Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Simd improvements #951

Merged
merged 6 commits into from
Jul 25, 2020
Merged

Simd improvements #951

merged 6 commits into from
Jul 25, 2020

Conversation

bjorn3
Copy link
Member

@bjorn3 bjorn3 commented Mar 31, 2020

No description provided.

@bjorn3 bjorn3 added C-enhancement Category: An issue proposing an enhancement or a PR with one. optimize-speed The speed of the generated executable A-core-arch Area: Necessary for full core::arch support labels Mar 31, 2020
@bjorn3
Copy link
Member Author

bjorn3 commented Mar 31, 2020

failures:

---- num::bignum::test_mul_pow2_overflow_2 stdout ----
---- num::bignum::test_mul_pow2_overflow_2 stderr ----
Unexpected error: child process exited with signal 4

failures:
    num::bignum::test_mul_pow2_overflow_2

Bisected to de85500. Omitting it for now.

@bjorn3
Copy link
Member Author

bjorn3 commented Mar 31, 2020

There is now a macOS only leading_zeros() problem caused by using the haswell preset. Debugging it is hard because I don't have access to a mac right now, so I have to use CI. (branch: simd_bisect)

@bjorn3
Copy link
Member Author

bjorn3 commented Apr 11, 2020

Cherry-picked the changed not related to SIMD onto master.

@bjorn3
Copy link
Member Author

bjorn3 commented Jul 25, 2020

Found the problem: The macOS CI uses an "Intel(R) Xeon(R) CPU E5-1650 v2 @ 3.50GHz" This is a Ivy Bridge EP, which means that lzcnt is not yet supported.

@bjorn3
Copy link
Member Author

bjorn3 commented Jul 25, 2020

Switched the target cpu from haswell to nehalem, which is good enough for SIMD support.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
A-core-arch Area: Necessary for full core::arch support C-enhancement Category: An issue proposing an enhancement or a PR with one. optimize-speed The speed of the generated executable
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

1 participant