tvm-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From GitBox <...@apache.org>
Subject [GitHub] [incubator-tvm] t-vi opened a new pull request #5752: Make batch matrix multiplication on GPU tunable
Date Tue, 09 Jun 2020 15:54:22 GMT

t-vi opened a new pull request #5752:
URL: https://github.com/apache/incubator-tvm/pull/5752


   Here is a PR making the hardcoded splits in the GPU batch matrix
   multiplication tunable through autotvm.
   
   (This is primarily aimed at the AMD GPU backend and done as part
   of a project for AMD, but should work for all users of the GPU
   schedule like the CUDA/nvptx backend as well.)
   
   I get reasonably good results for the workloads I tried - on par to 1.5x
   slower for batch matmul, but quite a speedup when integrated into
   BERT.
   
   This is my first PR adding autotvm tunings to the public repo, so please bear with me.
   


----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org



Mime
View raw message