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.

Sign up for GitHub

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

Jump to bottom

codegen: truncate Float16 vector ops also #46130

Merged
merged 1 commit into from
Aug 2, 2022
Merged

codegen: truncate Float16 vector ops also #46130

merged 1 commit into from
Aug 2, 2022

Conversation

vtjnash
Copy link
Sponsor Member

@vtjnash vtjnash commented Jul 21, 2022

No description provided.

@giordano
Copy link
Contributor

Is this meant to fix #45881?

@giordano giordano added compiler:codegen Generation of LLVM IR and native code float16 compiler:llvm For issues that relate to LLVM labels Jul 21, 2022
@vchuravy
Copy link
Member

Would be great to have tests in llvmpases for this!

@giordano
Copy link
Contributor

Would also be cool to finish #40216 at the same time, otherwise this would turn into one of the worst bug fixes, I quite liked the bug 😂

@gbaraldi
Copy link
Member

@vtjnash is it possible to make #43327 work without https://reviews.llvm.org/D120585. I think you mentioned it's possible to see the CPU features from inside the pass without a target machine.

@vtjnash vtjnash requested a review from vchuravy July 30, 2022 02:46
@vtjnash
Copy link
Sponsor Member Author

vtjnash commented Aug 2, 2022

Seems to have run into a rare test issue with #30415 (@ViralBShah)?

Error in testset SparseArrays/spqr:
Test Failed at /cache/build/default-amdci4-0/julialang/julia-master/julia-052c652e1c/share/julia/stdlib/v1.9/SparseArrays/test/spqr.jl:134
  Expression: rank(qr(S)) == 5
   Evaluated: 6 == 5
Error in testset SparseArrays/spqr:
Test Failed at /cache/build/default-amdci4-0/julialang/julia-master/julia-052c652e1c/share/julia/stdlib/v1.9/SparseArrays/test/spqr.jl:135
  Expression: rank(S) == 5
   Evaluated: 6 == 5

@vtjnash vtjnash merged commit eedf3f1 into master Aug 2, 2022
@vtjnash vtjnash deleted the jn/vfloat16-trunc branch August 2, 2022 15:30
@ViralBShah
Copy link
Member

I believe there are some fixes coming along on SparseArrays.jl soon.

ffucci pushed a commit to ffucci/julia that referenced this pull request Aug 11, 2022
@vtjnash
codegen: truncate Float16 vector ops also (JuliaLang#46130)
02940c4 
fix JuliaLang#45881
pcjentsch pushed a commit to pcjentsch/julia that referenced this pull request Aug 18, 2022
@vtjnash @pcjentsch
codegen: truncate Float16 vector ops also (JuliaLang#46130)
8e626d2 
fix JuliaLang#45881
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@vchuravy vchuravy Awaiting requested review from vchuravy

Assignees
No one assigned
Labels
compiler:codegen Generation of LLVM IR and native code compiler:llvm For issues that relate to LLVM float16
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
5 participants
@vtjnash @giordano @vchuravy @gbaraldi @ViralBShah