W, DO_VAVGR)
+DO_3OP(vavgr_d, 64, D, DO_VAVGR)
+DO_3OP(vavg_bu, 8, UB, DO_VAVG)
+DO_3OP(vavg_hu, 16, UH, DO_VAVG)
+DO_3OP(vavg_wu, 32, UW, DO_VAVG)
+DO_3OP(vavg_du, 64, UD, DO_VAVG)
+DO_3OP(vavgr_bu, 8, UB, DO_VAVGR)
+DO_3OP(vavgr_hu, 16, UH, DO_VAVGR)
+DO_3OP(vavgr_wu, 32, UW, DO_VAVGR)
+DO_3OP(vavgr_du, 64, UD, DO_VAVGR)
+
+#define DO_VABSD(a, b)  ((a > b) ? (a -b) : (b-a))
+
+DO_3OP(vabsd_b, 8, B, DO_VABSD)
+DO_3OP(vabsd_h, 16, H, DO_VABSD)
+DO_3OP(vabsd_w, 32, W, DO_VABSD)
+DO_3OP(vabsd_d, 64, D, DO_VABSD)
+DO_3OP(vabsd_bu, 8, UB, DO_VABSD)
+DO_3OP(vabsd_hu, 16, UH, DO_VABSD)
+DO_3OP(vabsd_wu, 32, UW, DO_VABSD)
+DO_3OP(vabsd_du, 64, UD, DO_VABSD)
+
+#define DO_VABS(a)  ((a < 0) ? (-a) : (a))
+
+#define DO_VADDA(NAME, BIT, E, DO_OP)                       \
+void HELPER(NAME)(void *vd, void *vj, void *vk, uint32_t v) \
+{                                                           \
+    int i;                                                  \
+    VReg *Vd = (VReg *)vd;                                  \
+    VReg *Vj = (VReg *)vj;                                  \
+    VReg *Vk = (VReg *)vk;                                  \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                     \
+        Vd->E(i) = DO_OP(Vj->E(i)) + DO_OP(Vk->E(i));       \
+    }                                                       \
+}
+
+DO_VADDA(vadda_b, 8, B, DO_VABS)
+DO_VADDA(vadda_h, 16, H, DO_VABS)
+DO_VADDA(vadda_w, 32, W, DO_VABS)
+DO_VADDA(vadda_d, 64, D, DO_VABS)
+
+#define DO_MIN(a, b) (a < b ? a : b)
+#define DO_MAX(a, b) (a > b ? a : b)
+
+#define VMINMAXI(NAME, BIT, E, DO_OP)                           \
+void HELPER(NAME)(void *vd, void *vj, uint64_t imm, uint32_t v) \
+{                                                               \
+    int i;                                                      \
+    VReg *Vd = (VReg *)vd;                                      \
+    VReg *Vj = (VReg *)vj;                                      \
+    typedef __typeof(Vd->E(0)) TD;                              \
+                                                                \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                         \
+        Vd->E(i) = DO_OP(Vj->E(i), (TD)imm);                    \
+    }                                                           \
+}
+
+VMINMAXI(vmini_b, 8, B, DO_MIN)
+VMINMAXI(vmini_h, 16, H, DO_MIN)
+VMINMAXI(vmini_w, 32, W, DO_MIN)
+VMINMAXI(vmini_d, 64, D, DO_MIN)
+VMINMAXI(vmaxi_b, 8, B, DO_MAX)
+VMINMAXI(vmaxi_h, 16, H, DO_MAX)
+VMINMAXI(vmaxi_w, 32, W, DO_MAX)
+VMINMAXI(vmaxi_d, 64, D, DO_MAX)
+VMINMAXI(vmini_bu, 8, UB, DO_MIN)
+VMINMAXI(vmini_hu, 16, UH, DO_MIN)
+VMINMAXI(vmini_wu, 32, UW, DO_MIN)
+VMINMAXI(vmini_du, 64, UD, DO_MIN)
+VMINMAXI(vmaxi_bu, 8, UB, DO_MAX)
+VMINMAXI(vmaxi_hu, 16, UH, DO_MAX)
+VMINMAXI(vmaxi_wu, 32, UW, DO_MAX)
+VMINMAXI(vmaxi_du, 64, UD, DO_MAX)
+
+#define DO_VMUH(NAME, BIT, E1, E2, DO_OP)                   \
+void HELPER(NAME)(void *vd, void *vj, void *vk, uint32_t v) \
+{                                                           \
+    int i;                                                  \
+    VReg *Vd = (VReg *)vd;                                  \
+    VReg *Vj = (VReg *)vj;                                  \
+    VReg *Vk = (VReg *)vk;                                  \
+    typedef __typeof(Vd->E1(0)) T;                          \
+                                                            \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                     \
+        Vd->E2(i) = ((T)Vj->E2(i)) * ((T)Vk->E2(i)) >> BIT; \
+    }                                                       \
+}
+
+void HELPER(vmuh_d)(void *vd, void *vj, void *vk, uint32_t v)
+{
+    uint64_t l, h1, h2;
+    VReg *Vd = (VReg *)vd;
+    VReg *Vj = (VReg *)vj;
+    VReg *Vk = (VReg *)vk;
+
+    muls64(&l, &h1, Vj->D(0), Vk->D(0));
+    muls64(&l, &h2, Vj->D(1), Vk->D(1));
+
+    Vd->D(0) = h1;
+    Vd->D(1) = h2;
+}
+
+DO_VMUH(vmuh_b, 8, H, B, DO_MUH)
+DO_VMUH(vmuh_h, 16, W, H, DO_MUH)
+DO_VMUH(vmuh_w, 32, D, W, DO_MUH)
+
+void HELPER(vmuh_du)(void *vd, void *vj, void *vk, uint32_t v)
+{
+    uint64_t l, h1, h2;
+    VReg *Vd = (VReg *)vd;
+    VReg *Vj = (VReg *)vj;
+    VReg *Vk = (VReg *)vk;
+
+    mulu64(&l, &h1, Vj->D(0), Vk->D(0));
+    mulu64(&l, &h2, Vj->D(1), Vk->D(1));
+
+    Vd->D(0) = h1;
+    Vd->D(1) = h2;
+}
+
+DO_VMUH(vmuh_bu, 8, UH, UB, DO_MUH)
+DO_VMUH(vmuh_hu, 16, UW, UH, DO_MUH)
+DO_VMUH(vmuh_wu, 32, UD, UW, DO_MUH)
+
+#define DO_MUL(a, b) (a * b)
+
+DO_EVEN(vmulwev_h_b, 16, H, B, DO_MUL)
+DO_EVEN(vmulwev_w_h, 32, W, H, DO_MUL)
+DO_EVEN(vmulwev_d_w, 64, D, W, DO_MUL)
+
+DO_ODD(vmulwod_h_b, 16, H, B, DO_MUL)
+DO_ODD(vmulwod_w_h, 32, W, H, DO_MUL)
+DO_ODD(vmulwod_d_w, 64, D, W, DO_MUL)
+
+DO_EVEN(vmulwev_h_bu, 16, UH, UB, DO_MUL)
+DO_EVEN(vmulwev_w_hu, 32, UW, UH, DO_MUL)
+DO_EVEN(vmulwev_d_wu, 64, UD, UW, DO_MUL)
+
+DO_ODD(vmulwod_h_bu, 16, UH, UB, DO_MUL)
+DO_ODD(vmulwod_w_hu, 32, UW, UH, DO_MUL)
+DO_ODD(vmulwod_d_wu, 64, UD, UW, DO_MUL)
+
+DO_EVEN_U_S(vmulwev_h_bu_b, 16, H, UH, B, UB, DO_MUL)
+DO_EVEN_U_S(vmulwev_w_hu_h, 32, W, UW, H, UH, DO_MUL)
+DO_EVEN_U_S(vmulwev_d_wu_w, 64, D, UD, W, UW, DO_MUL)
+
+DO_ODD_U_S(vmulwod_h_bu_b, 16, H, UH, B, UB, DO_MUL)
+DO_ODD_U_S(vmulwod_w_hu_h, 32, W, UW, H, UH, DO_MUL)
+DO_ODD_U_S(vmulwod_d_wu_w, 64, D, UD, W, UW, DO_MUL)
+
+#define DO_MADD(a, b, c)  (a + b * c)
+#define DO_MSUB(a, b, c)  (a - b * c)
+
+#define VMADDSUB(NAME, BIT, E, DO_OP)                       \
+void HELPER(NAME)(void *vd, void *vj, void *vk, uint32_t v) \
+{                                                           \
+    int i;                                                  \
+    VReg *Vd = (VReg *)vd;                                  \
+    VReg *Vj = (VReg *)vj;                                  \
+    VReg *Vk = (VReg *)vk;                                  \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                     \
+        Vd->E(i) = DO_OP(Vd->E(i), Vj->E(i) ,Vk->E(i));     \
+    }                                                       \
+}
+
+VMADDSUB(vmadd_b, 8, B, DO_MADD)
+VMADDSUB(vmadd_h, 16, H, DO_MADD)
+VMADDSUB(vmadd_w, 32, W, DO_MADD)
+VMADDSUB(vmadd_d, 64, D, DO_MADD)
+VMADDSUB(vmsub_b, 8, B, DO_MSUB)
+VMADDSUB(vmsub_h, 16, H, DO_MSUB)
+VMADDSUB(vmsub_w, 32, W, DO_MSUB)
+VMADDSUB(vmsub_d, 64, D, DO_MSUB)
+
+#define VMADDWEV(NAME, BIT, E1, E2, DO_OP)                        \
+void HELPER(NAME)(void *vd, void *vj, void *vk, uint32_t v)       \
+{                                                                 \
+    int i;                                                        \
+    VReg *Vd = (VReg *)vd;                                        \
+    VReg *Vj = (VReg *)vj;                                        \
+    VReg *Vk = (VReg *)vk;                                        \
+    typedef __typeof(Vd->E1(0)) TD;                               \
+                                                                  \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                           \
+        Vd->E1(i) += DO_OP((TD)Vj->E2(2 * i), (TD)Vk->E2(2 * i)); \
+    }                                                             \
+}
+
+VMADDWEV(vmaddwev_h_b, 16, H, B, DO_MUL)
+VMADDWEV(vmaddwev_w_h, 32, W, H, DO_MUL)
+VMADDWEV(vmaddwev_d_w, 64, D, W, DO_MUL)
+VMADDWEV(vmaddwev_h_bu, 16, UH, UB, DO_MUL)
+VMADDWEV(vmaddwev_w_hu, 32, UW, UH, DO_MUL)
+VMADDWEV(vmaddwev_d_wu, 64, UD, UW, DO_MUL)
+
+#define VMADDWOD(NAME, BIT, E1, E2, DO_OP)                  \
+void HELPER(NAME)(void *vd, void *vj, void *vk, uint32_t v) \
+{                                                           \
+    int i;                                                  \
+    VReg *Vd = (VReg *)vd;                                  \
+    VReg *Vj = (VReg *)vj;                                  \
+    VReg *Vk = (VReg *)vk;                                  \
+    typedef __typeof(Vd->E1(0)) TD;                         \
+                                                            \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                     \
+        Vd->E1(i) += DO_OP((TD)Vj->E2(2 * i + 1),           \
+                           (TD)Vk->E2(2 * i + 1));          \
+    }                                                       \
+}
+
+VMADDWOD(vmaddwod_h_b, 16, H, B, DO_MUL)
+VMADDWOD(vmaddwod_w_h, 32, W, H, DO_MUL)
+VMADDWOD(vmaddwod_d_w, 64, D, W, DO_MUL)
+VMADDWOD(vmaddwod_h_bu, 16,  UH, UB, DO_MUL)
+VMADDWOD(vmaddwod_w_hu, 32,  UW, UH, DO_MUL)
+VMADDWOD(vmaddwod_d_wu, 64,  UD, UW, DO_MUL)
+
+#define VMADDWEV_U_S(NAME, BIT, ES1, EU1, ES2, EU2, DO_OP)  \
+void HELPER(NAME)(void *vd, void *vj, void *vk, uint32_t v) \
+{                                                           \
+    int i;                                                  \
+    VReg *Vd = (VReg *)vd;                                  \
+    VReg *Vj = (VReg *)vj;                                  \
+    VReg *Vk = (VReg *)vk;                                  \
+    typedef __typeof(Vd->ES1(0)) TS1;                       \
+    typedef __typeof(Vd->EU1(0)) TU1;                       \
+                                                            \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                     \
+        Vd->ES1(i) += DO_OP((TU1)Vj->EU2(2 * i),            \
+                            (TS1)Vk->ES2(2 * i));           \
+    }                                                       \
+}
+
+VMADDWEV_U_S(vmaddwev_h_bu_b, 16, H, UH, B, UB, DO_MUL)
+VMADDWEV_U_S(vmaddwev_w_hu_h, 32, W, UW, H, UH, DO_MUL)
+VMADDWEV_U_S(vmaddwev_d_wu_w, 64, D, UD, W, UW, DO_MUL)
+
+#define VMADDWOD_U_S(NAME, BIT, ES1, EU1, ES2, EU2, DO_OP)  \
+void HELPER(NAME)(void *vd, void *vj, void *vk, uint32_t v) \
+{                                                           \
+    int i;                                                  \
+    VReg *Vd = (VReg *)vd;                                  \
+    VReg *Vj = (VReg *)vj;                                  \
+    VReg *Vk = (VReg *)vk;                                  \
+    typedef __typeof(Vd->ES1(0)) TS1;                       \
+    typedef __typeof(Vd->EU1(0)) TU1;                       \
+                                                            \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                     \
+        Vd->ES1(i) += DO_OP((TU1)Vj->EU2(2 * i + 1),         \
+                            (TS1)Vk->ES2(2 * i + 1));        \
+    }                                                       \
+}
+
+VMADDWOD_U_S(vmaddwod_h_bu_b, 16, H, UH, B, UB, DO_MUL)
+VMADDWOD_U_S(vmaddwod_w_hu_h, 32, W, UW, H, UH, DO_MUL)
+VMADDWOD_U_S(vmaddwod_d_wu_w, 64, D, UD, W, UW, DO_MUL)
+
+#define DO_DIVU(N, M) (unlikely(M == 0) ? 0 : N / M)
+#define DO_REMU(N, M) (unlikely(M == 0) ? 0 : N % M)
+#define DO_DIV(N, M)  (unlikely(M == 0) ? 0 :\
+        unlikely((N == -N) && (M == (__typeof(N))(-1))) ? N : N / M)
+#define DO_REM(N, M)  (unlikely(M == 0) ? 0 :\
+        unlikely((N == -N) && (M == (__typeof(N))(-1))) ? 0 : N % M)
+
+#define VDIV(NAME, BIT, E, DO_OP)                           \
+void HELPER(NAME)(CPULoongArchState *env,                   \
+                  uint32_t vd, uint32_t vj, uint32_t vk)    \
+{                                                           \
+    int i;                                                  \
+    VReg *Vd = &(env->fpr[vd].vreg);                        \
+    VReg *Vj = &(env->fpr[vj].vreg);                        \
+    VReg *Vk = &(env->fpr[vk].vreg);                        \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                     \
+        Vd->E(i) = DO_OP(Vj->E(i), Vk->E(i));               \
+    }                                                       \
+}
+
+VDIV(vdiv_b, 8, B, DO_DIV)
+VDIV(vdiv_h, 16, H, DO_DIV)
+VDIV(vdiv_w, 32, W, DO_DIV)
+VDIV(vdiv_d, 64, D, DO_DIV)
+VDIV(vdiv_bu, 8, UB, DO_DIVU)
+VDIV(vdiv_hu, 16, UH, DO_DIVU)
+VDIV(vdiv_wu, 32, UW, DO_DIVU)
+VDIV(vdiv_du, 64, UD, DO_DIVU)
+VDIV(vmod_b, 8, B, DO_REM)
+VDIV(vmod_h, 16, H, DO_REM)
+VDIV(vmod_w, 32, W, DO_REM)
+VDIV(vmod_d, 64, D, DO_REM)
+VDIV(vmod_bu, 8, UB, DO_REMU)
+VDIV(vmod_hu, 16, UH, DO_REMU)
+VDIV(vmod_wu, 32, UW, DO_REMU)
+VDIV(vmod_du, 64, UD, DO_REMU)
+
+#define VSAT_S(NAME, BIT, E)                                    \
+void HELPER(NAME)(void *vd, void *vj, uint64_t max, uint32_t v) \
+{                                                               \
+    int i;                                                      \
+    VReg *Vd = (VReg *)vd;                                      \
+    VReg *Vj = (VReg *)vj;                                      \
+    typedef __typeof(Vd->E(0)) TD;                              \
+                                                                \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                         \
+        Vd->E(i) = Vj->E(i) > (TD)max ? (TD)max :               \
+                   Vj->E(i) < (TD)~max ? (TD)~max: Vj->E(i);    \
+    }                                                           \
+}
+
+VSAT_S(vsat_b, 8, B)
+VSAT_S(vsat_h, 16, H)
+VSAT_S(vsat_w, 32, W)
+VSAT_S(vsat_d, 64, D)
+
+#define VSAT_U(NAME, BIT, E)                                    \
+void HELPER(NAME)(void *vd, void *vj, uint64_t max, uint32_t v) \
+{                                                               \
+    int i;                                                      \
+    VReg *Vd = (VReg *)vd;                                      \
+    VReg *Vj = (VReg *)vj;                                      \
+    typedef __typeof(Vd->E(0)) TD;                              \
+                                                                \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                         \
+        Vd->E(i) = Vj->E(i) > (TD)max ? (TD)max : Vj->E(i);     \
+    }                                                           \
+}
+
+VSAT_U(vsat_bu, 8, UB)
+VSAT_U(vsat_hu, 16, UH)
+VSAT_U(vsat_wu, 32, UW)
+VSAT_U(vsat_du, 64, UD)
+
+#define VEXTH(NAME, BIT, E1, E2)                                    \
+void HELPER(NAME)(CPULoongArchState *env, uint32_t vd, uint32_t vj) \
+{                                                                   \
+    int i;                                                          \
+    VReg *Vd = &(env->fpr[vd].vreg);                                \
+    VReg *Vj = &(env->fpr[vj].vreg);                                \
+                                                                    \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                             \
+        Vd->E1(i) = Vj->E2(i + LSX_LEN/BIT);                        \
+    }                                                               \
+}
+
+void HELPER(vexth_q_d)(CPULoongArchState *env, uint32_t vd, uint32_t vj)
+{
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    Vd->Q(0) = int128_makes64(Vj->D(1));
+}
+
+void HELPER(vexth_qu_du)(CPULoongArchState *env, uint32_t vd, uint32_t vj)
+{
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    Vd->Q(0) = int128_make64((uint64_t)Vj->D(1));
+}
+
+VEXTH(vexth_h_b, 16, H, B)
+VEXTH(vexth_w_h, 32, W, H)
+VEXTH(vexth_d_w, 64, D, W)
+VEXTH(vexth_hu_bu, 16, UH, UB)
+VEXTH(vexth_wu_hu, 32, UW, UH)
+VEXTH(vexth_du_wu, 64, UD, UW)
+
+#define DO_SIGNCOV(a, b)  (a == 0 ? 0 : a < 0 ? -b : b)
+
+DO_3OP(vsigncov_b, 8, B, DO_SIGNCOV)
+DO_3OP(vsigncov_h, 16, H, DO_SIGNCOV)
+DO_3OP(vsigncov_w, 32, W, DO_SIGNCOV)
+DO_3OP(vsigncov_d, 64, D, DO_SIGNCOV)
+
+static uint64_t do_vmskltz_b(int64_t val)
+{
+    uint64_t m = 0x8080808080808080ULL;
+    uint64_t c =  val & m;
+    c |= c << 7;
+    c |= c << 14;
+    c |= c << 28;
+    return c >> 56;
+}
+
+void HELPER(vmskltz_b)(CPULoongArchState *env, uint32_t vd, uint32_t vj)
+{
+    uint16_t temp = 0;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    temp = do_vmskltz_b(Vj->D(0));
+    temp |= (do_vmskltz_b(Vj->D(1)) << 8);
+    Vd->D(0) = temp;
+    Vd->D(1) = 0;
+}
+
+static uint64_t do_vmskltz_h(int64_t val)
+{
+    uint64_t m = 0x8000800080008000ULL;
+    uint64_t c =  val & m;
+    c |= c << 15;
+    c |= c << 30;
+    return c >> 60;
+}
+
+void HELPER(vmskltz_h)(CPULoongArchState *env, uint32_t vd, uint32_t vj)
+{
+    uint16_t temp = 0;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    temp = do_vmskltz_h(Vj->D(0));
+    temp |= (do_vmskltz_h(Vj->D(1)) << 4);
+    Vd->D(0) = temp;
+    Vd->D(1) = 0;
+}
+
+static uint64_t do_vmskltz_w(int64_t val)
+{
+    uint64_t m = 0x8000000080000000ULL;
+    uint64_t c =  val & m;
+    c |= c << 31;
+    return c >> 62;
+}
+
+void HELPER(vmskltz_w)(CPULoongArchState *env, uint32_t vd, uint32_t vj)
+{
+    uint16_t temp = 0;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    temp = do_vmskltz_w(Vj->D(0));
+    temp |= (do_vmskltz_w(Vj->D(1)) << 2);
+    Vd->D(0) = temp;
+    Vd->D(1) = 0;
+}
+
+static uint64_t do_vmskltz_d(int64_t val)
+{
+    return (uint64_t)val >> 63;
+}
+void HELPER(vmskltz_d)(CPULoongArchState *env, uint32_t vd, uint32_t vj)
+{
+    uint16_t temp = 0;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    temp = do_vmskltz_d(Vj->D(0));
+    temp |= (do_vmskltz_d(Vj->D(1)) << 1);
+    Vd->D(0) = temp;
+    Vd->D(1) = 0;
+}
+
+void HELPER(vmskgez_b)(CPULoongArchState *env, uint32_t vd, uint32_t vj)
+{
+    uint16_t temp = 0;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    temp =  do_vmskltz_b(Vj->D(0));
+    temp |= (do_vmskltz_b(Vj->D(1)) << 8);
+    Vd->D(0) = (uint16_t)(~temp);
+    Vd->D(1) = 0;
+}
+
+static uint64_t do_vmskez_b(uint64_t a)
+{
+    uint64_t m = 0x7f7f7f7f7f7f7f7fULL;
+    uint64_t c = ~(((a & m) + m) | a | m);
+    c |= c << 7;
+    c |= c << 14;
+    c |= c << 28;
+    return c >> 56;
+}
+
+void HELPER(vmsknz_b)(CPULoongArchState *env, uint32_t vd, uint32_t vj)
+{
+    uint16_t temp = 0;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    temp = do_vmskez_b(Vj->D(0));
+    temp |= (do_vmskez_b(Vj->D(1)) << 8);
+    Vd->D(0) = (uint16_t)(~temp);
+    Vd->D(1) = 0;
+}
+
+void HELPER(vnori_b)(void *vd, void *vj, uint64_t imm, uint32_t v)
+{
+    int i;
+    VReg *Vd = (VReg *)vd;
+    VReg *Vj = (VReg *)vj;
+
+    for (i = 0; i < LSX_LEN/8; i++) {
+        Vd->B(i) = ~(Vj->B(i) | (uint8_t)imm);
+    }
+}
+
+#define VSLLWIL(NAME, BIT, E1, E2)                        \
+void HELPER(NAME)(CPULoongArchState *env,                 \
+                  uint32_t vd, uint32_t vj, uint32_t imm) \
+{                                                         \
+    int i;                                                \
+    VReg temp;                                            \
+    VReg *Vd = &(env->fpr[vd].vreg);                      \
+    VReg *Vj = &(env->fpr[vj].vreg);                      \
+    typedef __typeof(temp.E1(0)) TD;                      \
+                                                          \
+    temp.D(0) = 0;                                        \
+    temp.D(1) = 0;                                        \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                   \
+        temp.E1(i) = (TD)Vj->E2(i) << (imm % BIT);        \
+    }                                                     \
+    *Vd = temp;                                           \
+}
+
+void HELPER(vextl_q_d)(CPULoongArchState *env, uint32_t vd, uint32_t vj)
+{
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    Vd->Q(0) = int128_makes64(Vj->D(0));
+}
+
+void HELPER(vextl_qu_du)(CPULoongArchState *env, uint32_t vd, uint32_t vj)
+{
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    Vd->Q(0) = int128_make64(Vj->D(0));
+}
+
+VSLLWIL(vsllwil_h_b, 16, H, B)
+VSLLWIL(vsllwil_w_h, 32, W, H)
+VSLLWIL(vsllwil_d_w, 64, D, W)
+VSLLWIL(vsllwil_hu_bu, 16, UH, UB)
+VSLLWIL(vsllwil_wu_hu, 32, UW, UH)
+VSLLWIL(vsllwil_du_wu, 64, UD, UW)
+
+#define do_vsrlr(E, T)                                  \
+static T do_vsrlr_ ##E(T s1, int sh)                    \
+{                                                       \
+    if (sh == 0) {                                      \
+        return s1;                                      \
+    } else {                                            \
+        return  (s1 >> sh)  + ((s1 >> (sh - 1)) & 0x1); \
+    }                                                   \
+}
+
+do_vsrlr(B, uint8_t)
+do_vsrlr(H, uint16_t)
+do_vsrlr(W, uint32_t)
+do_vsrlr(D, uint64_t)
+
+#define VSRLR(NAME, BIT, T, E)                                  \
+void HELPER(NAME)(CPULoongArchState *env,                       \
+                  uint32_t vd, uint32_t vj, uint32_t vk)        \
+{                                                               \
+    int i;                                                      \
+    VReg *Vd = &(env->fpr[vd].vreg);                            \
+    VReg *Vj = &(env->fpr[vj].vreg);                            \
+    VReg *Vk = &(env->fpr[vk].vreg);                            \
+                                                                \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                         \
+        Vd->E(i) = do_vsrlr_ ## E(Vj->E(i), ((T)Vk->E(i))%BIT); \
+    }                                                           \
+}
+
+VSRLR(vsrlr_b, 8,  uint8_t, B)
+VSRLR(vsrlr_h, 16, uint16_t, H)
+VSRLR(vsrlr_w, 32, uint32_t, W)
+VSRLR(vsrlr_d, 64, uint64_t, D)
+
+#define VSRLRI(NAME, BIT, E)                              \
+void HELPER(NAME)(CPULoongArchState *env,                 \
+                  uint32_t vd, uint32_t vj, uint32_t imm) \
+{                                                         \
+    int i;                                                \
+    VReg *Vd = &(env->fpr[vd].vreg);                      \
+    VReg *Vj = &(env->fpr[vj].vreg);                      \
+                                                          \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                   \
+        Vd->E(i) = do_vsrlr_ ## E(Vj->E(i), imm);         \
+    }                                                     \
+}
+
+VSRLRI(vsrlri_b, 8, B)
+VSRLRI(vsrlri_h, 16, H)
+VSRLRI(vsrlri_w, 32, W)
+VSRLRI(vsrlri_d, 64, D)
+
+#define do_vsrar(E, T)                                  \
+static T do_vsrar_ ##E(T s1, int sh)                    \
+{                                                       \
+    if (sh == 0) {                                      \
+        return s1;                                      \
+    } else {                                            \
+        return  (s1 >> sh)  + ((s1 >> (sh - 1)) & 0x1); \
+    }                                                   \
+}
+
+do_vsrar(B, int8_t)
+do_vsrar(H, int16_t)
+do_vsrar(W, int32_t)
+do_vsrar(D, int64_t)
+
+#define VSRAR(NAME, BIT, T, E)                                  \
+void HELPER(NAME)(CPULoongArchState *env,                       \
+                  uint32_t vd, uint32_t vj, uint32_t vk)        \
+{                                                               \
+    int i;                                                      \
+    VReg *Vd = &(env->fpr[vd].vreg);                            \
+    VReg *Vj = &(env->fpr[vj].vreg);                            \
+    VReg *Vk = &(env->fpr[vk].vreg);                            \
+                                                                \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                         \
+        Vd->E(i) = do_vsrar_ ## E(Vj->E(i), ((T)Vk->E(i))%BIT); \
+    }                                                           \
+}
+
+VSRAR(vsrar_b, 8,  uint8_t, B)
+VSRAR(vsrar_h, 16, uint16_t, H)
+VSRAR(vsrar_w, 32, uint32_t, W)
+VSRAR(vsrar_d, 64, uint64_t, D)
+
+#define VSRARI(NAME, BIT, E)                              \
+void HELPER(NAME)(CPULoongArchState *env,                 \
+                  uint32_t vd, uint32_t vj, uint32_t imm) \
+{                                                         \
+    int i;                                                \
+    VReg *Vd = &(env->fpr[vd].vreg);                      \
+    VReg *Vj = &(env->fpr[vj].vreg);                      \
+                                                          \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                   \
+        Vd->E(i) = do_vsrar_ ## E(Vj->E(i), imm);         \
+    }                                                     \
+}
+
+VSRARI(vsrari_b, 8, B)
+VSRARI(vsrari_h, 16, H)
+VSRARI(vsrari_w, 32, W)
+VSRARI(vsrari_d, 64, D)
+
+#define R_SHIFT(a, b) (a >> b)
+
+#define VSRLN(NAME, BIT, T, E1, E2)                             \
+void HELPER(NAME)(CPULoongArchState *env,                       \
+                  uint32_t vd, uint32_t vj, uint32_t vk)        \
+{                                                               \
+    int i;                                                      \
+    VReg *Vd = &(env->fpr[vd].vreg);                            \
+    VReg *Vj = &(env->fpr[vj].vreg);                            \
+    VReg *Vk = &(env->fpr[vk].vreg);                            \
+                                                                \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                         \
+        Vd->E1(i) = R_SHIFT((T)Vj->E2(i),((T)Vk->E2(i)) % BIT); \
+    }                                                           \
+    Vd->D(1) = 0;                                               \
+}
+
+VSRLN(vsrln_b_h, 16, uint16_t, B, H)
+VSRLN(vsrln_h_w, 32, uint32_t, H, W)
+VSRLN(vsrln_w_d, 64, uint64_t, W, D)
+
+#define VSRAN(NAME, BIT, T, E1, E2)                           \
+void HELPER(NAME)(CPULoongArchState *env,                     \
+                  uint32_t vd, uint32_t vj, uint32_t vk)      \
+{                                                             \
+    int i;                                                    \
+    VReg *Vd = &(env->fpr[vd].vreg);                          \
+    VReg *Vj = &(env->fpr[vj].vreg);                          \
+    VReg *Vk = &(env->fpr[vk].vreg);                          \
+                                                              \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                       \
+        Vd->E1(i) = R_SHIFT(Vj->E2(i), ((T)Vk->E2(i)) % BIT); \
+    }                                                         \
+    Vd->D(1) = 0;                                             \
+}
+
+VSRAN(vsran_b_h, 16, uint16_t, B, H)
+VSRAN(vsran_h_w, 32, uint32_t, H, W)
+VSRAN(vsran_w_d, 64, uint64_t, W, D)
+
+#define VSRLNI(NAME, BIT, T, E1, E2)                         \
+void HELPER(NAME)(CPULoongArchState *env,                    \
+                  uint32_t vd, uint32_t vj, uint32_t imm)    \
+{                                                            \
+    int i, max;                                              \
+    VReg temp;                                               \
+    VReg *Vd = &(env->fpr[vd].vreg);                         \
+    VReg *Vj = &(env->fpr[vj].vreg);                         \
+                                                             \
+    temp.D(0) = 0;                                           \
+    temp.D(1) = 0;                                           \
+    max = LSX_LEN/BIT;                                       \
+    for (i = 0; i < max; i++) {                              \
+        temp.E1(i) = R_SHIFT((T)Vj->E2(i), imm);             \
+        temp.E1(i + max) = R_SHIFT((T)Vd->E2(i), imm);       \
+    }                                                        \
+    *Vd = temp;                                              \
+}
+
+void HELPER(vsrlni_d_q)(CPULoongArchState *env,
+                        uint32_t vd, uint32_t vj, uint32_t imm)
+{
+    VReg temp;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    temp.D(0) = 0;
+    temp.D(1) = 0;
+    temp.D(0) = int128_getlo(int128_urshift(Vj->Q(0), imm % 128));
+    temp.D(1) = int128_getlo(int128_urshift(Vd->Q(0), imm % 128));
+    *Vd = temp;
+}
+
+VSRLNI(vsrlni_b_h, 16, uint16_t, B, H)
+VSRLNI(vsrlni_h_w, 32, uint32_t, H, W)
+VSRLNI(vsrlni_w_d, 64, uint64_t, W, D)
+
+#define VSRANI(NAME, BIT, E1, E2)                         \
+void HELPER(NAME)(CPULoongArchState *env,                 \
+                  uint32_t vd, uint32_t vj, uint32_t imm) \
+{                                                         \
+    int i, max;                                           \
+    VReg temp;                                            \
+    VReg *Vd = &(env->fpr[vd].vreg);                      \
+    VReg *Vj = &(env->fpr[vj].vreg);                      \
+                                                          \
+    temp.D(0) = 0;                                        \
+    temp.D(1) = 0;                                        \
+    max = LSX_LEN/BIT;                                    \
+    for (i = 0; i < max; i++) {                           \
+        temp.E1(i) = R_SHIFT(Vj->E2(i), imm);             \
+        temp.E1(i + max) = R_SHIFT(Vd->E2(i), imm);       \
+    }                                                     \
+    *Vd = temp;                                           \
+}
+
+void HELPER(vsrani_d_q)(CPULoongArchState *env,
+                        uint32_t vd, uint32_t vj, uint32_t imm)
+{
+    VReg temp;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    temp.D(0) = 0;
+    temp.D(1) = 0;
+    temp.D(0) = int128_getlo(int128_rshift(Vj->Q(0), imm % 128));
+    temp.D(1) = int128_getlo(int128_rshift(Vd->Q(0), imm % 128));
+    *Vd = temp;
+}
+
+VSRANI(vsrani_b_h, 16, B, H)
+VSRANI(vsrani_h_w, 32, H, W)
+VSRANI(vsrani_w_d, 64, W, D)
+
+#define VSRLRN(NAME, BIT, T, E1, E2)                                \
+void HELPER(NAME)(CPULoongArchState *env,                           \
+                  uint32_t vd, uint32_t vj, uint32_t vk)            \
+{                                                                   \
+    int i;                                                          \
+    VReg *Vd = &(env->fpr[vd].vreg);                                \
+    VReg *Vj = &(env->fpr[vj].vreg);                                \
+    VReg *Vk = &(env->fpr[vk].vreg);                                \
+                                                                    \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                             \
+        Vd->E1(i) = do_vsrlr_ ## E2(Vj->E2(i), ((T)Vk->E2(i))%BIT); \
+    }                                                               \
+    Vd->D(1) = 0;                                                   \
+}
+
+VSRLRN(vsrlrn_b_h, 16, uint16_t, B, H)
+VSRLRN(vsrlrn_h_w, 32, uint32_t, H, W)
+VSRLRN(vsrlrn_w_d, 64, uint64_t, W, D)
+
+#define VSRARN(NAME, BIT, T, E1, E2)                                \
+void HELPER(NAME)(CPULoongArchState *env,                           \
+                  uint32_t vd, uint32_t vj, uint32_t vk)            \
+{                                                                   \
+    int i;                                                          \
+    VReg *Vd = &(env->fpr[vd].vreg);                                \
+    VReg *Vj = &(env->fpr[vj].vreg);                                \
+    VReg *Vk = &(env->fpr[vk].vreg);                                \
+                                                                    \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                             \
+        Vd->E1(i) = do_vsrar_ ## E2(Vj->E2(i), ((T)Vk->E2(i))%BIT); \
+    }                                                               \
+    Vd->D(1) = 0;                                                   \
+}
+
+VSRARN(vsrarn_b_h, 16, uint8_t,  B, H)
+VSRARN(vsrarn_h_w, 32, uint16_t, H, W)
+VSRARN(vsrarn_w_d, 64, uint32_t, W, D)
+
+#define VSRLRNI(NAME, BIT, E1, E2)                          \
+void HELPER(NAME)(CPULoongArchState *env,                   \
+                  uint32_t vd, uint32_t vj, uint32_t imm)   \
+{                                                           \
+    int i, max;                                             \
+    VReg temp;                                              \
+    VReg *Vd = &(env->fpr[vd].vreg);                        \
+    VReg *Vj = &(env->fpr[vj].vreg);                        \
+                                                            \
+    temp.D(0) = 0;                                          \
+    temp.D(1) = 0;                                          \
+    max = LSX_LEN/BIT;                                      \
+    for (i = 0; i < max; i++) {                             \
+        temp.E1(i) = do_vsrlr_ ## E2(Vj->E2(i), imm);       \
+        temp.E1(i + max) = do_vsrlr_ ## E2(Vd->E2(i), imm); \
+    }                                                       \
+    *Vd = temp;                                             \
+}
+
+void HELPER(vsrlrni_d_q)(CPULoongArchState *env,
+                         uint32_t vd, uint32_t vj, uint32_t imm)
+{
+    VReg temp;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+    Int128 r1, r2;
+
+    if (imm == 0) {
+        temp.D(0) = int128_getlo(Vj->Q(0));
+        temp.D(1) = int128_getlo(Vd->Q(0));
+    } else {
+        r1 = int128_and(int128_urshift(Vj->Q(0), (imm -1)), int128_one());
+        r2 = int128_and(int128_urshift(Vd->Q(0), (imm -1)), int128_one());
+
+       temp.D(0) = int128_getlo(int128_add(int128_urshift(Vj->Q(0), imm), r1));
+       temp.D(1) = int128_getlo(int128_add(int128_urshift(Vd->Q(0), imm), r2));
+    }
+    *Vd = temp;
+}
+
+VSRLRNI(vsrlrni_b_h, 16, B, H)
+VSRLRNI(vsrlrni_h_w, 32, H, W)
+VSRLRNI(vsrlrni_w_d, 64, W, D)
+
+#define VSRARNI(NAME, BIT, E1, E2)                          \
+void HELPER(NAME)(CPULoongArchState *env,                   \
+                  uint32_t vd, uint32_t vj, uint32_t imm)   \
+{                                                           \
+    int i, max;                                             \
+    VReg temp;                                              \
+    VReg *Vd = &(env->fpr[vd].vreg);                        \
+    VReg *Vj = &(env->fpr[vj].vreg);                        \
+                                                            \
+    temp.D(0) = 0;                                          \
+    temp.D(1) = 0;                                          \
+    max = LSX_LEN/BIT;                                      \
+    for (i = 0; i < max; i++) {                             \
+        temp.E1(i) = do_vsrar_ ## E2(Vj->E2(i), imm);       \
+        temp.E1(i + max) = do_vsrar_ ## E2(Vd->E2(i), imm); \
+    }                                                       \
+    *Vd = temp;                                             \
+}
+
+void HELPER(vsrarni_d_q)(CPULoongArchState *env,
+                         uint32_t vd, uint32_t vj, uint32_t imm)
+{
+    VReg temp;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+    Int128 r1, r2;
+
+    if (imm == 0) {
+        temp.D(0) = int128_getlo(Vj->Q(0));
+        temp.D(1) = int128_getlo(Vd->Q(0));
+    } else {
+        r1 = int128_and(int128_rshift(Vj->Q(0), (imm -1)), int128_one());
+        r2 = int128_and(int128_rshift(Vd->Q(0), (imm -1)), int128_one());
+
+       temp.D(0) = int128_getlo(int128_add(int128_rshift(Vj->Q(0), imm), r1));
+       temp.D(1) = int128_getlo(int128_add(int128_rshift(Vd->Q(0), imm), r2));
+    }
+    *Vd = temp;
+}
+
+VSRARNI(vsrarni_b_h, 16, B, H)
+VSRARNI(vsrarni_h_w, 32, H, W)
+VSRARNI(vsrarni_w_d, 64, W, D)
+
+#define SSRLNS(NAME, T1, T2, T3)                    \
+static T1 do_ssrlns_ ## NAME(T2 e2, int sa, int sh) \
+{                                                   \
+        T1 shft_res;                                \
+        if (sa == 0) {                              \
+            shft_res = e2;                          \
+        } else {                                    \
+            shft_res = (((T1)e2) >> sa);            \
+        }                                           \
+        T3 mask;                                    \
+        mask = (1ull << sh) -1;                     \
+        if (shft_res > mask) {                      \
+            return mask;                            \
+        } else {                                    \
+            return  shft_res;                       \
+        }                                           \
+}
+
+SSRLNS(B, uint16_t, int16_t, uint8_t)
+SSRLNS(H, uint32_t, int32_t, uint16_t)
+SSRLNS(W, uint64_t, int64_t, uint32_t)
+
+#define VSSRLN(NAME, BIT, T, E1, E2)                                          \
+void HELPER(NAME)(CPULoongArchState *env,                                     \
+                  uint32_t vd, uint32_t vj, uint32_t vk)                      \
+{                                                                             \
+    int i;                                                                    \
+    VReg *Vd = &(env->fpr[vd].vreg);                                          \
+    VReg *Vj = &(env->fpr[vj].vreg);                                          \
+    VReg *Vk = &(env->fpr[vk].vreg);                                          \
+                                                                              \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                                       \
+        Vd->E1(i) = do_ssrlns_ ## E1(Vj->E2(i), (T)Vk->E2(i)% BIT, BIT/2 -1); \
+    }                                                                         \
+    Vd->D(1) = 0;                                                             \
+}
+
+VSSRLN(vssrln_b_h, 16, uint16_t, B, H)
+VSSRLN(vssrln_h_w, 32, uint32_t, H, W)
+VSSRLN(vssrln_w_d, 64, uint64_t, W, D)
+
+#define SSRANS(E, T1, T2)                        \
+static T1 do_ssrans_ ## E(T1 e2, int sa, int sh) \
+{                                                \
+        T1 shft_res;                             \
+        if (sa == 0) {                           \
+            shft_res = e2;                       \
+        } else {                                 \
+            shft_res = e2 >> sa;                 \
+        }                                        \
+        T2 mask;                                 \
+        mask = (1ll << sh) -1;                   \
+        if (shft_res > mask) {                   \
+            return  mask;                        \
+        } else if (shft_res < -(mask +1)) {      \
+            return  ~mask;                       \
+        } else {                                 \
+            return shft_res;                     \
+        }                                        \
+}
+
+SSRANS(B, int16_t, int8_t)
+SSRANS(H, int32_t, int16_t)
+SSRANS(W, int64_t, int32_t)
+
+#define VSSRAN(NAME, BIT, T, E1, E2)                                         \
+void HELPER(NAME)(CPULoongArchState *env,                                    \
+                  uint32_t vd, uint32_t vj, uint32_t vk)                     \
+{                                                                            \
+    int i;                                                                   \
+    VReg *Vd = &(env->fpr[vd].vreg);                                         \
+    VReg *Vj = &(env->fpr[vj].vreg);                                         \
+    VReg *Vk = &(env->fpr[vk].vreg);                                         \
+                                                                             \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                                      \
+        Vd->E1(i) = do_ssrans_ ## E1(Vj->E2(i), (T)Vk->E2(i)%BIT, BIT/2 -1); \
+    }                                                                        \
+    Vd->D(1) = 0;                                                            \
+}
+
+VSSRAN(vssran_b_h, 16, uint16_t, B, H)
+VSSRAN(vssran_h_w, 32, uint32_t, H, W)
+VSSRAN(vssran_w_d, 64, uint64_t, W, D)
+
+#define SSRLNU(E, T1, T2, T3)                    \
+static T1 do_ssrlnu_ ## E(T3 e2, int sa, int sh) \
+{                                                \
+        T1 shft_res;                             \
+        if (sa == 0) {                           \
+            shft_res = e2;                       \
+        } else {                                 \
+            shft_res = (((T1)e2) >> sa);         \
+        }                                        \
+        T2 mask;                                 \
+        mask = (1ull << sh) -1;                  \
+        if (shft_res > mask) {                   \
+            return mask;                         \
+        } else {                                 \
+            return shft_res;                     \
+        }                                        \
+}
+
+SSRLNU(B, uint16_t, uint8_t,  int16_t)
+SSRLNU(H, uint32_t, uint16_t, int32_t)
+SSRLNU(W, uint64_t, uint32_t, int64_t)
+
+#define VSSRLNU(NAME, BIT, T, E1, E2)                                     \
+void HELPER(NAME)(CPULoongArchState *env,                                 \
+                  uint32_t vd, uint32_t vj, uint32_t vk)                  \
+{                                                                         \
+    int i;                                                                \
+    VReg *Vd = &(env->fpr[vd].vreg);                                      \
+    VReg *Vj = &(env->fpr[vj].vreg);                                      \
+    VReg *Vk = &(env->fpr[vk].vreg);                                      \
+                                                                          \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                                   \
+        Vd->E1(i) = do_ssrlnu_ ## E1(Vj->E2(i), (T)Vk->E2(i)%BIT, BIT/2); \
+    }                                                                     \
+    Vd->D(1) = 0;                                                         \
+}
+
+VSSRLNU(vssrln_bu_h, 16, uint16_t, B, H)
+VSSRLNU(vssrln_hu_w, 32, uint32_t, H, W)
+VSSRLNU(vssrln_wu_d, 64, uint64_t, W, D)
+
+#define SSRANU(E, T1, T2, T3)                    \
+static T1 do_ssranu_ ## E(T3 e2, int sa, int sh) \
+{                                                \
+        T1 shft_res;                             \
+        if (sa == 0) {                           \
+            shft_res = e2;                       \
+        } else {                                 \
+            shft_res = e2 >> sa;                 \
+        }                                        \
+        if (e2 < 0) {                            \
+            shft_res = 0;                        \
+        }                                        \
+        T2 mask;                                 \
+        mask = (1ull << sh) -1;                  \
+        if (shft_res > mask) {                   \
+            return mask;                         \
+        } else {                                 \
+            return shft_res;                     \
+        }                                        \
+}
+
+SSRANU(B, uint16_t, uint8_t,  int16_t)
+SSRANU(H, uint32_t, uint16_t, int32_t)
+SSRANU(W, uint64_t, uint32_t, int64_t)
+
+#define VSSRANU(NAME, BIT, T, E1, E2)                                     \
+void HELPER(NAME)(CPULoongArchState *env,                                 \
+                  uint32_t vd, uint32_t vj, uint32_t vk)                  \
+{                                                                         \
+    int i;                                                                \
+    VReg *Vd = &(env->fpr[vd].vreg);                                      \
+    VReg *Vj = &(env->fpr[vj].vreg);                                      \
+    VReg *Vk = &(env->fpr[vk].vreg);                                      \
+                                                                          \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                                   \
+        Vd->E1(i) = do_ssranu_ ## E1(Vj->E2(i), (T)Vk->E2(i)%BIT, BIT/2); \
+    }                                                                     \
+    Vd->D(1) = 0;                                                         \
+}
+
+VSSRANU(vssran_bu_h, 16, uint16_t, B, H)
+VSSRANU(vssran_hu_w, 32, uint32_t, H, W)
+VSSRANU(vssran_wu_d, 64, uint64_t, W, D)
+
+#define VSSRLNI(NAME, BIT, E1, E2)                                            \
+void HELPER(NAME)(CPULoongArchState *env,                                     \
+                  uint32_t vd, uint32_t vj, uint32_t imm)                     \
+{                                                                             \
+    int i;                                                                    \
+    VReg temp;                                                                \
+    VReg *Vd = &(env->fpr[vd].vreg);                                          \
+    VReg *Vj = &(env->fpr[vj].vreg);                                          \
+                                                                              \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                                       \
+        temp.E1(i) = do_ssrlns_ ## E1(Vj->E2(i), imm, BIT/2 -1);              \
+        temp.E1(i + LSX_LEN/BIT) = do_ssrlns_ ## E1(Vd->E2(i), imm, BIT/2 -1);\
+    }                                                                         \
+    *Vd = temp;                                                               \
+}
+
+void HELPER(vssrlni_d_q)(CPULoongArchState *env,
+                         uint32_t vd, uint32_t vj, uint32_t imm)
+{
+    Int128 shft_res1, shft_res2, mask;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    if (imm == 0) {
+        shft_res1 = Vj->Q(0);
+        shft_res2 = Vd->Q(0);
+    } else {
+        shft_res1 = int128_urshift(Vj->Q(0), imm);
+        shft_res2 = int128_urshift(Vd->Q(0), imm);
+    }
+    mask = int128_sub(int128_lshift(int128_one(), 63), int128_one());
+
+    if (int128_ult(mask, shft_res1)) {
+        Vd->D(0) = int128_getlo(mask);
+    }else {
+        Vd->D(0) = int128_getlo(shft_res1);
+    }
+
+    if (int128_ult(mask, shft_res2)) {
+        Vd->D(1) = int128_getlo(mask);
+    }else {
+        Vd->D(1) = int128_getlo(shft_res2);
+    }
+}
+
+VSSRLNI(vssrlni_b_h, 16, B, H)
+VSSRLNI(vssrlni_h_w, 32, H, W)
+VSSRLNI(vssrlni_w_d, 64, W, D)
+
+#define VSSRANI(NAME, BIT, E1, E2)                                             \
+void HELPER(NAME)(CPULoongArchState *env,                                      \
+                  uint32_t vd, uint32_t vj, uint32_t imm)                      \
+{                                                                              \
+    int i;                                                                     \
+    VReg temp;                                                                 \
+    VReg *Vd = &(env->fpr[vd].vreg);                                           \
+    VReg *Vj = &(env->fpr[vj].vreg);                                           \
+                                                                               \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                                        \
+        temp.E1(i) = do_ssrans_ ## E1(Vj->E2(i), imm, BIT/2 -1);               \
+        temp.E1(i + LSX_LEN/BIT) = do_ssrans_ ## E1(Vd->E2(i), imm, BIT/2 -1); \
+    }                                                                          \
+    *Vd = temp;                                                                \
+}
+
+void HELPER(vssrani_d_q)(CPULoongArchState *env,
+                         uint32_t vd, uint32_t vj, uint32_t imm)
+{
+    Int128 shft_res1, shft_res2, mask, min;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    if (imm == 0) {
+        shft_res1 = Vj->Q(0);
+        shft_res2 = Vd->Q(0);
+    } else {
+        shft_res1 = int128_rshift(Vj->Q(0), imm);
+        shft_res2 = int128_rshift(Vd->Q(0), imm);
+    }
+    mask = int128_sub(int128_lshift(int128_one(), 63), int128_one());
+    min  = int128_lshift(int128_one(), 63);
+
+    if (int128_gt(shft_res1,  mask)) {
+        Vd->D(0) = int128_getlo(mask);
+    } else if (int128_lt(shft_res1, int128_neg(min))) {
+        Vd->D(0) = int128_getlo(min);
+    } else {
+        Vd->D(0) = int128_getlo(shft_res1);
+    }
+
+    if (int128_gt(shft_res2, mask)) {
+        Vd->D(1) = int128_getlo(mask);
+    } else if (int128_lt(shft_res2, int128_neg(min))) {
+        Vd->D(1) = int128_getlo(min);
+    } else {
+        Vd->D(1) = int128_getlo(shft_res2);
+    }
+}
+
+VSSRANI(vssrani_b_h, 16, B, H)
+VSSRANI(vssrani_h_w, 32, H, W)
+VSSRANI(vssrani_w_d, 64, W, D)
+
+#define VSSRLNUI(NAME, BIT, E1, E2)                                         \
+void HELPER(NAME)(CPULoongArchState *env,                                   \
+                  uint32_t vd, uint32_t vj, uint32_t imm)                   \
+{                                                                           \
+    int i;                                                                  \
+    VReg temp;                                                              \
+    VReg *Vd = &(env->fpr[vd].vreg);                                        \
+    VReg *Vj = &(env->fpr[vj].vreg);                                        \
+                                                                            \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                                     \
+        temp.E1(i) = do_ssrlnu_ ## E1(Vj->E2(i), imm, BIT/2);               \
+        temp.E1(i + LSX_LEN/BIT) = do_ssrlnu_ ## E1(Vd->E2(i), imm, BIT/2); \
+    }                                                                       \
+    *Vd = temp;                                                             \
+}
+
+void HELPER(vssrlni_du_q)(CPULoongArchState *env,
+                         uint32_t vd, uint32_t vj, uint32_t imm)
+{
+    Int128 shft_res1, shft_res2, mask;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    if (imm == 0) {
+        shft_res1 = Vj->Q(0);
+        shft_res2 = Vd->Q(0);
+    } else {
+        shft_res1 = int128_urshift(Vj->Q(0), imm);
+        shft_res2 = int128_urshift(Vd->Q(0), imm);
+    }
+    mask = int128_sub(int128_lshift(int128_one(), 64), int128_one());
+
+    if (int128_ult(mask, shft_res1)) {
+        Vd->D(0) = int128_getlo(mask);
+    }else {
+        Vd->D(0) = int128_getlo(shft_res1);
+    }
+
+    if (int128_ult(mask, shft_res2)) {
+        Vd->D(1) = int128_getlo(mask);
+    }else {
+        Vd->D(1) = int128_getlo(shft_res2);
+    }
+}
+
+VSSRLNUI(vssrlni_bu_h, 16, B, H)
+VSSRLNUI(vssrlni_hu_w, 32, H, W)
+VSSRLNUI(vssrlni_wu_d, 64, W, D)
+
+#define VSSRANUI(NAME, BIT, E1, E2)                                         \
+void HELPER(NAME)(CPULoongArchState *env,                                   \
+                  uint32_t vd, uint32_t vj, uint32_t imm)                   \
+{                                                                           \
+    int i;                                                                  \
+    VReg temp;                                                              \
+    VReg *Vd = &(env->fpr[vd].vreg);                                        \
+    VReg *Vj = &(env->fpr[vj].vreg);                                        \
+                                                                            \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                                     \
+        temp.E1(i) = do_ssranu_ ## E1(Vj->E2(i), imm, BIT/2);               \
+        temp.E1(i + LSX_LEN/BIT) = do_ssranu_ ## E1(Vd->E2(i), imm, BIT/2); \
+    }                                                                       \
+    *Vd = temp;                                                             \
+}
+
+void HELPER(vssrani_du_q)(CPULoongArchState *env,
+                         uint32_t vd, uint32_t vj, uint32_t imm)
+{
+    Int128 shft_res1, shft_res2, mask;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    if (imm == 0) {
+        shft_res1 = Vj->Q(0);
+        shft_res2 = Vd->Q(0);
+    } else {
+        shft_res1 = int128_rshift(Vj->Q(0), imm);
+        shft_res2 = int128_rshift(Vd->Q(0), imm);
+    }
+
+    if (int128_lt(Vj->Q(0), int128_zero())) {
+        shft_res1 = int128_zero();
+    }
+
+    if (int128_lt(Vd->Q(0), int128_zero())) {
+        shft_res2 = int128_zero();
+    }
+
+    mask = int128_sub(int128_lshift(int128_one(), 64), int128_one());
+
+    if (int128_ult(mask, shft_res1)) {
+        Vd->D(0) = int128_getlo(mask);
+    }else {
+        Vd->D(0) = int128_getlo(shft_res1);
+    }
+
+    if (int128_ult(mask, shft_res2)) {
+        Vd->D(1) = int128_getlo(mask);
+    }else {
+        Vd->D(1) = int128_getlo(shft_res2);
+    }
+}
+
+VSSRANUI(vssrani_bu_h, 16, B, H)
+VSSRANUI(vssrani_hu_w, 32, H, W)
+VSSRANUI(vssrani_wu_d, 64, W, D)
+
+#define SSRLRNS(E1, E2, T1, T2, T3)                \
+static T1 do_ssrlrns_ ## E1(T2 e2, int sa, int sh) \
+{                                                  \
+    T1 shft_res;                                   \
+                                                   \
+    shft_res = do_vsrlr_ ## E2(e2, sa);            \
+    T1 mask;                                       \
+    mask = (1ull << sh) -1;                        \
+    if (shft_res > mask) {                         \
+        return mask;                               \
+    } else {                                       \
+        return  shft_res;                          \
+    }                                              \
+}
+
+SSRLRNS(B, H, uint16_t, int16_t, uint8_t)
+SSRLRNS(H, W, uint32_t, int32_t, uint16_t)
+SSRLRNS(W, D, uint64_t, int64_t, uint32_t)
+
+#define VSSRLRN(NAME, BIT, T, E1, E2)                                         \
+void HELPER(NAME)(CPULoongArchState *env,                                     \
+                  uint32_t vd, uint32_t vj, uint32_t vk)                      \
+{                                                                             \
+    int i;                                                                    \
+    VReg *Vd = &(env->fpr[vd].vreg);                                          \
+    VReg *Vj = &(env->fpr[vj].vreg);                                          \
+    VReg *Vk = &(env->fpr[vk].vreg);                                          \
+                                                                              \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                                       \
+        Vd->E1(i) = do_ssrlrns_ ## E1(Vj->E2(i), (T)Vk->E2(i)%BIT, BIT/2 -1); \
+    }                                                                         \
+    Vd->D(1) = 0;                                                             \
+}
+
+VSSRLRN(vssrlrn_b_h, 16, uint16_t, B, H)
+VSSRLRN(vssrlrn_h_w, 32, uint32_t, H, W)
+VSSRLRN(vssrlrn_w_d, 64, uint64_t, W, D)
+
+#define SSRARNS(E1, E2, T1, T2)                    \
+static T1 do_ssrarns_ ## E1(T1 e2, int sa, int sh) \
+{                                                  \
+    T1 shft_res;                                   \
+                                                   \
+    shft_res = do_vsrar_ ## E2(e2, sa);            \
+    T2 mask;                                       \
+    mask = (1ll << sh) -1;                         \
+    if (shft_res > mask) {                         \
+        return  mask;                              \
+    } else if (shft_res < -(mask +1)) {            \
+        return  ~mask;                             \
+    } else {                                       \
+        return shft_res;                           \
+    }                                              \
+}
+
+SSRARNS(B, H, int16_t, int8_t)
+SSRARNS(H, W, int32_t, int16_t)
+SSRARNS(W, D, int64_t, int32_t)
+
+#define VSSRARN(NAME, BIT, T, E1, E2)                                         \
+void HELPER(NAME)(CPULoongArchState *env,                                     \
+                  uint32_t vd, uint32_t vj, uint32_t vk)                      \
+{                                                                             \
+    int i;                                                                    \
+    VReg *Vd = &(env->fpr[vd].vreg);                                          \
+    VReg *Vj = &(env->fpr[vj].vreg);                                          \
+    VReg *Vk = &(env->fpr[vk].vreg);                                          \
+                                                                              \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                                       \
+        Vd->E1(i) = do_ssrarns_ ## E1(Vj->E2(i), (T)Vk->E2(i)%BIT, BIT/2 -1); \
+    }                                                                         \
+    Vd->D(1) = 0;                                                             \
+}
+
+VSSRARN(vssrarn_b_h, 16, uint16_t, B, H)
+VSSRARN(vssrarn_h_w, 32, uint32_t, H, W)
+VSSRARN(vssrarn_w_d, 64, uint64_t, W, D)
+
+#define SSRLRNU(E1, E2, T1, T2, T3)                \
+static T1 do_ssrlrnu_ ## E1(T3 e2, int sa, int sh) \
+{                                                  \
+    T1 shft_res;                                   \
+                                                   \
+    shft_res = do_vsrlr_ ## E2(e2, sa);            \
+                                                   \
+    T2 mask;                                       \
+    mask = (1ull << sh) -1;                        \
+    if (shft_res > mask) {                         \
+        return mask;                               \
+    } else {                                       \
+        return shft_res;                           \
+    }                                              \
+}
+
+SSRLRNU(B, H, uint16_t, uint8_t, int16_t)
+SSRLRNU(H, W, uint32_t, uint16_t, int32_t)
+SSRLRNU(W, D, uint64_t, uint32_t, int64_t)
+
+#define VSSRLRNU(NAME, BIT, T, E1, E2)                                     \
+void HELPER(NAME)(CPULoongArchState *env,                                  \
+                  uint32_t vd, uint32_t vj, uint32_t vk)                   \
+{                                                                          \
+    int i;                                                                 \
+    VReg *Vd = &(env->fpr[vd].vreg);                                       \
+    VReg *Vj = &(env->fpr[vj].vreg);                                       \
+    VReg *Vk = &(env->fpr[vk].vreg);                                       \
+                                                                           \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                                    \
+        Vd->E1(i) = do_ssrlrnu_ ## E1(Vj->E2(i), (T)Vk->E2(i)%BIT, BIT/2); \
+    }                                                                      \
+    Vd->D(1) = 0;                                                          \
+}
+
+VSSRLRNU(vssrlrn_bu_h, 16, uint16_t, B, H)
+VSSRLRNU(vssrlrn_hu_w, 32, uint32_t, H, W)
+VSSRLRNU(vssrlrn_wu_d, 64, uint64_t, W, D)
+
+#define SSRARNU(E1, E2, T1, T2, T3)                \
+static T1 do_ssrarnu_ ## E1(T3 e2, int sa, int sh) \
+{                                                  \
+    T1 shft_res;                                   \
+                                                   \
+    if (e2 < 0) {                                  \
+        shft_res = 0;                              \
+    } else {                                       \
+        shft_res = do_vsrar_ ## E2(e2, sa);        \
+    }                                              \
+    T2 mask;                                       \
+    mask = (1ull << sh) -1;                        \
+    if (shft_res > mask) {                         \
+        return mask;                               \
+    } else {                                       \
+        return shft_res;                           \
+    }                                              \
+}
+
+SSRARNU(B, H, uint16_t, uint8_t, int16_t)
+SSRARNU(H, W, uint32_t, uint16_t, int32_t)
+SSRARNU(W, D, uint64_t, uint32_t, int64_t)
+
+#define VSSRARNU(NAME, BIT, T, E1, E2)                                     \
+void HELPER(NAME)(CPULoongArchState *env,                                  \
+                  uint32_t vd, uint32_t vj, uint32_t vk)                   \
+{                                                                          \
+    int i;                                                                 \
+    VReg *Vd = &(env->fpr[vd].vreg);                                       \
+    VReg *Vj = &(env->fpr[vj].vreg);                                       \
+    VReg *Vk = &(env->fpr[vk].vreg);                                       \
+                                                                           \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                                    \
+        Vd->E1(i) = do_ssrarnu_ ## E1(Vj->E2(i), (T)Vk->E2(i)%BIT, BIT/2); \
+    }                                                                      \
+    Vd->D(1) = 0;                                                          \
+}
+
+VSSRARNU(vssrarn_bu_h, 16, uint16_t, B, H)
+VSSRARNU(vssrarn_hu_w, 32, uint32_t, H, W)
+VSSRARNU(vssrarn_wu_d, 64, uint64_t, W, D)
+
+#define VSSRLRNI(NAME, BIT, E1, E2)                                            \
+void HELPER(NAME)(CPULoongArchState *env,                                      \
+                  uint32_t vd, uint32_t vj, uint32_t imm)                      \
+{                                                                              \
+    int i;                                                                     \
+    VReg temp;                                                                 \
+    VReg *Vd = &(env->fpr[vd].vreg);                                           \
+    VReg *Vj = &(env->fpr[vj].vreg);                                           \
+                                                                               \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                                        \
+        temp.E1(i) = do_ssrlrns_ ## E1(Vj->E2(i), imm, BIT/2 -1);              \
+        temp.E1(i + LSX_LEN/BIT) = do_ssrlrns_ ## E1(Vd->E2(i), imm, BIT/2 -1);\
+    }                                                                          \
+    *Vd = temp;                                                                \
+}
+
+#define VSSRLRNI_Q(NAME, sh)                                               \
+void HELPER(NAME)(CPULoongArchState *env,                                  \
+                          uint32_t vd, uint32_t vj, uint32_t imm)          \
+{                                                                          \
+    Int128 shft_res1, shft_res2, mask, r1, r2;                             \
+    VReg *Vd = &(env->fpr[vd].vreg);                                       \
+    VReg *Vj = &(env->fpr[vj].vreg);                                       \
+                                                                           \
+    if (imm == 0) {                                                        \
+        shft_res1 = Vj->Q(0);                                              \
+        shft_res2 = Vd->Q(0);                                              \
+    } else {                                                               \
+        r1 = int128_and(int128_urshift(Vj->Q(0), (imm -1)), int128_one()); \
+        r2 = int128_and(int128_urshift(Vd->Q(0), (imm -1)), int128_one()); \
+                                                                           \
+        shft_res1 = (int128_add(int128_urshift(Vj->Q(0), imm), r1));       \
+        shft_res2 = (int128_add(int128_urshift(Vd->Q(0), imm), r2));       \
+    }                                                                      \
+                                                                           \
+    mask = int128_sub(int128_lshift(int128_one(), sh), int128_one());      \
+                                                                           \
+    if (int128_ult(mask, shft_res1)) {                                     \
+        Vd->D(0) = int128_getlo(mask);                                     \
+    }else {                                                                \
+        Vd->D(0) = int128_getlo(shft_res1);                                \
+    }                                                                      \
+                                                                           \
+    if (int128_ult(mask, shft_res2)) {                                     \
+        Vd->D(1) = int128_getlo(mask);                                     \
+    }else {                                                                \
+        Vd->D(1) = int128_getlo(shft_res2);                                \
+    }                                                                      \
+}
+
+VSSRLRNI(vssrlrni_b_h, 16, B, H)
+VSSRLRNI(vssrlrni_h_w, 32, H, W)
+VSSRLRNI(vssrlrni_w_d, 64, W, D)
+VSSRLRNI_Q(vssrlrni_d_q, 63)
+
+#define VSSRARNI(NAME, BIT, E1, E2)                                             \
+void HELPER(NAME)(CPULoongArchState *env,                                       \
+                  uint32_t vd, uint32_t vj, uint32_t imm)                       \
+{                                                                               \
+    int i;                                                                      \
+    VReg temp;                                                                  \
+    VReg *Vd = &(env->fpr[vd].vreg);                                            \
+    VReg *Vj = &(env->fpr[vj].vreg);                                            \
+                                                                                \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                                         \
+        temp.E1(i) = do_ssrarns_ ## E1(Vj->E2(i), imm, BIT/2 -1);               \
+        temp.E1(i + LSX_LEN/BIT) = do_ssrarns_ ## E1(Vd->E2(i), imm, BIT/2 -1); \
+    }                                                                           \
+    *Vd = temp;                                                                 \
+}
+
+void HELPER(vssrarni_d_q)(CPULoongArchState *env,
+                          uint32_t vd, uint32_t vj, uint32_t imm)
+{
+    Int128 shft_res1, shft_res2, mask1, mask2, r1, r2;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    if (imm == 0) {
+        shft_res1 = Vj->Q(0);
+        shft_res2 = Vd->Q(0);
+    } else {
+        r1 = int128_and(int128_rshift(Vj->Q(0), (imm -1)), int128_one());
+        r2 = int128_and(int128_rshift(Vd->Q(0), (imm -1)), int128_one());
+
+        shft_res1 = int128_add(int128_rshift(Vj->Q(0), imm), r1);
+        shft_res2 = int128_add(int128_rshift(Vd->Q(0), imm), r2);
+    }
+
+    mask1 = int128_sub(int128_lshift(int128_one(), 63), int128_one());
+    mask2  = int128_lshift(int128_one(), 63);
+
+    if (int128_gt(shft_res1,  mask1)) {
+        Vd->D(0) = int128_getlo(mask1);
+    } else if (int128_lt(shft_res1, int128_neg(mask2))) {
+        Vd->D(0) = int128_getlo(mask2);
+    } else {
+        Vd->D(0) = int128_getlo(shft_res1);
+    }
+
+    if (int128_gt(shft_res2, mask1)) {
+        Vd->D(1) = int128_getlo(mask1);
+    } else if (int128_lt(shft_res2, int128_neg(mask2))) {
+        Vd->D(1) = int128_getlo(mask2);
+    } else {
+        Vd->D(1) = int128_getlo(shft_res2);
+    }
+}
+
+VSSRARNI(vssrarni_b_h, 16, B, H)
+VSSRARNI(vssrarni_h_w, 32, H, W)
+VSSRARNI(vssrarni_w_d, 64, W, D)
+
+#define VSSRLRNUI(NAME, BIT, E1, E2)                                         \
+void HELPER(NAME)(CPULoongArchState *env,                                    \
+                  uint32_t vd, uint32_t vj, uint32_t imm)                    \
+{                                                                            \
+    int i;                                                                   \
+    VReg temp;                                                               \
+    VReg *Vd = &(env->fpr[vd].vreg);                                         \
+    VReg *Vj = &(env->fpr[vj].vreg);                                         \
+                                                                             \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                                      \
+        temp.E1(i) = do_ssrlrnu_ ## E1(Vj->E2(i), imm, BIT/2);               \
+        temp.E1(i + LSX_LEN/BIT) = do_ssrlrnu_ ## E1(Vd->E2(i), imm, BIT/2); \
+    }                                                                        \
+    *Vd = temp;                                                              \
+}
+
+VSSRLRNUI(vssrlrni_bu_h, 16, B, H)
+VSSRLRNUI(vssrlrni_hu_w, 32, H, W)
+VSSRLRNUI(vssrlrni_wu_d, 64, W, D)
+VSSRLRNI_Q(vssrlrni_du_q, 64)
+
+#define VSSRARNUI(NAME, BIT, E1, E2)                                         \
+void HELPER(NAME)(CPULoongArchState *env,                                    \
+                  uint32_t vd, uint32_t vj, uint32_t imm)                    \
+{                                                                            \
+    int i;                                                                   \
+    VReg temp;                                                               \
+    VReg *Vd = &(env->fpr[vd].vreg);                                         \
+    VReg *Vj = &(env->fpr[vj].vreg);                                         \
+                                                                             \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                                      \
+        temp.E1(i) = do_ssrarnu_ ## E1(Vj->E2(i), imm, BIT/2);               \
+        temp.E1(i + LSX_LEN/BIT) = do_ssrarnu_ ## E1(Vd->E2(i), imm, BIT/2); \
+    }                                                                        \
+    *Vd = temp;                                                              \
+}
+
+void HELPER(vssrarni_du_q)(CPULoongArchState *env,
+                           uint32_t vd, uint32_t vj, uint32_t imm)
+{
+    Int128 shft_res1, shft_res2, mask1, mask2, r1, r2;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    if (imm == 0) {
+        shft_res1 = Vj->Q(0);
+        shft_res2 = Vd->Q(0);
+    } else {
+        r1 = int128_and(int128_rshift(Vj->Q(0), (imm -1)), int128_one());
+        r2 = int128_and(int128_rshift(Vd->Q(0), (imm -1)), int128_one());
+
+        shft_res1 = int128_add(int128_rshift(Vj->Q(0), imm), r1);
+        shft_res2 = int128_add(int128_rshift(Vd->Q(0), imm), r2);
+    }
+
+    if (int128_lt(Vj->Q(0), int128_zero())) {
+        shft_res1 = int128_zero();
+    }
+    if (int128_lt(Vd->Q(0), int128_zero())) {
+        shft_res2 = int128_zero();
+    }
+
+    mask1 = int128_sub(int128_lshift(int128_one(), 64), int128_one());
+    mask2  = int128_lshift(int128_one(), 64);
+
+    if (int128_gt(shft_res1,  mask1)) {
+        Vd->D(0) = int128_getlo(mask1);
+    } else if (int128_lt(shft_res1, int128_neg(mask2))) {
+        Vd->D(0) = int128_getlo(mask2);
+    } else {
+        Vd->D(0) = int128_getlo(shft_res1);
+    }
+
+    if (int128_gt(shft_res2, mask1)) {
+        Vd->D(1) = int128_getlo(mask1);
+    } else if (int128_lt(shft_res2, int128_neg(mask2))) {
+        Vd->D(1) = int128_getlo(mask2);
+    } else {
+        Vd->D(1) = int128_getlo(shft_res2);
+    }
+}
+
+VSSRARNUI(vssrarni_bu_h, 16, B, H)
+VSSRARNUI(vssrarni_hu_w, 32, H, W)
+VSSRARNUI(vssrarni_wu_d, 64, W, D)
+
+#define DO_2OP(NAME, BIT, E, DO_OP)                                 \
+void HELPER(NAME)(CPULoongArchState *env, uint32_t vd, uint32_t vj) \
+{                                                                   \
+    int i;                                                          \
+    VReg *Vd = &(env->fpr[vd].vreg);                                \
+    VReg *Vj = &(env->fpr[vj].vreg);                                \
+                                                                    \
+    for (i = 0; i < LSX_LEN/BIT; i++)                               \
+    {                                                               \
+        Vd->E(i) = DO_OP(Vj->E(i));                                 \
+    }                                                               \
+}
+
+#define DO_CLO_B(N)  (clz32(~N & 0xff) - 24)
+#define DO_CLO_H(N)  (clz32(~N & 0xffff) - 16)
+#define DO_CLO_W(N)  (clz32(~N))
+#define DO_CLO_D(N)  (clz64(~N))
+#define DO_CLZ_B(N)  (clz32(N) - 24)
+#define DO_CLZ_H(N)  (clz32(N) - 16)
+#define DO_CLZ_W(N)  (clz32(N))
+#define DO_CLZ_D(N)  (clz64(N))
+
+DO_2OP(vclo_b, 8, UB, DO_CLO_B)
+DO_2OP(vclo_h, 16, UH, DO_CLO_H)
+DO_2OP(vclo_w, 32, UW, DO_CLO_W)
+DO_2OP(vclo_d, 64, UD, DO_CLO_D)
+DO_2OP(vclz_b, 8, UB, DO_CLZ_B)
+DO_2OP(vclz_h, 16, UH, DO_CLZ_H)
+DO_2OP(vclz_w, 32, UW, DO_CLZ_W)
+DO_2OP(vclz_d, 64, UD, DO_CLZ_D)
+
+#define VPCNT(NAME, BIT, E, FN)                                     \
+void HELPER(NAME)(CPULoongArchState *env, uint32_t vd, uint32_t vj) \
+{                                                                   \
+    int i;                                                          \
+    VReg *Vd = &(env->fpr[vd].vreg);                                \
+    VReg *Vj = &(env->fpr[vj].vreg);                                \
+                                                                    \
+    for (i = 0; i < LSX_LEN/BIT; i++)                               \
+    {                                                               \
+        Vd->E(i) = FN(Vj->E(i));                                    \
+    }                                                               \
+}
+
+VPCNT(vpcnt_b, 8, UB, ctpop8)
+VPCNT(vpcnt_h, 16, UH, ctpop16)
+VPCNT(vpcnt_w, 32, UW, ctpop32)
+VPCNT(vpcnt_d, 64, UD, ctpop64)
+
+#define DO_BITCLR(a, bit) (a & ~(1ull << bit))
+#define DO_BITSET(a, bit) (a | 1ull << bit)
+#define DO_BITREV(a, bit) (a ^ (1ull << bit))
+
+#define DO_BIT(NAME, BIT, E, DO_OP)                         \
+void HELPER(NAME)(void *vd, void *vj, void *vk, uint32_t v) \
+{                                                           \
+    int i;                                                  \
+    VReg *Vd = (VReg *)vd;                                  \
+    VReg *Vj = (VReg *)vj;                                  \
+    VReg *Vk = (VReg *)vk;                                  \
+                                                            \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                     \
+        Vd->E(i) = DO_OP(Vj->E(i), Vk->E(i)%BIT);           \
+    }                                                       \
+}
+
+DO_BIT(vbitclr_b, 8, UB, DO_BITCLR)
+DO_BIT(vbitclr_h, 16, UH, DO_BITCLR)
+DO_BIT(vbitclr_w, 32, UW, DO_BITCLR)
+DO_BIT(vbitclr_d, 64, UD, DO_BITCLR)
+DO_BIT(vbitset_b, 8, UB, DO_BITSET)
+DO_BIT(vbitset_h, 16, UH, DO_BITSET)
+DO_BIT(vbitset_w, 32, UW, DO_BITSET)
+DO_BIT(vbitset_d, 64, UD, DO_BITSET)
+DO_BIT(vbitrev_b, 8, UB, DO_BITREV)
+DO_BIT(vbitrev_h, 16, UH, DO_BITREV)
+DO_BIT(vbitrev_w, 32, UW, DO_BITREV)
+DO_BIT(vbitrev_d, 64, UD, DO_BITREV)
+
+#define DO_BITI(NAME, BIT, E, DO_OP)                            \
+void HELPER(NAME)(void *vd, void *vj, uint64_t imm, uint32_t v) \
+{                                                               \
+    int i;                                                      \
+    VReg *Vd = (VReg *)vd;                                      \
+    VReg *Vj = (VReg *)vj;                                      \
+                                                                \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                         \
+        Vd->E(i) = DO_OP(Vj->E(i), imm);                        \
+    }                                                           \
+}
+
+DO_BITI(vbitclri_b, 8, UB, DO_BITCLR)
+DO_BITI(vbitclri_h, 16, UH, DO_BITCLR)
+DO_BITI(vbitclri_w, 32, UW, DO_BITCLR)
+DO_BITI(vbitclri_d, 64, UD, DO_BITCLR)
+DO_BITI(vbitseti_b, 8, UB, DO_BITSET)
+DO_BITI(vbitseti_h, 16, UH, DO_BITSET)
+DO_BITI(vbitseti_w, 32, UW, DO_BITSET)
+DO_BITI(vbitseti_d, 64, UD, DO_BITSET)
+DO_BITI(vbitrevi_b, 8, UB, DO_BITREV)
+DO_BITI(vbitrevi_h, 16, UH, DO_BITREV)
+DO_BITI(vbitrevi_w, 32, UW, DO_BITREV)
+DO_BITI(vbitrevi_d, 64, UD, DO_BITREV)
+
+#define VFRSTP(NAME, BIT, MASK, E)                       \
+void HELPER(NAME)(CPULoongArchState *env,                \
+                  uint32_t vd, uint32_t vj, uint32_t vk) \
+{                                                        \
+    int i, m;                                            \
+    VReg *Vd = &(env->fpr[vd].vreg);                     \
+    VReg *Vj = &(env->fpr[vj].vreg);                     \
+    VReg *Vk = &(env->fpr[vk].vreg);                     \
+                                                         \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                  \
+        if (Vj->E(i) < 0) {                              \
+            break;                                       \
+        }                                                \
+    }                                                    \
+    m = Vk->E(0) & MASK;                                 \
+    Vd->E(m) = i;                                        \
+}
+
+VFRSTP(vfrstp_b, 8, 0xf, B)
+VFRSTP(vfrstp_h, 16, 0x7, H)
+
+#define VFRSTPI(NAME, BIT, E)                             \
+void HELPER(NAME)(CPULoongArchState *env,                 \
+                  uint32_t vd, uint32_t vj, uint32_t imm) \
+{                                                         \
+    int i, m;                                             \
+    VReg *Vd = &(env->fpr[vd].vreg);                      \
+    VReg *Vj = &(env->fpr[vj].vreg);                      \
+                                                          \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                   \
+        if (Vj->E(i) < 0) {                               \
+            break;                                        \
+        }                                                 \
+    }                                                     \
+    m = imm % (LSX_LEN/BIT);                              \
+    Vd->E(m) = i;                                         \
+}
+
+VFRSTPI(vfrstpi_b, 8,  B)
+VFRSTPI(vfrstpi_h, 16, H)
+
+static void vec_update_fcsr0_mask(CPULoongArchState *env,
+                                  uintptr_t pc, int mask)
+{
+    int flags = get_float_exception_flags(&env->fp_status);
+
+    set_float_exception_flags(0, &env->fp_status);
+
+    flags &= ~mask;
+
+    if (flags) {
+        flags = ieee_ex_to_loongarch(flags);
+        UPDATE_FP_CAUSE(env->fcsr0, flags);
+    }
+
+    if (GET_FP_ENABLES(env->fcsr0) & flags) {
+        do_raise_exception(env, EXCCODE_FPE, pc);
+    } else {
+        UPDATE_FP_FLAGS(env->fcsr0, flags);
+    }
+}
+
+static void vec_update_fcsr0(CPULoongArchState *env, uintptr_t pc)
+{
+    vec_update_fcsr0_mask(env, pc, 0);
+}
+
+static inline void vec_clear_cause(CPULoongArchState *env)
+{
+    SET_FP_CAUSE(env->fcsr0, 0);
+}
+
+#define DO_3OP_F(NAME, BIT, E, FN)                          \
+void HELPER(NAME)(CPULoongArchState *env,                   \
+                  uint32_t vd, uint32_t vj, uint32_t vk)    \
+{                                                           \
+    int i;                                                  \
+    VReg *Vd = &(env->fpr[vd].vreg);                        \
+    VReg *Vj = &(env->fpr[vj].vreg);                        \
+    VReg *Vk = &(env->fpr[vk].vreg);                        \
+                                                            \
+    vec_clear_cause(env);                                   \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                     \
+        Vd->E(i) = FN(Vj->E(i), Vk->E(i), &env->fp_status); \
+        vec_update_fcsr0(env, GETPC());                     \
+    }                                                       \
+}
+
+DO_3OP_F(vfadd_s, 32, UW, float32_add)
+DO_3OP_F(vfadd_d, 64, UD, float64_add)
+DO_3OP_F(vfsub_s, 32, UW, float32_sub)
+DO_3OP_F(vfsub_d, 64, UD, float64_sub)
+DO_3OP_F(vfmul_s, 32, UW, float32_mul)
+DO_3OP_F(vfmul_d, 64, UD, float64_mul)
+DO_3OP_F(vfdiv_s, 32, UW, float32_div)
+DO_3OP_F(vfdiv_d, 64, UD, float64_div)
+DO_3OP_F(vfmax_s, 32, UW, float32_maxnum)
+DO_3OP_F(vfmax_d, 64, UD, float64_maxnum)
+DO_3OP_F(vfmin_s, 32, UW, float32_minnum)
+DO_3OP_F(vfmin_d, 64, UD, float64_minnum)
+DO_3OP_F(vfmaxa_s, 32, UW, float32_maxnummag)
+DO_3OP_F(vfmaxa_d, 64, UD, float64_maxnummag)
+DO_3OP_F(vfmina_s, 32, UW, float32_minnummag)
+DO_3OP_F(vfmina_d, 64, UD, float64_minnummag)
+
+#define DO_4OP_F(NAME, BIT, E, FN, flags)                                    \
+void HELPER(NAME)(CPULoongArchState *env,                                    \
+                  uint32_t vd, uint32_t vj, uint32_t vk, uint32_t va)        \
+{                                                                            \
+    int i;                                                                   \
+    VReg *Vd = &(env->fpr[vd].vreg);                                         \
+    VReg *Vj = &(env->fpr[vj].vreg);                                         \
+    VReg *Vk = &(env->fpr[vk].vreg);                                         \
+    VReg *Va = &(env->fpr[va].vreg);                                         \
+                                                                             \
+    vec_clear_cause(env);                                                    \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                                      \
+        Vd->E(i) = FN(Vj->E(i), Vk->E(i), Va->E(i), flags, &env->fp_status); \
+        vec_update_fcsr0(env, GETPC());                                      \
+    }                                                                        \
+}
+
+DO_4OP_F(vfmadd_s, 32, UW, float32_muladd, 0)
+DO_4OP_F(vfmadd_d, 64, UD, float64_muladd, 0)
+DO_4OP_F(vfmsub_s, 32, UW, float32_muladd, float_muladd_negate_c)
+DO_4OP_F(vfmsub_d, 64, UD, float64_muladd, float_muladd_negate_c)
+DO_4OP_F(vfnmadd_s, 32, UW, float32_muladd, float_muladd_negate_result)
+DO_4OP_F(vfnmadd_d, 64, UD, float64_muladd, float_muladd_negate_result)
+DO_4OP_F(vfnmsub_s, 32, UW, float32_muladd,
+         float_muladd_negate_c | float_muladd_negate_result)
+DO_4OP_F(vfnmsub_d, 64, UD, float64_muladd,
+         float_muladd_negate_c | float_muladd_negate_result)
+
+#define DO_2OP_F(NAME, BIT, E, FN)                                  \
+void HELPER(NAME)(CPULoongArchState *env, uint32_t vd, uint32_t vj) \
+{                                                                   \
+    int i;                                                          \
+    VReg *Vd = &(env->fpr[vd].vreg);                                \
+    VReg *Vj = &(env->fpr[vj].vreg);                                \
+                                                                    \
+    vec_clear_cause(env);                                           \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                             \
+        Vd->E(i) = FN(env, Vj->E(i));                               \
+    }                                                               \
+}
+
+#define FLOGB(BIT, T)                                            \
+static T do_flogb_## BIT(CPULoongArchState *env, T fj)           \
+{                                                                \
+    T fp, fd;                                                    \
+    float_status *status = &env->fp_status;                      \
+    FloatRoundMode old_mode = get_float_rounding_mode(status);   \
+                                                                 \
+    set_float_rounding_mode(float_round_down, status);           \
+    fp = float ## BIT ##_log2(fj, status);                       \
+    fd = float ## BIT ##_round_to_int(fp, status);               \
+    set_float_rounding_mode(old_mode, status);                   \
+    vec_update_fcsr0_mask(env, GETPC(), float_flag_inexact);     \
+    return fd;                                                   \
+}
+
+FLOGB(32, uint32_t)
+FLOGB(64, uint64_t)
+
+#define FCLASS(NAME, BIT, E, FN)                                    \
+void HELPER(NAME)(CPULoongArchState *env, uint32_t vd, uint32_t vj) \
+{                                                                   \
+    int i;                                                          \
+    VReg *Vd = &(env->fpr[vd].vreg);                                \
+    VReg *Vj = &(env->fpr[vj].vreg);                                \
+                                                                    \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                             \
+        Vd->E(i) = FN(env, Vj->E(i));                               \
+    }                                                               \
+}
+
+FCLASS(vfclass_s, 32, UW, helper_fclass_s)
+FCLASS(vfclass_d, 64, UD, helper_fclass_d)
+
+#define FSQRT(BIT, T)                                  \
+static T do_fsqrt_## BIT(CPULoongArchState *env, T fj) \
+{                                                      \
+    T fd;                                              \
+    fd = float ## BIT ##_sqrt(fj, &env->fp_status);    \
+    vec_update_fcsr0(env, GETPC());                    \
+    return fd;                                         \
+}
+
+FSQRT(32, uint32_t)
+FSQRT(64, uint64_t)
+
+#define FRECIP(BIT, T)                                                  \
+static T do_frecip_## BIT(CPULoongArchState *env, T fj)                 \
+{                                                                       \
+    T fd;                                                               \
+    fd = float ## BIT ##_div(float ## BIT ##_one, fj, &env->fp_status); \
+    vec_update_fcsr0(env, GETPC());                                     \
+    return fd;                                                          \
+}
+
+FRECIP(32, uint32_t)
+FRECIP(64, uint64_t)
+
+#define FRSQRT(BIT, T)                                                  \
+static T do_frsqrt_## BIT(CPULoongArchState *env, T fj)                 \
+{                                                                       \
+    T fd, fp;                                                           \
+    fp = float ## BIT ##_sqrt(fj, &env->fp_status);                     \
+    fd = float ## BIT ##_div(float ## BIT ##_one, fp, &env->fp_status); \
+    vec_update_fcsr0(env, GETPC());                                     \
+    return fd;                                                          \
+}
+
+FRSQRT(32, uint32_t)
+FRSQRT(64, uint64_t)
+
+DO_2OP_F(vflogb_s, 32, UW, do_flogb_32)
+DO_2OP_F(vflogb_d, 64, UD, do_flogb_64)
+DO_2OP_F(vfsqrt_s, 32, UW, do_fsqrt_32)
+DO_2OP_F(vfsqrt_d, 64, UD, do_fsqrt_64)
+DO_2OP_F(vfrecip_s, 32, UW, do_frecip_32)
+DO_2OP_F(vfrecip_d, 64, UD, do_frecip_64)
+DO_2OP_F(vfrsqrt_s, 32, UW, do_frsqrt_32)
+DO_2OP_F(vfrsqrt_d, 64, UD, do_frsqrt_64)
+
+static uint32_t float16_cvt_float32(uint16_t h, float_status *status)
+{
+    return float16_to_float32(h, true, status);
+}
+static uint64_t float32_cvt_float64(uint32_t s, float_status *status)
+{
+    return float32_to_float64(s, status);
+}
+
+static uint16_t float32_cvt_float16(uint32_t s, float_status *status)
+{
+    return float32_to_float16(s, true, status);
+}
+static uint32_t float64_cvt_float32(uint64_t d, float_status *status)
+{
+    return float64_to_float32(d, status);
+}
+
+void HELPER(vfcvtl_s_h)(CPULoongArchState *env, uint32_t vd, uint32_t vj)
+{
+    int i;
+    VReg temp;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    vec_clear_cause(env);
+    for (i = 0; i < LSX_LEN/32; i++) {
+        temp.UW(i) = float16_cvt_float32(Vj->UH(i), &env->fp_status);
+        vec_update_fcsr0(env, GETPC());
+    }
+    *Vd = temp;
+}
+
+void HELPER(vfcvtl_d_s)(CPULoongArchState *env, uint32_t vd, uint32_t vj)
+{
+    int i;
+    VReg temp;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    vec_clear_cause(env);
+    for (i = 0; i < LSX_LEN/64; i++) {
+        temp.UD(i) = float32_cvt_float64(Vj->UW(i), &env->fp_status);
+        vec_update_fcsr0(env, GETPC());
+    }
+    *Vd = temp;
+}
+
+void HELPER(vfcvth_s_h)(CPULoongArchState *env, uint32_t vd, uint32_t vj)
+{
+    int i;
+    VReg temp;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    vec_clear_cause(env);
+    for (i = 0; i < LSX_LEN/32; i++) {
+        temp.UW(i) = float16_cvt_float32(Vj->UH(i + 4), &env->fp_status);
+        vec_update_fcsr0(env, GETPC());
+    }
+    *Vd = temp;
+}
+
+void HELPER(vfcvth_d_s)(CPULoongArchState *env, uint32_t vd, uint32_t vj)
+{
+    int i;
+    VReg temp;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    vec_clear_cause(env);
+    for (i = 0; i < LSX_LEN/64; i++) {
+        temp.UD(i) = float32_cvt_float64(Vj->UW(i + 2), &env->fp_status);
+        vec_update_fcsr0(env, GETPC());
+    }
+    *Vd = temp;
+}
+
+void HELPER(vfcvt_h_s)(CPULoongArchState *env,
+                       uint32_t vd, uint32_t vj, uint32_t vk)
+{
+    int i;
+    VReg temp;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+    VReg *Vk = &(env->fpr[vk].vreg);
+
+    vec_clear_cause(env);
+    for(i = 0; i < LSX_LEN/32; i++) {
+        temp.UH(i + 4) = float32_cvt_float16(Vj->UW(i), &env->fp_status);
+        temp.UH(i)  = float32_cvt_float16(Vk->UW(i), &env->fp_status);
+        vec_update_fcsr0(env, GETPC());
+    }
+    *Vd = temp;
+}
+
+void HELPER(vfcvt_s_d)(CPULoongArchState *env,
+                       uint32_t vd, uint32_t vj, uint32_t vk)
+{
+    int i;
+    VReg temp;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+    VReg *Vk = &(env->fpr[vk].vreg);
+
+    vec_clear_cause(env);
+    for(i = 0; i < LSX_LEN/64; i++) {
+        temp.UW(i + 2) = float64_cvt_float32(Vj->UD(i), &env->fp_status);
+        temp.UW(i)  = float64_cvt_float32(Vk->UD(i), &env->fp_status);
+        vec_update_fcsr0(env, GETPC());
+    }
+    *Vd = temp;
+}
+
+void HELPER(vfrint_s)(CPULoongArchState *env, uint32_t vd, uint32_t vj)
+{
+    int i;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    vec_clear_cause(env);
+    for (i = 0; i < 4; i++) {
+        Vd->W(i) = float32_round_to_int(Vj->UW(i), &env->fp_status);
+        vec_update_fcsr0(env, GETPC());
+    }
+}
+
+void HELPER(vfrint_d)(CPULoongArchState *env, uint32_t vd, uint32_t vj)
+{
+    int i;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    vec_clear_cause(env);
+    for (i = 0; i < 2; i++) {
+        Vd->D(i) = float64_round_to_int(Vj->UD(i), &env->fp_status);
+        vec_update_fcsr0(env, GETPC());
+    }
+}
+
+#define FCVT_2OP(NAME, BIT, E, MODE)                                        \
+void HELPER(NAME)(CPULoongArchState *env, uint32_t vd, uint32_t vj)         \
+{                                                                           \
+    int i;                                                                  \
+    VReg *Vd = &(env->fpr[vd].vreg);                                        \
+    VReg *Vj = &(env->fpr[vj].vreg);                                        \
+                                                                            \
+    vec_clear_cause(env);                                                   \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                                     \
+        FloatRoundMode old_mode = get_float_rounding_mode(&env->fp_status); \
+        set_float_rounding_mode(MODE, &env->fp_status);                     \
+        Vd->E(i) = float## BIT ## _round_to_int(Vj->E(i), &env->fp_status); \
+        set_float_rounding_mode(old_mode, &env->fp_status);                 \
+        vec_update_fcsr0(env, GETPC());                                     \
+    }                                                                       \
+}
+
+FCVT_2OP(vfrintrne_s, 32, UW, float_round_nearest_even)
+FCVT_2OP(vfrintrne_d, 64, UD, float_round_nearest_even)
+FCVT_2OP(vfrintrz_s, 32, UW, float_round_to_zero)
+FCVT_2OP(vfrintrz_d, 64, UD, float_round_to_zero)
+FCVT_2OP(vfrintrp_s, 32, UW, float_round_up)
+FCVT_2OP(vfrintrp_d, 64, UD, float_round_up)
+FCVT_2OP(vfrintrm_s, 32, UW, float_round_down)
+FCVT_2OP(vfrintrm_d, 64, UD, float_round_down)
+
+#define FTINT(NAME, FMT1, FMT2, T1, T2,  MODE)                          \
+static T2 do_ftint ## NAME(CPULoongArchState *env, T1 fj)               \
+{                                                                       \
+    T2 fd;                                                              \
+    FloatRoundMode old_mode = get_float_rounding_mode(&env->fp_status); \
+                                                                        \
+    set_float_rounding_mode(MODE, &env->fp_status);                     \
+    fd = do_## FMT1 ##_to_## FMT2(env, fj);                             \
+    set_float_rounding_mode(old_mode, &env->fp_status);                 \
+    return fd;                                                          \
+}
+
+#define DO_FTINT(FMT1, FMT2, T1, T2)                                         \
+static T2 do_## FMT1 ##_to_## FMT2(CPULoongArchState *env, T1 fj)            \
+{                                                                            \
+    T2 fd;                                                                   \
+                                                                             \
+    fd = FMT1 ##_to_## FMT2(fj, &env->fp_status);                            \
+    if (get_float_exception_flags(&env->fp_status) & (float_flag_invalid)) { \
+        if (FMT1 ##_is_any_nan(fj)) {                                        \
+            fd = 0;                                                          \
+        }                                                                    \
+    }                                                                        \
+    vec_update_fcsr0(env, GETPC());                                          \
+    return fd;                                                               \
+}
+
+DO_FTINT(float32, int32, uint32_t, uint32_t)
+DO_FTINT(float64, int64, uint64_t, uint64_t)
+DO_FTINT(float32, uint32, uint32_t, uint32_t)
+DO_FTINT(float64, uint64, uint64_t, uint64_t)
+DO_FTINT(float64, int32, uint64_t, uint32_t)
+DO_FTINT(float32, int64, uint32_t, uint64_t)
+
+FTINT(rne_w_s, float32, int32, uint32_t, uint32_t, float_round_nearest_even)
+FTINT(rne_l_d, float64, int64, uint64_t, uint64_t, float_round_nearest_even)
+FTINT(rp_w_s, float32, int32, uint32_t, uint32_t, float_round_up)
+FTINT(rp_l_d, float64, int64, uint64_t, uint64_t, float_round_up)
+FTINT(rz_w_s, float32, int32, uint32_t, uint32_t, float_round_to_zero)
+FTINT(rz_l_d, float64, int64, uint64_t, uint64_t, float_round_to_zero)
+FTINT(rm_w_s, float32, int32, uint32_t, uint32_t, float_round_down)
+FTINT(rm_l_d, float64, int64, uint64_t, uint64_t, float_round_down)
+
+DO_2OP_F(vftintrne_w_s, 32, UW, do_ftintrne_w_s)
+DO_2OP_F(vftintrne_l_d, 64, UD, do_ftintrne_l_d)
+DO_2OP_F(vftintrp_w_s, 32, UW, do_ftintrp_w_s)
+DO_2OP_F(vftintrp_l_d, 64, UD, do_ftintrp_l_d)
+DO_2OP_F(vftintrz_w_s, 32, UW, do_ftintrz_w_s)
+DO_2OP_F(vftintrz_l_d, 64, UD, do_ftintrz_l_d)
+DO_2OP_F(vftintrm_w_s, 32, UW, do_ftintrm_w_s)
+DO_2OP_F(vftintrm_l_d, 64, UD, do_ftintrm_l_d)
+DO_2OP_F(vftint_w_s, 32, UW, do_float32_to_int32)
+DO_2OP_F(vftint_l_d, 64, UD, do_float64_to_int64)
+
+FTINT(rz_wu_s, float32, uint32, uint32_t, uint32_t, float_round_to_zero)
+FTINT(rz_lu_d, float64, uint64, uint64_t, uint64_t, float_round_to_zero)
+
+DO_2OP_F(vftintrz_wu_s, 32, UW, do_ftintrz_wu_s)
+DO_2OP_F(vftintrz_lu_d, 64, UD, do_ftintrz_lu_d)
+DO_2OP_F(vftint_wu_s, 32, UW, do_float32_to_uint32)
+DO_2OP_F(vftint_lu_d, 64, UD, do_float64_to_uint64)
+
+FTINT(rm_w_d, float64, int32, uint64_t, uint32_t, float_round_down)
+FTINT(rp_w_d, float64, int32, uint64_t, uint32_t, float_round_up)
+FTINT(rz_w_d, float64, int32, uint64_t, uint32_t, float_round_to_zero)
+FTINT(rne_w_d, float64, int32, uint64_t, uint32_t, float_round_nearest_even)
+
+#define FTINT_W_D(NAME, FN)                              \
+void HELPER(NAME)(CPULoongArchState *env,                \
+                  uint32_t vd, uint32_t vj, uint32_t vk) \
+{                                                        \
+    int i;                                               \
+    VReg temp;                                           \
+    VReg *Vd = &(env->fpr[vd].vreg);                     \
+    VReg *Vj = &(env->fpr[vj].vreg);                     \
+    VReg *Vk = &(env->fpr[vk].vreg);                     \
+                                                         \
+    vec_clear_cause(env);                                \
+    for (i = 0; i < 2; i++) {                            \
+        temp.W(i + 2) = FN(env, Vj->UD(i));              \
+        temp.W(i) = FN(env, Vk->UD(i));                  \
+    }                                                    \
+    *Vd = temp;                                          \
+}
+
+FTINT_W_D(vftint_w_d, do_float64_to_int32)
+FTINT_W_D(vftintrm_w_d, do_ftintrm_w_d)
+FTINT_W_D(vftintrp_w_d, do_ftintrp_w_d)
+FTINT_W_D(vftintrz_w_d, do_ftintrz_w_d)
+FTINT_W_D(vftintrne_w_d, do_ftintrne_w_d)
+
+FTINT(rml_l_s, float32, int64, uint32_t, uint64_t, float_round_down)
+FTINT(rpl_l_s, float32, int64, uint32_t, uint64_t, float_round_up)
+FTINT(rzl_l_s, float32, int64, uint32_t, uint64_t, float_round_to_zero)
+FTINT(rnel_l_s, float32, int64, uint32_t, uint64_t, float_round_nearest_even)
+FTINT(rmh_l_s, float32, int64, uint32_t, uint64_t, float_round_down)
+FTINT(rph_l_s, float32, int64, uint32_t, uint64_t, float_round_up)
+FTINT(rzh_l_s, float32, int64, uint32_t, uint64_t, float_round_to_zero)
+FTINT(rneh_l_s, float32, int64, uint32_t, uint64_t, float_round_nearest_even)
+
+#define FTINTL_L_S(NAME, FN)                                        \
+void HELPER(NAME)(CPULoongArchState *env, uint32_t vd, uint32_t vj) \
+{                                                                   \
+    int i;                                                          \
+    VReg temp;                                                      \
+    VReg *Vd = &(env->fpr[vd].vreg);                                \
+    VReg *Vj = &(env->fpr[vj].vreg);                                \
+                                                                    \
+    vec_clear_cause(env);                                           \
+    for (i = 0; i < 2; i++) {                                       \
+        temp.D(i) = FN(env, Vj->UW(i));                             \
+    }                                                               \
+    *Vd = temp;                                                     \
+}
+
+FTINTL_L_S(vftintl_l_s, do_float32_to_int64)
+FTINTL_L_S(vftintrml_l_s, do_ftintrml_l_s)
+FTINTL_L_S(vftintrpl_l_s, do_ftintrpl_l_s)
+FTINTL_L_S(vftintrzl_l_s, do_ftintrzl_l_s)
+FTINTL_L_S(vftintrnel_l_s, do_ftintrnel_l_s)
+
+#define FTINTH_L_S(NAME, FN)                                        \
+void HELPER(NAME)(CPULoongArchState *env, uint32_t vd, uint32_t vj) \
+{                                                                   \
+    int i;                                                          \
+    VReg temp;                                                      \
+    VReg *Vd = &(env->fpr[vd].vreg);                                \
+    VReg *Vj = &(env->fpr[vj].vreg);                                \
+                                                                    \
+    vec_clear_cause(env);                                           \
+    for (i = 0; i < 2; i++) {                                       \
+        temp.D(i) = FN(env, Vj->UW(i + 2));                         \
+    }                                                               \
+    *Vd = temp;                                                     \
+}
+
+FTINTH_L_S(vftinth_l_s, do_float32_to_int64)
+FTINTH_L_S(vftintrmh_l_s, do_ftintrmh_l_s)
+FTINTH_L_S(vftintrph_l_s, do_ftintrph_l_s)
+FTINTH_L_S(vftintrzh_l_s, do_ftintrzh_l_s)
+FTINTH_L_S(vftintrneh_l_s, do_ftintrneh_l_s)
+
+#define FFINT(NAME, FMT1, FMT2, T1, T2)                    \
+static T2 do_ffint_ ## NAME(CPULoongArchState *env, T1 fj) \
+{                                                          \
+    T2 fd;                                                 \
+                                                           \
+    fd = FMT1 ##_to_## FMT2(fj, &env->fp_status);          \
+    vec_update_fcsr0(env, GETPC());                        \
+    return fd;                                             \
+}
+
+FFINT(s_w, int32, float32, int32_t, uint32_t)
+FFINT(d_l, int64, float64, int64_t, uint64_t)
+FFINT(s_wu, uint32, float32, uint32_t, uint32_t)
+FFINT(d_lu, uint64, float64, uint64_t, uint64_t)
+
+DO_2OP_F(vffint_s_w, 32, W, do_ffint_s_w)
+DO_2OP_F(vffint_d_l, 64, D, do_ffint_d_l)
+DO_2OP_F(vffint_s_wu, 32, UW, do_ffint_s_wu)
+DO_2OP_F(vffint_d_lu, 64, UD, do_ffint_d_lu)
+
+void HELPER(vffintl_d_w)(CPULoongArchState *env, uint32_t vd, uint32_t vj)
+{
+    int i;
+    VReg temp;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    vec_clear_cause(env);
+    for (i = 0; i < 2; i++) {
+        temp.D(i) = int32_to_float64(Vj->W(i), &env->fp_status);
+        vec_update_fcsr0(env, GETPC());
+    }
+    *Vd = temp;
+}
+
+void HELPER(vffinth_d_w)(CPULoongArchState *env, uint32_t vd, uint32_t vj)
+{
+    int i;
+    VReg temp;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    vec_clear_cause(env);
+    for (i = 0; i < 2; i++) {
+        temp.D(i) = int32_to_float64(Vj->W(i + 2), &env->fp_status);
+        vec_update_fcsr0(env, GETPC());
+    }
+    *Vd = temp;
+}
+
+void HELPER(vffint_s_l)(CPULoongArchState *env,
+                        uint32_t vd, uint32_t vj, uint32_t vk)
+{
+    int i;
+    VReg temp;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+    VReg *Vk = &(env->fpr[vk].vreg);
+
+    vec_clear_cause(env);
+    for (i = 0; i < 2; i++) {
+        temp.W(i + 2) = int64_to_float32(Vj->D(i), &env->fp_status);
+        temp.W(i) = int64_to_float32(Vk->D(i), &env->fp_status);
+        vec_update_fcsr0(env, GETPC());
+    }
+    *Vd = temp;
+}
+
+#define VSEQ(a, b) (a == b ? -1 : 0)
+#define VSLE(a, b) (a <= b ? -1 : 0)
+#define VSLT(a, b) (a < b ? -1 : 0)
+
+#define VCMPI(NAME, BIT, E, DO_OP)                              \
+void HELPER(NAME)(void *vd, void *vj, uint64_t imm, uint32_t v) \
+{                                                               \
+    int i;                                                      \
+    VReg *Vd = (VReg *)vd;                                      \
+    VReg *Vj = (VReg *)vj;                                      \
+    typedef __typeof(Vd->E(0)) TD;                              \
+                                                                \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                         \
+        Vd->E(i) = DO_OP(Vj->E(i), (TD)imm);                    \
+    }                                                           \
+}
+
+VCMPI(vseqi_b, 8, B, VSEQ)
+VCMPI(vseqi_h, 16, H, VSEQ)
+VCMPI(vseqi_w, 32, W, VSEQ)
+VCMPI(vseqi_d, 64, D, VSEQ)
+VCMPI(vslei_b, 8, B, VSLE)
+VCMPI(vslei_h, 16, H, VSLE)
+VCMPI(vslei_w, 32, W, VSLE)
+VCMPI(vslei_d, 64, D, VSLE)
+VCMPI(vslei_bu, 8, UB, VSLE)
+VCMPI(vslei_hu, 16, UH, VSLE)
+VCMPI(vslei_wu, 32, UW, VSLE)
+VCMPI(vslei_du, 64, UD, VSLE)
+VCMPI(vslti_b, 8, B, VSLT)
+VCMPI(vslti_h, 16, H, VSLT)
+VCMPI(vslti_w, 32, W, VSLT)
+VCMPI(vslti_d, 64, D, VSLT)
+VCMPI(vslti_bu, 8, UB, VSLT)
+VCMPI(vslti_hu, 16, UH, VSLT)
+VCMPI(vslti_wu, 32, UW, VSLT)
+VCMPI(vslti_du, 64, UD, VSLT)
+
+static uint64_t vfcmp_common(CPULoongArchState *env,
+                             FloatRelation cmp, uint32_t flags)
+{
+    uint64_t ret = 0;
+
+    switch (cmp) {
+    case float_relation_less:
+        ret = (flags & FCMP_LT);
+        break;
+    case float_relation_equal:
+        ret = (flags & FCMP_EQ);
+        break;
+    case float_relation_greater:
+        ret = (flags & FCMP_GT);
+        break;
+    case float_relation_unordered:
+        ret = (flags & FCMP_UN);
+        break;
+    default:
+        g_assert_not_reached();
+    }
+
+    if (ret) {
+        ret = -1;
+    }
+
+    return ret;
+}
+
+#define VFCMP(NAME, BIT, E, FN)                                          \
+void HELPER(NAME)(CPULoongArchState *env,                                \
+                  uint32_t vd, uint32_t vj, uint32_t vk, uint32_t flags) \
+{                                                                        \
+    int i;                                                               \
+    VReg t;                                                              \
+    VReg *Vd = &(env->fpr[vd].vreg);                                     \
+    VReg *Vj = &(env->fpr[vj].vreg);                                     \
+    VReg *Vk = &(env->fpr[vk].vreg);                                     \
+                                                                         \
+    vec_clear_cause(env);                                                \
+    for (i = 0; i < LSX_LEN/BIT ; i++) {                                 \
+        FloatRelation cmp;                                               \
+        cmp = FN(Vj->E(i), Vk->E(i), &env->fp_status);                   \
+        t.E(i) = vfcmp_common(env, cmp, flags);                          \
+        vec_update_fcsr0(env, GETPC());                                  \
+    }                                                                    \
+    *Vd = t;                                                             \
+}
+
+VFCMP(vfcmp_c_s, 32, UW, float32_compare_quiet)
+VFCMP(vfcmp_s_s, 32, UW, float32_compare)
+VFCMP(vfcmp_c_d, 64, UD, float64_compare_quiet)
+VFCMP(vfcmp_s_d, 64, UD, float64_compare)
+
+void HELPER(vbitseli_b)(void *vd, void *vj,  uint64_t imm, uint32_t v)
+{
+    int i;
+    VReg *Vd = (VReg *)vd;
+    VReg *Vj = (VReg *)vj;
+
+    for (i = 0; i < 16; i++) {
+        Vd->B(i) = (~Vd->B(i) & Vj->B(i)) | (Vd->B(i) & imm);
+    }
+}
+
+/* Copy from target/arm/tcg/sve_helper.c */
+static inline bool do_match2(uint64_t n, uint64_t m0, uint64_t m1, int esz)
+{
+    uint64_t bits = 8 << esz;
+    uint64_t ones = dup_const(esz, 1);
+    uint64_t signs = ones << (bits - 1);
+    uint64_t cmp0, cmp1;
+
+    cmp1 = dup_const(esz, n);
+    cmp0 = cmp1 ^ m0;
+    cmp1 = cmp1 ^ m1;
+    cmp0 = (cmp0 - ones) & ~cmp0;
+    cmp1 = (cmp1 - ones) & ~cmp1;
+    return (cmp0 | cmp1) & signs;
+}
+
+#define SETANYEQZ(NAME, MO)                                         \
+void HELPER(NAME)(CPULoongArchState *env, uint32_t cd, uint32_t vj) \
+{                                                                   \
+    VReg *Vj = &(env->fpr[vj].vreg);                                \
+                                                                    \
+    env->cf[cd & 0x7] = do_match2(0, Vj->D(0), Vj->D(1), MO);       \
+}
+SETANYEQZ(vsetanyeqz_b, MO_8)
+SETANYEQZ(vsetanyeqz_h, MO_16)
+SETANYEQZ(vsetanyeqz_w, MO_32)
+SETANYEQZ(vsetanyeqz_d, MO_64)
+
+#define SETALLNEZ(NAME, MO)                                         \
+void HELPER(NAME)(CPULoongArchState *env, uint32_t cd, uint32_t vj) \
+{                                                                   \
+    VReg *Vj = &(env->fpr[vj].vreg);                                \
+                                                                    \
+    env->cf[cd & 0x7]= !do_match2(0, Vj->D(0), Vj->D(1), MO);       \
+}
+SETALLNEZ(vsetallnez_b, MO_8)
+SETALLNEZ(vsetallnez_h, MO_16)
+SETALLNEZ(vsetallnez_w, MO_32)
+SETALLNEZ(vsetallnez_d, MO_64)
+
+#define VPACKEV(NAME, BIT, E)                            \
+void HELPER(NAME)(CPULoongArchState *env,                \
+                  uint32_t vd, uint32_t vj, uint32_t vk) \
+{                                                        \
+    int i;                                               \
+    VReg temp;                                           \
+    VReg *Vd = &(env->fpr[vd].vreg);                     \
+    VReg *Vj = &(env->fpr[vj].vreg);                     \
+    VReg *Vk = &(env->fpr[vk].vreg);                     \
+                                                         \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                  \
+        temp.E(2 * i + 1) = Vj->E(2 * i);                \
+        temp.E(2 *i) = Vk->E(2 * i);                     \
+    }                                                    \
+    *Vd = temp;                                          \
+}
+
+VPACKEV(vpackev_b, 16, B)
+VPACKEV(vpackev_h, 32, H)
+VPACKEV(vpackev_w, 64, W)
+VPACKEV(vpackev_d, 128, D)
+
+#define VPACKOD(NAME, BIT, E)                            \
+void HELPER(NAME)(CPULoongArchState *env,                \
+                  uint32_t vd, uint32_t vj, uint32_t vk) \
+{                                                        \
+    int i;                                               \
+    VReg temp;                                           \
+    VReg *Vd = &(env->fpr[vd].vreg);                     \
+    VReg *Vj = &(env->fpr[vj].vreg);                     \
+    VReg *Vk = &(env->fpr[vk].vreg);                     \
+                                                         \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                  \
+        temp.E(2 * i + 1) = Vj->E(2 * i + 1);            \
+        temp.E(2 * i) = Vk->E(2 * i + 1);                \
+    }                                                    \
+    *Vd = temp;                                          \
+}
+
+VPACKOD(vpackod_b, 16, B)
+VPACKOD(vpackod_h, 32, H)
+VPACKOD(vpackod_w, 64, W)
+VPACKOD(vpackod_d, 128, D)
+
+#define VPICKEV(NAME, BIT, E)                            \
+void HELPER(NAME)(CPULoongArchState *env,                \
+                  uint32_t vd, uint32_t vj, uint32_t vk) \
+{                                                        \
+    int i;                                               \
+    VReg temp;                                           \
+    VReg *Vd = &(env->fpr[vd].vreg);                     \
+    VReg *Vj = &(env->fpr[vj].vreg);                     \
+    VReg *Vk = &(env->fpr[vk].vreg);                     \
+                                                         \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                  \
+        temp.E(i + LSX_LEN/BIT) = Vj->E(2 * i);          \
+        temp.E(i) = Vk->E(2 * i);                        \
+    }                                                    \
+    *Vd = temp;                                          \
+}
+
+VPICKEV(vpickev_b, 16, B)
+VPICKEV(vpickev_h, 32, H)
+VPICKEV(vpickev_w, 64, W)
+VPICKEV(vpickev_d, 128, D)
+
+#define VPICKOD(NAME, BIT, E)                            \
+void HELPER(NAME)(CPULoongArchState *env,                \
+                  uint32_t vd, uint32_t vj, uint32_t vk) \
+{                                                        \
+    int i;                                               \
+    VReg temp;                                           \
+    VReg *Vd = &(env->fpr[vd].vreg);                     \
+    VReg *Vj = &(env->fpr[vj].vreg);                     \
+    VReg *Vk = &(env->fpr[vk].vreg);                     \
+                                                         \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                  \
+        temp.E(i + LSX_LEN/BIT) = Vj->E(2 * i + 1);      \
+        temp.E(i) = Vk->E(2 * i + 1);                    \
+    }                                                    \
+    *Vd = temp;                                          \
+}
+
+VPICKOD(vpickod_b, 16, B)
+VPICKOD(vpickod_h, 32, H)
+VPICKOD(vpickod_w, 64, W)
+VPICKOD(vpickod_d, 128, D)
+
+#define VILVL(NAME, BIT, E)                              \
+void HELPER(NAME)(CPULoongArchState *env,                \
+                  uint32_t vd, uint32_t vj, uint32_t vk) \
+{                                                        \
+    int i;                                               \
+    VReg temp;                                           \
+    VReg *Vd = &(env->fpr[vd].vreg);                     \
+    VReg *Vj = &(env->fpr[vj].vreg);                     \
+    VReg *Vk = &(env->fpr[vk].vreg);                     \
+                                                         \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                  \
+        temp.E(2 * i + 1) = Vj->E(i);                    \
+        temp.E(2 * i) = Vk->E(i);                        \
+    }                                                    \
+    *Vd = temp;                                          \
+}
+
+VILVL(vilvl_b, 16, B)
+VILVL(vilvl_h, 32, H)
+VILVL(vilvl_w, 64, W)
+VILVL(vilvl_d, 128, D)
+
+#define VILVH(NAME, BIT, E)                              \
+void HELPER(NAME)(CPULoongArchState *env,                \
+                  uint32_t vd, uint32_t vj, uint32_t vk) \
+{                                                        \
+    int i;                                               \
+    VReg temp;                                           \
+    VReg *Vd = &(env->fpr[vd].vreg);                     \
+    VReg *Vj = &(env->fpr[vj].vreg);                     \
+    VReg *Vk = &(env->fpr[vk].vreg);                     \
+                                                         \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                  \
+        temp.E(2 * i + 1) = Vj->E(i + LSX_LEN/BIT);      \
+        temp.E(2 * i) = Vk->E(i + LSX_LEN/BIT);          \
+    }                                                    \
+    *Vd = temp;                                          \
+}
+
+VILVH(vilvh_b, 16, B)
+VILVH(vilvh_h, 32, H)
+VILVH(vilvh_w, 64, W)
+VILVH(vilvh_d, 128, D)
+
+void HELPER(vshuf_b)(CPULoongArchState *env,
+                     uint32_t vd, uint32_t vj, uint32_t vk, uint32_t va)
+{
+    int i, m;
+    VReg temp;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+    VReg *Vk = &(env->fpr[vk].vreg);
+    VReg *Va = &(env->fpr[va].vreg);
+
+    m = LSX_LEN/8;
+    for (i = 0; i < m ; i++) {
+        uint64_t k = (uint8_t)Va->B(i) % (2 * m);
+        temp.B(i) = k < m ? Vk->B(k) : Vj->B(k - m);
+    }
+    *Vd = temp;
+}
+
+#define VSHUF(NAME, BIT, E)                              \
+void HELPER(NAME)(CPULoongArchState *env,                \
+                  uint32_t vd, uint32_t vj, uint32_t vk) \
+{                                                        \
+    int i, m;                                            \
+    VReg temp;                                           \
+    VReg *Vd = &(env->fpr[vd].vreg);                     \
+    VReg *Vj = &(env->fpr[vj].vreg);                     \
+    VReg *Vk = &(env->fpr[vk].vreg);                     \
+                                                         \
+    m = LSX_LEN/BIT;                                     \
+    for (i = 0; i < m; i++) {                            \
+        uint64_t k  = ((uint8_t) Vd->E(i)) % (2 * m);    \
+        temp.E(i) = k < m ? Vk->E(k) : Vj->E(k - m);     \
+    }                                                    \
+    *Vd = temp;                                          \
+}
+
+VSHUF(vshuf_h, 16, H)
+VSHUF(vshuf_w, 32, W)
+VSHUF(vshuf_d, 64, D)
+
+#define VSHUF4I(NAME, BIT, E)                             \
+void HELPER(NAME)(CPULoongArchState *env,                 \
+                  uint32_t vd, uint32_t vj, uint32_t imm) \
+{                                                         \
+    int i;                                                \
+    VReg temp;                                            \
+    VReg *Vd = &(env->fpr[vd].vreg);                      \
+    VReg *Vj = &(env->fpr[vj].vreg);                      \
+                                                          \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                   \
+         temp.E(i) = Vj->E(((i) & 0xfc) + (((imm) >>      \
+                           (2 * ((i) & 0x03))) & 0x03));  \
+    }                                                     \
+    *Vd = temp;                                           \
+}
+
+VSHUF4I(vshuf4i_b, 8, B)
+VSHUF4I(vshuf4i_h, 16, H)
+VSHUF4I(vshuf4i_w, 32, W)
+
+void HELPER(vshuf4i_d)(CPULoongArchState *env,
+                       uint32_t vd, uint32_t vj, uint32_t imm)
+{
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    VReg temp;
+    temp.D(0) = (imm & 2 ? Vj : Vd)->D(imm & 1);
+    temp.D(1) = (imm & 8 ? Vj : Vd)->D((imm >> 2) & 1);
+    *Vd = temp;
+}
+
+void HELPER(vpermi_w)(CPULoongArchState *env,
+                      uint32_t vd, uint32_t vj, uint32_t imm)
+{
+    VReg temp;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    temp.W(0) = Vj->W(imm & 0x3);
+    temp.W(1) = Vj->W((imm >> 2) & 0x3);
+    temp.W(2) = Vd->W((imm >> 4) & 0x3);
+    temp.W(3) = Vd->W((imm >> 6) & 0x3);
+    *Vd = temp;
+}
+
+#define VEXTRINS(NAME, BIT, E, MASK)                      \
+void HELPER(NAME)(CPULoongArchState *env,                 \
+                  uint32_t vd, uint32_t vj, uint32_t imm) \
+{                                                         \
+    int ins, extr;                                        \
+    VReg *Vd = &(env->fpr[vd].vreg);                      \
+    VReg *Vj = &(env->fpr[vj].vreg);                      \
+                                                          \
+    ins = (imm >> 4) & MASK;                              \
+    extr = imm & MASK;                                    \
+    Vd->E(ins) = Vj->E(extr);                             \
+}
+
+VEXTRINS(vextrins_b, 8, B, 0xf)
+VEXTRINS(vextrins_h, 16, H, 0x7)
+VEXTRINS(vextrins_w, 32, W, 0x3)
+VEXTRINS(vextrins_d, 64, D, 0x1)

target/loongarch/machine.c

@@ -10,6 +10,72 @@
 #include "migration/cpu.h"
 #include "internals.h"
 
+static const VMStateDescription vmstate_fpu_reg = {
+    .name = "fpu_reg",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_UINT64(UD(0), VReg),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+#define VMSTATE_FPU_REGS(_field, _state, _start)            \
+    VMSTATE_STRUCT_SUB_ARRAY(_field, _state, _start, 32, 0, \
+                             vmstate_fpu_reg, fpr_t)
+
+static bool fpu_needed(void *opaque)
+{
+    LoongArchCPU *cpu = opaque;
+
+    return FIELD_EX64(cpu->env.cpucfg[2], CPUCFG2, FP);
+}
+
+static const VMStateDescription vmstate_fpu = {
+    .name = "cpu/fpu",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .needed = fpu_needed,
+    .fields = (VMStateField[]) {
+        VMSTATE_FPU_REGS(env.fpr, LoongArchCPU, 0),
+        VMSTATE_UINT32(env.fcsr0, LoongArchCPU),
+        VMSTATE_BOOL_ARRAY(env.cf, LoongArchCPU, 8),
+        VMSTATE_END_OF_LIST()
+    },
+};
+
+static const VMStateDescription vmstate_lsxh_reg = {
+    .name = "lsxh_reg",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_UINT64(UD(1), VReg),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+#define VMSTATE_LSXH_REGS(_field, _state, _start)           \
+    VMSTATE_STRUCT_SUB_ARRAY(_field, _state, _start, 32, 0, \
+                             vmstate_lsxh_reg, fpr_t)
+
+static bool lsx_needed(void *opaque)
+{
+    LoongArchCPU *cpu = opaque;
+
+    return FIELD_EX64(cpu->env.cpucfg[2], CPUCFG2, LSX);
+}
+
+static const VMStateDescription vmstate_lsx = {
+    .name = "cpu/lsx",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .needed = lsx_needed,
+    .fields = (VMStateField[]) {
+        VMSTATE_LSXH_REGS(env.fpr, LoongArchCPU, 0),
+        VMSTATE_END_OF_LIST()
+    },
+};
+
 /* TLB state */
 const VMStateDescription vmstate_tlb = {
     .name = "cpu/tlb",
@@ -24,18 +90,13 @@ const VMStateDescription vmstate_tlb = {
 };
 
 /* LoongArch CPU state */
-
 const VMStateDescription vmstate_loongarch_cpu = {
     .name = "cpu",
-    .version_id = 0,
-    .minimum_version_id = 0,
+    .version_id = 1,
+    .minimum_version_id = 1,
     .fields = (VMStateField[]) {
-
         VMSTATE_UINTTL_ARRAY(env.gpr, LoongArchCPU, 32),
         VMSTATE_UINTTL(env.pc, LoongArchCPU),
-        VMSTATE_UINT64_ARRAY(env.fpr, LoongArchCPU, 32),
-        VMSTATE_UINT32(env.fcsr0, LoongArchCPU),
-        VMSTATE_BOOL_ARRAY(env.cf, LoongArchCPU, 8),
 
         /* Remaining CSRs */
         VMSTATE_UINT64(env.CSR_CRMD, LoongArchCPU),
@@ -99,4 +160,8 @@ const VMStateDescription vmstate_loongarch_cpu = {
 
         VMSTATE_END_OF_LIST()
     },
+    .subsections = (const VMStateDescription*[]) {
+        &vmstate_fpu,
+        &vmstate_lsx,
+    }
 };

target/loongarch/meson.build

@@ -11,6 +11,7 @@ loongarch_tcg_ss.add(files(
   'op_helper.c',
   'translate.c',
   'gdbstub.c',
+  'lsx_helper.c',
 ))
 loongarch_tcg_ss.add(zlib)
 

target/loongarch/translate.c

@@ -8,6 +8,8 @@
 #include "qemu/osdep.h"
 #include "cpu.h"
 #include "tcg/tcg-op.h"
+#include "tcg/tcg-op-gvec.h"
+
 #include "exec/translator.h"
 #include "exec/helper-proto.h"
 #include "exec/helper-gen.h"
@@ -21,7 +23,6 @@
 /* Global register indices */
 TCGv cpu_gpr[32], cpu_pc;
 static TCGv cpu_lladdr, cpu_llval;
-TCGv_i64 cpu_fpr[32];
 
 #include "exec/gen-icount.h"
 
@@ -29,16 +30,43 @@ TCGv_i64 cpu_fpr[32];
 #define DISAS_EXIT        DISAS_TARGET_1
 #define DISAS_EXIT_UPDATE DISAS_TARGET_2
 
+static inline int vec_full_offset(int regno)
+{
+    return  offsetof(CPULoongArchState, fpr[regno]);
+}
+
+static inline void get_vreg64(TCGv_i64 dest, int regno, int index)
+{
+    tcg_gen_ld_i64(dest, cpu_env,
+                   offsetof(CPULoongArchState, fpr[regno].vreg.D(index)));
+}
+
+static inline void set_vreg64(TCGv_i64 src, int regno, int index)
+{
+    tcg_gen_st_i64(src, cpu_env,
+                   offsetof(CPULoongArchState, fpr[regno].vreg.D(index)));
+}
+
 static inline int plus_1(DisasContext *ctx, int x)
 {
     return x + 1;
 }
 
+static inline int shl_1(DisasContext *ctx, int x)
+{
+    return x << 1;
+}
+
 static inline int shl_2(DisasContext *ctx, int x)
 {
     return x << 2;
 }
 
+static inline int shl_3(DisasContext *ctx, int x)
+{
+    return x << 3;
+}
+
 /*
  * LoongArch the upper 32 bits are undefined ("can be any value").
  * QEMU chooses to nanbox, because it is most likely to show guest bugs early.
@@ -71,6 +99,7 @@ static void loongarch_tr_init_disas_context(DisasContextBase *dcbase,
                                             CPUState *cs)
 {
     int64_t bound;
+    CPULoongArchState *env = cs->env_ptr;
     DisasContext *ctx = container_of(dcbase, DisasContext, base);
 
     ctx->page_start = ctx->base.pc_first & TARGET_PAGE_MASK;
@@ -85,6 +114,10 @@ static void loongarch_tr_init_disas_context(DisasContextBase *dcbase,
     bound = -(ctx->base.pc_first | TARGET_PAGE_MASK) / 4;
     ctx->base.max_insns = MIN(ctx->base.max_insns, bound);
 
+    if (FIELD_EX64(env->cpucfg[2], CPUCFG2, LSX)) {
+        ctx->vl = LSX_LEN;
+    }
+
     ctx->zero = tcg_constant_tl(0);
 }
 
@@ -157,6 +190,20 @@ static void gen_set_gpr(int reg_num, TCGv t, DisasExtend dst_ext)
     }
 }
 
+static TCGv get_fpr(DisasContext *ctx, int reg_num)
+{
+    TCGv t = tcg_temp_new();
+    tcg_gen_ld_i64(t, cpu_env,
+                   offsetof(CPULoongArchState, fpr[reg_num].vreg.D(0)));
+    return  t;
+}
+
+static void set_fpr(int reg_num, TCGv val)
+{
+    tcg_gen_st_i64(val, cpu_env,
+                   offsetof(CPULoongArchState, fpr[reg_num].vreg.D(0)));
+}
+
 #include "decode-insns.c.inc"
 #include "insn_trans/trans_arith.c.inc"
 #include "insn_trans/trans_shift.c.inc"
@@ -171,6 +218,7 @@ static void gen_set_gpr(int reg_num, TCGv t, DisasExtend dst_ext)
 #include "insn_trans/trans_fmemory.c.inc"
 #include "insn_trans/trans_branch.c.inc"
 #include "insn_trans/trans_privileged.c.inc"
+#include "insn_trans/trans_lsx.c.inc"
 
 static void loongarch_tr_translate_insn(DisasContextBase *dcbase, CPUState *cs)
 {
@@ -250,11 +298,6 @@ void loongarch_translate_init(void)
                                         regnames[i]);
     }
 
-    for (i = 0; i < 32; i++) {
-        int off = offsetof(CPULoongArchState, fpr[i]);
-        cpu_fpr[i] = tcg_global_mem_new_i64(cpu_env, off, fregnames[i]);
-    }
-
     cpu_pc = tcg_global_mem_new(cpu_env, offsetof(CPULoongArchState, pc), "pc");
     cpu_lladdr = tcg_global_mem_new(cpu_env,
                     offsetof(CPULoongArchState, lladdr), "lladdr");

target/loongarch/translate.h

@@ -31,6 +31,7 @@ typedef struct DisasContext {
     uint32_t opcode;
     uint16_t mem_idx;
     uint16_t plv;
+    int vl;   /* Vector length */
     TCGv zero;
 } DisasContext;