[GitHub] [tvm] nverke commented on a diff in pull request #12783: [Hexagon] Reduce the number of tests run for VTCM testing in order to…

[GitBox <gi...@apache.org>]

nverke commented on code in PR #12783:
URL: https://github.com/apache/tvm/pull/12783#discussion_r974479650


##########
tests/python/contrib/test_hexagon/test_parallel_hvx_load_vtcm.py:
##########
@@ -308,7 +308,12 @@ def setup_and_run(hexagon_session, sch, a, b, c, operations, mem_scope="global")
     a_hexagon = tvm.runtime.ndarray.array(a, device=hexagon_session.device, mem_scope=mem_scope)
     b_hexagon = tvm.runtime.ndarray.array(b, device=hexagon_session.device, mem_scope=mem_scope)
     c_hexagon = tvm.runtime.ndarray.array(c, device=hexagon_session.device, mem_scope=mem_scope)
-    timer = module.time_evaluator("__tvm_main__", hexagon_session.device, number=100, repeat=10)
+
+    # These are reduced for CI but number=100 and repeat=10 does a good job of removing noise. 
+    number = 1 

Review Comment:
   Ooooh I will use this from now on thats super useful! 



-- 
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