Skip to content
This repository was archived by the owner on Aug 22, 2019. It is now read-only.

Conversation

@pointhi
Copy link
Contributor

@pointhi pointhi commented Jul 4, 2018

FIX: #847

Test seems to export different code as expected. Probably -march=native is required for avx2 testcase built

I was only able to create avx2 instructions. @mrigger on the other hand had sse2 instructions with the same name. If possible he should try to run the testcases as well to check if the sse2 implementation does not differ. (I was not able to test it for now)

@pointhi pointhi changed the title Add implementaiton of @llvm.x86.avx2.psrli.d and @llvm.x86.avx2.pslli… Add implementation of @llvm.x86.avx2.psrli.d and @llvm.x86.avx2.pslli… Jul 4, 2018
@pointhi pointhi force-pushed the sse2_vector_shift branch from 20f9a2c to 94e930b Compare July 25, 2018 09:22
….d, FIX: graalvm#847

Test seems to export different code as expected. Probably -march=native is required for avx2 testcase built
@pointhi pointhi force-pushed the sse2_vector_shift branch from 94e930b to 39a2a4e Compare July 25, 2018 09:45
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants