[Headers][X86] Allow integer/fp absolute intrinsics to be used in constexpr

[RKSimon]

Once #152497 and #152705 have landed we need to update the MMX/SSE/AVX2/AVX512 absolute functions to constexpr

These wrap __builtin_elementwise_abs:

_mm_abs_pi8
_mm_abs_pi16
_mm_abs_pi32

_mm_abs_epi8  _mm256_abs_epi8  _mm512_abs_epi8
_mm_abs_epi16 _mm256_abs_epi16 _mm512_abs_epi16
_mm_abs_epi32 _mm256_abs_epi32 _mm512_abs_epi32
_mm_abs_epi64 _mm256_abs_epi64 _mm512_abs_epi64

_mm_mask_abs_epi8  _mm256_mask_abs_epi8  _mm512_mask_abs_epi8
_mm_mask_abs_epi16 _mm256_mask_abs_epi16 _mm512_mask_abs_epi16
_mm_mask_abs_epi32 _mm256_mask_abs_epi32 _mm512_mask_abs_epi32
_mm_mask_abs_epi64 _mm256_mask_abs_epi64 _mm512_mask_abs_epi64

_mm_maskz_abs_epi8  _mm256_maskz_abs_epi8  _mm512_maskz_abs_epi8
_mm_maskz_abs_epi16 _mm256_maskz_abs_epi16 _mm512_maskz_abs_epi16
_mm_maskz_abs_epi32 _mm256_maskz_abs_epi32 _mm512_maskz_abs_epi32
_mm_maskz_abs_epi64 _mm256_maskz_abs_epi64 _mm512_maskz_abs_epi64

The AVX512 fp absolute use bit logic:

_mm512_abs_pd _mm512_mask_abs_pd
_mm512_abs_ps _mm512_mask_abs_ps

_mm_abs_ph _mm256_abs_ph _mm512_abs_ph

You can use #152305 as reference.

[llvmbot]

@llvm/issue-subscribers-backend-x86

Author: Simon Pilgrim (RKSimon)

Once #152497 and #152705 have landed we update the MMX/SSE/AVX2/AVX512 absolute functions to constexpr

These wrap __builtin_elementwise_abs:

_mm_abs_pi8
_mm_abs_pi16
_mm_abs_pi32

_mm_abs_epi8  _mm256_abs_epi8  _mm512_abs_epi8
_mm_abs_epi16 _mm256_abs_epi16 _mm512_abs_epi16
_mm_abs_epi32 _mm256_abs_epi32 _mm512_abs_epi32
_mm_abs_epi64 _mm256_abs_epi64 _mm512_abs_epi64

_mm_mask_abs_epi8  _mm256_mask_abs_epi8  _mm512_mask_abs_epi8
_mm_mask_abs_epi16 _mm256_mask_abs_epi16 _mm512_mask_abs_epi16
_mm_mask_abs_epi32 _mm256_mask_abs_epi32 _mm512_mask_abs_epi32
_mm_mask_abs_epi64 _mm256_mask_abs_epi64 _mm512_mask_abs_epi64

_mm_maskz_abs_epi8  _mm256_maskz_abs_epi8  _mm512_maskz_abs_epi8
_mm_maskz_abs_epi16 _mm256_maskz_abs_epi16 _mm512_maskz_abs_epi16
_mm_maskz_abs_epi32 _mm256_maskz_abs_epi32 _mm512_maskz_abs_epi32
_mm_maskz_abs_epi64 _mm256_maskz_abs_epi64 _mm512_maskz_abs_epi64

The AVX512 fp absolute use bit logic:

_mm512_abs_pd _mm512_mask_abs_pd
_mm512_abs_ps _mm512_mask_abs_ps

_mm_abs_ph _mm256_abs_ph _mm512_abs_ph

You can use #152305 as reference.

[llvmbot]

Hi!

This issue may be a good introductory issue for people new to working on LLVM. If you would like to work on this issue, your first steps are:

1. Check that no other contributor is working on this issue. If someone is assigned to the issue or claimed to be working on it, ping the person. After one week without a response, the assignee may be changed.
2. Leave a comment indicating that you are working on the issue, or just create a pull request after following the steps below. Mention this issue in the description of the pull request.
3. Fix the issue locally.
4. Run the test suite locally. Remember that the subdirectories under test/ create fine-grained testing targets, so you can e.g. use make check-clang-ast to only run Clang's AST tests.
5. Create a Git commit.
6. Run git clang-format HEAD~1 to format your changes.
7. Open a pull request to the upstream repository on GitHub. Detailed instructions can be found in GitHub's documentation. Mention this issue in the description of the pull request.

If you have any further questions about this issue, don't hesitate to ask via a comment in the thread below.

[llvmbot]

@llvm/issue-subscribers-good-first-issue

Author: Simon Pilgrim (RKSimon)

Once #152497 and #152705 have landed we update the MMX/SSE/AVX2/AVX512 absolute functions to constexpr

These wrap __builtin_elementwise_abs:

_mm_abs_pi8
_mm_abs_pi16
_mm_abs_pi32

_mm_abs_epi8  _mm256_abs_epi8  _mm512_abs_epi8
_mm_abs_epi16 _mm256_abs_epi16 _mm512_abs_epi16
_mm_abs_epi32 _mm256_abs_epi32 _mm512_abs_epi32
_mm_abs_epi64 _mm256_abs_epi64 _mm512_abs_epi64

_mm_mask_abs_epi8  _mm256_mask_abs_epi8  _mm512_mask_abs_epi8
_mm_mask_abs_epi16 _mm256_mask_abs_epi16 _mm512_mask_abs_epi16
_mm_mask_abs_epi32 _mm256_mask_abs_epi32 _mm512_mask_abs_epi32
_mm_mask_abs_epi64 _mm256_mask_abs_epi64 _mm512_mask_abs_epi64

_mm_maskz_abs_epi8  _mm256_maskz_abs_epi8  _mm512_maskz_abs_epi8
_mm_maskz_abs_epi16 _mm256_maskz_abs_epi16 _mm512_maskz_abs_epi16
_mm_maskz_abs_epi32 _mm256_maskz_abs_epi32 _mm512_maskz_abs_epi32
_mm_maskz_abs_epi64 _mm256_maskz_abs_epi64 _mm512_maskz_abs_epi64

The AVX512 fp absolute use bit logic:

_mm512_abs_pd _mm512_mask_abs_pd
_mm512_abs_ps _mm512_mask_abs_ps

_mm_abs_ph _mm256_abs_ph _mm512_abs_ph

You can use #152305 as reference.

[TianYe717]

@RKSimon Hi, I'd like work on this too. Can you assign it to me?

[RKSimon]

@RKSimon Hi, I'd like work on this too. Can you assign it to me?

If you ignore the avx512 mask/maskz variants for now you should be able to get the rest done in an initial patch

[TianYe717]

@RKSimon Hi, I'd like work on this too. Can you assign it to me?

If you ignore the avx512 mask/maskz variants for now you should be able to get the rest done in an initial patch

Thanks for the guidance. I’ll split the changes into two patches as suggested.