-
Notifications
You must be signed in to change notification settings - Fork 112
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
Add sm100 support to <nv/target> for NVCC #1745
Conversation
pre-commit.ci autofix |
/ok to test |
🟨 CI Results [ Failed: 1 | Passed: 301 | Total: 302 ]
|
# | Runner |
---|---|
232 | linux-amd64-cpu16 |
28 | linux-amd64-gpu-v100-latest-1 |
24 | linux-arm64-cpu16 |
18 | windows-amd64-cpu16 |
👃 Inspect Changes
Modifications in project?
Project | |
---|---|
CCCL Infrastructure | |
+/- | libcu++ |
CUB | |
Thrust | |
CUDA Experimental |
Modifications in project or dependencies?
Project | |
---|---|
CCCL Infrastructure | |
+/- | libcu++ |
+/- | CUB |
+/- | Thrust |
+/- | CUDA Experimental |
# undef NV_HAS_FEATURE_SM_100a | ||
# define NV_HAS_FEATURE_SM_100a __NV_HAS_FEATURE_SM_100a | ||
# if (defined(__CUDA_ARCH__) && (__CUDA_ARCH__ >= 1000) && defined(__CUDA_ARCH_FEAT_SM100_ALL)) | ||
# define _NV_TARGET_BOOL___NV_HAS_FEATURE_SM_100a 1 | ||
# else | ||
# define _NV_TARGET_BOOL___NV_HAS_FEATURE_SM_100a 0 | ||
# endif | ||
|
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.
I dont think that this is needed yet, as there is no SM100a feature
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.
I do think this is needed. SM100a features can build on top of this.
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.
I think we possibly don't care. If sm100a doesn't exist then it doesn't matter. The only people that would be bothered are those relying on intellisense.
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.
LGTM.
Question:
- do we want to have a test to check that it works?
- As a follow-up should we add sm100 to the build matrix?
There is something of a canary existing in the current tests. Compiling with an unknown architecture fails because we try to use |
/ok to test |
🟩 CI Results: Pass: 100%/302 | Total Time: 2d 06h | Avg Time: 10m 46s | Hits: 81%/369251
|
# | Runner |
---|---|
232 | linux-amd64-cpu16 |
28 | linux-amd64-gpu-v100-latest-1 |
24 | linux-arm64-cpu16 |
18 | windows-amd64-cpu16 |
👃 Inspect Changes
Modifications in project?
Project | |
---|---|
CCCL Infrastructure | |
+/- | libcu++ |
CUB | |
Thrust | |
CUDA Experimental |
Modifications in project or dependencies?
Project | |
---|---|
CCCL Infrastructure | |
+/- | libcu++ |
+/- | CUB |
+/- | Thrust |
+/- | CUDA Experimental |
Description
closes: #1738
Checklist