[GitHub] [incubator-tvm-vta] huajsj commented on pull request #7: [pynq_driver] fix device early return

2020-04-30 Thread GitBox 


huajsj commented on pull request #7:
URL: https://github.com/apache/incubator-tvm-vta/pull/7#issuecomment-621981787


   @remotego , thanks for the detailed explain, the logic make sense, code LGTM.
   
   



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

[GitHub] [incubator-tvm-vta] huajsj commented on pull request #7: [pynq_driver] fix device early return

2020-04-29 Thread GitBox 


huajsj commented on pull request #7:
URL: https://github.com/apache/incubator-tvm-vta/pull/7#issuecomment-621612870


   @remotego, Thanks for the detailed explain, but for this problem I think you 
may have a glance on related pynq driver logic,  actually there is no "racing 
condition" between "processor" and "FPGA" , because they are checking on 
different register.
   
   on line 124 the VTA_START get write into register with offset "0", and in 
line 134 the logic is go to check register with offset 
VTA_COMPUTE_DONE_RD_OFFSET which is "24", i think the work ground may work in 
some scenario but if we can not find root cause it may not reliable.



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

[GitHub] [incubator-tvm-vta] huajsj commented on pull request #7: [pynq_driver] fix device early return

2020-04-29 Thread GitBox 


huajsj commented on pull request #7:
URL: https://github.com/apache/incubator-tvm-vta/pull/7#issuecomment-621379576


   @zhanghaohit, thanks for the contribution,  do we know the root cause for 
this early return issue? a sleep solution may not always work and would impact 
performance, we better to avoid that.



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