Enable simplify libcalls for ARM PCS

Teach SimplifyLibcalls that in can treat functions annotated with
apcs, aapcs or aapcs_vfp like normal C functions if they only take
and return integer or pointer values, and the target is not iOS.

Differential Revision: https://reviews.llvm.org/D24453

llvm-svn: 281322
This commit is contained in:
Sam Parker 2016-09-13 12:10:14 +00:00
parent 544b1df64f
commit 214f7bf5cc
3 changed files with 264 additions and 3 deletions

View File

@ -56,6 +56,38 @@ static bool ignoreCallingConv(LibFunc::Func Func) {
Func == LibFunc::llabs || Func == LibFunc::strlen;
}
static bool isCallingConvCCompatible(CallInst *CI) {
switch(CI->getCallingConv()) {
default:
return false;
case llvm::CallingConv::C:
return true;
case llvm::CallingConv::ARM_APCS:
case llvm::CallingConv::ARM_AAPCS:
case llvm::CallingConv::ARM_AAPCS_VFP: {
// The iOS ABI diverges from the standard in some cases, so for now don't
// try to simplify those calls.
if (Triple(CI->getModule()->getTargetTriple()).isiOS())
return false;
auto *FuncTy = CI->getFunctionType();
if (!FuncTy->getReturnType()->isPointerTy() &&
!FuncTy->getReturnType()->isIntegerTy() &&
!FuncTy->getReturnType()->isVoidTy())
return false;
for (auto Param : FuncTy->params()) {
if (!Param->isPointerTy() && !Param->isIntegerTy())
return false;
}
return true;
}
}
return false;
}
/// Return true if it only matters that the value is equal or not-equal to zero.
static bool isOnlyUsedInZeroEqualityComparison(Value *V) {
for (User *U : V->users()) {
@ -1898,7 +1930,7 @@ Value *LibCallSimplifier::optimizeStringMemoryLibCall(CallInst *CI,
if (TLI->getLibFunc(*Callee, Func) && TLI->has(Func)) {
// Make sure we never change the calling convention.
assert((ignoreCallingConv(Func) ||
CI->getCallingConv() == llvm::CallingConv::C) &&
isCallingConvCCompatible(CI)) &&
"Optimizing string/memory libcall would change the calling convention");
switch (Func) {
case LibFunc::strcat:
@ -1965,7 +1997,7 @@ Value *LibCallSimplifier::optimizeCall(CallInst *CI) {
SmallVector<OperandBundleDef, 2> OpBundles;
CI->getOperandBundlesAsDefs(OpBundles);
IRBuilder<> Builder(CI, /*FPMathTag=*/nullptr, OpBundles);
bool isCallingConvC = CI->getCallingConv() == llvm::CallingConv::C;
bool isCallingConvC = isCallingConvCCompatible(CI);
// Command-line parameter overrides instruction attribute.
if (EnableUnsafeFPShrink.getNumOccurrences() > 0)
@ -2321,7 +2353,7 @@ Value *FortifiedLibCallSimplifier::optimizeCall(CallInst *CI) {
SmallVector<OperandBundleDef, 2> OpBundles;
CI->getOperandBundlesAsDefs(OpBundles);
IRBuilder<> Builder(CI, /*FPMathTag=*/nullptr, OpBundles);
bool isCallingConvC = CI->getCallingConv() == llvm::CallingConv::C;
bool isCallingConvC = isCallingConvCCompatible(CI);
// First, check that this is a known library functions and that the prototype
// is correct.

View File

@ -0,0 +1,153 @@
; Test that the strcmp library call simplifier works correctly.
; RUN: opt < %s -instcombine -S | FileCheck %s
target datalayout = "e-m:e-p:32:32-i64:64-v128:64:128-a:0:32-n32-S64"
@hello = constant [6 x i8] c"hello\00"
@hell = constant [5 x i8] c"hell\00"
@bell = constant [5 x i8] c"bell\00"
@null = constant [1 x i8] zeroinitializer
declare i32 @strcmp(i8*, i8*)
; strcmp("", x) -> -*x
define arm_aapcscc i32 @test1(i8* %str2) {
; CHECK-LABEL: @test1(
; CHECK: %strcmpload = load i8, i8* %str
; CHECK: %1 = zext i8 %strcmpload to i32
; CHECK: %2 = sub nsw i32 0, %1
; CHECK: ret i32 %2
%str1 = getelementptr inbounds [1 x i8], [1 x i8]* @null, i32 0, i32 0
%temp1 = call arm_apcscc i32 @strcmp(i8* %str1, i8* %str2)
ret i32 %temp1
}
; strcmp(x, "") -> *x
define arm_aapcscc i32 @test2(i8* %str1) {
; CHECK-LABEL: @test2(
; CHECK: %strcmpload = load i8, i8* %str
; CHECK: %1 = zext i8 %strcmpload to i32
; CHECK: ret i32 %1
%str2 = getelementptr inbounds [1 x i8], [1 x i8]* @null, i32 0, i32 0
%temp1 = call arm_aapcscc i32 @strcmp(i8* %str1, i8* %str2)
ret i32 %temp1
}
; strcmp(x, y) -> cnst
define arm_aapcscc i32 @test3() {
; CHECK-LABEL: @test3(
; CHECK: ret i32 -1
%str1 = getelementptr inbounds [5 x i8], [5 x i8]* @hell, i32 0, i32 0
%str2 = getelementptr inbounds [6 x i8], [6 x i8]* @hello, i32 0, i32 0
%temp1 = call arm_aapcscc i32 @strcmp(i8* %str1, i8* %str2)
ret i32 %temp1
}
define arm_aapcscc i32 @test4() {
; CHECK-LABEL: @test4(
; CHECK: ret i32 1
%str1 = getelementptr inbounds [5 x i8], [5 x i8]* @hell, i32 0, i32 0
%str2 = getelementptr inbounds [1 x i8], [1 x i8]* @null, i32 0, i32 0
%temp1 = call arm_aapcscc i32 @strcmp(i8* %str1, i8* %str2)
ret i32 %temp1
}
; strcmp(x, y) -> memcmp(x, y, <known length>)
; (This transform is rather difficult to trigger in a useful manner)
define arm_aapcscc i32 @test5(i1 %b) {
; CHECK-LABEL: @test5(
; CHECK: %memcmp = call i32 @memcmp(i8* getelementptr inbounds ([6 x i8], [6 x i8]* @hello, i32 0, i32 0), i8* %str2, i32 5)
; CHECK: ret i32 %memcmp
%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 arm_aapcscc i32 @strcmp(i8* %str1, i8* %str2)
ret i32 %temp3
}
; strcmp(x,x) -> 0
define arm_aapcscc i32 @test6(i8* %str) {
; CHECK-LABEL: @test6(
; CHECK: ret i32 0
%temp1 = call arm_aapcscc i32 @strcmp(i8* %str, i8* %str)
ret i32 %temp1
}
; strcmp("", x) -> -*x
define arm_aapcs_vfpcc i32 @test1_vfp(i8* %str2) {
; CHECK-LABEL: @test1_vfp(
; CHECK: %strcmpload = load i8, i8* %str
; CHECK: %1 = zext i8 %strcmpload to i32
; CHECK: %2 = sub nsw i32 0, %1
; CHECK: ret i32 %2
%str1 = getelementptr inbounds [1 x i8], [1 x i8]* @null, i32 0, i32 0
%temp1 = call arm_aapcs_vfpcc i32 @strcmp(i8* %str1, i8* %str2)
ret i32 %temp1
}
; strcmp(x, "") -> *x
define arm_aapcs_vfpcc i32 @test2_vfp(i8* %str1) {
; CHECK-LABEL: @test2_vfp(
; CHECK: %strcmpload = load i8, i8* %str
; CHECK: %1 = zext i8 %strcmpload to i32
; CHECK: ret i32 %1
%str2 = getelementptr inbounds [1 x i8], [1 x i8]* @null, i32 0, i32 0
%temp1 = call arm_aapcs_vfpcc i32 @strcmp(i8* %str1, i8* %str2)
ret i32 %temp1
}
; strcmp(x, y) -> cnst
define arm_aapcs_vfpcc i32 @test3_vfp() {
; CHECK-LABEL: @test3_vfp(
; CHECK: ret i32 -1
%str1 = getelementptr inbounds [5 x i8], [5 x i8]* @hell, i32 0, i32 0
%str2 = getelementptr inbounds [6 x i8], [6 x i8]* @hello, i32 0, i32 0
%temp1 = call arm_aapcs_vfpcc i32 @strcmp(i8* %str1, i8* %str2)
ret i32 %temp1
}
define arm_aapcs_vfpcc i32 @test4_vfp() {
; CHECK-LABEL: @test4_vfp(
; CHECK: ret i32 1
%str1 = getelementptr inbounds [5 x i8], [5 x i8]* @hell, i32 0, i32 0
%str2 = getelementptr inbounds [1 x i8], [1 x i8]* @null, i32 0, i32 0
%temp1 = call arm_aapcs_vfpcc i32 @strcmp(i8* %str1, i8* %str2)
ret i32 %temp1
}
; strcmp(x, y) -> memcmp(x, y, <known length>)
; (This transform is rather difficult to trigger in a useful manner)
define arm_aapcs_vfpcc i32 @test5_vfp(i1 %b) {
; CHECK-LABEL: @test5_vfp(
; CHECK: %memcmp = call i32 @memcmp(i8* getelementptr inbounds ([6 x i8], [6 x i8]* @hello, i32 0, i32 0), i8* %str2, i32 5)
; CHECK: ret i32 %memcmp
%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 arm_aapcs_vfpcc i32 @strcmp(i8* %str1, i8* %str2)
ret i32 %temp3
}
; strcmp(x,x) -> 0
define arm_aapcs_vfpcc i32 @test6_vfp(i8* %str) {
; CHECK-LABEL: @test6_vfp(
; CHECK: ret i32 0
%temp1 = call arm_aapcs_vfpcc i32 @strcmp(i8* %str, i8* %str)
ret i32 %temp1
}

View File

@ -0,0 +1,76 @@
; Test that the strcpy library call simplifier works correctly for ARM procedure calls
; RUN: opt < %s -instcombine -S | FileCheck %s
;
; This transformation requires the pointer size, as it assumes that size_t is
; the size of a pointer.
target datalayout = "e-m:e-p:32:32-i64:64-v128:64:128-a:0:32-n32-S64"
@hello = constant [6 x i8] c"hello\00"
@a = common global [32 x i8] zeroinitializer, align 1
@b = common global [32 x i8] zeroinitializer, align 1
declare i8* @strcpy(i8*, i8*)
define arm_aapcscc void @test_simplify1() {
; CHECK-LABEL: @test_simplify1(
%dst = getelementptr [32 x i8], [32 x i8]* @a, i32 0, i32 0
%src = getelementptr [6 x i8], [6 x i8]* @hello, i32 0, i32 0
call arm_aapcscc i8* @strcpy(i8* %dst, i8* %src)
; CHECK: @llvm.memcpy.p0i8.p0i8.i32
ret void
}
define arm_aapcscc i8* @test_simplify2() {
; CHECK-LABEL: @test_simplify2(
%dst = getelementptr [32 x i8], [32 x i8]* @a, i32 0, i32 0
%ret = call arm_aapcscc i8* @strcpy(i8* %dst, i8* %dst)
; CHECK: ret i8* getelementptr inbounds ([32 x i8], [32 x i8]* @a, i32 0, i32 0)
ret i8* %ret
}
define arm_aapcscc i8* @test_no_simplify1() {
; CHECK-LABEL: @test_no_simplify1(
%dst = getelementptr [32 x i8], [32 x i8]* @a, i32 0, i32 0
%src = getelementptr [32 x i8], [32 x i8]* @b, i32 0, i32 0
%ret = call arm_aapcscc i8* @strcpy(i8* %dst, i8* %src)
; CHECK: call arm_aapcscc i8* @strcpy
ret i8* %ret
}
define arm_aapcs_vfpcc void @test_simplify1_vfp() {
; CHECK-LABEL: @test_simplify1_vfp(
%dst = getelementptr [32 x i8], [32 x i8]* @a, i32 0, i32 0
%src = getelementptr [6 x i8], [6 x i8]* @hello, i32 0, i32 0
call arm_aapcs_vfpcc i8* @strcpy(i8* %dst, i8* %src)
; CHECK: @llvm.memcpy.p0i8.p0i8.i32
ret void
}
define arm_aapcs_vfpcc i8* @test_simplify2_vfp() {
; CHECK-LABEL: @test_simplify2_vfp(
%dst = getelementptr [32 x i8], [32 x i8]* @a, i32 0, i32 0
%ret = call arm_aapcs_vfpcc i8* @strcpy(i8* %dst, i8* %dst)
; CHECK: ret i8* getelementptr inbounds ([32 x i8], [32 x i8]* @a, i32 0, i32 0)
ret i8* %ret
}
define arm_aapcs_vfpcc i8* @test_no_simplify1_vfp() {
; CHECK-LABEL: @test_no_simplify1_vfp(
%dst = getelementptr [32 x i8], [32 x i8]* @a, i32 0, i32 0
%src = getelementptr [32 x i8], [32 x i8]* @b, i32 0, i32 0
%ret = call arm_aapcs_vfpcc i8* @strcpy(i8* %dst, i8* %src)
; CHECK: call arm_aapcs_vfpcc i8* @strcpy
ret i8* %ret
}