First version of cuda.bindings.path_finder
#447
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Tested interactively with:
```
import cuda_paths
nvvm_path = cuda_paths._get_nvvm_path()
print(f"{nvvm_path=}")
```
|
Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually. Contributors can view more details about this message here. |
rwgk
changed the title
get_nvvm_path()
|
/ok to test |
|
```
______________________ ERROR collecting test_nvjitlink.py ______________________
tests/test_nvjitlink.py:62: in <module>
not check_nvjitlink_usable(), reason="nvJitLink not usable, maybe not installed or too old (<12.3)"
tests/test_nvjitlink.py:58: in check_nvjitlink_usable
return inner_nvjitlink._inspect_function_pointer("__nvJitLinkVersion") != 0
cuda/bindings/_internal/nvjitlink.pyx:257: in cuda.bindings._internal.nvjitlink._inspect_function_pointer
???
cuda/bindings/_internal/nvjitlink.pyx:260: in cuda.bindings._internal.nvjitlink._inspect_function_pointer
???
cuda/bindings/_internal/nvjitlink.pyx:208: in cuda.bindings._internal.nvjitlink._inspect_function_pointers
???
cuda/bindings/_internal/nvjitlink.pyx:102: in cuda.bindings._internal.nvjitlink._check_or_init_nvjitlink
???
cuda/bindings/_internal/nvjitlink.pyx:59: in cuda.bindings._internal.nvjitlink.load_library
???
/opt/hostedtoolcache/Python/3.13.2/x64/lib/python3.13/site-packages/cuda/bindings/path_finder.py:312: in get_cuda_paths
"nvvm": _get_nvvm_path(),
/opt/hostedtoolcache/Python/3.13.2/x64/lib/python3.13/site-packages/cuda/bindings/path_finder.py:285: in _get_nvvm_path
by, path = _get_nvvm_path_decision()
/opt/hostedtoolcache/Python/3.13.2/x64/lib/python3.13/site-packages/cuda/bindings/path_finder.py:96: in _get_nvvm_path_decision
if os.path.exists(nvvm_ctk_dir):
<frozen genericpath>:19: in exists
???
E TypeError: stat: path should be string, bytes, os.PathLike or integer, not NoneType
```
|
/ok to test |
```
______________________ ERROR collecting test_nvjitlink.py ______________________
tests/test_nvjitlink.py:62: in <module>
not check_nvjitlink_usable(), reason="nvJitLink not usable, maybe not installed or too old (<12.3)"
tests/test_nvjitlink.py:58: in check_nvjitlink_usable
return inner_nvjitlink._inspect_function_pointer("__nvJitLinkVersion") != 0
cuda/bindings/_internal/nvjitlink.pyx:257: in cuda.bindings._internal.nvjitlink._inspect_function_pointer
???
cuda/bindings/_internal/nvjitlink.pyx:260: in cuda.bindings._internal.nvjitlink._inspect_function_pointer
???
cuda/bindings/_internal/nvjitlink.pyx:208: in cuda.bindings._internal.nvjitlink._inspect_function_pointers
???
cuda/bindings/_internal/nvjitlink.pyx:102: in cuda.bindings._internal.nvjitlink._check_or_init_nvjitlink
???
cuda/bindings/_internal/nvjitlink.pyx:59: in cuda.bindings._internal.nvjitlink.load_library
???
/opt/hostedtoolcache/Python/3.13.2/x64/lib/python3.13/site-packages/cuda/bindings/path_finder.py:313: in get_cuda_paths
"libdevice": _get_libdevice_paths(),
/opt/hostedtoolcache/Python/3.13.2/x64/lib/python3.13/site-packages/cuda/bindings/path_finder.py:126: in _get_libdevice_paths
by, libdir = _get_libdevice_path_decision()
/opt/hostedtoolcache/Python/3.13.2/x64/lib/python3.13/site-packages/cuda/bindings/path_finder.py:73: in _get_libdevice_path_decision
if os.path.exists(libdevice_ctk_dir):
<frozen genericpath>:19: in exists
???
E TypeError: stat: path should be string, bytes, os.PathLike or integer, not NoneType
```
|
/ok to test |
|
/ok to test |
…ath.join(None, "libnvJitLink.so")
|
/ok to test |
|
/ok to test |
|
/ok to test |
…gs/_bindings/cynvrtc.pyx.in
|
/ok to test |
|
/ok to test |
|
Tracking link provided by @leofang on chat: There, when the |
|
/ok to test |
rwgk
changed the title
cuda.bindings.path_finder
|
Auto-sync is disabled for ready for review pull requests in this repository. Workflows must be run manually. Contributors can view more details about this message here. |
|
@leofang @kkraus14 This PR is ready for review. It's certain that more work is needed, but I believe what I have now is a meaningful milestone. I backed out my experiments with NVRTC for now (see PR description). After this PR is merged, I want to pick up that work, and then work towards replacing more/all dynamic library loading code with calls to |
|
To stay organized while we're in a code freeze, I created the "temporary integration branch" with name |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The third iteration of this PR description is:
Closes #453 (expected, but currently not tested)
This PR has these main aspects:
to pure Python code under the new
cuda/bindings/_path_finderdirectory.The API for calling from cython is simply:
load_nvidia_dynamic_library()first attempts to load the dynamic library using the system search features (rpath|LD_LIBRARY_PATH|PATH). If that succeeds, the handle to the library (a Pythoninton all platforms) is returned.Otherwise,
load_nvidia_dynamic_library()callsfind_nvidia_dynamic_library()to determine an absolute pathname for the dynamic library. Then it loads the library given that pathname.find_nvidia_dynamic_library()first searches for the library undersite-packages/nvidia, usingsys.pathto search for site-packages, in order. If that fails, it uses a clone ofnumba/cuda/cuda_paths.pyto search for the library.To pass all tests in the cuda-python CI, this trick is needed under Linux:
Here the last
/lib/is replaced with/lib64/or vice versa inget_cuda_paths()[name].infoand both are searched.@functools.cacheis used forload_nvidia_dynamic_library(name), therefore the involved search & load code is certain to be invoked only once per process, per library.numba/cuda/cuda_paths.pywas changed as little as possible, so that it is feasible to keep our copy in sync with the original while they both exist. The idea is to work towards usingcuda.bindings.path_finderfrom numba-cuda. (After that is achieved, the code undercuda/bindings/_path_findercan probably be refactored significantly.)TODO
.pyxfiles need to be backported to the upstream code generator.Deferred (follow-on PRs)
path_finder.load_nvidia_dynamic_library("nvrtc")— This was attempted but backed out. Special handling ofnvrtc-builtins64_128.dllis required, to replace or emulate this existing code.The second iteration of this PR description was:
These commits expand the experiment to adopt the entire numba/cuda/cuda_paths.py
Example:
The first iteration of this PR description was:
Experiment related to #441, triggered by this comment (by @kkraus14).
Context: Potentially use this code from cuda_bindings/cuda/bindings/_internal/nvvm_linux.pyx
This PR: Stripped-down (and ruff'ed) copies of:
https://github.com/NVIDIA/numba-cuda/blob/bf487d78a40eea87f009d636882a5000a7524c95/numba_cuda/numba/cuda/cuda_paths.py
https://github.com/numba/numba/blob/f0d24824fcd6a454827e3c108882395d00befc04/numba/misc/findlib.py
Tested interactively with:
Output:
Advantage of this approach: Battle-tested and time-tested.
Disadvantages: TBD