anijain2305 opened a new pull request #5197: [TOPI x86] Adding unroll_kw config 
option for depthwise conv2d.
URL: https://github.com/apache/incubator-tvm/pull/5197
 
 
   @yzhliu 
   
   unroll_kw is used for normal conv2d schedules as well. In the case of 
depthwise conv2d, the input pixels are actually vectorized (not broadcasted as 
in the case with normal conv2d). This potentially can create opportunities for 
reusing the data vector across two output pixels. Therefore, adding unroll_kw 
config option.
   
   In any case, this does not bring perf degradation. It makes search space 
larger.
   
   Concern - This might require a minor change in Tophub configuration. I can 
make that change once this PR is merged (or just before).
   
   

----------------------------------------------------------------
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]


With regards,
Apache Git Services

Reply via email to