Skip to content

AMDGPU: Move fpenvIEEEMode into TTI #141945

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.

Sign up for GitHub

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

Open
wants to merge 1 commit into
base: users/arsenm/amdgpu/reduce-cost-f64-copysign
Choose a base branch
from
Open

AMDGPU: Move fpenvIEEEMode into TTI #141945

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
28 changes: 3 additions & 25 deletions llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,28 +60,6 @@ static APFloat fmed3AMDGCN(const APFloat &Src0, const APFloat &Src1,
return maxnum(Src0, Src1);
}

enum class KnownIEEEMode { Unknown, On, Off };

/// Return KnownIEEEMode::On if we know if the use context can assume
/// "amdgpu-ieee"="true" and KnownIEEEMode::Off if we can assume
/// "amdgpu-ieee"="false".
static KnownIEEEMode fpenvIEEEMode(const Instruction &I,
const GCNSubtarget &ST) {
if (!ST.hasIEEEMode()) // Only mode on gfx12
return KnownIEEEMode::On;

const Function *F = I.getFunction();
if (!F)
return KnownIEEEMode::Unknown;

Attribute IEEEAttr = F->getFnAttribute("amdgpu-ieee");
if (IEEEAttr.isValid())
return IEEEAttr.getValueAsBool() ? KnownIEEEMode::On : KnownIEEEMode::Off;

return AMDGPU::isShader(F->getCallingConv()) ? KnownIEEEMode::Off
: KnownIEEEMode::On;
}

// Check if a value can be converted to a 16-bit value without losing
// precision.
// The value is expected to be either a float (IsFloat = true) or an unsigned
Expand Down Expand Up @@ -1003,7 +981,7 @@ GCNTTIImpl::instCombineIntrinsic(InstCombiner &IC, IntrinsicInst &II) const {
// TODO: Also can fold to 2 operands with infinities.
if ((match(Src0, m_APFloat(ConstSrc0)) && ConstSrc0->isNaN()) ||
isa<UndefValue>(Src0)) {
switch (fpenvIEEEMode(II, *ST)) {
switch (fpenvIEEEMode(II)) {
case KnownIEEEMode::On:
// TODO: If Src2 is snan, does it need quieting?
if (ConstSrc0 && ConstSrc0->isSignaling())
Expand All @@ -1018,7 +996,7 @@ GCNTTIImpl::instCombineIntrinsic(InstCombiner &IC, IntrinsicInst &II) const {
}
} else if ((match(Src1, m_APFloat(ConstSrc1)) && ConstSrc1->isNaN()) ||
isa<UndefValue>(Src1)) {
switch (fpenvIEEEMode(II, *ST)) {
switch (fpenvIEEEMode(II)) {
case KnownIEEEMode::On:
// TODO: If Src2 is snan, does it need quieting?
if (ConstSrc1 && ConstSrc1->isSignaling())
Expand All @@ -1034,7 +1012,7 @@ GCNTTIImpl::instCombineIntrinsic(InstCombiner &IC, IntrinsicInst &II) const {
}
} else if ((match(Src2, m_APFloat(ConstSrc2)) && ConstSrc2->isNaN()) ||
isa<UndefValue>(Src2)) {
switch (fpenvIEEEMode(II, *ST)) {
switch (fpenvIEEEMode(II)) {
case KnownIEEEMode::On:
if (ConstSrc2 && ConstSrc2->isSignaling()) {
auto *Quieted = ConstantFP::get(II.getType(), ConstSrc2->makeQuiet());
Expand Down
17 changes: 17 additions & 0 deletions llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1445,3 +1445,20 @@ void GCNTTIImpl::collectKernelLaunchBounds(
LB.push_back({"amdgpu-waves-per-eu[0]", WavesPerEU.first});
LB.push_back({"amdgpu-waves-per-eu[1]", WavesPerEU.second});
}

GCNTTIImpl::KnownIEEEMode
GCNTTIImpl::fpenvIEEEMode(const Instruction &I) const {
if (!ST->hasIEEEMode()) // Only mode on gfx12
return KnownIEEEMode::On;

const Function *F = I.getFunction();
if (!F)
return KnownIEEEMode::Unknown;

Attribute IEEEAttr = F->getFnAttribute("amdgpu-ieee");
if (IEEEAttr.isValid())
return IEEEAttr.getValueAsBool() ? KnownIEEEMode::On : KnownIEEEMode::Off;

return AMDGPU::isShader(F->getCallingConv()) ? KnownIEEEMode::Off
: KnownIEEEMode::On;
}
7 changes: 7 additions & 0 deletions llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -281,6 +281,13 @@ class GCNTTIImpl final : public BasicTTIImplBase<GCNTTIImpl> {
void collectKernelLaunchBounds(
const Function &F,
SmallVectorImpl<std::pair<StringRef, int64_t>> &LB) const override;

enum class KnownIEEEMode { Unknown, On, Off };

/// Return KnownIEEEMode::On if we know if the use context can assume
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
/// Return KnownIEEEMode::On if we know if the use context can assume
/// \returns KnownIEEEMode::On if we know if the use context can assume

/// "amdgpu-ieee"="true" and KnownIEEEMode::Off if we can assume
/// "amdgpu-ieee"="false".
KnownIEEEMode fpenvIEEEMode(const Instruction &I) const;
};

} // end namespace llvm
Expand Down
Loading