[GitHub] [incubator-tvm] merrymercy commented on a change in pull request #6391: [AutoTVM][Ansor] Enable random fill and CPU cache flush for AutoTVM and Ansor

[GitBox]

merrymercy commented on a change in pull request #6391:
URL: https://github.com/apache/incubator-tvm/pull/6391#discussion_r483899527



##########
File path: python/tvm/auto_scheduler/measure.py
##########
@@ -697,7 +696,7 @@ def timed_func():
                 args = [ndarray.empty(get_const_tuple(x.shape), x.dtype, ctx) 
for x in
                         build_res.args]
                 assert tvm.get_global_func("tvm.contrib.random.random_fill", 
True), \
-                    "Do you enable USE_RANDOM in the config.cmake?"
+                    "Please make sure USE_RANDOM is ON in the config.cmake"
                 random_fill = 
remote.get_function("tvm.contrib.random.random_fill")

Review comment:
       Then we should remove the assert `assert 
tvm.get_global_func("tvm.contrib.random.random_fill", True)` and use some try 
catch to capture the error from devices.




----------------------------------------------------------------
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:
us...@infra.apache.org