Lunderberg commented on pull request #8196:
URL: https://github.com/apache/tvm/pull/8196#issuecomment-859635982
Ooh, that's a nice side-effect to get! I guess that confirms that the
segfault was caused by out-of-order destruction, though I'm still not quite
sure how that happened, given
Lunderberg commented on pull request #8196:
URL: https://github.com/apache/tvm/pull/8196#issuecomment-858700548
The performance tests are matched pre/post change for cases that access the
thread-specific resources, so I think it's good to go.
@tqchen Any follow-up concerns?
--
Lunderberg commented on pull request #8196:
URL: https://github.com/apache/tvm/pull/8196#issuecomment-857142889
On second thought, it looks like that difference was because
`pytest-benchmark` does not include warmup runs by default. That run just
happened to be the first that required
Lunderberg commented on pull request #8196:
URL: https://github.com/apache/tvm/pull/8196#issuecomment-857140287
Running some performance tests, it looks like the refactor has very little
impact on the overall runtime. The plots below show the Q1/median/Q3 runtimes
for different low-level
Lunderberg commented on pull request #8196:
URL: https://github.com/apache/tvm/pull/8196#issuecomment-855005511
Thank you @tqchen , and that makes sense with the potential overhead issues.
I had been assuming that the main performance cost would be in the
`std::unordered_map` lookup.
Lunderberg commented on pull request #8196:
URL: https://github.com/apache/tvm/pull/8196#issuecomment-854898061
Potential reviewers: @masahi @tmoreau89
--
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
