tvm-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From GitBox <...@apache.org>
Subject [GitHub] [incubator-tvm] comaniac commented on a change in pull request #5752: Make batch matrix multiplication on GPU tunable
Date Tue, 09 Jun 2020 18:02:18 GMT

comaniac commented on a change in pull request #5752:
URL: https://github.com/apache/incubator-tvm/pull/5752#discussion_r437618804



##########
File path: python/tvm/relay/op/strategy/cuda.py
##########
@@ -463,9 +463,9 @@ def batch_matmul_strategy_cuda(attrs, inputs, out_type, target):
     """batch_matmul cuda strategy"""
     strategy = _op.OpStrategy()
     strategy.add_implementation(
-        wrap_compute_batch_matmul(topi.nn.batch_matmul),
+        wrap_compute_batch_matmul(topi.cuda.batch_matmul),
         wrap_topi_schedule(topi.cuda.schedule_batch_matmul),
-        name="batch_matmul.cuda",
+        name="batch_matmul.gpu",

Review comment:
       Yeah I realized that ROCM uses many CUDA schedules and it results in confusion. We
can find lots of CUDA schedules have `if target == 'rocm'`. However, it would be better to
have a separate PR to correct this if everone agrees to do so.




----------------------------------------------------------------
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