AMDGPU: Move fpenvIEEEMode into TTI #141945
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This was referenced May 29, 2025
|
Warning This pull request is not mergeable via GitHub because a downstack PR is open. Once all requirements are satisfied, merge this PR as a stack on Graphite.
This stack of pull requests is managed by Graphite. Learn more about stacking. |
This was referenced May 29, 2025
|
@llvm/pr-subscribers-backend-amdgpu Author: Matt Arsenault (arsenm) ChangesFull diff: https://github.com/llvm/llvm-project/pull/141945.diff 3 Files Affected:
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp b/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp
index 5f6ab24182d5e..b0774385547c6 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp
@@ -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
@@ -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())
@@ -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())
@@ -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());
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
index c1ccc8f6798a6..563c46f57dfa5 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
@@ -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;
+}
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h
index ec298c7e9631a..0fae301abf532 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h
@@ -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
+ /// "amdgpu-ieee"="true" and KnownIEEEMode::Off if we can assume
+ /// "amdgpu-ieee"="false".
+ KnownIEEEMode fpenvIEEEMode(const Instruction &I) const;
};
} // end namespace llvm
|
|
@llvm/pr-subscribers-llvm-analysis Author: Matt Arsenault (arsenm) ChangesFull diff: https://github.com/llvm/llvm-project/pull/141945.diff 3 Files Affected:
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp b/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp
index 5f6ab24182d5e..b0774385547c6 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp
@@ -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
@@ -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())
@@ -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())
@@ -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());
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
index c1ccc8f6798a6..563c46f57dfa5 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
@@ -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;
+}
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h
index ec298c7e9631a..0fae301abf532 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h
@@ -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
+ /// "amdgpu-ieee"="true" and KnownIEEEMode::Off if we can assume
+ /// "amdgpu-ieee"="false".
+ KnownIEEEMode fpenvIEEEMode(const Instruction &I) const;
};
} // end namespace llvm
|
Pierre-vh
approved these changes
Jun 2, 2025
|
|
||
| enum class KnownIEEEMode { Unknown, On, Off }; | ||
|
|
||
| /// Return KnownIEEEMode::On if we know if the use context can assume |
There was a problem hiding this comment.
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 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.