Merge sendrecv kernel from NCCL 2.7.3

This commit was cherry-picked and modified from https://github.com/NVIDIA/nccl/commit/89072c82e551d7c8bf7bd5ca77780ef540b7611e [ROCm/rccl commit: 964c4c2061]
2020-06-29 08:47:46 -07:00
parent 3c674c9c1f
commit 77d94493c3
3 changed files with 51 additions and 31 deletions
@@ -82,7 +82,7 @@ DECL_ALL_COLLS
 #define BROADCAST_CHUNKSTEPS 1
 #define REDUCE_SLICESTEPS 1
 #define REDUCE_CHUNKSTEPS 1
-#define SENDRECV_SLICEFACTOR 4
+#define SENDRECV_SLICEFACTOR 1
 #define GATHER_SLICESTEPS 4
 #define GATHER_CHUNKSTEPS 4
 #define SCATTER_SLICESTEPS 4