Skip to content

[X86] Allow AVX512 masked bitlogic intrinsics to be used in constexpr #161544

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

[X86] Allow AVX512 masked bitlogic intrinsics to be used in constexpr #161544

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 14 additions & 14 deletions clang/lib/Headers/avx512dqintrin.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -172,14 +172,14 @@ _mm512_xor_pd(__m512d __A, __m512d __B) {
return (__m512d)((__v8du)__A ^ (__v8du)__B);
}

static __inline__ __m512d __DEFAULT_FN_ATTRS512
static __inline__ __m512d __DEFAULT_FN_ATTRS512_CONSTEXPR
_mm512_mask_xor_pd(__m512d __W, __mmask8 __U, __m512d __A, __m512d __B) {
return (__m512d)__builtin_ia32_selectpd_512((__mmask8)__U,
(__v8df)_mm512_xor_pd(__A, __B),
(__v8df)__W);
}

static __inline__ __m512d __DEFAULT_FN_ATTRS512
static __inline__ __m512d __DEFAULT_FN_ATTRS512_CONSTEXPR
_mm512_maskz_xor_pd(__mmask8 __U, __m512d __A, __m512d __B) {
return (__m512d)__builtin_ia32_selectpd_512((__mmask8)__U,
(__v8df)_mm512_xor_pd(__A, __B),
Expand All @@ -191,14 +191,14 @@ _mm512_xor_ps (__m512 __A, __m512 __B) {
return (__m512)((__v16su)__A ^ (__v16su)__B);
}

static __inline__ __m512 __DEFAULT_FN_ATTRS512
static __inline__ __m512 __DEFAULT_FN_ATTRS512_CONSTEXPR
_mm512_mask_xor_ps(__m512 __W, __mmask16 __U, __m512 __A, __m512 __B) {
return (__m512)__builtin_ia32_selectps_512((__mmask16)__U,
(__v16sf)_mm512_xor_ps(__A, __B),
(__v16sf)__W);
}

static __inline__ __m512 __DEFAULT_FN_ATTRS512
static __inline__ __m512 __DEFAULT_FN_ATTRS512_CONSTEXPR
_mm512_maskz_xor_ps(__mmask16 __U, __m512 __A, __m512 __B) {
return (__m512)__builtin_ia32_selectps_512((__mmask16)__U,
(__v16sf)_mm512_xor_ps(__A, __B),
Expand All @@ -210,14 +210,14 @@ _mm512_or_pd(__m512d __A, __m512d __B) {
return (__m512d)((__v8du)__A | (__v8du)__B);
}

static __inline__ __m512d __DEFAULT_FN_ATTRS512
static __inline__ __m512d __DEFAULT_FN_ATTRS512_CONSTEXPR
_mm512_mask_or_pd(__m512d __W, __mmask8 __U, __m512d __A, __m512d __B) {
return (__m512d)__builtin_ia32_selectpd_512((__mmask8)__U,
(__v8df)_mm512_or_pd(__A, __B),
(__v8df)__W);
}

static __inline__ __m512d __DEFAULT_FN_ATTRS512
static __inline__ __m512d __DEFAULT_FN_ATTRS512_CONSTEXPR
_mm512_maskz_or_pd(__mmask8 __U, __m512d __A, __m512d __B) {
return (__m512d)__builtin_ia32_selectpd_512((__mmask8)__U,
(__v8df)_mm512_or_pd(__A, __B),
Expand All @@ -229,14 +229,14 @@ _mm512_or_ps(__m512 __A, __m512 __B) {
return (__m512)((__v16su)__A | (__v16su)__B);
}

static __inline__ __m512 __DEFAULT_FN_ATTRS512
static __inline__ __m512 __DEFAULT_FN_ATTRS512_CONSTEXPR
_mm512_mask_or_ps(__m512 __W, __mmask16 __U, __m512 __A, __m512 __B) {
return (__m512)__builtin_ia32_selectps_512((__mmask16)__U,
(__v16sf)_mm512_or_ps(__A, __B),
(__v16sf)__W);
}

static __inline__ __m512 __DEFAULT_FN_ATTRS512
static __inline__ __m512 __DEFAULT_FN_ATTRS512_CONSTEXPR
_mm512_maskz_or_ps(__mmask16 __U, __m512 __A, __m512 __B) {
return (__m512)__builtin_ia32_selectps_512((__mmask16)__U,
(__v16sf)_mm512_or_ps(__A, __B),
Expand All @@ -255,7 +255,7 @@ _mm512_mask_and_pd(__m512d __W, __mmask8 __U, __m512d __A, __m512d __B) {
(__v8df)__W);
}

static __inline__ __m512d __DEFAULT_FN_ATTRS512
static __inline__ __m512d __DEFAULT_FN_ATTRS512_CONSTEXPR
_mm512_maskz_and_pd(__mmask8 __U, __m512d __A, __m512d __B) {
return (__m512d)__builtin_ia32_selectpd_512((__mmask8)__U,
(__v8df)_mm512_and_pd(__A, __B),
Expand All @@ -274,7 +274,7 @@ _mm512_mask_and_ps(__m512 __W, __mmask16 __U, __m512 __A, __m512 __B) {
(__v16sf)__W);
}

static __inline__ __m512 __DEFAULT_FN_ATTRS512
static __inline__ __m512 __DEFAULT_FN_ATTRS512_CONSTEXPR
_mm512_maskz_and_ps(__mmask16 __U, __m512 __A, __m512 __B) {
return (__m512)__builtin_ia32_selectps_512((__mmask16)__U,
(__v16sf)_mm512_and_ps(__A, __B),
Expand All @@ -286,14 +286,14 @@ _mm512_andnot_pd(__m512d __A, __m512d __B) {
return (__m512d)(~(__v8du)__A & (__v8du)__B);
}

static __inline__ __m512d __DEFAULT_FN_ATTRS512
static __inline__ __m512d __DEFAULT_FN_ATTRS512_CONSTEXPR
_mm512_mask_andnot_pd(__m512d __W, __mmask8 __U, __m512d __A, __m512d __B) {
return (__m512d)__builtin_ia32_selectpd_512((__mmask8)__U,
(__v8df)_mm512_andnot_pd(__A, __B),
(__v8df)__W);
}

static __inline__ __m512d __DEFAULT_FN_ATTRS512
static __inline__ __m512d __DEFAULT_FN_ATTRS512_CONSTEXPR
_mm512_maskz_andnot_pd(__mmask8 __U, __m512d __A, __m512d __B) {
return (__m512d)__builtin_ia32_selectpd_512((__mmask8)__U,
(__v8df)_mm512_andnot_pd(__A, __B),
Expand All @@ -305,14 +305,14 @@ _mm512_andnot_ps(__m512 __A, __m512 __B) {
return (__m512)(~(__v16su)__A & (__v16su)__B);
}

static __inline__ __m512 __DEFAULT_FN_ATTRS512
static __inline__ __m512 __DEFAULT_FN_ATTRS512_CONSTEXPR
_mm512_mask_andnot_ps(__m512 __W, __mmask16 __U, __m512 __A, __m512 __B) {
return (__m512)__builtin_ia32_selectps_512((__mmask16)__U,
(__v16sf)_mm512_andnot_ps(__A, __B),
(__v16sf)__W);
}

static __inline__ __m512 __DEFAULT_FN_ATTRS512
static __inline__ __m512 __DEFAULT_FN_ATTRS512_CONSTEXPR
_mm512_maskz_andnot_ps(__mmask16 __U, __m512 __A, __m512 __B) {
return (__m512)__builtin_ia32_selectps_512((__mmask16)__U,
(__v16sf)_mm512_andnot_ps(__A, __B),
Expand Down
66 changes: 33 additions & 33 deletions clang/lib/Headers/avx512vldqintrin.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,224 +62,224 @@ _mm_maskz_mullo_epi64(__mmask8 __U, __m128i __A, __m128i __B) {
(__v2di)_mm_setzero_si128());
}

static __inline__ __m256d __DEFAULT_FN_ATTRS256
static __inline__ __m256d __DEFAULT_FN_ATTRS256_CONSTEXPR
_mm256_mask_andnot_pd(__m256d __W, __mmask8 __U, __m256d __A, __m256d __B) {
return (__m256d)__builtin_ia32_selectpd_256((__mmask8)__U,
(__v4df)_mm256_andnot_pd(__A, __B),
(__v4df)__W);
}

static __inline__ __m256d __DEFAULT_FN_ATTRS256
static __inline__ __m256d __DEFAULT_FN_ATTRS256_CONSTEXPR
_mm256_maskz_andnot_pd(__mmask8 __U, __m256d __A, __m256d __B) {
return (__m256d)__builtin_ia32_selectpd_256((__mmask8)__U,
(__v4df)_mm256_andnot_pd(__A, __B),
(__v4df)_mm256_setzero_pd());
}

static __inline__ __m128d __DEFAULT_FN_ATTRS128
static __inline__ __m128d __DEFAULT_FN_ATTRS128_CONSTEXPR
_mm_mask_andnot_pd(__m128d __W, __mmask8 __U, __m128d __A, __m128d __B) {
return (__m128d)__builtin_ia32_selectpd_128((__mmask8)__U,
(__v2df)_mm_andnot_pd(__A, __B),
(__v2df)__W);
}

static __inline__ __m128d __DEFAULT_FN_ATTRS128
static __inline__ __m128d __DEFAULT_FN_ATTRS128_CONSTEXPR
_mm_maskz_andnot_pd(__mmask8 __U, __m128d __A, __m128d __B) {
return (__m128d)__builtin_ia32_selectpd_128((__mmask8)__U,
(__v2df)_mm_andnot_pd(__A, __B),
(__v2df)_mm_setzero_pd());
}

static __inline__ __m256 __DEFAULT_FN_ATTRS256
static __inline__ __m256 __DEFAULT_FN_ATTRS256_CONSTEXPR
_mm256_mask_andnot_ps(__m256 __W, __mmask8 __U, __m256 __A, __m256 __B) {
return (__m256)__builtin_ia32_selectps_256((__mmask8)__U,
(__v8sf)_mm256_andnot_ps(__A, __B),
(__v8sf)__W);
}

static __inline__ __m256 __DEFAULT_FN_ATTRS256
static __inline__ __m256 __DEFAULT_FN_ATTRS256_CONSTEXPR
_mm256_maskz_andnot_ps(__mmask8 __U, __m256 __A, __m256 __B) {
return (__m256)__builtin_ia32_selectps_256((__mmask8)__U,
(__v8sf)_mm256_andnot_ps(__A, __B),
(__v8sf)_mm256_setzero_ps());
}

static __inline__ __m128 __DEFAULT_FN_ATTRS128
static __inline__ __m128 __DEFAULT_FN_ATTRS128_CONSTEXPR
_mm_mask_andnot_ps(__m128 __W, __mmask8 __U, __m128 __A, __m128 __B) {
return (__m128)__builtin_ia32_selectps_128((__mmask8)__U,
(__v4sf)_mm_andnot_ps(__A, __B),
(__v4sf)__W);
}

static __inline__ __m128 __DEFAULT_FN_ATTRS128
static __inline__ __m128 __DEFAULT_FN_ATTRS128_CONSTEXPR
_mm_maskz_andnot_ps(__mmask8 __U, __m128 __A, __m128 __B) {
return (__m128)__builtin_ia32_selectps_128((__mmask8)__U,
(__v4sf)_mm_andnot_ps(__A, __B),
(__v4sf)_mm_setzero_ps());
}

static __inline__ __m256d __DEFAULT_FN_ATTRS256
static __inline__ __m256d __DEFAULT_FN_ATTRS256_CONSTEXPR
_mm256_mask_and_pd(__m256d __W, __mmask8 __U, __m256d __A, __m256d __B) {
return (__m256d)__builtin_ia32_selectpd_256((__mmask8)__U,
(__v4df)_mm256_and_pd(__A, __B),
(__v4df)__W);
}

static __inline__ __m256d __DEFAULT_FN_ATTRS256
static __inline__ __m256d __DEFAULT_FN_ATTRS256_CONSTEXPR
_mm256_maskz_and_pd(__mmask8 __U, __m256d __A, __m256d __B) {
return (__m256d)__builtin_ia32_selectpd_256((__mmask8)__U,
(__v4df)_mm256_and_pd(__A, __B),
(__v4df)_mm256_setzero_pd());
}

static __inline__ __m128d __DEFAULT_FN_ATTRS128
static __inline__ __m128d __DEFAULT_FN_ATTRS128_CONSTEXPR
_mm_mask_and_pd(__m128d __W, __mmask8 __U, __m128d __A, __m128d __B) {
return (__m128d)__builtin_ia32_selectpd_128((__mmask8)__U,
(__v2df)_mm_and_pd(__A, __B),
(__v2df)__W);
}

static __inline__ __m128d __DEFAULT_FN_ATTRS128
static __inline__ __m128d __DEFAULT_FN_ATTRS128_CONSTEXPR
_mm_maskz_and_pd(__mmask8 __U, __m128d __A, __m128d __B) {
return (__m128d)__builtin_ia32_selectpd_128((__mmask8)__U,
(__v2df)_mm_and_pd(__A, __B),
(__v2df)_mm_setzero_pd());
}

static __inline__ __m256 __DEFAULT_FN_ATTRS256
static __inline__ __m256 __DEFAULT_FN_ATTRS256_CONSTEXPR
_mm256_mask_and_ps(__m256 __W, __mmask8 __U, __m256 __A, __m256 __B) {
return (__m256)__builtin_ia32_selectps_256((__mmask8)__U,
(__v8sf)_mm256_and_ps(__A, __B),
(__v8sf)__W);
}

static __inline__ __m256 __DEFAULT_FN_ATTRS256
static __inline__ __m256 __DEFAULT_FN_ATTRS256_CONSTEXPR
_mm256_maskz_and_ps(__mmask8 __U, __m256 __A, __m256 __B) {
return (__m256)__builtin_ia32_selectps_256((__mmask8)__U,
(__v8sf)_mm256_and_ps(__A, __B),
(__v8sf)_mm256_setzero_ps());
}

static __inline__ __m128 __DEFAULT_FN_ATTRS128
static __inline__ __m128 __DEFAULT_FN_ATTRS128_CONSTEXPR
_mm_mask_and_ps(__m128 __W, __mmask8 __U, __m128 __A, __m128 __B) {
return (__m128)__builtin_ia32_selectps_128((__mmask8)__U,
(__v4sf)_mm_and_ps(__A, __B),
(__v4sf)__W);
}

static __inline__ __m128 __DEFAULT_FN_ATTRS128
static __inline__ __m128 __DEFAULT_FN_ATTRS128_CONSTEXPR
_mm_maskz_and_ps(__mmask8 __U, __m128 __A, __m128 __B) {
return (__m128)__builtin_ia32_selectps_128((__mmask8)__U,
(__v4sf)_mm_and_ps(__A, __B),
(__v4sf)_mm_setzero_ps());
}

static __inline__ __m256d __DEFAULT_FN_ATTRS256
static __inline__ __m256d __DEFAULT_FN_ATTRS256_CONSTEXPR
_mm256_mask_xor_pd(__m256d __W, __mmask8 __U, __m256d __A, __m256d __B) {
return (__m256d)__builtin_ia32_selectpd_256((__mmask8)__U,
(__v4df)_mm256_xor_pd(__A, __B),
(__v4df)__W);
}

static __inline__ __m256d __DEFAULT_FN_ATTRS256
static __inline__ __m256d __DEFAULT_FN_ATTRS256_CONSTEXPR
_mm256_maskz_xor_pd(__mmask8 __U, __m256d __A, __m256d __B) {
return (__m256d)__builtin_ia32_selectpd_256((__mmask8)__U,
(__v4df)_mm256_xor_pd(__A, __B),
(__v4df)_mm256_setzero_pd());
}

static __inline__ __m128d __DEFAULT_FN_ATTRS128
static __inline__ __m128d __DEFAULT_FN_ATTRS128_CONSTEXPR
_mm_mask_xor_pd(__m128d __W, __mmask8 __U, __m128d __A, __m128d __B) {
return (__m128d)__builtin_ia32_selectpd_128((__mmask8)__U,
(__v2df)_mm_xor_pd(__A, __B),
(__v2df)__W);
}

static __inline__ __m128d __DEFAULT_FN_ATTRS128
_mm_maskz_xor_pd (__mmask8 __U, __m128d __A, __m128d __B) {
static __inline__ __m128d __DEFAULT_FN_ATTRS128_CONSTEXPR
_mm_maskz_xor_pd(__mmask8 __U, __m128d __A, __m128d __B) {
return (__m128d)__builtin_ia32_selectpd_128((__mmask8)__U,
(__v2df)_mm_xor_pd(__A, __B),
(__v2df)_mm_setzero_pd());
}

static __inline__ __m256 __DEFAULT_FN_ATTRS256
static __inline__ __m256 __DEFAULT_FN_ATTRS256_CONSTEXPR
_mm256_mask_xor_ps(__m256 __W, __mmask8 __U, __m256 __A, __m256 __B) {
return (__m256)__builtin_ia32_selectps_256((__mmask8)__U,
(__v8sf)_mm256_xor_ps(__A, __B),
(__v8sf)__W);
}

static __inline__ __m256 __DEFAULT_FN_ATTRS256
static __inline__ __m256 __DEFAULT_FN_ATTRS256_CONSTEXPR
_mm256_maskz_xor_ps(__mmask8 __U, __m256 __A, __m256 __B) {
return (__m256)__builtin_ia32_selectps_256((__mmask8)__U,
(__v8sf)_mm256_xor_ps(__A, __B),
(__v8sf)_mm256_setzero_ps());
}

static __inline__ __m128 __DEFAULT_FN_ATTRS128
static __inline__ __m128 __DEFAULT_FN_ATTRS128_CONSTEXPR
_mm_mask_xor_ps(__m128 __W, __mmask8 __U, __m128 __A, __m128 __B) {
return (__m128)__builtin_ia32_selectps_128((__mmask8)__U,
(__v4sf)_mm_xor_ps(__A, __B),
(__v4sf)__W);
}

static __inline__ __m128 __DEFAULT_FN_ATTRS128
static __inline__ __m128 __DEFAULT_FN_ATTRS128_CONSTEXPR
_mm_maskz_xor_ps(__mmask8 __U, __m128 __A, __m128 __B) {
return (__m128)__builtin_ia32_selectps_128((__mmask8)__U,
(__v4sf)_mm_xor_ps(__A, __B),
(__v4sf)_mm_setzero_ps());
}

static __inline__ __m256d __DEFAULT_FN_ATTRS256
static __inline__ __m256d __DEFAULT_FN_ATTRS256_CONSTEXPR
_mm256_mask_or_pd(__m256d __W, __mmask8 __U, __m256d __A, __m256d __B) {
return (__m256d)__builtin_ia32_selectpd_256((__mmask8)__U,
(__v4df)_mm256_or_pd(__A, __B),
(__v4df)__W);
}

static __inline__ __m256d __DEFAULT_FN_ATTRS256
static __inline__ __m256d __DEFAULT_FN_ATTRS256_CONSTEXPR
_mm256_maskz_or_pd(__mmask8 __U, __m256d __A, __m256d __B) {
return (__m256d)__builtin_ia32_selectpd_256((__mmask8)__U,
(__v4df)_mm256_or_pd(__A, __B),
(__v4df)_mm256_setzero_pd());
}

static __inline__ __m128d __DEFAULT_FN_ATTRS128
static __inline__ __m128d __DEFAULT_FN_ATTRS128_CONSTEXPR
_mm_mask_or_pd(__m128d __W, __mmask8 __U, __m128d __A, __m128d __B) {
return (__m128d)__builtin_ia32_selectpd_128((__mmask8)__U,
(__v2df)_mm_or_pd(__A, __B),
(__v2df)__W);
}

static __inline__ __m128d __DEFAULT_FN_ATTRS128
static __inline__ __m128d __DEFAULT_FN_ATTRS128_CONSTEXPR
_mm_maskz_or_pd(__mmask8 __U, __m128d __A, __m128d __B) {
return (__m128d)__builtin_ia32_selectpd_128((__mmask8)__U,
(__v2df)_mm_or_pd(__A, __B),
(__v2df)_mm_setzero_pd());
}

static __inline__ __m256 __DEFAULT_FN_ATTRS256
static __inline__ __m256 __DEFAULT_FN_ATTRS256_CONSTEXPR
_mm256_mask_or_ps(__m256 __W, __mmask8 __U, __m256 __A, __m256 __B) {
return (__m256)__builtin_ia32_selectps_256((__mmask8)__U,
(__v8sf)_mm256_or_ps(__A, __B),
(__v8sf)__W);
}

static __inline__ __m256 __DEFAULT_FN_ATTRS256
static __inline__ __m256 __DEFAULT_FN_ATTRS256_CONSTEXPR
_mm256_maskz_or_ps(__mmask8 __U, __m256 __A, __m256 __B) {
return (__m256)__builtin_ia32_selectps_256((__mmask8)__U,
(__v8sf)_mm256_or_ps(__A, __B),
(__v8sf)_mm256_setzero_ps());
}

static __inline__ __m128 __DEFAULT_FN_ATTRS128
static __inline__ __m128 __DEFAULT_FN_ATTRS128_CONSTEXPR
_mm_mask_or_ps(__m128 __W, __mmask8 __U, __m128 __A, __m128 __B) {
return (__m128)__builtin_ia32_selectps_128((__mmask8)__U,
(__v4sf)_mm_or_ps(__A, __B),
(__v4sf)__W);
}

static __inline__ __m128 __DEFAULT_FN_ATTRS128
static __inline__ __m128 __DEFAULT_FN_ATTRS128_CONSTEXPR
_mm_maskz_or_ps(__mmask8 __U, __m128 __A, __m128 __B) {
return (__m128)__builtin_ia32_selectps_128((__mmask8)__U,
(__v4sf)_mm_or_ps(__A, __B),
Expand Down
Loading