ANSHUMAN87 commented on pull request #6066:
URL: https://github.com/apache/incubator-tvm/pull/6066#issuecomment-667549552


   > One thing I think it is good to have in this PR is to get some benchmark 
data, since we now enable this pass by default. IMO this pass is especially 
valuable when tackling dynamic kernels in GPU which introduces a lot of 
branchings. It's great to see how much performance improvement we can have. For 
CPU, we need to make sure this pass doesn't introduce regression for some 
common workloads, such as resnet.
   
   @kevinthesun : I have verified the inference time for Resnet50 on CPU. There 
is no performance impact. In fact i did not find anything as Hoisting candidate.
   
   ### Hoisting Disabled :
   
![image](https://user-images.githubusercontent.com/32511895/89104943-9dde3a80-d43a-11ea-994d-85e1468c8241.png)
   
   
   ### Hoisting Enabled:
   
![image](https://user-images.githubusercontent.com/32511895/89104952-b2223780-d43a-11ea-8f92-e7fb4e555115.png)
   


----------------------------------------------------------------
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:
[email protected]


Reply via email to