cuda11prof
|
add nvprof11 for CUDA compat >= 8.0 (#5)
|
2020-09-09 16:44:22 +08:00 |
Makefile
|
Initial Commit
|
2020-09-03 23:07:44 +08:00 |
hip_batch_matmul.cc
|
Initial Commit
|
2020-09-03 23:07:44 +08:00 |
hip_convfwd_multialgo.cc
|
Initial Commit
|
2020-09-03 23:07:44 +08:00 |
hip_convfwd_multialgo_cuda.cc
|
Initial Commit
|
2020-09-03 23:07:44 +08:00 |
hip_matmul.cc
|
custom matmul layout (#12)
|
2020-09-12 14:19:05 +08:00 |
ipu_onnxrt.py
|
fix a sharding bug in IPU backend (#251)
|
2021-04-26 06:54:22 +08:00 |
roc_prof
|
Initial Commit
|
2020-09-03 23:07:44 +08:00 |