AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'rccl/develop' into 2.19.4

Browse Source 
[ROCm/rccl commit: d999d9ad21]
This commit is contained in:
Wenkai Du
2024-02-09 11:31:03 -06:00
parent e319d0a49d 6775a75906
commit d5f5091e5d
13 changed files with 108 additions and 120 deletions
Download Patch File Download Diff File Expand all files Collapse all files
projects/rccl/src/device/msccl_kernel_impl.h
+1 -1
View File
@@ -372,7 +372,7 @@ __device__ __forceinline__ void mscclRunInterpreter(
return;
}
if (t->hasDependence && tid == nthreads-1)
__atomic_store_n(&mscclFlags[bid].flag, (uint64_t) COMPUTE_FLAG(workIndex, iter, step), (t->type == MSCCL_REDUCE || t->type == MSCCL_RECV) ? __ATOMIC_RELEASE : __ATOMIC_RELAXED);
__atomic_store_n(&mscclFlags[bid].flag, (uint64_t) COMPUTE_FLAG(workIndex, iter, step), ((t->type == MSCCL_REDUCE || t->type == MSCCL_RECV) && (t->dstBuffer != MSCCL_SCRATCH_BUFFER)) ? __ATOMIC_RELEASE : __ATOMIC_RELAXED);
step++;
}
}