AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
a46ea105830fbc3fbb222a00a82862df49cc9a9f
rocm-systems/src/collectives/device
T
History
Sylvain Jeaugey a46ea10583 2.9.6-1 
Add support for CUDA graphs.
Fuse BCM Gen4 switches to avoid suboptimal performance on some platforms. Issue #439.
Fix bootstrap issue caused by connection reordering.
Fix CPU locking block.
Improve CollNet algorithm.
Improve performance on DGX A100 for communicators with only one GPU per node.
2021-04-12 16:00:46 -07:00
..
all_gather.cu
2.8.3-1
2020-11-17 11:08:52 -08:00
all_gather.h
2.8.3-1
2020-11-17 11:08:52 -08:00
all_reduce.cu
2.8.3-1
2020-11-17 11:08:52 -08:00
all_reduce.h
2.9.6-1
2021-04-12 16:00:46 -07:00
broadcast.cu
2.8.3-1
2020-11-17 11:08:52 -08:00
broadcast.h
2.8.3-1
2020-11-17 11:08:52 -08:00
common_kernel.h
2.8.3-1
2020-11-17 11:08:52 -08:00
common.h
2.9.6-1
2021-04-12 16:00:46 -07:00
functions.cu
2.8.3-1
2020-11-17 11:08:52 -08:00
gen_rules.sh
2.7.3-1
2020-06-08 09:31:44 -07:00
Makefile
2.7.3-1
2020-06-08 09:31:44 -07:00
op128.h
2.5.6-1 (#255)
2019-11-19 14:57:39 -08:00
primitives.h
2.9.6-1
2021-04-12 16:00:46 -07:00
prims_ll128.h
2.9.6-1
2021-04-12 16:00:46 -07:00
prims_ll.h
2.9.6-1
2021-04-12 16:00:46 -07:00
reduce_kernel.h
2.4.2-1
2019-01-29 15:19:27 -08:00
reduce_scatter.cu
2.8.3-1
2020-11-17 11:08:52 -08:00
reduce_scatter.h
2.8.3-1
2020-11-17 11:08:52 -08:00
reduce.cu
2.8.3-1
2020-11-17 11:08:52 -08:00
reduce.h
2.8.3-1
2020-11-17 11:08:52 -08:00
sendrecv.cu
2.8.3-1
2020-11-17 11:08:52 -08:00
sendrecv.h
2.9.6-1
2021-04-12 16:00:46 -07:00