instcombine: Migrate strstr optimizations

This patch migrates the strstr optimizations from the simplify-libcalls
pass into the instcombine library call simplifier.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@167682 91177308-0d34-0410-b5e6-96231b3b80d8

lib/Transforms/Scalar/SimplifyLibCalls.cpp

@@ -99,94 +99,11 @@ static bool CallHasFloatingPointArgument(const CallInst *CI) {
   return false;
 }
 
-/// IsOnlyUsedInEqualityComparison - Return true if it is only used in equality
-/// comparisons with With.
-static bool IsOnlyUsedInEqualityComparison(Value *V, Value *With) {
-  for (Value::use_iterator UI = V->use_begin(), E = V->use_end();
-       UI != E; ++UI) {
-    if (ICmpInst *IC = dyn_cast<ICmpInst>(*UI))
-      if (IC->isEquality() && IC->getOperand(1) == With)
-        continue;
-    // Unknown instruction.
-    return false;
-  }
-  return true;
-}
-
 //===----------------------------------------------------------------------===//
-// String and Memory LibCall Optimizations
+// Memory LibCall Optimizations
 //===----------------------------------------------------------------------===//
 
 namespace {
-//===---------------------------------------===//
-// 'strstr' Optimizations
-
-struct StrStrOpt : public LibCallOptimization {
-  virtual Value *CallOptimizer(Function *Callee, CallInst *CI, IRBuilder<> &B) {
-    FunctionType *FT = Callee->getFunctionType();
-    if (FT->getNumParams() != 2 ||
-        !FT->getParamType(0)->isPointerTy() ||
-        !FT->getParamType(1)->isPointerTy() ||
-        !FT->getReturnType()->isPointerTy())
-      return 0;
-
-    // fold strstr(x, x) -> x.
-    if (CI->getArgOperand(0) == CI->getArgOperand(1))
-      return B.CreateBitCast(CI->getArgOperand(0), CI->getType());
-
-    // fold strstr(a, b) == a -> strncmp(a, b, strlen(b)) == 0
-    if (TD && IsOnlyUsedInEqualityComparison(CI, CI->getArgOperand(0))) {
-      Value *StrLen = EmitStrLen(CI->getArgOperand(1), B, TD, TLI);
-      if (!StrLen)
-        return 0;
-      Value *StrNCmp = EmitStrNCmp(CI->getArgOperand(0), CI->getArgOperand(1),
-                                   StrLen, B, TD, TLI);
-      if (!StrNCmp)
-        return 0;
-      for (Value::use_iterator UI = CI->use_begin(), UE = CI->use_end();
-           UI != UE; ) {
-        ICmpInst *Old = cast<ICmpInst>(*UI++);
-        Value *Cmp = B.CreateICmp(Old->getPredicate(), StrNCmp,
-                                  ConstantInt::getNullValue(StrNCmp->getType()),
-                                  "cmp");
-        Old->replaceAllUsesWith(Cmp);
-        Old->eraseFromParent();
-      }
-      return CI;
-    }
-
-    // See if either input string is a constant string.
-    StringRef SearchStr, ToFindStr;
-    bool HasStr1 = getConstantStringInfo(CI->getArgOperand(0), SearchStr);
-    bool HasStr2 = getConstantStringInfo(CI->getArgOperand(1), ToFindStr);
-
-    // fold strstr(x, "") -> x.
-    if (HasStr2 && ToFindStr.empty())
-      return B.CreateBitCast(CI->getArgOperand(0), CI->getType());
-
-    // If both strings are known, constant fold it.
-    if (HasStr1 && HasStr2) {
-      std::string::size_type Offset = SearchStr.find(ToFindStr);
-
-      if (Offset == StringRef::npos) // strstr("foo", "bar") -> null
-        return Constant::getNullValue(CI->getType());
-
-      // strstr("abcd", "bc") -> gep((char*)"abcd", 1)
-      Value *Result = CastToCStr(CI->getArgOperand(0), B);
-      Result = B.CreateConstInBoundsGEP1_64(Result, Offset, "strstr");
-      return B.CreateBitCast(Result, CI->getType());
-    }
-
-    // fold strstr(x, "y") -> strchr(x, 'y').
-    if (HasStr2 && ToFindStr.size() == 1) {
-      Value *StrChr= EmitStrChr(CI->getArgOperand(0), ToFindStr[0], B, TD, TLI);
-      return StrChr ? B.CreateBitCast(StrChr, CI->getType()) : 0;
-    }
-    return 0;
-  }
-};
-
-
 //===---------------------------------------===//
 // 'memcmp' Optimizations
 
@@ -969,8 +886,7 @@ namespace {
     TargetLibraryInfo *TLI;
 
     StringMap<LibCallOptimization*> Optimizations;
-    // String and Memory LibCall Optimizations
-    StrStrOpt StrStr;
+    // Memory LibCall Optimizations
     MemCmpOpt MemCmp; MemCpyOpt MemCpy; MemMoveOpt MemMove; MemSetOpt MemSet;
     // Math Library Optimizations
     CosOpt Cos; PowOpt Pow; Exp2Opt Exp2;
@@ -1037,8 +953,7 @@ void SimplifyLibCalls::AddOpt(LibFunc::Func F1, LibFunc::Func F2,
 /// Optimizations - Populate the Optimizations map with all the optimizations
 /// we know.
 void SimplifyLibCalls::InitOptimizations() {
-  // String and Memory LibCall Optimizations
-  Optimizations["strstr"] = &StrStr;
+  // Memory LibCall Optimizations
   Optimizations["memcmp"] = &MemCmp;
   AddOpt(LibFunc::memcpy, &MemCpy);
   Optimizations["memmove"] = &MemMove;

lib/Transforms/Utils/SimplifyLibCalls.cpp

@@ -86,6 +86,20 @@ static bool isOnlyUsedInZeroEqualityComparison(Value *V) {
   return true;
 }
 
+/// isOnlyUsedInEqualityComparison - Return true if it is only used in equality
+/// comparisons with With.
+static bool isOnlyUsedInEqualityComparison(Value *V, Value *With) {
+  for (Value::use_iterator UI = V->use_begin(), E = V->use_end();
+       UI != E; ++UI) {
+    if (ICmpInst *IC = dyn_cast<ICmpInst>(*UI))
+      if (IC->isEquality() && IC->getOperand(1) == With)
+        continue;
+    // Unknown instruction.
+    return false;
+  }
+  return true;
+}
+
 //===----------------------------------------------------------------------===//
 // Fortified Library Call Optimizations
 //===----------------------------------------------------------------------===//
@@ -836,6 +850,70 @@ struct StrCSpnOpt : public LibCallOptimization {
   }
 };
 
+struct StrStrOpt : public LibCallOptimization {
+  virtual Value *callOptimizer(Function *Callee, CallInst *CI, IRBuilder<> &B) {
+    FunctionType *FT = Callee->getFunctionType();
+    if (FT->getNumParams() != 2 ||
+        !FT->getParamType(0)->isPointerTy() ||
+        !FT->getParamType(1)->isPointerTy() ||
+        !FT->getReturnType()->isPointerTy())
+      return 0;
+
+    // fold strstr(x, x) -> x.
+    if (CI->getArgOperand(0) == CI->getArgOperand(1))
+      return B.CreateBitCast(CI->getArgOperand(0), CI->getType());
+
+    // fold strstr(a, b) == a -> strncmp(a, b, strlen(b)) == 0
+    if (TD && isOnlyUsedInEqualityComparison(CI, CI->getArgOperand(0))) {
+      Value *StrLen = EmitStrLen(CI->getArgOperand(1), B, TD, TLI);
+      if (!StrLen)
+        return 0;
+      Value *StrNCmp = EmitStrNCmp(CI->getArgOperand(0), CI->getArgOperand(1),
+                                   StrLen, B, TD, TLI);
+      if (!StrNCmp)
+        return 0;
+      for (Value::use_iterator UI = CI->use_begin(), UE = CI->use_end();
+           UI != UE; ) {
+        ICmpInst *Old = cast<ICmpInst>(*UI++);
+        Value *Cmp = B.CreateICmp(Old->getPredicate(), StrNCmp,
+                                  ConstantInt::getNullValue(StrNCmp->getType()),
+                                  "cmp");
+        LCS->replaceAllUsesWith(Old, Cmp);
+      }
+      return CI;
+    }
+
+    // See if either input string is a constant string.
+    StringRef SearchStr, ToFindStr;
+    bool HasStr1 = getConstantStringInfo(CI->getArgOperand(0), SearchStr);
+    bool HasStr2 = getConstantStringInfo(CI->getArgOperand(1), ToFindStr);
+
+    // fold strstr(x, "") -> x.
+    if (HasStr2 && ToFindStr.empty())
+      return B.CreateBitCast(CI->getArgOperand(0), CI->getType());
+
+    // If both strings are known, constant fold it.
+    if (HasStr1 && HasStr2) {
+      std::string::size_type Offset = SearchStr.find(ToFindStr);
+
+      if (Offset == StringRef::npos) // strstr("foo", "bar") -> null
+        return Constant::getNullValue(CI->getType());
+
+      // strstr("abcd", "bc") -> gep((char*)"abcd", 1)
+      Value *Result = CastToCStr(CI->getArgOperand(0), B);
+      Result = B.CreateConstInBoundsGEP1_64(Result, Offset, "strstr");
+      return B.CreateBitCast(Result, CI->getType());
+    }
+
+    // fold strstr(x, "y") -> strchr(x, 'y').
+    if (HasStr2 && ToFindStr.size() == 1) {
+      Value *StrChr= EmitStrChr(CI->getArgOperand(0), ToFindStr[0], B, TD, TLI);
+      return StrChr ? B.CreateBitCast(StrChr, CI->getType()) : 0;
+    }
+    return 0;
+  }
+};
+
 } // End anonymous namespace.
 
 namespace llvm {
@@ -869,6 +947,7 @@ class LibCallSimplifierImpl {
   StrToOpt StrTo;
   StrSpnOpt StrSpn;
   StrCSpnOpt StrCSpn;
+  StrStrOpt StrStr;
 
   void initOptimizations();
   void addOpt(LibFunc::Func F, LibCallOptimization* Opt);
@@ -914,6 +993,7 @@ void LibCallSimplifierImpl::initOptimizations() {
   addOpt(LibFunc::strtoull, &StrTo);
   addOpt(LibFunc::strspn, &StrSpn);
   addOpt(LibFunc::strcspn, &StrCSpn);
+  addOpt(LibFunc::strstr, &StrStr);
 }
 
 Value *LibCallSimplifierImpl::optimizeCall(CallInst *CI) {

test/Transforms/InstCombine/strstr-1.ll

@@ -0,0 +1,65 @@
+; Test that the strstr library call simplifier works correctly.
+;
+; RUN: opt < %s -instcombine -S | FileCheck %s
+
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+
+@.str = private constant [1 x i8] zeroinitializer
+@.str1 = private constant [2 x i8] c"a\00"
+@.str2 = private constant [6 x i8] c"abcde\00"
+@.str3 = private constant [4 x i8] c"bcd\00"
+
+declare i8* @strstr(i8*, i8*)
+
+; Check strstr(str, "") -> str.
+
+define i8* @test_simplify1(i8* %str) {
+; CHECK: @test_simplify1
+  %pat = getelementptr inbounds [1 x i8]* @.str, i32 0, i32 0
+  %ret = call i8* @strstr(i8* %str, i8* %pat)
+  ret i8* %ret
+; CHECK-NEXT: ret i8* %str
+}
+
+; Check strstr(str, "a") -> strchr(str, 'a').
+
+define i8* @test_simplify2(i8* %str) {
+; CHECK: @test_simplify2
+  %pat = getelementptr inbounds [2 x i8]* @.str1, i32 0, i32 0
+  %ret = call i8* @strstr(i8* %str, i8* %pat)
+  ret i8* %ret
+; CHECK-NEXT: @strchr(i8* %str, i32 97)
+}
+
+; Check strstr("abcde", "bcd") -> "abcde" + 1.
+
+define i8* @test_simplify3() {
+; CHECK: @test_simplify3
+  %str = getelementptr inbounds [6 x i8]* @.str2, i32 0, i32 0
+  %pat = getelementptr inbounds [4 x i8]* @.str3, i32 0, i32 0
+  %ret = call i8* @strstr(i8* %str, i8* %pat)
+  ret i8* %ret
+; CHECK-NEXT: getelementptr inbounds ([6 x i8]* @.str2, i64 0, i64 1)
+}
+
+; Check strstr(str, str) -> str.
+
+define i8* @test_simplify4(i8* %str) {
+; CHECK: @test_simplify4
+  %ret = call i8* @strstr(i8* %str, i8* %str)
+  ret i8* %ret
+; CHECK-NEXT: ret i8* %str
+}
+
+; Check strstr(str, pat) == str -> strncmp(str, pat, strlen(str)) == 0.
+
+define i1 @test_simplify5(i8* %str, i8* %pat) {
+; CHECK: @test_simplify5
+  %ret = call i8* @strstr(i8* %str, i8* %pat)
+  %cmp = icmp eq i8* %ret, %str
+  ret i1 %cmp
+; CHECK: [[LEN:%[a-z]+]] = call {{i[0-9]+}} @strlen(i8* %pat)
+; CHECK: [[NCMP:%[a-z]+]] = call {{i[0-9]+}} @strncmp(i8* %str, i8* %pat, {{i[0-9]+}} [[LEN]])
+; CHECK: icmp eq {{i[0-9]+}} [[NCMP]], 0
+; CHECK: ret i1
+}

test/Transforms/InstCombine/strstr-2.ll

@@ -0,0 +1,18 @@
+; Test that the strstr library call simplifier works correctly.
+;
+; RUN: opt < %s -instcombine -S | FileCheck %s
+
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+
+@null = private constant [1 x i8] zeroinitializer
+
+declare i8 @strstr(i8*, i8*)
+
+define i8 @test_no_simplify1(i8* %str) {
+; CHECK: @test_no_simplify1
+  %pat = getelementptr inbounds [1 x i8]* @null, i32 0, i32 0
+  %ret = call i8 @strstr(i8* %str, i8* %pat)
+; CHECK-NEXT: call i8 @strstr
+  ret i8 %ret
+; CHECK-NEXT: ret i8 %ret
+}

test/Transforms/SimplifyLibCalls/StrStr.ll

@@ -1,60 +0,0 @@
-; RUN: opt < %s -simplify-libcalls -S | FileCheck %s
-; PR5783
-
-target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128-n8:16:32"
-target triple = "i386-apple-darwin9.0"
-
-@.str = private constant [1 x i8] zeroinitializer ; <[1 x i8]*> [#uses=1]
-@.str1 = private constant [2 x i8] c"a\00"        ; <[2 x i8]*> [#uses=1]
-@.str2 = private constant [6 x i8] c"abcde\00"    ; <[6 x i8]*> [#uses=1]
-@.str3 = private constant [4 x i8] c"bcd\00"      ; <[4 x i8]*> [#uses=1]
-
-define i8* @test1(i8* %P) nounwind readonly {
-entry:
-  %call = tail call i8* @strstr(i8* %P, i8* getelementptr inbounds ([1 x i8]* @.str, i32 0, i32 0)) nounwind ; <i8*> [#uses=1]
-  ret i8* %call
-; strstr(P, "") -> P
-; CHECK: @test1
-; CHECK: ret i8* %P
-}
-
-declare i8* @strstr(i8*, i8* nocapture) nounwind readonly
-
-define i8* @test2(i8* %P) nounwind readonly {
-entry:
-  %call = tail call i8* @strstr(i8* %P, i8* getelementptr inbounds ([2 x i8]* @.str1, i32 0, i32 0)) nounwind ; <i8*> [#uses=1]
-  ret i8* %call
-; strstr(P, "a") -> strchr(P, 'a')
-; CHECK: @test2
-; CHECK: @strchr(i8* %P, i32 97)
-}
-
-define i8* @test3(i8* nocapture %P) nounwind readonly {
-entry:
-  %call = tail call i8* @strstr(i8* getelementptr inbounds ([6 x i8]* @.str2, i32 0, i32 0), i8* getelementptr inbounds ([4 x i8]* @.str3, i32 0, i32 0)) nounwind ; <i8*> [#uses=1]
-  ret i8* %call
-; strstr("abcde", "bcd") -> "abcde"+1
-; CHECK: @test3
-; CHECK: getelementptr inbounds ([6 x i8]* @.str2, i32 0, i64 1)
-}
-
-define i8* @test4(i8* %P) nounwind readonly {
-entry:
-  %call = tail call i8* @strstr(i8* %P, i8* %P) nounwind ; <i8*> [#uses=1]
-  ret i8* %call
-; strstr(P, P) -> P
-; CHECK: @test4
-; CHECK: ret i8* %P
-}
-
-define i1 @test5(i8* %P, i8* %Q) nounwind readonly {
-entry:
-  %call = tail call i8* @strstr(i8* %P, i8* %Q) nounwind ; <i8*> [#uses=1]
-  %cmp = icmp eq i8* %call, %P
-  ret i1 %cmp
-; CHECK: @test5
-; CHECK: [[LEN:%[a-z]+]] = call {{i[0-9]+}} @strlen(i8* %Q)
-; CHECK: [[NCMP:%[a-z]+]] = call {{i[0-9]+}} @strncmp(i8* %P, i8* %Q, {{i[0-9]+}} [[LEN]])
-; CHECK: icmp eq {{i[0-9]+}} [[NCMP]], 0
-; CHECK: ret i1
-}