Open
Conversation
Contributor
Author
|
Performance looks good: |
Contributor
Author
|
I have absolutely no idea why |
This comment has been minimized.
This comment has been minimized.
This implements the `iota` algorithm for the cuda backend. * `std::iota` see https://en.cppreference.com/w/cpp/algorithm/iota.html It provides tests and benchmarks similar to Thrust and some boilerplate for libcu++ The functionality is publicly available yet and implemented in a private internal header Fixes NVIDIA#7927
davebayer
approved these changes
Mar 9, 2026
Contributor
🥳 CI Workflow Results🟩 Finished in 1h 19m: Pass: 100%/99 | Total: 1d 01h | Max: 53m 50s | Hits: 98%/255735See results here. |
oleksandr-pavlyk
approved these changes
Mar 9, 2026
jrhemstad
reviewed
Mar 10, 2026
Comment on lines
+73
to
+98
| # if _LIBCUDACXX_HAS_NVFP16() | ||
| // We cannot rely on operator+ and constructors from integers to be available for the extended fp types | ||
| if constexpr (is_same_v<_Tp, __half>) | ||
| { | ||
| return ::__hadd(__init_, ::__ull2half_rn(__index)); | ||
| } | ||
| else | ||
| # endif // _LIBCUDACXX_HAS_NVFP16() | ||
| # if _LIBCUDACXX_HAS_NVBF16() | ||
| if constexpr (is_same_v<_Tp, __nv_bfloat16>) | ||
| { | ||
| return ::__hadd(__init_, ::__ull2bfloat16_rn(__index)); | ||
| } | ||
| else | ||
| # endif // _LIBCUDACXX_HAS_NVBF16() | ||
| if constexpr (is_arithmetic_v<_Tp>) | ||
| { // avoid warnings about integer conversions | ||
| return static_cast<_Tp>(__init_ + static_cast<_Tp>(__index)); | ||
| } | ||
| else if constexpr (__can_operator_plus_integral<_Tp>) | ||
| { | ||
| return __init_ + __index; | ||
| } | ||
| else if constexpr (__can_operator_plus_conversion<_Tp>) | ||
| { | ||
| return __init_ + static_cast<_Tp>(__index); |
Collaborator
There was a problem hiding this comment.
question: Shouldn't cuda::std::plus already handle all these details? Can we just use that here?
Contributor
Author
There was a problem hiding this comment.
Unfortunately, it does not but does the plain return __x + __y;
That means we can get integer promotion / sign conversion warnings
jrhemstad
reviewed
Mar 10, 2026
| _InputIterator __first, | ||
| _InputIterator __last, | ||
| const _Tp& __init, | ||
| const _Tp& __step) |
Collaborator
There was a problem hiding this comment.
comment: Adding a parallel iota is one thing, but adding an iota with a step feels too extreme to still be called cuda::std::iota.
I'm leaning more towards a cuda::sequence algorithm here, otherwise we're starting to twist our promise that everything in cuda/std is conforming.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This implements the
iotaalgorithm for the cuda backend.std::iotasee https://en.cppreference.com/w/cpp/algorithm/iota.htmlIt provides tests and benchmarks similar to Thrust and some boilerplate for libcu++
The functionality is publicly available yet and implemented in a private internal header
Fixes #7927