release/20.x: cuda clang: Fix argument order for __reduce_max_sync (#132881) #134295
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
|
@durga4github What do you think about merging this PR to the release branch? |
llvmbot
added
clang
|
@llvm/pr-subscribers-clang Author: None (llvmbot) ChangesBackport 2d1517d Requested by: @Artem-B Full diff: https://github.com/llvm/llvm-project/pull/134295.diff 1 Files Affected:
diff --git a/clang/lib/Headers/__clang_cuda_intrinsics.h b/clang/lib/Headers/__clang_cuda_intrinsics.h
index a04e8b6de44d0..8b230af6f6647 100644
--- a/clang/lib/Headers/__clang_cuda_intrinsics.h
+++ b/clang/lib/Headers/__clang_cuda_intrinsics.h
@@ -515,32 +515,32 @@ __device__ inline cuuint32_t __nvvm_get_smem_pointer(void *__ptr) {
#if !defined(__CUDA_ARCH__) || __CUDA_ARCH__ >= 800
__device__ inline unsigned __reduce_add_sync(unsigned __mask,
unsigned __value) {
- return __nvvm_redux_sync_add(__mask, __value);
+ return __nvvm_redux_sync_add(__value, __mask);
}
__device__ inline unsigned __reduce_min_sync(unsigned __mask,
unsigned __value) {
- return __nvvm_redux_sync_umin(__mask, __value);
+ return __nvvm_redux_sync_umin(__value, __mask);
}
__device__ inline unsigned __reduce_max_sync(unsigned __mask,
unsigned __value) {
- return __nvvm_redux_sync_umax(__mask, __value);
+ return __nvvm_redux_sync_umax(__value, __mask);
}
__device__ inline int __reduce_min_sync(unsigned __mask, int __value) {
- return __nvvm_redux_sync_min(__mask, __value);
+ return __nvvm_redux_sync_min(__value, __mask);
}
__device__ inline int __reduce_max_sync(unsigned __mask, int __value) {
- return __nvvm_redux_sync_max(__mask, __value);
+ return __nvvm_redux_sync_max(__value, __mask);
}
__device__ inline unsigned __reduce_or_sync(unsigned __mask, unsigned __value) {
- return __nvvm_redux_sync_or(__mask, __value);
+ return __nvvm_redux_sync_or(__value, __mask);
}
__device__ inline unsigned __reduce_and_sync(unsigned __mask,
unsigned __value) {
- return __nvvm_redux_sync_and(__mask, __value);
+ return __nvvm_redux_sync_and(__value, __mask);
}
__device__ inline unsigned __reduce_xor_sync(unsigned __mask,
unsigned __value) {
- return __nvvm_redux_sync_xor(__mask, __value);
+ return __nvvm_redux_sync_xor(__value, __mask);
}
__device__ inline void __nv_memcpy_async_shared_global_4(void *__dst,
|
|
@llvm/pr-subscribers-backend-x86 Author: None (llvmbot) ChangesBackport 2d1517d Requested by: @Artem-B Full diff: https://github.com/llvm/llvm-project/pull/134295.diff 1 Files Affected:
diff --git a/clang/lib/Headers/__clang_cuda_intrinsics.h b/clang/lib/Headers/__clang_cuda_intrinsics.h
index a04e8b6de44d0..8b230af6f6647 100644
--- a/clang/lib/Headers/__clang_cuda_intrinsics.h
+++ b/clang/lib/Headers/__clang_cuda_intrinsics.h
@@ -515,32 +515,32 @@ __device__ inline cuuint32_t __nvvm_get_smem_pointer(void *__ptr) {
#if !defined(__CUDA_ARCH__) || __CUDA_ARCH__ >= 800
__device__ inline unsigned __reduce_add_sync(unsigned __mask,
unsigned __value) {
- return __nvvm_redux_sync_add(__mask, __value);
+ return __nvvm_redux_sync_add(__value, __mask);
}
__device__ inline unsigned __reduce_min_sync(unsigned __mask,
unsigned __value) {
- return __nvvm_redux_sync_umin(__mask, __value);
+ return __nvvm_redux_sync_umin(__value, __mask);
}
__device__ inline unsigned __reduce_max_sync(unsigned __mask,
unsigned __value) {
- return __nvvm_redux_sync_umax(__mask, __value);
+ return __nvvm_redux_sync_umax(__value, __mask);
}
__device__ inline int __reduce_min_sync(unsigned __mask, int __value) {
- return __nvvm_redux_sync_min(__mask, __value);
+ return __nvvm_redux_sync_min(__value, __mask);
}
__device__ inline int __reduce_max_sync(unsigned __mask, int __value) {
- return __nvvm_redux_sync_max(__mask, __value);
+ return __nvvm_redux_sync_max(__value, __mask);
}
__device__ inline unsigned __reduce_or_sync(unsigned __mask, unsigned __value) {
- return __nvvm_redux_sync_or(__mask, __value);
+ return __nvvm_redux_sync_or(__value, __mask);
}
__device__ inline unsigned __reduce_and_sync(unsigned __mask,
unsigned __value) {
- return __nvvm_redux_sync_and(__mask, __value);
+ return __nvvm_redux_sync_and(__value, __mask);
}
__device__ inline unsigned __reduce_xor_sync(unsigned __mask,
unsigned __value) {
- return __nvvm_redux_sync_xor(__mask, __value);
+ return __nvvm_redux_sync_xor(__value, __mask);
}
__device__ inline void __nv_memcpy_async_shared_global_4(void *__dst,
|
|
|
|
I was the reviewer of the original PR. |
As Artem mentioned, it is a low-risk fix impacting the lowering to the redux_sync family of intrinsics only. So, it is good to merge it to the release branch. |
durga4github
approved these changes
Apr 4, 2025
github-project-automation
bot
moved this from Needs Triage
to Needs Merge
in LLVM Release Status
Fixes: llvm#131415 --------- Signed-off-by: Austin Schuh <austin.linux@gmail.com> (cherry picked from commit 2d1517d)
github-project-automation
bot
moved this from Needs Merge
to Done
in LLVM Release Status
|
@Artem-B (or anyone else). If you would like to add a note about this fix in the release notes (completely optional). Please reply to this comment with a one or two sentence description of the fix. When you are done, please add the release:note label to this PR. |
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.
Backport 2d1517d
Requested by: @Artem-B