User Details
- User Since
- Apr 3 2020, 3:29 AM (41 w, 3 d)
Dec 15 2020
Thanks!
Thanks!
Can you also add this for ROCM?
Can be a separate CL ofc.
Dec 14 2020
Dec 11 2020
Add tests
Thanks!
Thanks!
Dec 9 2020
Looks good. Thanks!
We probably want this for rsqrt, too.
I saw the exact same failure and I'm pretty sure it is unrelated.
Dec 8 2020
Add test case
Nov 27 2020
Address comments
Nov 26 2020
Thanks!
Sorry, I saw this only now.
Thank you!
Nov 24 2020
Nov 23 2020
Nov 20 2020
Thanks!
Thanks!
Thanks!
Nov 13 2020
I believe this is still relevant as the FIXME is still present. The mlir-cuda-runner tests still fail.
@rriddle
Nov 5 2020
Nov 4 2020
Nov 3 2020
Yes, I reverted it yesterday as it caused problems with the integrate. I will re-land this when I figure out how to install an old GCC version.
Nov 2 2020
Unfortunately, I could not reproduce this failure,
I tried with gcc/g++ (Debian 10.2.0-9) 10.2.0.
Oct 30 2020
Oct 29 2020
Looks good!
Address comment
Fix clang-tidy
Oct 28 2020
Thanks! Will do that
Oct 27 2020
Oct 26 2020
Oct 23 2020
Rebase
Oct 21 2020
Address comment
Address comments
Oct 19 2020
Sep 30 2020
Sep 29 2020
Address comments
Sep 28 2020
Address comments
Thanks
Sep 24 2020
Sep 23 2020
We do not intend to add a standard lowering for atan as there would be many possible approximations.
Like @bondhugula said, it helps us with the lowering from lmhlo to std where we can subsequently apply our approximation.
Sorry for the missing discussion on Discourse. Should I still post it?