================
@@ -149,22 +149,23 @@ _DEFAULT_FN_ATTRS static __inline__ void
__gpu_sync_lane(uint64_t __lane_mask) {
// Shuffles the the lanes inside the warp according to the given index.
_DEFAULT_FN_ATTRS static __inline__ uint32_t
-__gpu_shuffle_idx_u32(uint64_t __lane_mask, uint32_t __idx, uint32_t __x) {
+__gpu_shuffle_idx_u32(uint64_t __lane_mask, uint32_t __idx, uint32_t __x,
+ uint32_t __width) {
uint32_t __mask = (uint32_t)__lane_mask;
- return __nvvm_shfl_sync_idx_i32(__mask, __x, __idx, __gpu_num_lanes() - 1u);
+ return __nvvm_shfl_sync_idx_i32(__mask, __x, __idx,
+ ((__gpu_num_lanes() - __width) << 8u) |
0x1f);
----------------
jhuber6 wrote:
I took it from
https://github.com/llvm/llvm-project/blob/main/clang/lib/Headers/__clang_cuda_intrinsics.h#L88
and it gave me the output I expected, so I assumed it was right.
https://github.com/llvm/llvm-project/pull/125896
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
