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

ptxas path bug when ptxas is not found in /usr/local/cuda/bin #486

Closed
apd10 opened this issue Mar 28, 2022 · 1 comment
Closed

ptxas path bug when ptxas is not found in /usr/local/cuda/bin #486

apd10 opened this issue Mar 28, 2022 · 1 comment

Comments

@apd10
Copy link
Contributor

apd10 commented Mar 28, 2022

Issue: is that when ptxas is not found in /usr/local/cuda/bin , then the code crashes even if we enable TRITON_PTXAS_PATH environment variable (which would be the usual approach)

Bug in Code: The issue is in code. Code stores a single value of "ret" and it gets updated when it tries running the ptxas from /usr/local/cuda/bin with the error string thus erasing the value of ret which was valid for a previous call.
@apd10 apd10 mentioned this issue Mar 28, 2022
Merged
@ptillet
Copy link
Collaborator

ptillet commented Apr 4, 2022

Thanks! I've just merged your patch

@ptillet ptillet closed this as completed Apr 4, 2022
@0xdevalias 0xdevalias mentioned this issue Nov 10, 2022
Open
htyu pushed a commit to htyu/triton that referenced this issue Feb 6, 2024
@vgokhale @zhanglx13
[GEMM] [Tuning] Option to try different initialization strategies (tr…
49f6c3a 
…iton-lang#486)

* Add a few different GEMM init strategies

* Minor fixes

* Fix order when transposed

* Fix transpose

* Update tune_gemm.py

Fix blank lines

* remove init_type from mnks

* Fix trig_float

---------

Co-authored-by: Lixun Zhang <lixun.zhang@amd.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@ptillet @apd10