[SelectionDAG] Allow the user to specify a memeq function.

Summary:
Right now, when we encounter a string equality check,
e.g. `if (memcmp(a, b, s) == 0)`, we try to expand to a comparison if `s` is a
small compile-time constant, and fall back on calling `memcmp()` else.

This is sub-optimal because memcmp has to compute much more than
equality.

This patch replaces `memcmp(a, b, s) == 0` by `bcmp(a, b, s) == 0` on platforms
that support `bcmp`.

`bcmp` can be made much more efficient than `memcmp` because equality
compare is trivially parallel while lexicographic ordering has a chain
dependency.

Subscribers: fedor.sergeev, jyknight, ckennelly, gchatelet, llvm-commits

Differential Revision: https://reviews.llvm.org/D56593

llvm-svn: 355672

llvm/docs/ReleaseNotes.rst

@@ -40,6 +40,11 @@ Non-comprehensive list of changes in this release
    functionality, or simply have a lot to talk about), see the `NOTE` below
    for adding a new subsection.
 
+* The optimizer will now convert calls to memcmp into a calls to bcmp in some
+  circumstances. Users who are building freestanding code (not depending on the
+  platform's libc) without specifying -ffreestanding may need to either pass
+  -fno-builtin-bcmp, or provide a bcmp function.
+
 .. NOTE
    If you would like to document a larger change, then you can add a
    subsection about it right here. You can copy the following boilerplate

llvm/include/llvm/Transforms/Utils/BuildLibCalls.h

@@ -92,6 +92,10 @@ namespace llvm {
   Value *emitMemCmp(Value *Ptr1, Value *Ptr2, Value *Len, IRBuilder<> &B,
                     const DataLayout &DL, const TargetLibraryInfo *TLI);
 
+  /// Emit a call to the bcmp function.
+  Value *emitBCmp(Value *Ptr1, Value *Ptr2, Value *Len, IRBuilder<> &B,
+                  const DataLayout &DL, const TargetLibraryInfo *TLI);
+
   /// Emit a call to the unary function named 'Name' (e.g.  'floor'). This
   /// function is known to take a single of type matching 'Op' and returns one
   /// value with the same type. If 'Op' is a long double, 'l' is added as the

llvm/lib/Analysis/TargetLibraryInfo.cpp

@@ -49,6 +49,16 @@ static bool hasSinCosPiStret(const Triple &T) {
   return true;
 }
 
+static bool hasBcmp(const Triple &TT) {
+  // Posix removed support from bcmp() in 2001, but the glibc and several
+  // implementations of the libc still have it.
+  if (TT.isOSLinux())
+    return TT.isGNUEnvironment() || TT.isMusl();
+  // Both NetBSD and OpenBSD are planning to remove the function. Windows does
+  // not have it.
+  return TT.isOSFreeBSD() || TT.isOSSolaris() || TT.isOSDarwin();
+}
+
 /// Initialize the set of available library functions based on the specified
 /// target triple. This should be carefully written so that a missing target
 /// triple gets a sane set of defaults.
@@ -141,6 +151,9 @@ static void initialize(TargetLibraryInfoImpl &TLI, const Triple &T,
     TLI.setUnavailable(LibFunc_sincospif_stret);
   }
 
+  if (!hasBcmp(T))
+    TLI.setUnavailable(LibFunc_bcmp);
+
   if (T.isMacOSX() && T.getArch() == Triple::x86 &&
       !T.isMacOSXVersionLT(10, 7)) {
     // x86-32 OSX has a scheme where fwrite and fputs (and some other functions

llvm/lib/Transforms/Utils/BuildLibCalls.cpp

@@ -930,28 +930,41 @@ Value *llvm::emitMemChr(Value *Ptr, Value *Val, Value *Len, IRBuilder<> &B,
   return CI;
 }
 
-Value *llvm::emitMemCmp(Value *Ptr1, Value *Ptr2, Value *Len, IRBuilder<> &B,
-                        const DataLayout &DL, const TargetLibraryInfo *TLI) {
-  if (!TLI->has(LibFunc_memcmp))
+// Common code for memcmp() and bcmp(), which have the exact same properties,
+// just a slight difference in semantics.
+static Value *emitMemCmpOrBcmp(llvm::LibFunc libfunc, Value *Ptr1, Value *Ptr2,
+                               Value *Len, IRBuilder<> &B, const DataLayout &DL,
+                               const TargetLibraryInfo *TLI) {
+  if (!TLI->has(libfunc))
     return nullptr;
 
   Module *M = B.GetInsertBlock()->getModule();
-  StringRef MemCmpName = TLI->getName(LibFunc_memcmp);
+  StringRef CmpFnName = TLI->getName(libfunc);
   LLVMContext &Context = B.GetInsertBlock()->getContext();
-  FunctionCallee MemCmp =
-      M->getOrInsertFunction(MemCmpName, B.getInt32Ty(), B.getInt8PtrTy(),
+  FunctionCallee CmpFn =
+      M->getOrInsertFunction(CmpFnName, B.getInt32Ty(), B.getInt8PtrTy(),
                              B.getInt8PtrTy(), DL.getIntPtrType(Context));
-  inferLibFuncAttributes(M, MemCmpName, *TLI);
+  inferLibFuncAttributes(M, CmpFnName, *TLI);
   CallInst *CI = B.CreateCall(
-      MemCmp, {castToCStr(Ptr1, B), castToCStr(Ptr2, B), Len}, MemCmpName);
+      CmpFn, {castToCStr(Ptr1, B), castToCStr(Ptr2, B), Len}, CmpFnName);
 
   if (const Function *F =
-          dyn_cast<Function>(MemCmp.getCallee()->stripPointerCasts()))
+          dyn_cast<Function>(CmpFn.getCallee()->stripPointerCasts()))
     CI->setCallingConv(F->getCallingConv());
 
   return CI;
 }
 
+Value *llvm::emitMemCmp(Value *Ptr1, Value *Ptr2, Value *Len, IRBuilder<> &B,
+                        const DataLayout &DL, const TargetLibraryInfo *TLI) {
+  return emitMemCmpOrBcmp(LibFunc_memcmp, Ptr1, Ptr2, Len, B, DL, TLI);
+}
+
+Value *llvm::emitBCmp(Value *Ptr1, Value *Ptr2, Value *Len, IRBuilder<> &B,
+                      const DataLayout &DL, const TargetLibraryInfo *TLI) {
+  return emitMemCmpOrBcmp(LibFunc_bcmp, Ptr1, Ptr2, Len, B, DL, TLI);
+}
+
 /// Append a suffix to the function name according to the type of 'Op'.
 static void appendTypeSuffix(Value *Op, StringRef &Name,
                              SmallString<20> &NameBuffer) {

llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp

@@ -831,18 +831,9 @@ Value *LibCallSimplifier::optimizeMemChr(CallInst *CI, IRBuilder<> &B) {
   return B.CreateGEP(B.getInt8Ty(), SrcStr, B.getInt64(I), "memchr");
 }
 
-Value *LibCallSimplifier::optimizeMemCmp(CallInst *CI, IRBuilder<> &B) {
-  Value *LHS = CI->getArgOperand(0), *RHS = CI->getArgOperand(1);
-
-  if (LHS == RHS) // memcmp(s,s,x) -> 0
-    return Constant::getNullValue(CI->getType());
-
-  // Make sure we have a constant length.
-  ConstantInt *LenC = dyn_cast<ConstantInt>(CI->getArgOperand(2));
-  if (!LenC)
-    return nullptr;
-
-  uint64_t Len = LenC->getZExtValue();
+static Value *optimizeMemCmpConstantSize(CallInst *CI, Value *LHS, Value *RHS,
+                                         uint64_t Len, IRBuilder<> &B,
+                                         const DataLayout &DL) {
   if (Len == 0) // memcmp(s1,s2,0) -> 0
     return Constant::getNullValue(CI->getType());
 
@@ -912,6 +903,28 @@ Value *LibCallSimplifier::optimizeMemCmp(CallInst *CI, IRBuilder<> &B) {
       Ret = 1;
     return ConstantInt::get(CI->getType(), Ret);
   }
+  return nullptr;
+}
+
+Value *LibCallSimplifier::optimizeMemCmp(CallInst *CI, IRBuilder<> &B) {
+  Value *LHS = CI->getArgOperand(0), *RHS = CI->getArgOperand(1);
+  Value *Size = CI->getArgOperand(2);
+
+  if (LHS == RHS) // memcmp(s,s,x) -> 0
+    return Constant::getNullValue(CI->getType());
+
+  // Handle constant lengths.
+  if (ConstantInt *LenC = dyn_cast<ConstantInt>(Size))
+    if (Value *Res = optimizeMemCmpConstantSize(CI, LHS, RHS,
+                                                LenC->getZExtValue(), B, DL))
+      return Res;
+
+  // memcmp(x, y, Len) == 0 -> bcmp(x, y, Len) == 0
+  // `bcmp` can be more efficient than memcmp because it only has to know that
+  // there is a difference, not where is is.
+  if (isOnlyUsedInZeroEqualityComparison(CI) && TLI->has(LibFunc_bcmp)) {
+    return emitBCmp(LHS, RHS, Size, B, DL, TLI);
+  }
 
   return nullptr;
 }
@@ -1137,10 +1150,10 @@ static Value *optimizeTrigReflections(CallInst *Call, LibFunc Func,
                                       IRBuilder<> &B) {
   if (!isa<FPMathOperator>(Call))
     return nullptr;
-  
+
   IRBuilder<>::FastMathFlagGuard Guard(B);
   B.setFastMathFlags(Call->getFastMathFlags());
-  
+
   // TODO: Can this be shared to also handle LLVM intrinsics?
   Value *X;
   switch (Func) {

llvm/test/CodeGen/X86/memcmp.ll

@@ -1340,3 +1340,70 @@ define i32 @huge_length(i8* %X, i8* %Y) nounwind {
   %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 9223372036854775807) nounwind
   ret i32 %m
 }
+
+define i1 @huge_length_eq(i8* %X, i8* %Y) nounwind {
+; X86-LABEL: huge_length_eq:
+; X86:       # %bb.0:
+; X86-NEXT:    pushl $2147483647 # imm = 0x7FFFFFFF
+; X86-NEXT:    pushl $-1
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    calll memcmp
+; X86-NEXT:    addl $16, %esp
+; X86-NEXT:    testl %eax, %eax
+; X86-NEXT:    sete %al
+; X86-NEXT:    retl
+;
+; X64-LABEL: huge_length_eq:
+; X64:       # %bb.0:
+; X64-NEXT:    pushq %rax
+; X64-NEXT:    movabsq $9223372036854775807, %rdx # imm = 0x7FFFFFFFFFFFFFFF
+; X64-NEXT:    callq memcmp
+; X64-NEXT:    testl %eax, %eax
+; X64-NEXT:    sete %al
+; X64-NEXT:    popq %rcx
+; X64-NEXT:    retq
+
+  %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 9223372036854775807) nounwind
+  %c = icmp eq i32 %m, 0
+  ret i1 %c
+}
+
+; This checks non-constant sizes.
+define i32 @nonconst_length(i8* %X, i8* %Y, i64 %size) nounwind {
+; X86-LABEL: nonconst_length:
+; X86:       # %bb.0:
+; X86-NEXT:    jmp memcmp # TAILCALL
+;
+; X64-LABEL: nonconst_length:
+; X64:       # %bb.0:
+; X64-NEXT:    jmp memcmp # TAILCALL
+  %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 %size) nounwind
+  ret i32 %m
+}
+
+define i1 @nonconst_length_eq(i8* %X, i8* %Y, i64 %size) nounwind {
+; X86-LABEL: nonconst_length_eq:
+; X86:       # %bb.0:
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    calll memcmp
+; X86-NEXT:    addl $16, %esp
+; X86-NEXT:    testl %eax, %eax
+; X86-NEXT:    sete %al
+; X86-NEXT:    retl
+;
+; X64-LABEL: nonconst_length_eq:
+; X64:       # %bb.0:
+; X64-NEXT:    pushq %rax
+; X64-NEXT:    callq memcmp
+; X64-NEXT:    testl %eax, %eax
+; X64-NEXT:    sete %al
+; X64-NEXT:    popq %rcx
+; X64-NEXT:    retq
+  %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 %size) nounwind
+  %c = icmp eq i32 %m, 0
+  ret i1 %c
+}

llvm/test/Transforms/InferFunctionAttrs/annotate.ll

@@ -1,5 +1,5 @@
-; RUN: opt < %s -mtriple=x86_64-- -inferattrs -S | FileCheck %s
-; RUN: opt < %s -mtriple=x86_64-- -passes=inferattrs -S | FileCheck %s
+; RUN: opt < %s -mtriple=x86_64-- -inferattrs -S | FileCheck -check-prefix=CHECK-UNKNOWN %s
+; RUN: opt < %s -mtriple=x86_64-- -passes=inferattrs -S | FileCheck -check-prefix=CHECK-UNKNOWN %s
 ; RUN: opt < %s -mtriple=x86_64-apple-macosx10.8.0 -inferattrs -S | FileCheck -check-prefix=CHECK -check-prefix=CHECK-DARWIN %s
 ; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -inferattrs -S | FileCheck -check-prefix=CHECK -check-prefix=CHECK-LINUX %s
 ; RUN: opt < %s -mtriple=nvptx -inferattrs -S | FileCheck -check-prefix=CHECK-NVPTX %s
@@ -241,7 +241,10 @@ declare i64 @atol(i8*)
 ; CHECK: declare i64 @atoll(i8* nocapture) [[G1]]
 declare i64 @atoll(i8*)
 
-; CHECK: declare i32 @bcmp(i8* nocapture, i8* nocapture, i64) [[G1]]
+; CHECK-DARWIN: declare i32 @bcmp(i8* nocapture, i8* nocapture, i64) [[G1]]
+; CHECK-LINUX: declare i32 @bcmp(i8* nocapture, i8* nocapture, i64) [[G1]]
+; CHECK-UNKNOWN-NOT: declare i32 @bcmp(i8* nocapture, i8* nocapture, i64) [[G1]]
+; CHECK-NVPTX-NOT: declare i32 @bcmp(i8* nocapture, i8* nocapture, i64) [[G1]]
 declare i32 @bcmp(i8*, i8*, i64)
 
 ; CHECK: declare void @bcopy(i8* nocapture readonly, i8* nocapture, i64) [[G0]]

llvm/test/Transforms/InstCombine/memcmp-1.ll

@@ -1,6 +1,7 @@
 ; Test that the memcmp library call simplifier works correctly.
 ;
-; RUN: opt < %s -instcombine -S | FileCheck %s
+; RUN: opt < %s -instcombine -S | FileCheck --check-prefix=CHECK --check-prefix=NOBCMP %s
+; RUN: opt < %s -instcombine -mtriple=x86_64-unknown-linux-gnu -S | FileCheck --check-prefix=CHECK --check-prefix=BCMP %s
 
 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-n8:16:32:64"
 
@@ -130,3 +131,21 @@ define i1 @test_simplify9(i16 %x, i16 %y) {
   %cmp = icmp eq i32 %call, 0
   ret i1 %cmp
 }
+
+; Check memcmp(mem1, mem2, size)==0 -> bcmp(mem1, mem2, size)==0
+
+define i1 @test_simplify10(i8* %mem1, i8* %mem2, i32 %size) {
+; NOBCMP-LABEL: @test_simplify10(
+; NOBCMP-NEXT:    [[CALL:%.*]] = call i32 @memcmp(i8* %mem1, i8* %mem2, i32 %size)
+; NOBCMP-NEXT:    [[CMP:%.*]] = icmp eq i32 [[CALL]], 0
+; NOBCMP-NEXT:    ret i1 [[CMP]]
+;
+; BCMP-LABEL: @test_simplify10(
+; BCMP-NEXT:    [[CALL:%.*]] = call i32 @bcmp(i8* %mem1, i8* %mem2, i32 %size)
+; BCMP-NEXT:    [[CMP:%.*]] = icmp eq i32 [[CALL]], 0
+; BCMP-NEXT:    ret i1 [[CMP]]
+;
+  %call = call i32 @memcmp(i8* %mem1, i8* %mem2, i32 %size)
+  %cmp = icmp eq i32 %call, 0
+  ret i1 %cmp
+}

llvm/test/Transforms/InstCombine/strcmp-1.ll

@@ -1,5 +1,6 @@
 ; Test that the strcmp library call simplifier works correctly.
-; RUN: opt < %s -instcombine -S | FileCheck %s
+; RUN: opt < %s -instcombine -S | FileCheck %s --check-prefix=NOBCMP
+; RUN: opt < %s -instcombine -mtriple=unknown-unknown-linux-gnu -S | FileCheck %s --check-prefix=BCMP
 
 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"
 
@@ -80,3 +81,24 @@ define i32 @test6(i8* %str) {
   %temp1 = call i32 @strcmp(i8* %str, i8* %str)
   ret i32 %temp1
 }
+
+; strcmp(x, y) == 0  -> bcmp(x, y, <known length>)
+define i1 @test7(i1 %b) {
+; BCMP-LABEL: @test7(
+; BCMP: %bcmp = call i32 @bcmp(i8* getelementptr inbounds ([6 x i8], [6 x i8]* @hello, i32 0, i32 0), i8* %str2, i32 5)
+; BCMP: %res = icmp eq i32 %bcmp, 0
+; BCMP: ret i1 %res
+
+; NOBCMP-LABEL: @test7(
+; NOBCMP: %memcmp = call i32 @memcmp(i8* getelementptr inbounds ([6 x i8], [6 x i8]* @hello, i32 0, i32 0), i8* %str2, i32 5)
+; NOBCMP: %res = icmp eq i32 %memcmp, 0
+; NOBCMP: ret i1 %res
+
+  %str1 = getelementptr inbounds [6 x i8], [6 x i8]* @hello, i32 0, i32 0
+  %temp1 = getelementptr inbounds [5 x i8], [5 x i8]* @hell, i32 0, i32 0
+  %temp2 = getelementptr inbounds [5 x i8], [5 x i8]* @bell, i32 0, i32 0
+  %str2 = select i1 %b, i8* %temp1, i8* %temp2
+  %temp3 = call i32 @strcmp(i8* %str1, i8* %str2)
+  %res = icmp eq i32 %temp3, 0
+  ret i1 %res
+}