AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
192 Commits 3 Branches 0 Tags
b8cf48fc16b4bf1d053e1208c443ca72b5ad02c3
Commit Graph

6 Commits

Author SHA1 Message Date
gilbertlee-amd b8cf48fc16 Adding TransferBench tool (#113) 
* Adding standalone TransferBench tool
 2019-08-07 17:21:41 -06:00
Wenkai Du 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
Wenkai Du e6a0da444f Match primitives unroll counts with latest RCCL (#91) 2019-06-26 15:09:13 -07:00
Wenkai Du 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
Wenkai Du 42b488507d rccl-prim-test: print GPU info and set iterations (#77) 2019-06-05 15:16:33 -07:00
Wenkai Du 1bb6d2104c Add RCCL primitive testing (#70) 2019-05-23 16:52:17 -06:00