[IR] Return correct memory effects for convergencectrl
#129874
Merged
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
|
@llvm/pr-subscribers-backend-amdgpu @llvm/pr-subscribers-llvm-transforms Author: Yingwei Zheng (dtcxzyw) Changes
Full diff: https://github.com/llvm/llvm-project/pull/129874.diff 3 Files Affected:
diff --git a/llvm/lib/IR/Instructions.cpp b/llvm/lib/IR/Instructions.cpp
index b5d1bc81b9d95..d2cf0ae2c1778 100644
--- a/llvm/lib/IR/Instructions.cpp
+++ b/llvm/lib/IR/Instructions.cpp
@@ -609,15 +609,17 @@ bool CallBase::hasReadingOperandBundles() const {
// Implementation note: this is a conservative implementation of operand
// bundle semantics, where *any* non-assume operand bundle (other than
// ptrauth) forces a callsite to be at least readonly.
- return hasOperandBundlesOtherThan(
- {LLVMContext::OB_ptrauth, LLVMContext::OB_kcfi}) &&
+ return hasOperandBundlesOtherThan({LLVMContext::OB_ptrauth,
+ LLVMContext::OB_kcfi,
+ LLVMContext::OB_convergencectrl}) &&
getIntrinsicID() != Intrinsic::assume;
}
bool CallBase::hasClobberingOperandBundles() const {
return hasOperandBundlesOtherThan(
{LLVMContext::OB_deopt, LLVMContext::OB_funclet,
- LLVMContext::OB_ptrauth, LLVMContext::OB_kcfi}) &&
+ LLVMContext::OB_ptrauth, LLVMContext::OB_kcfi,
+ LLVMContext::OB_convergencectrl}) &&
getIntrinsicID() != Intrinsic::assume;
}
diff --git a/llvm/test/Transforms/DCE/op_bundles.ll b/llvm/test/Transforms/DCE/op_bundles.ll
new file mode 100644
index 0000000000000..0d3b4db8265e8
--- /dev/null
+++ b/llvm/test/Transforms/DCE/op_bundles.ll
@@ -0,0 +1,12 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt -S < %s -passes=dce | FileCheck %s
+
+define void @dead_readfirstlane_convergencetoken(<2 x i32> %src) convergent {
+; CHECK-LABEL: define void @dead_readfirstlane_convergencetoken(
+; CHECK-SAME: <2 x i32> [[SRC:%.*]]) #[[ATTR0:[0-9]+]] {
+; CHECK-NEXT: ret void
+;
+ %t = tail call token @llvm.experimental.convergence.entry()
+ %vec = call <2 x i32> @llvm.amdgcn.readfirstlane.v2i32(<2 x i32> %src) [ "convergencectrl"(token %t) ]
+ ret void
+}
diff --git a/llvm/test/Transforms/IRNormalizer/regression-convergence-tokens.ll b/llvm/test/Transforms/IRNormalizer/regression-convergence-tokens.ll
index 633cf091da508..88eff971b9576 100644
--- a/llvm/test/Transforms/IRNormalizer/regression-convergence-tokens.ll
+++ b/llvm/test/Transforms/IRNormalizer/regression-convergence-tokens.ll
@@ -7,14 +7,14 @@ define i32 @nested(i32 %src) #0 {
; CHECK-SAME: i32 [[A0:%.*]]) #[[ATTR0:[0-9]+]] {
; CHECK-NEXT: [[BB15160:.*:]]
; CHECK-NEXT: [[T1:%.*]] = call token @llvm.experimental.convergence.entry()
-; CHECK-NEXT: %"vl15001llvm.experimental.convergence.anchor()" = call token @llvm.experimental.convergence.anchor()
-; CHECK-NEXT: %"op68297llvm.amdgcn.readfirstlane.i32([[A0]], vl15001llvm.experimental.convergence.anchor())" = call i32 @llvm.amdgcn.readfirstlane.i32(i32 [[A0]]) [ "convergencectrl"(token %"vl15001llvm.experimental.convergence.anchor()") ]
-; CHECK-NEXT: ret i32 undef
+; CHECK-NEXT: %"vl77672llvm.experimental.convergence.anchor()" = call token @llvm.experimental.convergence.anchor()
+; CHECK-NEXT: %"op68297(vl77672)" = call i32 @llvm.amdgcn.readfirstlane.i32(i32 [[A0]]) [ "convergencectrl"(token %"vl77672llvm.experimental.convergence.anchor()") ]
+; CHECK-NEXT: ret i32 %"op68297(vl77672)"
;
%t1 = call token @llvm.experimental.convergence.entry()
%t2 = call token @llvm.experimental.convergence.anchor()
%r2 = call i32 @llvm.amdgcn.readfirstlane(i32 %src) [ "convergencectrl"(token %t2) ]
- ret i32 undef
+ ret i32 %r2
}
; Function Attrs: convergent nounwind readnone
|
|
@llvm/pr-subscribers-llvm-ir Author: Yingwei Zheng (dtcxzyw) Changes
Full diff: https://github.com/llvm/llvm-project/pull/129874.diff 3 Files Affected:
diff --git a/llvm/lib/IR/Instructions.cpp b/llvm/lib/IR/Instructions.cpp
index b5d1bc81b9d95..d2cf0ae2c1778 100644
--- a/llvm/lib/IR/Instructions.cpp
+++ b/llvm/lib/IR/Instructions.cpp
@@ -609,15 +609,17 @@ bool CallBase::hasReadingOperandBundles() const {
// Implementation note: this is a conservative implementation of operand
// bundle semantics, where *any* non-assume operand bundle (other than
// ptrauth) forces a callsite to be at least readonly.
- return hasOperandBundlesOtherThan(
- {LLVMContext::OB_ptrauth, LLVMContext::OB_kcfi}) &&
+ return hasOperandBundlesOtherThan({LLVMContext::OB_ptrauth,
+ LLVMContext::OB_kcfi,
+ LLVMContext::OB_convergencectrl}) &&
getIntrinsicID() != Intrinsic::assume;
}
bool CallBase::hasClobberingOperandBundles() const {
return hasOperandBundlesOtherThan(
{LLVMContext::OB_deopt, LLVMContext::OB_funclet,
- LLVMContext::OB_ptrauth, LLVMContext::OB_kcfi}) &&
+ LLVMContext::OB_ptrauth, LLVMContext::OB_kcfi,
+ LLVMContext::OB_convergencectrl}) &&
getIntrinsicID() != Intrinsic::assume;
}
diff --git a/llvm/test/Transforms/DCE/op_bundles.ll b/llvm/test/Transforms/DCE/op_bundles.ll
new file mode 100644
index 0000000000000..0d3b4db8265e8
--- /dev/null
+++ b/llvm/test/Transforms/DCE/op_bundles.ll
@@ -0,0 +1,12 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt -S < %s -passes=dce | FileCheck %s
+
+define void @dead_readfirstlane_convergencetoken(<2 x i32> %src) convergent {
+; CHECK-LABEL: define void @dead_readfirstlane_convergencetoken(
+; CHECK-SAME: <2 x i32> [[SRC:%.*]]) #[[ATTR0:[0-9]+]] {
+; CHECK-NEXT: ret void
+;
+ %t = tail call token @llvm.experimental.convergence.entry()
+ %vec = call <2 x i32> @llvm.amdgcn.readfirstlane.v2i32(<2 x i32> %src) [ "convergencectrl"(token %t) ]
+ ret void
+}
diff --git a/llvm/test/Transforms/IRNormalizer/regression-convergence-tokens.ll b/llvm/test/Transforms/IRNormalizer/regression-convergence-tokens.ll
index 633cf091da508..88eff971b9576 100644
--- a/llvm/test/Transforms/IRNormalizer/regression-convergence-tokens.ll
+++ b/llvm/test/Transforms/IRNormalizer/regression-convergence-tokens.ll
@@ -7,14 +7,14 @@ define i32 @nested(i32 %src) #0 {
; CHECK-SAME: i32 [[A0:%.*]]) #[[ATTR0:[0-9]+]] {
; CHECK-NEXT: [[BB15160:.*:]]
; CHECK-NEXT: [[T1:%.*]] = call token @llvm.experimental.convergence.entry()
-; CHECK-NEXT: %"vl15001llvm.experimental.convergence.anchor()" = call token @llvm.experimental.convergence.anchor()
-; CHECK-NEXT: %"op68297llvm.amdgcn.readfirstlane.i32([[A0]], vl15001llvm.experimental.convergence.anchor())" = call i32 @llvm.amdgcn.readfirstlane.i32(i32 [[A0]]) [ "convergencectrl"(token %"vl15001llvm.experimental.convergence.anchor()") ]
-; CHECK-NEXT: ret i32 undef
+; CHECK-NEXT: %"vl77672llvm.experimental.convergence.anchor()" = call token @llvm.experimental.convergence.anchor()
+; CHECK-NEXT: %"op68297(vl77672)" = call i32 @llvm.amdgcn.readfirstlane.i32(i32 [[A0]]) [ "convergencectrl"(token %"vl77672llvm.experimental.convergence.anchor()") ]
+; CHECK-NEXT: ret i32 %"op68297(vl77672)"
;
%t1 = call token @llvm.experimental.convergence.entry()
%t2 = call token @llvm.experimental.convergence.anchor()
%r2 = call i32 @llvm.amdgcn.readfirstlane(i32 %src) [ "convergencectrl"(token %t2) ]
- ret i32 undef
+ ret i32 %r2
}
; Function Attrs: convergent nounwind readnone
|
dtcxzyw
commented
Mar 5, 2025
| ; | ||
| %t1 = call token @llvm.experimental.convergence.entry() | ||
| %t2 = call token @llvm.experimental.convergence.anchor() | ||
| %r2 = call i32 @llvm.amdgcn.readfirstlane(i32 %src) [ "convergencectrl"(token %t2) ] | ||
| ret i32 undef | ||
| ret i32 %r2 |
There was a problem hiding this comment.
IRNormalizer does not set name for dead values.
dtcxzyw
force-pushed
the
convergent-bundle
branch
from
a4744bf to
74d812e
Compare
Rebased |
llvmbot
added
backend:AMDGPU
llvm:instcombine
arsenm
approved these changes
Mar 5, 2025
|
LLVM Buildbot has detected a new failure on builder Full details are available at: https://lab.llvm.org/buildbot/#/builders/30/builds/16964 Here is the relevant piece of the build log for the reference |
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.
convergencectrldoesn't imply any memory access.Closes #129856.