tvm-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From GitBox <...@apache.org>
Subject [GitHub] [incubator-tvm] Shawn-Inspur commented on a change in pull request #5600: [TOPI] Improve CUDA softmax scheduling
Date Sat, 23 May 2020 06:10:09 GMT

Shawn-Inspur commented on a change in pull request #5600:
URL: https://github.com/apache/incubator-tvm/pull/5600#discussion_r429518516



##########
File path: topi/python/topi/cuda/softmax.py
##########
@@ -53,13 +54,61 @@ def schedule_softmax(outs):
         raise ValueError('Tag is expected to be softmax_output or log_softmax_output. \
                          Got {0}'.format(op_tag))
 
+    # The nvptx backend only supports 32-bits warp shuffle instructions.
+    #
+    # TODO(tvm-team) Fix nvptx codegen or deprecate nvptx backend.
+    def sched_warp_softmax():
+        if tgt.target_name == "nvptx":
+            return softmax.dtype == "float32" or softmax.dtype == "int32"
+        return True

Review comment:
       This makes sense to 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