You are viewing a plain text version of this content. The canonical link for it is here.

Posted to commits@tvm.apache.org by GitBox <gi...@apache.org> on 2022/05/20 19:53:55 UTC

[GitHub] [tvm] masahi commented on a diff in pull request #11389: Fix int8 cuda kernels on older SM versions

masahi commented on code in PR #11389:
URL: https://github.com/apache/tvm/pull/11389#discussion_r878504009


##########
python/tvm/topi/cuda/batch_matmul.py:
##########
@@ -367,7 +367,7 @@ def _schedule_batch_matmul_int8(cfg, s, output):
     # dp4a tensorize
 
     target = tvm.target.Target.current(allow_none=False)
-    do_tensorize = True
+    do_tensorize = target.supports_integer_dot_product

Review Comment:
   I think we can always initialize `do_tensorize` as
   ```
   do_tensorize = "+dotprod" in target.mattr or target.supports_integer_dot_product
   ```
   and remove `if is_target(["vulkan", "rocm"]):` below.



-- 
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.

To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org

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