[llvm] [LLVM] New NoDivergenceSource function attribute (PR #111832)
Tim Renouf via llvm-commits
llvm-commits at lists.llvm.org
Fri Oct 11 07:25:27 PDT 2024
https://github.com/trenouf updated https://github.com/llvm/llvm-project/pull/111832
>From 3bb577263d38831e579d8b114ed599ab799ae2ab Mon Sep 17 00:00:00 2001
From: Tim Renouf <tim.renouf at amd.com>
Date: Wed, 9 Oct 2024 18:48:50 +0100
Subject: [PATCH 1/3] [LLVM] New NoDivergenceSource function attribute
A call to a function that has this attribute is not a source of
divergence, as used by UniformityAnalysis. That allows a front-end
to use known-name calls as an instruction extension mechanism (e.g.
https://github.com/GPUOpen-Drivers/llvm-dialects ) without such a
call being a source of divergence.
---
llvm/docs/LangRef.rst | 10 ++++++++++
llvm/include/llvm/Bitcode/LLVMBitCodes.h | 1 +
llvm/include/llvm/IR/Attributes.td | 3 +++
llvm/lib/Analysis/UniformityAnalysis.cpp | 9 ++++++++-
llvm/lib/Bitcode/Reader/BitcodeReader.cpp | 2 ++
llvm/lib/Bitcode/Writer/BitcodeWriter.cpp | 2 ++
llvm/lib/Transforms/Utils/CodeExtractor.cpp | 1 +
.../AMDGPU/nodivergencesource.ll | 16 ++++++++++++++++
llvm/test/Bitcode/attributes.ll | 6 ++++++
9 files changed, 49 insertions(+), 1 deletion(-)
create mode 100644 llvm/test/Analysis/UniformityAnalysis/AMDGPU/nodivergencesource.ll
diff --git a/llvm/docs/LangRef.rst b/llvm/docs/LangRef.rst
index 0c7279de06cd68..4c94ffbc1d7376 100644
--- a/llvm/docs/LangRef.rst
+++ b/llvm/docs/LangRef.rst
@@ -2082,6 +2082,16 @@ example:
function call, use of ``longjmp``, or other means. It is a compiler hint that
is used at module level to improve dataflow analysis, dropped during linking,
and has no effect on functions defined in the current module.
+``nodivergencesource``
+ A call to this function is not a source of divergence. In uniformity
+ analysis, a *source of divergence* is an instruction that generates
+ divergence even if its inputs are uniform. A call with no further information
+ would normally be considered a source of divergence; setting this attribute
+ on a function means that a call to it is not a source of divergence.
+
+ This is useful where known-name calls are being used as an extension
+ mechanism for instructions, as for example in `llvm-dialects
+ <https://github.com/GPUOpen-Drivers/llvm-dialects>`.
``noduplicate``
This attribute indicates that calls to the function cannot be
duplicated. A call to a ``noduplicate`` function may be moved
diff --git a/llvm/include/llvm/Bitcode/LLVMBitCodes.h b/llvm/include/llvm/Bitcode/LLVMBitCodes.h
index cbd92fd52fc75a..a6959d9b62742a 100644
--- a/llvm/include/llvm/Bitcode/LLVMBitCodes.h
+++ b/llvm/include/llvm/Bitcode/LLVMBitCodes.h
@@ -764,6 +764,7 @@ enum AttributeKindCodes {
ATTR_KIND_SANITIZE_REALTIME_UNSAFE = 97,
ATTR_KIND_CORO_ELIDE_SAFE = 98,
ATTR_KIND_NO_EXT = 99,
+ ATTR_KIND_NO_DIVERGENCE_SOURCE = 100,
};
enum ComdatSelectionKindCodes {
diff --git a/llvm/include/llvm/IR/Attributes.td b/llvm/include/llvm/IR/Attributes.td
index d05a6ca92aaba0..b6d36a5f7ae4fb 100644
--- a/llvm/include/llvm/IR/Attributes.td
+++ b/llvm/include/llvm/IR/Attributes.td
@@ -183,6 +183,9 @@ def NoCallback : EnumAttr<"nocallback", IntersectAnd, [FnAttr]>;
/// Function creates no aliases of pointer.
def NoCapture : EnumAttr<"nocapture", IntersectAnd, [ParamAttr]>;
+/// Function is not a source of divergence.
+def NoDivergenceSource : EnumAttr<"nodivergencesource", IntersectAnd, [FnAttr]>;
+
/// Call cannot be duplicated.
def NoDuplicate : EnumAttr<"noduplicate", IntersectPreserve, [FnAttr]>;
diff --git a/llvm/lib/Analysis/UniformityAnalysis.cpp b/llvm/lib/Analysis/UniformityAnalysis.cpp
index 2d617db431c588..b0be6379a15125 100644
--- a/llvm/lib/Analysis/UniformityAnalysis.cpp
+++ b/llvm/lib/Analysis/UniformityAnalysis.cpp
@@ -32,7 +32,14 @@ bool llvm::GenericUniformityAnalysisImpl<SSAContext>::markDefsDivergent(
template <> void llvm::GenericUniformityAnalysisImpl<SSAContext>::initialize() {
for (auto &I : instructions(F)) {
- if (TTI->isSourceOfDivergence(&I))
+ bool NoDivergenceSource = false;
+ if (auto Call = dyn_cast<CallInst>(&I)) {
+ if (Function *Callee = Call->getCalledFunction()) {
+ if (Callee->hasFnAttribute(Attribute::NoDivergenceSource))
+ NoDivergenceSource = true;
+ }
+ }
+ if (!NoDivergenceSource && TTI->isSourceOfDivergence(&I))
markDivergent(I);
else if (TTI->isAlwaysUniform(&I))
addUniformOverride(I);
diff --git a/llvm/lib/Bitcode/Reader/BitcodeReader.cpp b/llvm/lib/Bitcode/Reader/BitcodeReader.cpp
index 6f997510b03609..b8dc5ecbf7abda 100644
--- a/llvm/lib/Bitcode/Reader/BitcodeReader.cpp
+++ b/llvm/lib/Bitcode/Reader/BitcodeReader.cpp
@@ -2048,6 +2048,8 @@ static Attribute::AttrKind getAttrFromCode(uint64_t Code) {
return Attribute::NoCallback;
case bitc::ATTR_KIND_NO_CAPTURE:
return Attribute::NoCapture;
+ case bitc::ATTR_KIND_NO_DIVERGENCE_SOURCE:
+ return Attribute::NoDivergenceSource;
case bitc::ATTR_KIND_NO_DUPLICATE:
return Attribute::NoDuplicate;
case bitc::ATTR_KIND_NOFREE:
diff --git a/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp b/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
index d9086bfebbd2a9..a44b6a8614357d 100644
--- a/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
+++ b/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
@@ -761,6 +761,8 @@ static uint64_t getAttrKindEncoding(Attribute::AttrKind Kind) {
return bitc::ATTR_KIND_NO_CALLBACK;
case Attribute::NoCapture:
return bitc::ATTR_KIND_NO_CAPTURE;
+ case Attribute::NoDivergenceSource:
+ return bitc::ATTR_KIND_NO_DIVERGENCE_SOURCE;
case Attribute::NoDuplicate:
return bitc::ATTR_KIND_NO_DUPLICATE;
case Attribute::NoFree:
diff --git a/llvm/lib/Transforms/Utils/CodeExtractor.cpp b/llvm/lib/Transforms/Utils/CodeExtractor.cpp
index f58448dd9562d5..5b42099398f8ff 100644
--- a/llvm/lib/Transforms/Utils/CodeExtractor.cpp
+++ b/llvm/lib/Transforms/Utils/CodeExtractor.cpp
@@ -917,6 +917,7 @@ Function *CodeExtractor::constructFunction(const ValueSet &inputs,
case Attribute::NoFPClass:
case Attribute::CoroDestroyOnlyWhenComplete:
case Attribute::CoroElideSafe:
+ case Attribute::NoDivergenceSource:
continue;
// Those attributes should be safe to propagate to the extracted function.
case Attribute::AlwaysInline:
diff --git a/llvm/test/Analysis/UniformityAnalysis/AMDGPU/nodivergencesource.ll b/llvm/test/Analysis/UniformityAnalysis/AMDGPU/nodivergencesource.ll
new file mode 100644
index 00000000000000..9c893ac3ba76a0
--- /dev/null
+++ b/llvm/test/Analysis/UniformityAnalysis/AMDGPU/nodivergencesource.ll
@@ -0,0 +1,16 @@
+; RUN: opt -mtriple amdgcn-- -passes='print<uniformity>' -disable-output %s 2>&1 | FileCheck %s
+
+; CHECK: DIVERGENT: %divergentval
+; CHECK-NOT: DIVERGENT: %uniformval
+; CHECK: %uniformval
+define void @test() {
+ %divergentval = call i32 @normalfunc()
+ %uniformval = call i32 @nodivergencesourcefunc()
+ ret void
+}
+
+declare i32 @normalfunc() #0
+declare i32 @nodivergencesourcefunc() #1
+
+attributes #0 = { nounwind }
+attributes #1 = { nounwind nodivergencesource }
diff --git a/llvm/test/Bitcode/attributes.ll b/llvm/test/Bitcode/attributes.ll
index a66eda19ff5735..737f49aa86a7ba 100644
--- a/llvm/test/Bitcode/attributes.ll
+++ b/llvm/test/Bitcode/attributes.ll
@@ -537,6 +537,11 @@ define void @f91(ptr dead_on_unwind %p) {
ret void
}
+; CHECK: define void @f94() [[NODIVERGENCESOURCE:#[0-9]+]]
+define void @f94() nodivergencesource {
+ ret void;
+}
+
; CHECK: define range(i32 -1, 42) i32 @range_attribute(<4 x i32> range(i32 -1, 42) %a)
define range(i32 -1, 42) i32 @range_attribute(<4 x i32> range(i32 -1, 42) %a) {
ret i32 0
@@ -615,4 +620,5 @@ define void @initializes(ptr initializes((-4, 0), (4, 8)) %a) {
; CHECK: attributes [[FNRETTHUNKEXTERN]] = { fn_ret_thunk_extern }
; CHECK: attributes [[SKIPPROFILE]] = { skipprofile }
; CHECK: attributes [[OPTDEBUG]] = { optdebug }
+; CHECK: attributes [[NODIVERGENCESOURCE]] = { nodivergencesource }
; CHECK: attributes #[[NOBUILTIN]] = { nobuiltin }
>From e1905675f2e6b4c7723936b93ce85433b69f260d Mon Sep 17 00:00:00 2001
From: Tim Renouf <tim.renouf at amd.com>
Date: Thu, 10 Oct 2024 16:02:40 +0100
Subject: [PATCH 2/3] Use CallBase::hasFnAttr
---
llvm/lib/Analysis/UniformityAnalysis.cpp | 8 ++------
1 file changed, 2 insertions(+), 6 deletions(-)
diff --git a/llvm/lib/Analysis/UniformityAnalysis.cpp b/llvm/lib/Analysis/UniformityAnalysis.cpp
index b0be6379a15125..3675b22057fa8c 100644
--- a/llvm/lib/Analysis/UniformityAnalysis.cpp
+++ b/llvm/lib/Analysis/UniformityAnalysis.cpp
@@ -33,12 +33,8 @@ bool llvm::GenericUniformityAnalysisImpl<SSAContext>::markDefsDivergent(
template <> void llvm::GenericUniformityAnalysisImpl<SSAContext>::initialize() {
for (auto &I : instructions(F)) {
bool NoDivergenceSource = false;
- if (auto Call = dyn_cast<CallInst>(&I)) {
- if (Function *Callee = Call->getCalledFunction()) {
- if (Callee->hasFnAttribute(Attribute::NoDivergenceSource))
- NoDivergenceSource = true;
- }
- }
+ if (auto Call = dyn_cast<CallBase>(&I))
+ NoDivergenceSource = Call->hasFnAttr(Attribute::NoDivergenceSource);
if (!NoDivergenceSource && TTI->isSourceOfDivergence(&I))
markDivergent(I);
else if (TTI->isAlwaysUniform(&I))
>From 795bbbaf25315437ad5ea2f775bbcc2d6db56cf6 Mon Sep 17 00:00:00 2001
From: Tim Renouf <tim.renouf at amd.com>
Date: Fri, 11 Oct 2024 14:56:58 +0100
Subject: [PATCH 3/3] Move check to TargetTransformInfo
---
llvm/lib/Analysis/TargetTransformInfo.cpp | 4 ++++
llvm/lib/Analysis/UniformityAnalysis.cpp | 5 +----
2 files changed, 5 insertions(+), 4 deletions(-)
diff --git a/llvm/lib/Analysis/TargetTransformInfo.cpp b/llvm/lib/Analysis/TargetTransformInfo.cpp
index 3dc29fc7cd77b1..fd6627577d7f2a 100644
--- a/llvm/lib/Analysis/TargetTransformInfo.cpp
+++ b/llvm/lib/Analysis/TargetTransformInfo.cpp
@@ -288,6 +288,10 @@ bool TargetTransformInfo::hasBranchDivergence(const Function *F) const {
}
bool TargetTransformInfo::isSourceOfDivergence(const Value *V) const {
+ if (auto Call = dyn_cast<CallBase>(V)) {
+ if (Call->hasFnAttr(Attribute::NoDivergenceSource))
+ return false;
+ }
return TTIImpl->isSourceOfDivergence(V);
}
diff --git a/llvm/lib/Analysis/UniformityAnalysis.cpp b/llvm/lib/Analysis/UniformityAnalysis.cpp
index 3675b22057fa8c..2d617db431c588 100644
--- a/llvm/lib/Analysis/UniformityAnalysis.cpp
+++ b/llvm/lib/Analysis/UniformityAnalysis.cpp
@@ -32,10 +32,7 @@ bool llvm::GenericUniformityAnalysisImpl<SSAContext>::markDefsDivergent(
template <> void llvm::GenericUniformityAnalysisImpl<SSAContext>::initialize() {
for (auto &I : instructions(F)) {
- bool NoDivergenceSource = false;
- if (auto Call = dyn_cast<CallBase>(&I))
- NoDivergenceSource = Call->hasFnAttr(Attribute::NoDivergenceSource);
- if (!NoDivergenceSource && TTI->isSourceOfDivergence(&I))
+ if (TTI->isSourceOfDivergence(&I))
markDivergent(I);
else if (TTI->isAlwaysUniform(&I))
addUniformOverride(I);
More information about the llvm-commits
mailing list