-
Notifications
You must be signed in to change notification settings - Fork 200
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
Fix cub::DeviceTransform
unwrapping cudax:async_buffer::iterator
#4083
base: main
Are you sure you want to change the base?
Fix cub::DeviceTransform
unwrapping cudax:async_buffer::iterator
#4083
Conversation
5b400f5
to
f0ea8dd
Compare
🟨 CI finished in 1h 16m: Pass: 26%/93 | Total: 22h 34m | Avg: 14m 33s | Max: 1h 14m | Hits: 52%/39457
|
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: 93)
# | Runner |
---|---|
66 | linux-amd64-cpu16 |
9 | windows-amd64-cpu16 |
6 | linux-amd64-gpu-rtxa6000-latest-1 |
4 | linux-arm64-cpu16 |
3 | linux-amd64-gpu-h100-latest-1 |
3 | linux-amd64-gpu-rtx4090-latest-1 |
2 | linux-amd64-gpu-rtx2080-latest-1 |
|
||
namespace cudax = cuda::experimental; | ||
|
||
C2H_TEST("DeviceTransform::Transform cudax::async_device_buffer", "[device][device_transform]", algorithms) |
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.
ditto we should move to cudax
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 kind of disagree. This test is more about cub::DeviceTransform
correctly working on the async_device_vector
, than whether the vector can be transformed.
f0ea8dd
to
ef41394
Compare
🟨 CI finished in 1h 19m: Pass: 43%/115 | Total: 2d 13h | Avg: 32m 05s | Max: 1h 17m | Hits: 59%/56460
|
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: 115)
# | Runner |
---|---|
79 | linux-amd64-cpu16 |
11 | windows-amd64-cpu16 |
8 | linux-arm64-cpu16 |
6 | linux-amd64-gpu-rtxa6000-latest-1 |
4 | linux-amd64-gpu-rtx2080-latest-1 |
4 | linux-amd64-gpu-h100-latest-1 |
3 | linux-amd64-gpu-rtx4090-latest-1 |
d2a5c30
to
b275629
Compare
b275629
to
fb1d7bf
Compare
🟨 CI finished in 1h 06m: Pass: 42%/115 | Total: 2d 11h | Avg: 31m 10s | Max: 1h 05m | Hits: 66%/53046
|
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: 115)
# | Runner |
---|---|
79 | linux-amd64-cpu16 |
11 | windows-amd64-cpu16 |
8 | linux-arm64-cpu16 |
6 | linux-amd64-gpu-rtxa6000-latest-1 |
4 | linux-amd64-gpu-rtx2080-latest-1 |
4 | linux-amd64-gpu-h100-latest-1 |
3 | linux-amd64-gpu-rtx4090-latest-1 |
This PR fixes a performance issue when
cub::DeviceTransform
is used withcudax:async_buffer
, by fixingthrust::is_contiguous_iterator
.Adding tests requires CUB and Thrust unit tests to have access to cudax. Please advice me on how to correctly link against
cudax
.