[llvm-branch-commits] [llvm] AMDGPU: Move fpenvIEEEMode into TTI (PR #141945)

2025-06-17 Thread Matt Arsenault via llvm-branch-commits 

arsenm wrote:

### Merge activity

* **Jun 17, 10:54 PM UTC**: A user started a stack merge that includes this 
pull request via 
[Graphite](https://app.graphite.dev/github/pr/llvm/llvm-project/141945).


https://github.com/llvm/llvm-project/pull/141945
___
llvm-branch-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: Move fpenvIEEEMode into TTI (PR #141945)

2025-06-17 Thread Matt Arsenault via llvm-branch-commits 

https://github.com/arsenm updated 
https://github.com/llvm/llvm-project/pull/141945

>From 99162375bef4a757fc95bfba805c559b7b13fbfe Mon Sep 17 00:00:00 2001
From: Matt Arsenault 
Date: Thu, 29 May 2025 11:16:22 +0200
Subject: [PATCH] AMDGPU: Move fpenvIEEEMode into TTI

---
 .../AMDGPU/AMDGPUInstCombineIntrinsic.cpp | 28 ++-
 .../AMDGPU/AMDGPUTargetTransformInfo.cpp  | 17 +++
 .../Target/AMDGPU/AMDGPUTargetTransformInfo.h |  7 +
 3 files changed, 27 insertions(+), 25 deletions(-)

diff --git a/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp 
b/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp
index 9be8821d5bf96..d12170a60905b 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
@@ -1004,7 +982,7 @@ 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(Src0)) {
-  switch (fpenvIEEEMode(II, *ST)) {
+  switch (fpenvIEEEMode(II)) {
   case KnownIEEEMode::On:
 // TODO: If Src2 is snan, does it need quieting?
 if (ConstSrc0 && ConstSrc0->isSignaling())
@@ -1019,7 +997,7 @@ GCNTTIImpl::instCombineIntrinsic(InstCombiner &IC, 
IntrinsicInst &II) const {
   }
 } else if ((match(Src1, m_APFloat(ConstSrc1)) && ConstSrc1->isNaN()) ||
isa(Src1)) {
-  switch (fpenvIEEEMode(II, *ST)) {
+  switch (fpenvIEEEMode(II)) {
   case KnownIEEEMode::On:
 // TODO: If Src2 is snan, does it need quieting?
 if (ConstSrc1 && ConstSrc1->isSignaling())
@@ -1035,7 +1013,7 @@ GCNTTIImpl::instCombineIntrinsic(InstCombiner &IC, 
IntrinsicInst &II) const {
   }
 } else if ((match(Src2, m_APFloat(ConstSrc2)) && ConstSrc2->isNaN()) ||
isa(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 b79c9be3eac93..ce2098a3a19bb 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 {
   void collectKernelLaunchBounds(
   const Function &F,
   SmallVectorImpl> &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".
+

[llvm-branch-commits] [llvm] AMDGPU: Move fpenvIEEEMode into TTI (PR #141945)

2025-06-17 Thread Matt Arsenault via llvm-branch-commits 

https://github.com/arsenm updated 
https://github.com/llvm/llvm-project/pull/141945

>From 99162375bef4a757fc95bfba805c559b7b13fbfe Mon Sep 17 00:00:00 2001
From: Matt Arsenault 
Date: Thu, 29 May 2025 11:16:22 +0200
Subject: [PATCH] AMDGPU: Move fpenvIEEEMode into TTI

---
 .../AMDGPU/AMDGPUInstCombineIntrinsic.cpp | 28 ++-
 .../AMDGPU/AMDGPUTargetTransformInfo.cpp  | 17 +++
 .../Target/AMDGPU/AMDGPUTargetTransformInfo.h |  7 +
 3 files changed, 27 insertions(+), 25 deletions(-)

diff --git a/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp 
b/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp
index 9be8821d5bf96..d12170a60905b 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
@@ -1004,7 +982,7 @@ 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(Src0)) {
-  switch (fpenvIEEEMode(II, *ST)) {
+  switch (fpenvIEEEMode(II)) {
   case KnownIEEEMode::On:
 // TODO: If Src2 is snan, does it need quieting?
 if (ConstSrc0 && ConstSrc0->isSignaling())
@@ -1019,7 +997,7 @@ GCNTTIImpl::instCombineIntrinsic(InstCombiner &IC, 
IntrinsicInst &II) const {
   }
 } else if ((match(Src1, m_APFloat(ConstSrc1)) && ConstSrc1->isNaN()) ||
isa(Src1)) {
-  switch (fpenvIEEEMode(II, *ST)) {
+  switch (fpenvIEEEMode(II)) {
   case KnownIEEEMode::On:
 // TODO: If Src2 is snan, does it need quieting?
 if (ConstSrc1 && ConstSrc1->isSignaling())
@@ -1035,7 +1013,7 @@ GCNTTIImpl::instCombineIntrinsic(InstCombiner &IC, 
IntrinsicInst &II) const {
   }
 } else if ((match(Src2, m_APFloat(ConstSrc2)) && ConstSrc2->isNaN()) ||
isa(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 b79c9be3eac93..ce2098a3a19bb 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 {
   void collectKernelLaunchBounds(
   const Function &F,
   SmallVectorImpl> &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".
+

[llvm-branch-commits] [llvm] AMDGPU: Move fpenvIEEEMode into TTI (PR #141945)

2025-06-17 Thread Matt Arsenault via llvm-branch-commits 

https://github.com/arsenm updated 
https://github.com/llvm/llvm-project/pull/141945

>From 63d221ae57f3fb5f2e41bc29ff93338c209ab0fe Mon Sep 17 00:00:00 2001
From: Matt Arsenault 
Date: Thu, 29 May 2025 11:16:22 +0200
Subject: [PATCH] AMDGPU: Move fpenvIEEEMode into TTI

---
 .../AMDGPU/AMDGPUInstCombineIntrinsic.cpp | 28 ++-
 .../AMDGPU/AMDGPUTargetTransformInfo.cpp  | 17 +++
 .../Target/AMDGPU/AMDGPUTargetTransformInfo.h |  7 +
 3 files changed, 27 insertions(+), 25 deletions(-)

diff --git a/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp 
b/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp
index 9be8821d5bf96..d12170a60905b 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
@@ -1004,7 +982,7 @@ 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(Src0)) {
-  switch (fpenvIEEEMode(II, *ST)) {
+  switch (fpenvIEEEMode(II)) {
   case KnownIEEEMode::On:
 // TODO: If Src2 is snan, does it need quieting?
 if (ConstSrc0 && ConstSrc0->isSignaling())
@@ -1019,7 +997,7 @@ GCNTTIImpl::instCombineIntrinsic(InstCombiner &IC, 
IntrinsicInst &II) const {
   }
 } else if ((match(Src1, m_APFloat(ConstSrc1)) && ConstSrc1->isNaN()) ||
isa(Src1)) {
-  switch (fpenvIEEEMode(II, *ST)) {
+  switch (fpenvIEEEMode(II)) {
   case KnownIEEEMode::On:
 // TODO: If Src2 is snan, does it need quieting?
 if (ConstSrc1 && ConstSrc1->isSignaling())
@@ -1035,7 +1013,7 @@ GCNTTIImpl::instCombineIntrinsic(InstCombiner &IC, 
IntrinsicInst &II) const {
   }
 } else if ((match(Src2, m_APFloat(ConstSrc2)) && ConstSrc2->isNaN()) ||
isa(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 b79c9be3eac93..ce2098a3a19bb 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 {
   void collectKernelLaunchBounds(
   const Function &F,
   SmallVectorImpl> &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".
+

[llvm-branch-commits] [llvm] AMDGPU: Move fpenvIEEEMode into TTI (PR #141945)

2025-06-02 Thread Pierre van Houtryve via llvm-branch-commits 

https://github.com/Pierre-vh edited 
https://github.com/llvm/llvm-project/pull/141945
___
llvm-branch-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: Move fpenvIEEEMode into TTI (PR #141945)

2025-06-02 Thread Pierre van Houtryve via llvm-branch-commits 


@@ -281,6 +281,13 @@ class GCNTTIImpl final : public 
BasicTTIImplBase {
   void collectKernelLaunchBounds(
   const Function &F,
   SmallVectorImpl> &LB) const override;
+
+  enum class KnownIEEEMode { Unknown, On, Off };
+
+  /// Return KnownIEEEMode::On if we know if the use context can assume

Pierre-vh wrote:

```suggestion
  /// \returns KnownIEEEMode::On if we know if the use context can assume
```


https://github.com/llvm/llvm-project/pull/141945
___
llvm-branch-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: Move fpenvIEEEMode into TTI (PR #141945)

2025-06-02 Thread Pierre van Houtryve via llvm-branch-commits 

https://github.com/Pierre-vh approved this pull request.

unrelated to this patch but `KnownIEEEMode::Unknown` looks weird, maybe it 
should just be named `IEEEMode`?

https://github.com/llvm/llvm-project/pull/141945
___
llvm-branch-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: Move fpenvIEEEMode into TTI (PR #141945)

2025-05-29 Thread via llvm-branch-commits 

llvmbot wrote:




@llvm/pr-subscribers-llvm-analysis

Author: Matt Arsenault (arsenm)


Changes



---
Full diff: https://github.com/llvm/llvm-project/pull/141945.diff


3 Files Affected:

- (modified) llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp (+3-25) 
- (modified) llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp (+17) 
- (modified) llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h (+7) 


``diff
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(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(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(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 {
   void collectKernelLaunchBounds(
   const Function &F,
   SmallVectorImpl> &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-branch-commits] [llvm] AMDGPU: Move fpenvIEEEMode into TTI (PR #141945)

2025-05-29 Thread via llvm-branch-commits 

llvmbot wrote:




@llvm/pr-subscribers-backend-amdgpu

Author: Matt Arsenault (arsenm)


Changes



---
Full diff: https://github.com/llvm/llvm-project/pull/141945.diff


3 Files Affected:

- (modified) llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp (+3-25) 
- (modified) llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp (+17) 
- (modified) llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h (+7) 


``diff
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(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(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(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 {
   void collectKernelLaunchBounds(
   const Function &F,
   SmallVectorImpl> &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-branch-commits] [llvm] AMDGPU: Move fpenvIEEEMode into TTI (PR #141945)

2025-05-29 Thread Matt Arsenault via llvm-branch-commits 

https://github.com/arsenm ready_for_review 
https://github.com/llvm/llvm-project/pull/141945
___
llvm-branch-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: Move fpenvIEEEMode into TTI (PR #141945)

2025-05-29 Thread Matt Arsenault via llvm-branch-commits 

arsenm wrote:

> [!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  href="https://app.graphite.dev/github/pr/llvm/llvm-project/141945?utm_source=stack-comment-downstack-mergeability-warning";
>  >on Graphite.
> https://graphite.dev/docs/merge-pull-requests";>Learn more

* **#141948** https://app.graphite.dev/github/pr/llvm/llvm-project/141948?utm_source=stack-comment-icon";
 target="_blank">https://static.graphite.dev/graphite-32x32-black.png"; alt="Graphite" 
width="10px" height="10px"/>
* **#141947** https://app.graphite.dev/github/pr/llvm/llvm-project/141947?utm_source=stack-comment-icon";
 target="_blank">https://static.graphite.dev/graphite-32x32-black.png"; alt="Graphite" 
width="10px" height="10px"/>
* **#141946** https://app.graphite.dev/github/pr/llvm/llvm-project/141946?utm_source=stack-comment-icon";
 target="_blank">https://static.graphite.dev/graphite-32x32-black.png"; alt="Graphite" 
width="10px" height="10px"/>
* **#141945** https://app.graphite.dev/github/pr/llvm/llvm-project/141945?utm_source=stack-comment-icon";
 target="_blank">https://static.graphite.dev/graphite-32x32-black.png"; alt="Graphite" 
width="10px" height="10px"/> 👈 https://app.graphite.dev/github/pr/llvm/llvm-project/141945?utm_source=stack-comment-view-in-graphite";
 target="_blank">(View in Graphite)
* **#141944** https://app.graphite.dev/github/pr/llvm/llvm-project/141944?utm_source=stack-comment-icon";
 target="_blank">https://static.graphite.dev/graphite-32x32-black.png"; alt="Graphite" 
width="10px" height="10px"/>
* **#141943** https://app.graphite.dev/github/pr/llvm/llvm-project/141943?utm_source=stack-comment-icon";
 target="_blank">https://static.graphite.dev/graphite-32x32-black.png"; alt="Graphite" 
width="10px" height="10px"/>
* **#141904** https://app.graphite.dev/github/pr/llvm/llvm-project/141904?utm_source=stack-comment-icon";
 target="_blank">https://static.graphite.dev/graphite-32x32-black.png"; alt="Graphite" 
width="10px" height="10px"/>
* **#141903** https://app.graphite.dev/github/pr/llvm/llvm-project/141903?utm_source=stack-comment-icon";
 target="_blank">https://static.graphite.dev/graphite-32x32-black.png"; alt="Graphite" 
width="10px" height="10px"/>
* `main`




This stack of pull requests is managed by https://graphite.dev?utm-source=stack-comment";>Graphite. Learn 
more about https://stacking.dev/?utm_source=stack-comment";>stacking.


https://github.com/llvm/llvm-project/pull/141945
___
llvm-branch-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: Move fpenvIEEEMode into TTI (PR #141945)

2025-05-29 Thread Matt Arsenault via llvm-branch-commits 

https://github.com/arsenm created 
https://github.com/llvm/llvm-project/pull/141945

None

>From dc0d24948146621e6ba5e39c21ea7f4494a14ed1 Mon Sep 17 00:00:00 2001
From: Matt Arsenault 
Date: Thu, 29 May 2025 11:16:22 +0200
Subject: [PATCH] AMDGPU: Move fpenvIEEEMode into TTI

---
 .../AMDGPU/AMDGPUInstCombineIntrinsic.cpp | 28 ++-
 .../AMDGPU/AMDGPUTargetTransformInfo.cpp  | 17 +++
 .../Target/AMDGPU/AMDGPUTargetTransformInfo.h |  7 +
 3 files changed, 27 insertions(+), 25 deletions(-)

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(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(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(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 {
   void collectKernelLaunchBounds(
   const Function &F,
   SmallVectorImpl> &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"="fal