Skip to content

AMDGPU: Handle other fmin flavors in fract combine #141987

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
May 29, 2025
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 14 additions & 5 deletions llvm/lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -327,7 +327,7 @@ class AMDGPUCodeGenPrepareImpl

bool visitIntrinsicInst(IntrinsicInst &I);
bool visitBitreverseIntrinsicInst(IntrinsicInst &I);
bool visitMinNum(IntrinsicInst &I);
bool visitFMinLike(IntrinsicInst &I);
bool visitSqrt(IntrinsicInst &I);
bool run();
};
Expand Down Expand Up @@ -2200,7 +2200,9 @@ bool AMDGPUCodeGenPrepareImpl::visitIntrinsicInst(IntrinsicInst &I) {
case Intrinsic::bitreverse:
return visitBitreverseIntrinsicInst(I);
case Intrinsic::minnum:
return visitMinNum(I);
case Intrinsic::minimumnum:
case Intrinsic::minimum:
return visitFMinLike(I);
case Intrinsic::sqrt:
return visitSqrt(I);
default:
Expand All @@ -2219,15 +2221,22 @@ bool AMDGPUCodeGenPrepareImpl::visitBitreverseIntrinsicInst(IntrinsicInst &I) {
}

/// Match non-nan fract pattern.
/// minnum(fsub(x, floor(x)), nextafter(1.0, -1.0)
/// minnum(fsub(x, floor(x)), nextafter(1.0, -1.0))
/// minimumnum(fsub(x, floor(x)), nextafter(1.0, -1.0))
/// minimum(fsub(x, floor(x)), nextafter(1.0, -1.0))
///
/// If fract is a useful instruction for the subtarget. Does not account for the
/// nan handling; the instruction has a nan check on the input value.
Value *AMDGPUCodeGenPrepareImpl::matchFractPat(IntrinsicInst &I) {
if (ST.hasFractBug())
return nullptr;

if (I.getIntrinsicID() != Intrinsic::minnum)
Intrinsic::ID IID = I.getIntrinsicID();

// The value is only used in contexts where we know the input isn't a nan, so
// any of the fmin variants are fine.
if (IID != Intrinsic::minnum &&
IID != Intrinsic::minimumnum & IID != Intrinsic::minimum)
return nullptr;

Type *Ty = I.getType();
Expand Down Expand Up @@ -2273,7 +2282,7 @@ Value *AMDGPUCodeGenPrepareImpl::applyFractPat(IRBuilder<> &Builder,
return insertValues(Builder, FractArg->getType(), ResultVals);
}

bool AMDGPUCodeGenPrepareImpl::visitMinNum(IntrinsicInst &I) {
bool AMDGPUCodeGenPrepareImpl::visitFMinLike(IntrinsicInst &I) {
Value *FractArg = matchFractPat(I);
if (!FractArg)
return false;
Expand Down
Loading
Loading