Skip to content

[Clang] Fix 'gpuintrin.h' match when included with no arch set #129927

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
jhuber6 merged 1 commit into from
Mar 7, 2025
Merged

[Clang] Fix 'gpuintrin.h' match when included with no arch set #129927

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 12 additions & 8 deletions clang/lib/Headers/nvptxintrin.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -180,8 +180,9 @@ __gpu_shuffle_idx_u64(uint64_t __lane_mask, uint32_t __idx, uint64_t __x,
_DEFAULT_FN_ATTRS static __inline__ uint64_t
__gpu_match_any_u32(uint64_t __lane_mask, uint32_t __x) {
// Newer targets can use the dedicated CUDA support.
if (__CUDA_ARCH__ >= 700 || __nvvm_reflect("__CUDA_ARCH") >= 700)
return __nvvm_match_any_sync_i32(__lane_mask, __x);
#if __CUDA_ARCH__ >= 700
return __nvvm_match_any_sync_i32(__lane_mask, __x);
#endif

uint32_t __match_mask = 0;
bool __done = 0;
Expand All @@ -201,8 +202,9 @@ __gpu_match_any_u32(uint64_t __lane_mask, uint32_t __x) {
_DEFAULT_FN_ATTRS static __inline__ uint64_t
__gpu_match_any_u64(uint64_t __lane_mask, uint64_t __x) {
// Newer targets can use the dedicated CUDA support.
if (__CUDA_ARCH__ >= 700 || __nvvm_reflect("__CUDA_ARCH") >= 700)
return __nvvm_match_any_sync_i64(__lane_mask, __x);
#if __CUDA_ARCH__ >= 700
return __nvvm_match_any_sync_i64(__lane_mask, __x);
#endif

uint64_t __match_mask = 0;

Expand All @@ -224,9 +226,10 @@ __gpu_match_any_u64(uint64_t __lane_mask, uint64_t __x) {
_DEFAULT_FN_ATTRS static __inline__ uint64_t
__gpu_match_all_u32(uint64_t __lane_mask, uint32_t __x) {
// Newer targets can use the dedicated CUDA support.
#if __CUDA_ARCH__ >= 700
int predicate;
if (__CUDA_ARCH__ >= 700 || __nvvm_reflect("__CUDA_ARCH") >= 700)
return __nvvm_match_all_sync_i32p(__lane_mask, __x, &predicate);
return __nvvm_match_all_sync_i32p(__lane_mask, __x, &predicate);
#endif

uint32_t __first = __gpu_read_first_lane_u64(__lane_mask, __x);
uint64_t __ballot = __gpu_ballot(__lane_mask, __x == __first);
Expand All @@ -237,9 +240,10 @@ __gpu_match_all_u32(uint64_t __lane_mask, uint32_t __x) {
_DEFAULT_FN_ATTRS static __inline__ uint64_t
__gpu_match_all_u64(uint64_t __lane_mask, uint64_t __x) {
// Newer targets can use the dedicated CUDA support.
#if __CUDA_ARCH__ >= 700
int predicate;
if (__CUDA_ARCH__ >= 700 || __nvvm_reflect("__CUDA_ARCH") >= 700)
return __nvvm_match_all_sync_i64p(__lane_mask, __x, &predicate);
return __nvvm_match_all_sync_i64p(__lane_mask, __x, &predicate);
#endif

uint64_t __first = __gpu_read_first_lane_u64(__lane_mask, __x);
uint64_t __ballot = __gpu_ballot(__lane_mask, __x == __first);
Expand Down