-
Notifications
You must be signed in to change notification settings - Fork 194
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
[STF] Executable CUDA graphs caching policies #3868
Merged
Merged
Conversation
This file contains 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
… graphs should be cached or not, and query what was the cache behaviour.
caugonnet
commented
Feb 20, 2025
@@ -233,6 +233,16 @@ class graph_ctx : public backend_ctx<graph_ctx> | |||
return *_graph; | |||
} | |||
|
|||
void graph_set_cache_policy(executable_graph_cache_policy<::std::function<bool(size_t)>> policy) override |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Is a mere bool value sufficient instead of this ?
caugonnet
commented
Feb 20, 2025
cudax/include/cuda/experimental/__stf/internal/executable_graph_cache.cuh
Show resolved
Hide resolved
caugonnet
commented
Feb 20, 2025
cudax/include/cuda/experimental/__stf/internal/executable_graph_cache.cuh
Outdated
Show resolved
Hide resolved
miscco
approved these changes
Feb 20, 2025
/ok to test |
🟨 CI finished in 18m 47s: Pass: 18%/22 | Total: 1h 19m | Avg: 3m 35s | Max: 10m 54s | Hits: 73%/1234
|
Project | |
---|---|
CCCL Infrastructure | |
libcu++ | |
CUB | |
Thrust | |
+/- | CUDA Experimental |
python | |
CCCL C Parallel Library | |
Catch2Helper |
Modifications in project or dependencies?
Project | |
---|---|
CCCL Infrastructure | |
libcu++ | |
CUB | |
Thrust | |
+/- | CUDA Experimental |
python | |
CCCL C Parallel Library | |
Catch2Helper |
🏃 Runner counts (total jobs: 22)
# | Runner |
---|---|
13 | linux-amd64-cpu16 |
4 | linux-arm64-cpu16 |
2 | windows-amd64-cpu16 |
2 | linux-amd64-gpu-rtx2080-latest-1 |
1 | linux-amd64-gpu-h100-latest-1 |
caugonnet
commented
Feb 21, 2025
cudax/include/cuda/experimental/__stf/internal/executable_graph_cache.cuh
Outdated
Show resolved
Hide resolved
/ok to test |
🟨 CI finished in 17m 44s: Pass: 9%/22 | Total: 1h 29m | Avg: 4m 03s | Max: 17m 44s | Hits: 61%/524
|
Project | |
---|---|
CCCL Infrastructure | |
libcu++ | |
CUB | |
Thrust | |
+/- | CUDA Experimental |
python | |
CCCL C Parallel Library | |
Catch2Helper |
Modifications in project or dependencies?
Project | |
---|---|
CCCL Infrastructure | |
libcu++ | |
CUB | |
Thrust | |
+/- | CUDA Experimental |
python | |
CCCL C Parallel Library | |
Catch2Helper |
🏃 Runner counts (total jobs: 22)
# | Runner |
---|---|
13 | linux-amd64-cpu16 |
4 | linux-arm64-cpu16 |
2 | windows-amd64-cpu16 |
2 | linux-amd64-gpu-rtx2080-latest-1 |
1 | linux-amd64-gpu-h100-latest-1 |
/ok to test |
🟨 CI finished in 51m 57s: Pass: 90%/22 | Total: 4h 50m | Avg: 13m 12s | Max: 18m 02s | Hits: 64%/10608
|
Project | |
---|---|
CCCL Infrastructure | |
libcu++ | |
CUB | |
Thrust | |
+/- | CUDA Experimental |
python | |
CCCL C Parallel Library | |
Catch2Helper |
Modifications in project or dependencies?
Project | |
---|---|
CCCL Infrastructure | |
libcu++ | |
CUB | |
Thrust | |
+/- | CUDA Experimental |
python | |
CCCL C Parallel Library | |
Catch2Helper |
🏃 Runner counts (total jobs: 22)
# | Runner |
---|---|
13 | linux-amd64-cpu16 |
4 | linux-arm64-cpu16 |
2 | windows-amd64-cpu16 |
2 | linux-amd64-gpu-rtx2080-latest-1 |
1 | linux-amd64-gpu-h100-latest-1 |
/ok to test |
🟨 CI finished in 32m 12s: Pass: 90%/22 | Total: 4h 49m | Avg: 13m 08s | Max: 17m 08s | Hits: 64%/10626
|
Project | |
---|---|
CCCL Infrastructure | |
libcu++ | |
CUB | |
Thrust | |
+/- | CUDA Experimental |
python | |
CCCL C Parallel Library | |
Catch2Helper |
Modifications in project or dependencies?
Project | |
---|---|
CCCL Infrastructure | |
libcu++ | |
CUB | |
Thrust | |
+/- | CUDA Experimental |
python | |
CCCL C Parallel Library | |
Catch2Helper |
🏃 Runner counts (total jobs: 22)
# | Runner |
---|---|
13 | linux-amd64-cpu16 |
4 | linux-arm64-cpu16 |
2 | windows-amd64-cpu16 |
2 | linux-amd64-gpu-rtx2080-latest-1 |
1 | linux-amd64-gpu-h100-latest-1 |
This reverts commit 643748a.
/ok to test |
🟩 CI finished in 27m 56s: Pass: 100%/22 | Total: 1h 56m | Avg: 5m 16s | Max: 12m 12s | Hits: 96%/11338
|
Project | |
---|---|
CCCL Infrastructure | |
libcu++ | |
CUB | |
Thrust | |
+/- | CUDA Experimental |
python | |
CCCL C Parallel Library | |
Catch2Helper |
Modifications in project or dependencies?
Project | |
---|---|
CCCL Infrastructure | |
libcu++ | |
CUB | |
Thrust | |
+/- | CUDA Experimental |
python | |
CCCL C Parallel Library | |
Catch2Helper |
🏃 Runner counts (total jobs: 22)
# | Runner |
---|---|
13 | linux-amd64-cpu16 |
4 | linux-arm64-cpu16 |
2 | windows-amd64-cpu16 |
2 | linux-amd64-gpu-rtx2080-latest-1 |
1 | linux-amd64-gpu-h100-latest-1 |
/ok to test |
/ok to test |
🟩 CI finished in 28m 08s: Pass: 100%/22 | Total: 4h 07m | Avg: 11m 16s | Max: 14m 42s | Hits: 70%/11338
|
Project | |
---|---|
CCCL Infrastructure | |
libcu++ | |
CUB | |
Thrust | |
+/- | CUDA Experimental |
python | |
CCCL C Parallel Library | |
Catch2Helper |
Modifications in project or dependencies?
Project | |
---|---|
CCCL Infrastructure | |
libcu++ | |
CUB | |
Thrust | |
+/- | CUDA Experimental |
python | |
CCCL C Parallel Library | |
Catch2Helper |
🏃 Runner counts (total jobs: 22)
# | Runner |
---|---|
13 | linux-amd64-cpu16 |
4 | linux-arm64-cpu16 |
2 | windows-amd64-cpu16 |
2 | linux-amd64-gpu-rtx2080-latest-1 |
1 | linux-amd64-gpu-h100-latest-1 |
caugonnet
commented
Feb 24, 2025
cudax/include/cuda/experimental/__stf/internal/executable_graph_cache.cuh
Show resolved
Hide resolved
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.
Facilities to choose whether executable CUDA graphs should be cached or not, and query what was the cache behaviour. This may lead to reporting inefficient use of CUDA graphs, or give user better control. (users may be tools relying on CUDA graphs)
Description
closes
Checklist