================
@@ -179,8 +179,10 @@ __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)
+#if __CUDA_ARCH__ >= 700
+ if (__nvvm_reflect("__CUDA_ARCH") >= 700)
----------------
jhuber6 wrote:
Probably just because I forgot to but it was a no-op so I didn't notice.
And yeah, I wish there was a way to let `nvvm_reflect` call these without the
incurring the wrath of the compiler. You can spoof some target attributes but
that's always broken when inlined.
https://github.com/llvm/llvm-project/pull/129927
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
