Skip to content
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.

Sign up for GitHub

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

Jump to bottom

GPU batch 3 #4

Merged
merged 37 commits into from
Jul 26, 2024
Merged

GPU batch 3 #4

merged 37 commits into from
Jul 26, 2024

Conversation

mborland
Copy link
Member

Adds CUDA and SYCL support for: log1p, log1pmx, pow, sin_pi, cos_pi, digamma, trigamma, the bernoulli distribution

Re-implements std::numeric_limits so that we can use it rather than all the hackish workarounds.

@mborland
Add markers for log1p
cb3701b
@mborland
Add log1p CUDA testing
4df80c1
@mborland
Add SYCL testing for log1p and log1pmx
78a8d32
@mborland
Fix use of static const char* in log1pmx
428d666
@mborland
Loosen tolerance
944f45e
@mborland
Add GPU support to digamma
2e77757
@mborland
Add digamma CUDA testing
8c97086
@mborland
Add sycl test of digamma
9fb4677
@mborland
Begin adding our own definition of numeric_limits
6c1e9d7
@mborland
Make pow GPU compatible
1629e75
@mborland
Make sin_pi GPU compatible
c887a74
@mborland
Make trigamma GPU compatible
5f4ab0d
@mborland
Add trigamma CUDA testing
525b18c
@mborland
Rename dispatching function
db7fb65
@mborland
Eliminate recursion in sin_pi for SYCL
c049fab
@mborland
Remove recursion from trigamma
cfc1ad0
@mborland
Add trigamma SYCL testing
0fe35eb
@mborland
Add sycl testing of pow
48f8734
@mborland
Add CUDA sin_pi testing
b51d312
@mborland
Pass integral_constant directly instead of creating pointer
e4519a7
@mborland
Add missing include guards for numeric limits
20f17d4
@mborland
Make cos_pi GPU capable
85e2e4c
@mborland
Add cos_pi CUDA testing
3c598df
@mborland
Add all the integer types to numeric limits
502f04f
@mborland
Simplify error handling using the new numeric limits
8a5796a
@mborland
Add GPU support to derived accessors
0210fa3
@mborland
Add GPU support to complement distributions
226e42e
@mborland
Add GPU support to the bernoulli distribution
fcbcf04
@mborland
Add SYCL testing of bernoulli distribution
6bf19ff
@mborland
Add bernoulli cdf CUDA testing
0e7ab64
@mborland
Copy link
Member Author

These changes have been sent upstream in: boostorg/math#1164

@mborland mborland merged commit a2f5a20 into master Jul 26, 2024
2 checks passed
@mborland mborland deleted the CUDA_3_test branch July 26, 2024 20:32
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
1 participant
@mborland