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

Add Alltoallv RCCL kernel implementation (#269)

Browse Source 
* Add alltoallv API and implementation

* Extend Rome P2P channel limit to multinode and alltoall kernels

* topo_expl: fix compilation and sync up with main

* gtest: use RCCL alltoallv API

* Code review changes
This commit is contained in:
Wenkai Du
2020-09-30 16:25:36 -07:00
committed by GitHub
parent aa985bfb7e
commit b871ea3c0c
22 changed files with 300 additions and 60 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/include/collectives.h
+4 -1
View File
@@ -8,7 +8,7 @@
#ifndef NCCL_COLLECTIVES_H_
#define NCCL_COLLECTIVES_H_
#define FUNC_INDEX_P2P (3+NCCL_NUM_FUNCTIONS*NCCL_NUM_ALGORITHMS*NCCL_NUM_PROTOCOLS*ncclNumTypes*ncclNumOps)
#define FUNC_INDEX_P2P (4+NCCL_NUM_FUNCTIONS*NCCL_NUM_ALGORITHMS*NCCL_NUM_PROTOCOLS*ncclNumTypes*ncclNumOps)
#define FUNC_INDEX(coll, redop, dtype, al, pr) ((coll >= NCCL_NUM_FUNCTIONS) \
? (coll-NCCL_NUM_FUNCTIONS+NCCL_NUM_FUNCTIONS*NCCL_NUM_ALGORITHMS*NCCL_NUM_PROTOCOLS*ncclNumTypes*ncclNumOps) \
: ((((((coll)*ncclNumOps + (redop))*ncclNumTypes) + (dtype))*NCCL_NUM_ALGORITHMS+(al))*NCCL_NUM_PROTOCOLS+(pr)))
@@ -61,6 +61,7 @@
DECL_COLL5(ncclGather, copy, i8) \
DECL_COLL5(ncclScatter, copy, i8) \
DECL_COLL5(ncclAllToAll, copy, i8) \
DECL_COLL5(ncclAllToAllv, copy, i8) \
DECL_COLL5(ncclSendRecv, copy, i8) \
DECL_ALL_COLLS
@@ -89,5 +90,7 @@ DECL_ALL_COLLS
#define SCATTER_CHUNKSTEPS 4
#define ALLTOALL_SLICESTEPS 4
#define ALLTOALL_CHUNKSTEPS 4
#define ALLTOALLV_SLICESTEPS 4
#define ALLTOALLV_CHUNKSTEPS 4
#endif