forked from OSchip/llvm-project
Handle IntToPtr in isBytewiseValue
Summary: This helps with more efficient use of memset for pattern initialization From @pcc prototype for -ftrivial-auto-var-init=pattern optimizations Binary size change on CTMark, (with -fuse-ld=lld -Wl,--icf=all, similar results with default linker options) ``` master patch diff Os 8.238864e+05 8.238864e+05 0.0 O3 1.054797e+06 1.054797e+06 0.0 Os zero 8.292384e+05 8.292384e+05 0.0 O3 zero 1.062626e+06 1.062626e+06 0.0 Os pattern 8.579712e+05 8.338048e+05 -0.030299 O3 pattern 1.090502e+06 1.067574e+06 -0.020481 ``` Zero vs Pattern on master ``` zero pattern diff Os 8.292384e+05 8.579712e+05 0.036578 O3 1.062626e+06 1.090502e+06 0.025124 ``` Zero vs Pattern with the patch ``` zero pattern diff Os 8.292384e+05 8.338048e+05 0.003333 O3 1.062626e+06 1.067574e+06 0.003193 ``` Reviewers: pcc, eugenis Subscribers: hiraditya, cfe-commits, llvm-commits Tags: #clang, #llvm Differential Revision: https://reviews.llvm.org/D63967 llvm-svn: 365858
This commit is contained in:
parent
669ad5ff15
commit
c559e63798
|
@ -1042,14 +1042,8 @@ TEST_UNINIT(intptr4, int*[4]);
|
|||
// CHECK: %uninit = alloca [4 x i32*], align
|
||||
// CHECK-NEXT: call void @{{.*}}used{{.*}}%uninit)
|
||||
// PATTERN-O1-LABEL: @test_intptr4_uninit()
|
||||
// PATTERN-O1: %1 = getelementptr inbounds [4 x i32*], [4 x i32*]* %uninit, i64 0, i64 0
|
||||
// PATTERN-O1-NEXT: store i32* inttoptr (i64 -6148914691236517206 to i32*), i32** %1, align 16
|
||||
// PATTERN-O1-NEXT: %2 = getelementptr inbounds [4 x i32*], [4 x i32*]* %uninit, i64 0, i64 1
|
||||
// PATTERN-O1-NEXT: store i32* inttoptr (i64 -6148914691236517206 to i32*), i32** %2, align 8
|
||||
// PATTERN-O1-NEXT: %3 = getelementptr inbounds [4 x i32*], [4 x i32*]* %uninit, i64 0, i64 2
|
||||
// PATTERN-O1-NEXT: store i32* inttoptr (i64 -6148914691236517206 to i32*), i32** %3, align 16
|
||||
// PATTERN-O1-NEXT: %4 = getelementptr inbounds [4 x i32*], [4 x i32*]* %uninit, i64 0, i64 3
|
||||
// PATTERN-O1-NEXT: store i32* inttoptr (i64 -6148914691236517206 to i32*), i32** %4, align 8
|
||||
// PATTERN-O1: %1 = bitcast [4 x i32*]* %uninit to i8*
|
||||
// PATTERN-O1-NEXT: call void @llvm.memset.p0i8.i64(i8* nonnull align 16 %1, i8 -86, i64 32, i1 false)
|
||||
// ZERO-LABEL: @test_intptr4_uninit()
|
||||
// ZERO: call void @llvm.memset{{.*}}, i8 0,
|
||||
|
||||
|
|
|
@ -3218,6 +3218,17 @@ Value *llvm::isBytewiseValue(Value *V, const DataLayout &DL) {
|
|||
}
|
||||
}
|
||||
|
||||
if (auto *CE = dyn_cast<ConstantExpr>(C)) {
|
||||
if (CE->getOpcode() == Instruction::IntToPtr) {
|
||||
auto PS = DL.getPointerSizeInBits(
|
||||
cast<PointerType>(CE->getType())->getAddressSpace());
|
||||
return isBytewiseValue(
|
||||
ConstantExpr::getIntegerCast(CE->getOperand(0),
|
||||
Type::getIntNTy(Ctx, PS), false),
|
||||
DL);
|
||||
}
|
||||
}
|
||||
|
||||
auto Merge = [&](Value *LHS, Value *RHS) -> Value * {
|
||||
if (LHS == RHS)
|
||||
return LHS;
|
||||
|
|
|
@ -794,11 +794,11 @@ const std::pair<const char *, const char *> IsBytewiseValueTests[] = {
|
|||
"i16* inttoptr (i64 0 to i16*)",
|
||||
},
|
||||
{
|
||||
"",
|
||||
"i8 -1",
|
||||
"i16* inttoptr (i64 -1 to i16*)",
|
||||
},
|
||||
{
|
||||
"",
|
||||
"i8 -86",
|
||||
"i16* inttoptr (i64 -6148914691236517206 to i16*)",
|
||||
},
|
||||
{
|
||||
|
@ -806,7 +806,7 @@ const std::pair<const char *, const char *> IsBytewiseValueTests[] = {
|
|||
"i16* inttoptr (i48 -1 to i16*)",
|
||||
},
|
||||
{
|
||||
"",
|
||||
"i8 -1",
|
||||
"i16* inttoptr (i96 -1 to i16*)",
|
||||
},
|
||||
{
|
||||
|
|
Loading…
Reference in New Issue