[WebAssembly] Add SIMD QFMA/QFMS

Summary:
Adds clang builtins and LLVM intrinsics for these experimental
instructions. They are not implemented in engines yet, but that is ok
because the user must opt into using them by calling the builtins.

Reviewers: aheejin, dschuff

Reviewed By: aheejin

Subscribers: sbc100, jgravelle-google, hiraditya, sunfish, cfe-commits, llvm-commits

Tags: #clang, #llvm

Differential Revision: https://reviews.llvm.org/D67020

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@370556 91177308-0d34-0410-b5e6-96231b3b80d8

include/clang/Basic/BuiltinsWebAssembly.def

@@ -108,6 +108,11 @@ TARGET_BUILTIN(__builtin_wasm_max_f64x2, "V2dV2dV2d", "nc", "unimplemented-simd1
 TARGET_BUILTIN(__builtin_wasm_sqrt_f32x4, "V4fV4f", "nc", "unimplemented-simd128")
 TARGET_BUILTIN(__builtin_wasm_sqrt_f64x2, "V2dV2d", "nc", "unimplemented-simd128")
 
+TARGET_BUILTIN(__builtin_wasm_qfma_f32x4, "V4fV4fV4fV4f", "nc", "simd128")
+TARGET_BUILTIN(__builtin_wasm_qfms_f32x4, "V4fV4fV4fV4f", "nc", "simd128")
+TARGET_BUILTIN(__builtin_wasm_qfma_f64x2, "V2dV2dV2dV2d", "nc", "unimplemented-simd128")
+TARGET_BUILTIN(__builtin_wasm_qfms_f64x2, "V2dV2dV2dV2d", "nc", "unimplemented-simd128")
+
 TARGET_BUILTIN(__builtin_wasm_trunc_saturate_s_i32x4_f32x4, "V4iV4f", "nc", "simd128")
 TARGET_BUILTIN(__builtin_wasm_trunc_saturate_u_i32x4_f32x4, "V4iV4f", "nc", "simd128")
 TARGET_BUILTIN(__builtin_wasm_trunc_saturate_s_i64x2_f64x2, "V2LLiV2d", "nc", "unimplemented-simd128")

lib/CodeGen/CGBuiltin.cpp

@@ -14173,7 +14173,29 @@ Value *CodeGenFunction::EmitWebAssemblyBuiltinExpr(unsigned BuiltinID,
     Function *Callee = CGM.getIntrinsic(Intrinsic::sqrt, Vec->getType());
     return Builder.CreateCall(Callee, {Vec});
   }
-
+  case WebAssembly::BI__builtin_wasm_qfma_f32x4:
+  case WebAssembly::BI__builtin_wasm_qfms_f32x4:
+  case WebAssembly::BI__builtin_wasm_qfma_f64x2:
+  case WebAssembly::BI__builtin_wasm_qfms_f64x2: {
+    Value *A = EmitScalarExpr(E->getArg(0));
+    Value *B = EmitScalarExpr(E->getArg(1));
+    Value *C = EmitScalarExpr(E->getArg(2));
+    unsigned IntNo;
+    switch (BuiltinID) {
+    case WebAssembly::BI__builtin_wasm_qfma_f32x4:
+    case WebAssembly::BI__builtin_wasm_qfma_f64x2:
+      IntNo = Intrinsic::wasm_qfma;
+      break;
+    case WebAssembly::BI__builtin_wasm_qfms_f32x4:
+    case WebAssembly::BI__builtin_wasm_qfms_f64x2:
+      IntNo = Intrinsic::wasm_qfms;
+      break;
+    default:
+      llvm_unreachable("unexpected builtin ID");
+    }
+    Function *Callee = CGM.getIntrinsic(IntNo, A->getType());
+    return Builder.CreateCall(Callee, {A, B, C});
+  }
   default:
     return nullptr;
   }

test/CodeGen/builtins-wasm.c

@@ -412,6 +412,34 @@ f64x2 sqrt_f64x2(f64x2 x) {
   // WEBASSEMBLY: ret
 }
 
+f32x4 qfma_f32x4(f32x4 a, f32x4 b, f32x4 c) {
+  return __builtin_wasm_qfma_f32x4(a, b, c);
+  // WEBASSEMBLY: call <4 x float> @llvm.wasm.qfma.v4f32(
+  // WEBASSEMBLY-SAME: <4 x float> %a, <4 x float> %b, <4 x float> %c)
+  // WEBASSEMBLY-NEXT: ret
+}
+
+f32x4 qfms_f32x4(f32x4 a, f32x4 b, f32x4 c) {
+  return __builtin_wasm_qfms_f32x4(a, b, c);
+  // WEBASSEMBLY: call <4 x float> @llvm.wasm.qfms.v4f32(
+  // WEBASSEMBLY-SAME: <4 x float> %a, <4 x float> %b, <4 x float> %c)
+  // WEBASSEMBLY-NEXT: ret
+}
+
+f64x2 qfma_f64x2(f64x2 a, f64x2 b, f64x2 c) {
+  return __builtin_wasm_qfma_f64x2(a, b, c);
+  // WEBASSEMBLY: call <2 x double> @llvm.wasm.qfma.v2f64(
+  // WEBASSEMBLY-SAME: <2 x double> %a, <2 x double> %b, <2 x double> %c)
+  // WEBASSEMBLY-NEXT: ret
+}
+
+f64x2 qfms_f64x2(f64x2 a, f64x2 b, f64x2 c) {
+  return __builtin_wasm_qfms_f64x2(a, b, c);
+  // WEBASSEMBLY: call <2 x double> @llvm.wasm.qfms.v2f64(
+  // WEBASSEMBLY-SAME: <2 x double> %a, <2 x double> %b, <2 x double> %c)
+  // WEBASSEMBLY-NEXT: ret
+}
+
 i32x4 trunc_saturate_s_i32x4_f32x4(f32x4 f) {
   return __builtin_wasm_trunc_saturate_s_i32x4_f32x4(f);
   // WEBASSEMBLY: call <4 x i32> @llvm.wasm.trunc.saturate.signed.v4i32.v4f32(<4 x float> %f)