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

Win32 clang build #22

Open
wants to merge 10 commits into
base: main
Choose a base branch
from
Open

Win32 clang build #22

wants to merge 10 commits into from

Conversation

wkpark
Copy link
Owner

@wkpark wkpark commented Oct 19, 2024

clang + windows build matrix

wkpark and others added 10 commits October 19, 2024 17:26
 * remove AVX/BMI optimization
 * based on Windows support PR triton-lang#2465 by @andreigh
   - triton-lang#2465
 * manually applied, rebased, fix lint errors
 * remove '/A' platform option to use ninja
 * use sysconfig.get_config_var() to get the path of python*.lib
 * clang fix for windows
 * remove '-fPIC' for windows clang
 * fix download_and_copy() to support windows
 * add "exe" extension for windows
 * use "pyd" extension for windows to make importlib work
 * third_party/nvidia: fix for windows
 * win32 fix _path_to_binary()
 * add library_dir, include_dir for win32
 * backend/compiler lazy remove temp files to support windows
 * additional works done by @mantaionut (2024/05/31)
 * rework for latest triton and cleanup (2024/10/14)
 * extract minimal fixes to support win32+clang (2024/10/16)
 * get exe/so extension using sysconfig (suggested by @anmyachev)

see also:
 intel/intel-xpu-backend-for-triton#2478

Original-author-by: Andrei Gheorghe <andrei@dharmaventures.co>
Signed-off-by: Won-Kyu Park <wkpark@gmail.com>
 * additional fix by @woct0rdho
 * lint Utility.cpp
 * based on Windows support PR triton-lang#2456 by @andreigh
 * WIN32 fix using LoadLibrary
 * nvidia: nvcuda.dll, cupti*.dll, cublasLT*.dll
 * amd: fix dlfcn to support win32
 * hsa: not supported but added for future use
 * lint
 * update build matrix
 * use python 3.12
 * add env vars.LLVM_LOCAL_HASH to use local llvm compiler
 * upload wheels
@wkpark wkpark force-pushed the main branch 2 times, most recently from f58d88a to a69014a Compare October 23, 2024 04:21
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants