maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[PowerPC] add store (load float*) pattern to isProfitableToHoist 

store (load float*) can be optimized to store(load i32*) in InstCombine pass.

Add store (load float*) to isProfitableToHoist to make sure we don't break
the opt in InstCombine pass.

Reviewed By: jsji

Differential Revision: https://reviews.llvm.org/D82341
This commit is contained in:
Chen Zheng 2020-07-21 20:40:32 -04:00
parent cf55866185
commit e8425b27fe
2 changed files with 46 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

59
llvm/lib/Target/PowerPC/PPCISelLowering.cpp
View File

@ -16381,31 +16381,56 @@ bool PPCTargetLowering::isFMAFasterThanFMulAndFAdd(const Function &F,
}
}
// Currently this is a copy from AArch64TargetLowering::isProfitableToHoist.
// FIXME: add more patterns which are profitable to hoist.
// FIXME: add more patterns which are not profitable to hoist.
bool PPCTargetLowering::isProfitableToHoist(Instruction *I) const {
if (I->getOpcode() != Instruction::FMul)
return true;
if (!I->hasOneUse())
return true;
Instruction *User = I->user_back();
assert(User && "A single use instruction with no uses.");
if (User->getOpcode() != Instruction::FSub &&
User->getOpcode() != Instruction::FAdd)
switch (I->getOpcode()) {
case Instruction::FMul: {
// Don't break FMA, PowerPC prefers FMA.
if (User->getOpcode() != Instruction::FSub &&
User->getOpcode() != Instruction::FAdd)
return true;
const TargetOptions &Options = getTargetMachine().Options;
const Function *F = I->getFunction();
const DataLayout &DL = F->getParent()->getDataLayout();
Type *Ty = User->getOperand(0)->getType();
return !(
isFMAFasterThanFMulAndFAdd(*F, Ty) &&
isOperationLegalOrCustom(ISD::FMA, getValueType(DL, Ty)) &&
(Options.AllowFPOpFusion == FPOpFusion::Fast || Options.UnsafeFPMath));
}
case Instruction::Load: {
// Don't break "store (load float*)" pattern, this pattern will be combined
// to "store (load int32)" in later InstCombine pass. See function
// combineLoadToOperationType. On PowerPC, loading a float point takes more
// cycles than loading a 32 bit integer.
LoadInst *LI = cast<LoadInst>(I);
// For the loads that combineLoadToOperationType does nothing, like
// ordered load, it should be profitable to hoist them.
// For swifterror load, it can only be used for pointer to pointer type, so
// later type check should get rid of this case.
if (!LI->isUnordered())
return true;
if (User->getOpcode() != Instruction::Store)
return true;
if (I->getType()->getTypeID() != Type::FloatTyID)
return true;
return false;
}
default:
return true;
const TargetOptions &Options = getTargetMachine().Options;
const Function *F = I->getFunction();
const DataLayout &DL = F->getParent()->getDataLayout();
Type *Ty = User->getOperand(0)->getType();
return !(
isFMAFasterThanFMulAndFAdd(*F, Ty) &&
isOperationLegalOrCustom(ISD::FMA, getValueType(DL, Ty)) &&
(Options.AllowFPOpFusion == FPOpFusion::Fast || Options.UnsafeFPMath));
}
return true;
}
const MCPhysReg *

7
llvm/test/Transforms/SimplifyCFG/PowerPC/prefer-load-i32.ll
View File

@ -3,7 +3,7 @@
define float @foo(float* %src, float* %dest, i32 signext %count, i32 signext %cond) {
; CHECK-LABEL: @foo(
; CHECK-LABEL: entry:
; CHECK: %0 = load float, float* %arrayidx, align 4
; CHECK-NOT: load float
entry:
%cmp = icmp sgt i32 %cond, 10
%idxprom = sext i32 %count to i64
@ -11,14 +11,15 @@ entry:
br i1 %cmp, label %if.then, label %if.else
; CHECK-LABEL: if.then:
; CHECK-NOT: load float
; CHECK: %0 = load float, float* %arrayidx, align 4
if.then: ; preds = %entry
%0 = load float, float* %arrayidx, align 4
%res = fmul float %0, 3.000000e+00
br label %if.end
; CHECK-LABEL: if.else:
; CHECK-NOT: load float
; CHECK: %1 = load float, float* %arrayidx, align 4
; CHECK: store float %1, float* %arrayidx4, align 4
if.else: ; preds = %entry
%1 = load float, float* %arrayidx, align 4
%idxprom3 = sext i32 %count to i64