From: David L Kreitzer Date: Wed, 13 Apr 2016 14:31:06 +0000 (+0000) Subject: Simplify strlen to a subtraction for certain cases. X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=752c1448fe9c61866393725704de259c9da096c6;p=platform%2Fupstream%2Fllvm.git Simplify strlen to a subtraction for certain cases. Patch by Li Huang (li1.huang@intel.com) Differential Revision: http://reviews.llvm.org/D18230 llvm-svn: 266200 --- diff --git a/llvm/include/llvm/Analysis/ValueTracking.h b/llvm/include/llvm/Analysis/ValueTracking.h index b3b26f2..1f09771 100644 --- a/llvm/include/llvm/Analysis/ValueTracking.h +++ b/llvm/include/llvm/Analysis/ValueTracking.h @@ -26,6 +26,7 @@ namespace llvm { class AssumptionCache; class DataLayout; class DominatorTree; + class GEPOperator; class Instruction; class Loop; class LoopInfo; @@ -183,6 +184,10 @@ namespace llvm { DL); } + /// Returns true if the GEP is based on a pointer to a string (array of i8), + /// and is indexing into this string. + bool isGEPBasedOnPointerToString(const GEPOperator *GEP); + /// getConstantStringInfo - This function computes the length of a /// null-terminated C string pointed to by V. If successful, it returns true /// and returns the string in Str. If unsuccessful, it returns false. This diff --git a/llvm/lib/Analysis/ValueTracking.cpp b/llvm/lib/Analysis/ValueTracking.cpp index 757c3b6..55aa24d 100644 --- a/llvm/lib/Analysis/ValueTracking.cpp +++ b/llvm/lib/Analysis/ValueTracking.cpp @@ -2650,6 +2650,24 @@ Value *llvm::GetPointerBaseWithConstantOffset(Value *Ptr, int64_t &Offset, return Ptr; } +bool llvm::isGEPBasedOnPointerToString(const GEPOperator *GEP) { + // Make sure the GEP has exactly three arguments. + if (GEP->getNumOperands() != 3) + return false; + + // Make sure the index-ee is a pointer to array of i8. + ArrayType *AT = dyn_cast(GEP->getSourceElementType()); + if (!AT || !AT->getElementType()->isIntegerTy(8)) + return false; + + // Check to make sure that the first operand of the GEP is an integer and + // has value 0 so that we are sure we're indexing into the initializer. + const ConstantInt *FirstIdx = dyn_cast(GEP->getOperand(1)); + if (!FirstIdx || !FirstIdx->isZero()) + return false; + + return true; +} /// This function computes the length of a null-terminated C string pointed to /// by V. If successful, it returns true and returns the string in Str. @@ -2664,19 +2682,9 @@ bool llvm::getConstantStringInfo(const Value *V, StringRef &Str, // If the value is a GEP instruction or constant expression, treat it as an // offset. if (const GEPOperator *GEP = dyn_cast(V)) { - // Make sure the GEP has exactly three arguments. - if (GEP->getNumOperands() != 3) - return false; - - // Make sure the index-ee is a pointer to array of i8. - ArrayType *AT = dyn_cast(GEP->getSourceElementType()); - if (!AT || !AT->getElementType()->isIntegerTy(8)) - return false; - - // Check to make sure that the first operand of the GEP is an integer and - // has value 0 so that we are sure we're indexing into the initializer. - const ConstantInt *FirstIdx = dyn_cast(GEP->getOperand(1)); - if (!FirstIdx || !FirstIdx->isZero()) + // The GEP operator should be based on a pointer to string constant, and is + // indexing into the string constant. + if (!isGEPBasedOnPointerToString(GEP)) return false; // If the second index isn't a ConstantInt, then this is a variable index diff --git a/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp b/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp index 35aa8ee..b0c8fc7 100644 --- a/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp +++ b/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp @@ -535,6 +535,57 @@ Value *LibCallSimplifier::optimizeStrLen(CallInst *CI, IRBuilder<> &B) { if (uint64_t Len = GetStringLength(Src)) return ConstantInt::get(CI->getType(), Len - 1); + // If s is a constant pointer pointing to a string literal, we can fold + // strlen(s + x) to strlen(s) - x, when x is known to be in the range + // [0, strlen(s)] or the string has a single null terminator '\0' at the end. + // We only try to simplify strlen when the pointer s points to an array + // of i8. Otherwise, we would need to scale the offset x before doing the + // subtraction. This will make the optimization more complex, and it's not + // very useful because calling strlen for a pointer of other types is + // very uncommon. + if (GEPOperator *GEP = dyn_cast(Src)) { + if (!isGEPBasedOnPointerToString(GEP)) + return nullptr; + + StringRef Str; + if (getConstantStringInfo(GEP->getOperand(0), Str, 0, false)) { + size_t NullTermIdx = Str.find('\0'); + + // If the string does not have '\0', leave it to strlen to compute + // its length. + if (NullTermIdx == StringRef::npos) + return nullptr; + + Value *Offset = GEP->getOperand(2); + unsigned BitWidth = Offset->getType()->getIntegerBitWidth(); + APInt KnownZero(BitWidth, 0); + APInt KnownOne(BitWidth, 0); + computeKnownBits(Offset, KnownZero, KnownOne, DL, 0, nullptr, CI, + nullptr); + KnownZero.flipAllBits(); + size_t ArrSize = + cast(GEP->getSourceElementType())->getNumElements(); + + // KnownZero's bits are flipped, so zeros in KnownZero now represent + // bits known to be zeros in Offset, and ones in KnowZero represent + // bits unknown in Offset. Therefore, Offset is known to be in range + // [0, NullTermIdx] when the flipped KnownZero is non-negative and + // unsigned-less-than NullTermIdx. + // + // If Offset is not provably in the range [0, NullTermIdx], we can still + // optimize if we can prove that the program has undefined behavior when + // Offset is outside that range. That is the case when GEP->getOperand(0) + // is a pointer to an object whose memory extent is NullTermIdx+1. + if ((KnownZero.isNonNegative() && KnownZero.ule(NullTermIdx)) || + (GEP->isInBounds() && isa(GEP->getOperand(0)) && + NullTermIdx == ArrSize - 1)) + return B.CreateSub(ConstantInt::get(CI->getType(), NullTermIdx), + Offset); + } + + return nullptr; + } + // strlen(x?"foo":"bars") --> x ? 3 : 4 if (SelectInst *SI = dyn_cast(Src)) { uint64_t LenTrue = GetStringLength(SI->getTrueValue()); diff --git a/llvm/test/Transforms/InstCombine/strlen-1.ll b/llvm/test/Transforms/InstCombine/strlen-1.ll index 65f742a..f3287c0 100644 --- a/llvm/test/Transforms/InstCombine/strlen-1.ll +++ b/llvm/test/Transforms/InstCombine/strlen-1.ll @@ -1,4 +1,4 @@ -; NOTE: Assertions have been autogenerated by update_test_checks.py +; NOTE: Assertions have been autogenerated by utils/update_test_checks.py ; Test that the strlen library call simplifier works correctly. ; ; RUN: opt < %s -instcombine -S | FileCheck %s @@ -113,9 +113,8 @@ define i32 @test_simplify9(i1 %x) { define i32 @test_simplify10(i32 %x) { ; CHECK-LABEL: @test_simplify10( -; CHECK-NEXT: [[HELLO_P:%.*]] = getelementptr inbounds [6 x i8], [6 x i8]* @hello, i32 0, i32 %x -; CHECK-NEXT: [[HELLO_L:%.*]] = call i32 @strlen(i8* [[HELLO_P]]) -; CHECK-NEXT: ret i32 [[HELLO_L]] +; CHECK-NEXT: [[TMP1:%.*]] = sub i32 5, %x +; CHECK-NEXT: ret i32 [[TMP1]] ; %hello_p = getelementptr inbounds [6 x i8], [6 x i8]* @hello, i32 0, i32 %x %hello_l = call i32 @strlen(i8* %hello_p) @@ -127,9 +126,8 @@ define i32 @test_simplify10(i32 %x) { define i32 @test_simplify11(i32 %x) { ; CHECK-LABEL: @test_simplify11( ; CHECK-NEXT: [[AND:%.*]] = and i32 %x, 7 -; CHECK-NEXT: [[HELLO_P:%.*]] = getelementptr inbounds [13 x i8], [13 x i8]* @null_hello_mid, i32 0, i32 [[AND]] -; CHECK-NEXT: [[HELLO_L:%.*]] = call i32 @strlen(i8* [[HELLO_P]]) -; CHECK-NEXT: ret i32 [[HELLO_L]] +; CHECK-NEXT: [[TMP1:%.*]] = sub nsw i32 9, [[AND]] +; CHECK-NEXT: ret i32 [[TMP1]] ; %and = and i32 %x, 7 %hello_p = getelementptr inbounds [13 x i8], [13 x i8]* @null_hello_mid, i32 0, i32 %and