Conversation
|
@rhornung67 would it be possible to setup a read the docs for this branch? |
artv3
requested review from
mdavis36,
rchen20 and
rhornung67
and removed request for
rhornung67
|
I've beefed up the launch docs in this PR, I believe it is ready for others to take a look at. CI is failing for CUDA for known reasons orthogonal to this PR. |
|
@artv3 I think the problem is that we're testing against camp main and @MrBurmark PR for camp was merged. That change doesn't export the CUDA targets properly. |
|
Now that I know the right target to link against I might have a hope of updating camp to depend on that, though I don't know how to do anything more magical like blt might do. |
|
I can't find the message from David about what is the correct CMake call. I'm also looking into something else that may help. |
|
docs/sphinx/user_guide/tutorial/matrix_transpose_local_array.rst
Outdated
Show resolved
Hide resolved
|
|
||
| // kernel body using index 'i' | ||
|
|
||
| }); |
There was a problem hiding this comment.
vertical alignment of }); with statement it corresponds to
rhornung67
left a comment
rhornung67
left a comment
There was a problem hiding this comment.
Overall looks good. A few formatting text changes to be made noted in comments.
Co-authored-by: Rich Hornung <hornung1@llnl.gov>
Co-authored-by: Rich Hornung <hornung1@llnl.gov>
Co-authored-by: Rich Hornung <hornung1@llnl.gov>
Co-authored-by: Rich Hornung <hornung1@llnl.gov>
Co-authored-by: Rich Hornung <hornung1@llnl.gov>
Co-authored-by: Rich Hornung <hornung1@llnl.gov>
Co-authored-by: Rich Hornung <hornung1@llnl.gov>
Co-authored-by: Rich Hornung <hornung1@llnl.gov>
Co-authored-by: Rich Hornung <hornung1@llnl.gov>
Co-authored-by: Rich Hornung <hornung1@llnl.gov>
|
@MrBurmark @rchen20 @mdavis36 did you guys want to take a look? or should I merge? |
Co-authored-by: Robert Chen <chen59@llnl.gov>
5 participants
Addressing missing docs in launch (#1068)
Attempt to address #1471
This PR adds in documentation for:
Dynamic shared memory usage
launch types, seq_launch_t, omp_launch_t, cuda_launch_t
loop tiling