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

Merge remote-tracking branch 'nccl/master' into develop

Browse Source 
[ROCm/rccl commit: cb6e23ae67]
This commit is contained in:
BertanDogancay
2025-04-30 13:30:11 -05:00
parent 33c390b36e 70bd1af305
commit 064062ef70
41 changed files with 1315 additions and 504 deletions
Download Patch File Download Diff File Expand all files Collapse all files
projects/rccl/src/include/enqueue.h
+1 -1
View File
@@ -17,7 +17,7 @@
#define NCCL_SIMPLE_ALIGNMENT (WARP_SIZE * 8LL * 16LL)
#define NCCL_BYTES_ALIGNMENT 16
ncclResult_t ncclInitKernelsForDevice(int cudaArch, size_t* maxStackSize);
ncclResult_t ncclInitKernelsForDevice(int cudaArch, int maxSharedMem, size_t* maxStackSize);
ncclResult_t ncclEnqueueCheck(struct ncclInfo* info);
ncclResult_t ncclLaunchPrepare(struct ncclComm* comm);
ncclResult_t ncclLaunchKernelBefore_NoUncapturedCuda(struct ncclComm* comm, struct ncclKernelPlan* plan);