Pinned
18 contributions in the last year
Less
More
Contribution activity
August 2021
Created a pull request in pytorch/pytorch that received 6 comments
Cruise perf fixes for ScatterGather kernel when compiled with clang-cuda
Fixes #63000 Namely, make aggressive inlining for ScatterGather kernels to improve it's performance when compiled with clang-cuda. Also include mis…
+7
−7
•
6
comments
Opened 2 other pull requests in 1 repository
pytorch/pytorch
1
open
1
closed
Created an issue in pytorch/pytorch that received 1 comment
When compiled with clang ScatterGather kernel perf is significantly worse
1
comment