-
Notifications
You must be signed in to change notification settings - Fork 188
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 CUB tests for segmented sort/radix sort with 64-bit num. items and segments #2254
Conversation
Additional comment. The tests for segmented sort/radix sort seem a bit messy and they can probably be simplified and partially merged, since they evaluate similar functions. |
/ok to test |
🟨 CI finished in 4h 11m: Pass: 65%/250 | Total: 2d 14h | Avg: 15m 00s | Max: 47m 29s | Hits: 99%/11560
|
Project | |
---|---|
CCCL Infrastructure | |
libcu++ | |
+/- | CUB |
Thrust | |
CUDA Experimental | |
pycuda |
Modifications in project or dependencies?
Project | |
---|---|
CCCL Infrastructure | |
libcu++ | |
+/- | CUB |
+/- | Thrust |
CUDA Experimental | |
+/- | pycuda |
🏃 Runner counts (total jobs: 250)
# | Runner |
---|---|
178 | linux-amd64-cpu16 |
41 | linux-amd64-gpu-v100-latest-1 |
16 | linux-arm64-cpu16 |
15 | windows-amd64-cpu16 |
Added a macro guard to protect segmented sort tests that are not supported yet. |
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.
Thanks a lot for helping to add tests here. Overall the tests are written very nicely. I would just need to extend coverage a bit, particularly across offset types, for it to meet my current use case for verifying the correctness when using different offset types during benchmarking, i.e., int32_t
, uint32_t
, int64_t
, uint64_t
.
…rwrite flag, catch OOM exceptions
@elstehle, thanks for the careful review! |
…cl into cub/test/64bit_segmented_sort
/ok to test |
/ok to test |
🟩 CI finished in 4h 51m: Pass: 100%/251 | Total: 1d 17h | Avg: 9m 58s | Max: 1h 24m | Hits: 99%/24375
|
Project | |
---|---|
CCCL Infrastructure | |
libcu++ | |
+/- | CUB |
Thrust | |
CUDA Experimental | |
pycuda |
Modifications in project or dependencies?
Project | |
---|---|
CCCL Infrastructure | |
libcu++ | |
+/- | CUB |
+/- | Thrust |
CUDA Experimental | |
+/- | pycuda |
🏃 Runner counts (total jobs: 251)
# | Runner |
---|---|
178 | linux-amd64-cpu16 |
42 | linux-amd64-gpu-v100-latest-1 |
16 | linux-arm64-cpu16 |
15 | windows-amd64-cpu16 |
Co-authored-by: Elias Stehle <[email protected]>
Co-authored-by: Elias Stehle <[email protected]>
Co-authored-by: Elias Stehle <[email protected]>
Co-authored-by: Elias Stehle <[email protected]>
/ok to test |
the idea of |
🟨 CI finished in 50m 38s: Pass: 99%/208 | Total: 1d 15h | Avg: 11m 15s | Max: 34m 49s | Hits: 98%/14058
|
Project | |
---|---|
CCCL Infrastructure | |
libcu++ | |
+/- | CUB |
Thrust | |
CUDA Experimental | |
pycuda | |
CUDA C Core Library |
Modifications in project or dependencies?
Project | |
---|---|
CCCL Infrastructure | |
libcu++ | |
+/- | CUB |
+/- | Thrust |
CUDA Experimental | |
+/- | pycuda |
+/- | CUDA C Core Library |
🏃 Runner counts (total jobs: 208)
# | Runner |
---|---|
171 | linux-amd64-cpu16 |
16 | linux-arm64-cpu16 |
12 | linux-amd64-gpu-v100-latest-1 |
9 | windows-amd64-cpu16 |
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.
One last change request, otherwise looks good to be merged.
I left the comments only on cub/test/catch2_test_device_segmented_radix_sort_keys.cu
, but they equally apply to the other test files.
…cl into cub/test/64bit_segmented_sort
/ok to test |
🟩 CI finished in 1h 08m: Pass: 100%/208 | Total: 1d 15h | Avg: 11m 26s | Max: 34m 06s | Hits: 98%/14058
|
Project | |
---|---|
CCCL Infrastructure | |
libcu++ | |
+/- | CUB |
Thrust | |
CUDA Experimental | |
pycuda | |
CUDA C Core Library |
Modifications in project or dependencies?
Project | |
---|---|
CCCL Infrastructure | |
libcu++ | |
+/- | CUB |
+/- | Thrust |
CUDA Experimental | |
+/- | pycuda |
+/- | CUDA C Core Library |
🏃 Runner counts (total jobs: 208)
# | Runner |
---|---|
171 | linux-amd64-cpu16 |
16 | linux-arm64-cpu16 |
12 | linux-amd64-gpu-v100-latest-1 |
9 | windows-amd64-cpu16 |
/ok to test |
/ok to test |
🟩 CI finished in 1h 47m: Pass: 100%/208 | Total: 1d 14h | Avg: 11m 05s | Max: 39m 46s | Hits: 98%/14058
|
Project | |
---|---|
CCCL Infrastructure | |
libcu++ | |
+/- | CUB |
Thrust | |
CUDA Experimental | |
pycuda | |
CUDA C Core Library |
Modifications in project or dependencies?
Project | |
---|---|
CCCL Infrastructure | |
libcu++ | |
+/- | CUB |
+/- | Thrust |
CUDA Experimental | |
+/- | pycuda |
+/- | CUDA C Core Library |
🏃 Runner counts (total jobs: 208)
# | Runner |
---|---|
171 | linux-amd64-cpu16 |
16 | linux-arm64-cpu16 |
12 | linux-amd64-gpu-v100-latest-1 |
9 | windows-amd64-cpu16 |
/ok to test |
🟩 CI finished in 1h 01m: Pass: 100%/208 | Total: 1d 01h | Avg: 7m 24s | Max: 49m 15s | Hits: 99%/14058
|
Project | |
---|---|
CCCL Infrastructure | |
libcu++ | |
+/- | CUB |
Thrust | |
CUDA Experimental | |
pycuda | |
CUDA C Core Library |
Modifications in project or dependencies?
Project | |
---|---|
CCCL Infrastructure | |
libcu++ | |
+/- | CUB |
+/- | Thrust |
CUDA Experimental | |
+/- | pycuda |
+/- | CUDA C Core Library |
🏃 Runner counts (total jobs: 208)
# | Runner |
---|---|
171 | linux-amd64-cpu16 |
16 | linux-arm64-cpu16 |
12 | linux-amd64-gpu-v100-latest-1 |
9 | windows-amd64-cpu16 |
Provide 64-bit num. items and segments for
DispatchSegmentedSort
andDispatchSegmentedRadixSort
, both forKeys
andPairs
.Address #2139 and #2140
The integration is blocked by #50