a270ee080e
Read operation throughput
2019-09-03 14:58:40 +05:30
e5b13d69e5
display each workgroup ,links and directions with throughputs
2019-08-30 13:28:23 +05:30
40e30b5168
Update rccl_prim_test.cpp
2019-08-19 12:44:11 +05:30
deea20d49c
Merge branch 'master' into xgmi_bench
2019-08-16 10:56:56 +05:30
f11c8f60cd
RCCL 2.4 update
2019-08-14 10:42:35 -07:00
65e2f5d87b
Modified the code to use RTC clock frequency based on gpu gcn id
2019-08-14 12:55:12 +05:30
0f74929dab
Merge branch 'xgmi_bench' of https://github.com/rpathani/rccl into xgmi_bench
...
# Conflicts:
# tools/rccl-prim-test/rccl_prim_test.cpp
2019-08-13 11:36:56 +05:30
3bbf924ff8
Adding linkinfo and srcGPU to destGPU info
2019-08-13 11:28:50 +05:30
5a2f74b8d0
Adding linkinfo and srcGPU to destGPU info
2019-08-09 12:44:06 +05:30
b8cf48fc16
Adding TransferBench tool ( #113 )
...
* Adding standalone TransferBench tool
2019-08-07 17:21:41 -06:00
70804da15b
Refactor primitive test to support multiple GPUs in rings ( #94 )
...
* Refactor primitive test to support multiple GPUs in rings
* Make GPUs sync before transfer optional
* Use same ring format as RCCL
* Extend to 8 GPUs and report errors if there is no P2P access
* Control GPUs sync before ops from command line with "-s" option
* Change buffer size through command line option "-n"
Rename iterations command line option to "-i"
2019-07-05 14:29:20 -07:00
e6a0da444f
Match primitives unroll counts with latest RCCL ( #91 )
2019-06-26 15:09:13 -07:00
ee14676064
Calculate and print kernel throughput ( #78 )
...
* rccl-prim-test: print GPU info and set iterations
* Calculate and print kernel throughput
2019-06-07 10:39:30 -07:00
42b488507d
rccl-prim-test: print GPU info and set iterations ( #77 )
2019-06-05 15:16:33 -07:00
1bb6d2104c
Add RCCL primitive testing ( #70 )
2019-05-23 16:52:17 -06:00
rohit pathania
Wenkai Du
gilbertlee-amd
Wenkai Du