public inbox for gcc-cvs@sourceware.org help / color / mirror / Atom feed
From: Haochen Jiang <jianghc@gcc.gnu.org> To: gcc-cvs@gcc.gnu.org Subject: [gcc r14-1234] i386: Fix incorrect intrinsic signature for AVX512 s{lli|rai|rli} Date: Thu, 25 May 2023 08:08:18 +0000 (GMT) [thread overview] Message-ID: <20230525080818.4C16E388217A@sourceware.org> (raw) https://gcc.gnu.org/g:4a84a2db2ad7cc57c1674849f845c42ed4ad12ab commit r14-1234-g4a84a2db2ad7cc57c1674849f845c42ed4ad12ab Author: Hu, Lin1 <lin1.hu@intel.com> Date: Tue May 23 10:08:29 2023 +0800 i386: Fix incorrect intrinsic signature for AVX512 s{lli|rai|rli} This patch aims to fix incorrect intrinsic signature for _mm{512|256|}_s{lli|rai|rli}_epi*. gcc/ChangeLog: PR target/109173 PR target/109174 * config/i386/avx512bwintrin.h (_mm512_srli_epi16): Change type from int to const int or const int to const unsigned int. (_mm512_mask_srli_epi16): Ditto. (_mm512_slli_epi16): Ditto. (_mm512_mask_slli_epi16): Ditto. (_mm512_maskz_slli_epi16): Ditto. (_mm512_srai_epi16): Ditto. (_mm512_mask_srai_epi16): Ditto. (_mm512_maskz_srai_epi16): Ditto. * config/i386/avx512fintrin.h (_mm512_slli_epi64): Ditto. (_mm512_mask_slli_epi64): Ditto. (_mm512_maskz_slli_epi64): Ditto. (_mm512_srli_epi64): Ditto. (_mm512_mask_srli_epi64): Ditto. (_mm512_maskz_srli_epi64): Ditto. (_mm512_srai_epi64): Ditto. (_mm512_mask_srai_epi64): Ditto. (_mm512_maskz_srai_epi64): Ditto. (_mm512_slli_epi32): Ditto. (_mm512_mask_slli_epi32): Ditto. (_mm512_maskz_slli_epi32): Ditto. (_mm512_srli_epi32): Ditto. (_mm512_mask_srli_epi32): Ditto. (_mm512_maskz_srli_epi32): Ditto. (_mm512_srai_epi32): Ditto. (_mm512_mask_srai_epi32): Ditto. (_mm512_maskz_srai_epi32): Ditto. * config/i386/avx512vlbwintrin.h (_mm256_mask_srai_epi16): Ditto. (_mm256_maskz_srai_epi16): Ditto. (_mm_mask_srai_epi16): Ditto. (_mm_maskz_srai_epi16): Ditto. (_mm256_mask_slli_epi16): Ditto. (_mm256_maskz_slli_epi16): Ditto. (_mm_mask_slli_epi16): Ditto. (_mm_maskz_slli_epi16): Ditto. (_mm_maskz_srli_epi16): Ditto. * config/i386/avx512vlintrin.h (_mm256_mask_srli_epi32): Ditto. (_mm256_maskz_srli_epi32): Ditto. (_mm_mask_srli_epi32): Ditto. (_mm_maskz_srli_epi32): Ditto. (_mm256_mask_srli_epi64): Ditto. (_mm256_maskz_srli_epi64): Ditto. (_mm_mask_srli_epi64): Ditto. (_mm_maskz_srli_epi64): Ditto. (_mm256_mask_srai_epi32): Ditto. (_mm256_maskz_srai_epi32): Ditto. (_mm_mask_srai_epi32): Ditto. (_mm_maskz_srai_epi32): Ditto. (_mm256_srai_epi64): Ditto. (_mm256_mask_srai_epi64): Ditto. (_mm256_maskz_srai_epi64): Ditto. (_mm_srai_epi64): Ditto. (_mm_mask_srai_epi64): Ditto. (_mm_maskz_srai_epi64): Ditto. (_mm_mask_slli_epi32): Ditto. (_mm_maskz_slli_epi32): Ditto. (_mm_mask_slli_epi64): Ditto. (_mm_maskz_slli_epi64): Ditto. (_mm256_mask_slli_epi32): Ditto. (_mm256_maskz_slli_epi32): Ditto. (_mm256_mask_slli_epi64): Ditto. (_mm256_maskz_slli_epi64): Ditto. gcc/testsuite/ChangeLog: PR target/109173 PR target/109174 * gcc.target/i386/pr109173-1.c: New test. * gcc.target/i386/pr109174-1.c: Ditto. Diff: --- gcc/config/i386/avx512bwintrin.h | 47 +++++----- gcc/config/i386/avx512fintrin.h | 122 +++++++++++++----------- gcc/config/i386/avx512vlbwintrin.h | 54 ++++++----- gcc/config/i386/avx512vlintrin.h | 144 +++++++++++++++-------------- gcc/testsuite/gcc.target/i386/pr109173-1.c | 57 ++++++++++++ gcc/testsuite/gcc.target/i386/pr109174-1.c | 45 +++++++++ 6 files changed, 302 insertions(+), 167 deletions(-) diff --git a/gcc/config/i386/avx512bwintrin.h b/gcc/config/i386/avx512bwintrin.h index 89790f7917b..d1cd549ce18 100644 --- a/gcc/config/i386/avx512bwintrin.h +++ b/gcc/config/i386/avx512bwintrin.h @@ -2880,7 +2880,7 @@ _mm512_maskz_dbsad_epu8 (__mmask32 __U, __m512i __A, __m512i __B, extern __inline __m512i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm512_srli_epi16 (__m512i __A, const int __imm) +_mm512_srli_epi16 (__m512i __A, const unsigned int __imm) { return (__m512i) __builtin_ia32_psrlwi512_mask ((__v32hi) __A, __imm, (__v32hi) @@ -2891,7 +2891,7 @@ _mm512_srli_epi16 (__m512i __A, const int __imm) extern __inline __m512i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) _mm512_mask_srli_epi16 (__m512i __W, __mmask32 __U, __m512i __A, - const int __imm) + const unsigned int __imm) { return (__m512i) __builtin_ia32_psrlwi512_mask ((__v32hi) __A, __imm, (__v32hi) __W, @@ -2910,7 +2910,7 @@ _mm512_maskz_srli_epi16 (__mmask32 __U, __m512i __A, const int __imm) extern __inline __m512i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm512_slli_epi16 (__m512i __A, const int __B) +_mm512_slli_epi16 (__m512i __A, const unsigned int __B) { return (__m512i) __builtin_ia32_psllwi512_mask ((__v32hi) __A, __B, (__v32hi) @@ -2921,7 +2921,7 @@ _mm512_slli_epi16 (__m512i __A, const int __B) extern __inline __m512i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) _mm512_mask_slli_epi16 (__m512i __W, __mmask32 __U, __m512i __A, - const int __B) + const unsigned int __B) { return (__m512i) __builtin_ia32_psllwi512_mask ((__v32hi) __A, __B, (__v32hi) __W, @@ -2930,7 +2930,7 @@ _mm512_mask_slli_epi16 (__m512i __W, __mmask32 __U, __m512i __A, extern __inline __m512i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm512_maskz_slli_epi16 (__mmask32 __U, __m512i __A, const int __B) +_mm512_maskz_slli_epi16 (__mmask32 __U, __m512i __A, const unsigned int __B) { return (__m512i) __builtin_ia32_psllwi512_mask ((__v32hi) __A, __B, (__v32hi) @@ -3008,7 +3008,7 @@ _mm512_maskz_shufflelo_epi16 (__mmask32 __U, __m512i __A, extern __inline __m512i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm512_srai_epi16 (__m512i __A, const int __imm) +_mm512_srai_epi16 (__m512i __A, const unsigned int __imm) { return (__m512i) __builtin_ia32_psrawi512_mask ((__v32hi) __A, __imm, (__v32hi) @@ -3019,7 +3019,7 @@ _mm512_srai_epi16 (__m512i __A, const int __imm) extern __inline __m512i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) _mm512_mask_srai_epi16 (__m512i __W, __mmask32 __U, __m512i __A, - const int __imm) + const unsigned int __imm) { return (__m512i) __builtin_ia32_psrawi512_mask ((__v32hi) __A, __imm, (__v32hi) __W, @@ -3028,7 +3028,7 @@ _mm512_mask_srai_epi16 (__m512i __W, __mmask32 __U, __m512i __A, extern __inline __m512i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm512_maskz_srai_epi16 (__mmask32 __U, __m512i __A, const int __imm) +_mm512_maskz_srai_epi16 (__mmask32 __U, __m512i __A, const unsigned int __imm) { return (__m512i) __builtin_ia32_psrawi512_mask ((__v32hi) __A, __imm, (__v32hi) @@ -3196,29 +3196,32 @@ _mm512_bsrli_epi128 (__m512i __A, const int __N) #define _mm512_srli_epi16(A, B) \ ((__m512i) __builtin_ia32_psrlwi512_mask ((__v32hi)(__m512i)(A), \ - (int)(B), (__v32hi)_mm512_setzero_si512 (), (__mmask32)-1)) + (unsigned int)(B), (__v32hi)_mm512_setzero_si512 (), (__mmask32)-1)) #define _mm512_mask_srli_epi16(W, U, A, B) \ ((__m512i) __builtin_ia32_psrlwi512_mask ((__v32hi)(__m512i)(A), \ - (int)(B), (__v32hi)(__m512i)(W), (__mmask32)(U))) + (unsigned int)(B), (__v32hi)(__m512i)(W), (__mmask32)(U))) #define _mm512_maskz_srli_epi16(U, A, B) \ ((__m512i) __builtin_ia32_psrlwi512_mask ((__v32hi)(__m512i)(A), \ (int)(B), (__v32hi)_mm512_setzero_si512 (), (__mmask32)(U))) -#define _mm512_slli_epi16(X, C) \ - ((__m512i)__builtin_ia32_psllwi512_mask ((__v32hi)(__m512i)(X), (int)(C),\ - (__v32hi)(__m512i)_mm512_setzero_si512 (), \ +#define _mm512_slli_epi16(X, C) \ + ((__m512i)__builtin_ia32_psllwi512_mask ((__v32hi)(__m512i)(X), \ + (unsigned int)(C), \ + (__v32hi)(__m512i)_mm512_setzero_si512 (), \ (__mmask32)-1)) -#define _mm512_mask_slli_epi16(W, U, X, C) \ - ((__m512i)__builtin_ia32_psllwi512_mask ((__v32hi)(__m512i)(X), (int)(C),\ - (__v32hi)(__m512i)(W),\ +#define _mm512_mask_slli_epi16(W, U, X, C) \ + ((__m512i)__builtin_ia32_psllwi512_mask ((__v32hi)(__m512i)(X), \ + (unsigned int)(C), \ + (__v32hi)(__m512i)(W), \ (__mmask32)(U))) -#define _mm512_maskz_slli_epi16(U, X, C) \ - ((__m512i)__builtin_ia32_psllwi512_mask ((__v32hi)(__m512i)(X), (int)(C),\ - (__v32hi)(__m512i)_mm512_setzero_si512 (), \ +#define _mm512_maskz_slli_epi16(U, X, C) \ + ((__m512i)__builtin_ia32_psllwi512_mask ((__v32hi)(__m512i)(X), \ + (unsigned int)(C), \ + (__v32hi)(__m512i)_mm512_setzero_si512 (), \ (__mmask32)(U))) #define _mm512_shufflehi_epi16(A, B) \ @@ -3257,15 +3260,15 @@ _mm512_bsrli_epi128 (__m512i __A, const int __N) #define _mm512_srai_epi16(A, B) \ ((__m512i) __builtin_ia32_psrawi512_mask ((__v32hi)(__m512i)(A), \ - (int)(B), (__v32hi)_mm512_setzero_si512 (), (__mmask32)-1)) + (unsigned int)(B), (__v32hi)_mm512_setzero_si512 (), (__mmask32)-1)) #define _mm512_mask_srai_epi16(W, U, A, B) \ ((__m512i) __builtin_ia32_psrawi512_mask ((__v32hi)(__m512i)(A), \ - (int)(B), (__v32hi)(__m512i)(W), (__mmask32)(U))) + (unsigned int)(B), (__v32hi)(__m512i)(W), (__mmask32)(U))) #define _mm512_maskz_srai_epi16(U, A, B) \ ((__m512i) __builtin_ia32_psrawi512_mask ((__v32hi)(__m512i)(A), \ - (int)(B), (__v32hi)_mm512_setzero_si512 (), (__mmask32)(U))) + (unsigned int)(B), (__v32hi)_mm512_setzero_si512 (), (__mmask32)(U))) #define _mm512_mask_blend_epi16(__U, __A, __W) \ ((__m512i) __builtin_ia32_blendmw_512_mask ((__v32hi) (__A), \ diff --git a/gcc/config/i386/avx512fintrin.h b/gcc/config/i386/avx512fintrin.h index 89b321970cc..517e7878d8c 100644 --- a/gcc/config/i386/avx512fintrin.h +++ b/gcc/config/i386/avx512fintrin.h @@ -1037,19 +1037,22 @@ _mm512_maskz_slli_epi64 (__mmask8 __U, __m512i __A, unsigned int __B) (__mmask8) __U); } #else -#define _mm512_slli_epi64(X, C) \ - ((__m512i) __builtin_ia32_psllqi512_mask ((__v8di)(__m512i)(X), (int)(C),\ - (__v8di)(__m512i)_mm512_undefined_epi32 (),\ +#define _mm512_slli_epi64(X, C) \ + ((__m512i) __builtin_ia32_psllqi512_mask ((__v8di)(__m512i)(X), \ + (unsigned int)(C), \ + (__v8di)(__m512i)_mm512_undefined_epi32 (), \ (__mmask8)-1)) -#define _mm512_mask_slli_epi64(W, U, X, C) \ - ((__m512i) __builtin_ia32_psllqi512_mask ((__v8di)(__m512i)(X), (int)(C),\ - (__v8di)(__m512i)(W),\ +#define _mm512_mask_slli_epi64(W, U, X, C) \ + ((__m512i) __builtin_ia32_psllqi512_mask ((__v8di)(__m512i)(X), \ + (unsigned int)(C), \ + (__v8di)(__m512i)(W), \ (__mmask8)(U))) -#define _mm512_maskz_slli_epi64(U, X, C) \ - ((__m512i) __builtin_ia32_psllqi512_mask ((__v8di)(__m512i)(X), (int)(C),\ - (__v8di)(__m512i)_mm512_setzero_si512 (),\ +#define _mm512_maskz_slli_epi64(U, X, C) \ + ((__m512i) __builtin_ia32_psllqi512_mask ((__v8di)(__m512i)(X), \ + (unsigned int)(C), \ + (__v8di)(__m512i)_mm512_setzero_si512 (), \ (__mmask8)(U))) #endif @@ -1116,19 +1119,22 @@ _mm512_maskz_srli_epi64 (__mmask8 __U, __m512i __A, unsigned int __B) (__mmask8) __U); } #else -#define _mm512_srli_epi64(X, C) \ - ((__m512i) __builtin_ia32_psrlqi512_mask ((__v8di)(__m512i)(X), (int)(C),\ - (__v8di)(__m512i)_mm512_undefined_epi32 (),\ +#define _mm512_srli_epi64(X, C) \ + ((__m512i) __builtin_ia32_psrlqi512_mask ((__v8di)(__m512i)(X), \ + (unsigned int)(C), \ + (__v8di)(__m512i)_mm512_undefined_epi32 (), \ (__mmask8)-1)) -#define _mm512_mask_srli_epi64(W, U, X, C) \ - ((__m512i) __builtin_ia32_psrlqi512_mask ((__v8di)(__m512i)(X), (int)(C),\ - (__v8di)(__m512i)(W),\ +#define _mm512_mask_srli_epi64(W, U, X, C) \ + ((__m512i) __builtin_ia32_psrlqi512_mask ((__v8di)(__m512i)(X), \ + (unsigned int)(C), \ + (__v8di)(__m512i)(W), \ (__mmask8)(U))) -#define _mm512_maskz_srli_epi64(U, X, C) \ - ((__m512i) __builtin_ia32_psrlqi512_mask ((__v8di)(__m512i)(X), (int)(C),\ - (__v8di)(__m512i)_mm512_setzero_si512 (),\ +#define _mm512_maskz_srli_epi64(U, X, C) \ + ((__m512i) __builtin_ia32_psrlqi512_mask ((__v8di)(__m512i)(X), \ + (unsigned int)(C), \ + (__v8di)(__m512i)_mm512_setzero_si512 (), \ (__mmask8)(U))) #endif @@ -1195,19 +1201,22 @@ _mm512_maskz_srai_epi64 (__mmask8 __U, __m512i __A, unsigned int __B) (__mmask8) __U); } #else -#define _mm512_srai_epi64(X, C) \ - ((__m512i) __builtin_ia32_psraqi512_mask ((__v8di)(__m512i)(X), (int)(C),\ - (__v8di)(__m512i)_mm512_undefined_epi32 (),\ +#define _mm512_srai_epi64(X, C) \ + ((__m512i) __builtin_ia32_psraqi512_mask ((__v8di)(__m512i)(X), \ + (unsigned int)(C), \ + (__v8di)(__m512i)_mm512_undefined_epi32 (), \ (__mmask8)-1)) -#define _mm512_mask_srai_epi64(W, U, X, C) \ - ((__m512i) __builtin_ia32_psraqi512_mask ((__v8di)(__m512i)(X), (int)(C),\ - (__v8di)(__m512i)(W),\ +#define _mm512_mask_srai_epi64(W, U, X, C) \ + ((__m512i) __builtin_ia32_psraqi512_mask ((__v8di)(__m512i)(X), \ + (unsigned int)(C), \ + (__v8di)(__m512i)(W), \ (__mmask8)(U))) -#define _mm512_maskz_srai_epi64(U, X, C) \ - ((__m512i) __builtin_ia32_psraqi512_mask ((__v8di)(__m512i)(X), (int)(C),\ - (__v8di)(__m512i)_mm512_setzero_si512 (),\ +#define _mm512_maskz_srai_epi64(U, X, C) \ + ((__m512i) __builtin_ia32_psraqi512_mask ((__v8di)(__m512i)(X), \ + (unsigned int)(C), \ + (__v8di)(__m512i)_mm512_setzero_si512 (), \ (__mmask8)(U))) #endif @@ -1274,19 +1283,22 @@ _mm512_maskz_slli_epi32 (__mmask16 __U, __m512i __A, unsigned int __B) (__mmask16) __U); } #else -#define _mm512_slli_epi32(X, C) \ - ((__m512i) __builtin_ia32_pslldi512_mask ((__v16si)(__m512i)(X), (int)(C),\ - (__v16si)(__m512i)_mm512_undefined_epi32 (),\ +#define _mm512_slli_epi32(X, C) \ + ((__m512i) __builtin_ia32_pslldi512_mask ((__v16si)(__m512i)(X), \ + (unsigned int)(C), \ + (__v16si)(__m512i)_mm512_undefined_epi32 (), \ (__mmask16)-1)) -#define _mm512_mask_slli_epi32(W, U, X, C) \ - ((__m512i) __builtin_ia32_pslldi512_mask ((__v16si)(__m512i)(X), (int)(C),\ - (__v16si)(__m512i)(W),\ +#define _mm512_mask_slli_epi32(W, U, X, C) \ + ((__m512i) __builtin_ia32_pslldi512_mask ((__v16si)(__m512i)(X), \ + (unsigned int)(C), \ + (__v16si)(__m512i)(W), \ (__mmask16)(U))) -#define _mm512_maskz_slli_epi32(U, X, C) \ - ((__m512i) __builtin_ia32_pslldi512_mask ((__v16si)(__m512i)(X), (int)(C),\ - (__v16si)(__m512i)_mm512_setzero_si512 (),\ +#define _mm512_maskz_slli_epi32(U, X, C) \ + ((__m512i) __builtin_ia32_pslldi512_mask ((__v16si)(__m512i)(X), \ + (unsigned int)(C), \ + (__v16si)(__m512i)_mm512_setzero_si512 (), \ (__mmask16)(U))) #endif @@ -1353,19 +1365,22 @@ _mm512_maskz_srli_epi32 (__mmask16 __U, __m512i __A, unsigned int __B) (__mmask16) __U); } #else -#define _mm512_srli_epi32(X, C) \ - ((__m512i) __builtin_ia32_psrldi512_mask ((__v16si)(__m512i)(X), (int)(C),\ +#define _mm512_srli_epi32(X, C) \ + ((__m512i) __builtin_ia32_psrldi512_mask ((__v16si)(__m512i)(X), \ + (unsigned int)(C), \ (__v16si)(__m512i)_mm512_undefined_epi32 (),\ (__mmask16)-1)) -#define _mm512_mask_srli_epi32(W, U, X, C) \ - ((__m512i) __builtin_ia32_psrldi512_mask ((__v16si)(__m512i)(X), (int)(C),\ - (__v16si)(__m512i)(W),\ +#define _mm512_mask_srli_epi32(W, U, X, C) \ + ((__m512i) __builtin_ia32_psrldi512_mask ((__v16si)(__m512i)(X), \ + (unsigned int)(C), \ + (__v16si)(__m512i)(W), \ (__mmask16)(U))) -#define _mm512_maskz_srli_epi32(U, X, C) \ - ((__m512i) __builtin_ia32_psrldi512_mask ((__v16si)(__m512i)(X), (int)(C),\ - (__v16si)(__m512i)_mm512_setzero_si512 (),\ +#define _mm512_maskz_srli_epi32(U, X, C) \ + ((__m512i) __builtin_ia32_psrldi512_mask ((__v16si)(__m512i)(X), \ + (unsigned int)(C), \ + (__v16si)(__m512i)_mm512_setzero_si512 (), \ (__mmask16)(U))) #endif @@ -1432,19 +1447,22 @@ _mm512_maskz_srai_epi32 (__mmask16 __U, __m512i __A, unsigned int __B) (__mmask16) __U); } #else -#define _mm512_srai_epi32(X, C) \ - ((__m512i) __builtin_ia32_psradi512_mask ((__v16si)(__m512i)(X), (int)(C),\ +#define _mm512_srai_epi32(X, C) \ + ((__m512i) __builtin_ia32_psradi512_mask ((__v16si)(__m512i)(X), \ + (unsigned int)(C), \ (__v16si)(__m512i)_mm512_undefined_epi32 (),\ (__mmask16)-1)) -#define _mm512_mask_srai_epi32(W, U, X, C) \ - ((__m512i) __builtin_ia32_psradi512_mask ((__v16si)(__m512i)(X), (int)(C),\ - (__v16si)(__m512i)(W),\ +#define _mm512_mask_srai_epi32(W, U, X, C) \ + ((__m512i) __builtin_ia32_psradi512_mask ((__v16si)(__m512i)(X), \ + (unsigned int)(C), \ + (__v16si)(__m512i)(W), \ (__mmask16)(U))) -#define _mm512_maskz_srai_epi32(U, X, C) \ - ((__m512i) __builtin_ia32_psradi512_mask ((__v16si)(__m512i)(X), (int)(C),\ - (__v16si)(__m512i)_mm512_setzero_si512 (),\ +#define _mm512_maskz_srai_epi32(U, X, C) \ + ((__m512i) __builtin_ia32_psradi512_mask ((__v16si)(__m512i)(X), \ + (unsigned int)(C), \ + (__v16si)(__m512i)_mm512_setzero_si512 (), \ (__mmask16)(U))) #endif diff --git a/gcc/config/i386/avx512vlbwintrin.h b/gcc/config/i386/avx512vlbwintrin.h index 3654cf214c4..bc58fa4c5c1 100644 --- a/gcc/config/i386/avx512vlbwintrin.h +++ b/gcc/config/i386/avx512vlbwintrin.h @@ -1759,7 +1759,7 @@ _mm_maskz_shufflelo_epi16 (__mmask8 __U, __m128i __A, const int __imm) extern __inline __m256i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) _mm256_mask_srai_epi16 (__m256i __W, __mmask16 __U, __m256i __A, - const int __imm) + const unsigned int __imm) { return (__m256i) __builtin_ia32_psrawi256_mask ((__v16hi) __A, __imm, (__v16hi) __W, @@ -1768,7 +1768,7 @@ _mm256_mask_srai_epi16 (__m256i __W, __mmask16 __U, __m256i __A, extern __inline __m256i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm256_maskz_srai_epi16 (__mmask16 __U, __m256i __A, const int __imm) +_mm256_maskz_srai_epi16 (__mmask16 __U, __m256i __A, const unsigned int __imm) { return (__m256i) __builtin_ia32_psrawi256_mask ((__v16hi) __A, __imm, (__v16hi) @@ -1779,7 +1779,7 @@ _mm256_maskz_srai_epi16 (__mmask16 __U, __m256i __A, const int __imm) extern __inline __m128i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) _mm_mask_srai_epi16 (__m128i __W, __mmask8 __U, __m128i __A, - const int __imm) + const unsigned int __imm) { return (__m128i) __builtin_ia32_psrawi128_mask ((__v8hi) __A, __imm, (__v8hi) __W, @@ -1788,7 +1788,7 @@ _mm_mask_srai_epi16 (__m128i __W, __mmask8 __U, __m128i __A, extern __inline __m128i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm_maskz_srai_epi16 (__mmask8 __U, __m128i __A, const int __imm) +_mm_maskz_srai_epi16 (__mmask8 __U, __m128i __A, const unsigned int __imm) { return (__m128i) __builtin_ia32_psrawi128_mask ((__v8hi) __A, __imm, (__v8hi) @@ -1799,7 +1799,7 @@ _mm_maskz_srai_epi16 (__mmask8 __U, __m128i __A, const int __imm) extern __inline __m256i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) _mm256_mask_slli_epi16 (__m256i __W, __mmask16 __U, __m256i __A, - int __B) + unsigned int __B) { return (__m256i) __builtin_ia32_psllwi256_mask ((__v16hi) __A, __B, (__v16hi) __W, @@ -1808,7 +1808,7 @@ _mm256_mask_slli_epi16 (__m256i __W, __mmask16 __U, __m256i __A, extern __inline __m256i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm256_maskz_slli_epi16 (__mmask16 __U, __m256i __A, int __B) +_mm256_maskz_slli_epi16 (__mmask16 __U, __m256i __A, unsigned int __B) { return (__m256i) __builtin_ia32_psllwi256_mask ((__v16hi) __A, __B, (__v16hi) @@ -1818,7 +1818,7 @@ _mm256_maskz_slli_epi16 (__mmask16 __U, __m256i __A, int __B) extern __inline __m128i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm_mask_slli_epi16 (__m128i __W, __mmask8 __U, __m128i __A, int __B) +_mm_mask_slli_epi16 (__m128i __W, __mmask8 __U, __m128i __A, unsigned int __B) { return (__m128i) __builtin_ia32_psllwi128_mask ((__v8hi) __A, __B, (__v8hi) __W, @@ -1827,7 +1827,7 @@ _mm_mask_slli_epi16 (__m128i __W, __mmask8 __U, __m128i __A, int __B) extern __inline __m128i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm_maskz_slli_epi16 (__mmask8 __U, __m128i __A, int __B) +_mm_maskz_slli_epi16 (__mmask8 __U, __m128i __A, unsigned int __B) { return (__m128i) __builtin_ia32_psllwi128_mask ((__v8hi) __A, __B, (__v8hi) @@ -1855,23 +1855,23 @@ _mm_maskz_slli_epi16 (__mmask8 __U, __m128i __A, int __B) #define _mm_maskz_srli_epi16(U, A, B) \ ((__m128i) __builtin_ia32_psrlwi128_mask ((__v8hi)(__m128i)(A), \ - (int)(B), (__v8hi)_mm_setzero_si128(), (__mmask8)(U))) + (int)(B), (__v8hi)_mm_setzero_si128 (), (__mmask8)(U))) #define _mm256_mask_srai_epi16(W, U, A, B) \ ((__m256i) __builtin_ia32_psrawi256_mask ((__v16hi)(__m256i)(A), \ - (int)(B), (__v16hi)(__m256i)(W), (__mmask16)(U))) + (unsigned int)(B), (__v16hi)(__m256i)(W), (__mmask16)(U))) #define _mm256_maskz_srai_epi16(U, A, B) \ ((__m256i) __builtin_ia32_psrawi256_mask ((__v16hi)(__m256i)(A), \ - (int)(B), (__v16hi)_mm256_setzero_si256 (), (__mmask16)(U))) + (unsigned int)(B), (__v16hi)_mm256_setzero_si256 (), (__mmask16)(U))) #define _mm_mask_srai_epi16(W, U, A, B) \ ((__m128i) __builtin_ia32_psrawi128_mask ((__v8hi)(__m128i)(A), \ - (int)(B), (__v8hi)(__m128i)(W), (__mmask8)(U))) + (unsigned int)(B), (__v8hi)(__m128i)(W), (__mmask8)(U))) #define _mm_maskz_srai_epi16(U, A, B) \ ((__m128i) __builtin_ia32_psrawi128_mask ((__v8hi)(__m128i)(A), \ - (int)(B), (__v8hi)_mm_setzero_si128(), (__mmask8)(U))) + (unsigned int)(B), (__v8hi)_mm_setzero_si128(), (__mmask8)(U))) #define _mm256_mask_shufflehi_epi16(W, U, A, B) \ ((__m256i) __builtin_ia32_pshufhw256_mask ((__v16hi)(__m256i)(A), (int)(B), \ @@ -1930,14 +1930,16 @@ _mm_maskz_slli_epi16 (__mmask8 __U, __m128i __A, int __B) (__v2di)(__m128i)_mm_setzero_si128 (), \ (__mmask16)(U))) -#define _mm_mask_slli_epi16(W, U, X, C) \ - ((__m128i)__builtin_ia32_psllwi128_mask ((__v8hi)(__m128i)(X), (int)(C),\ - (__v8hi)(__m128i)(W),\ +#define _mm_mask_slli_epi16(W, U, X, C) \ + ((__m128i)__builtin_ia32_psllwi128_mask ((__v8hi)(__m128i)(X), \ + (unsigned int)(C), \ + (__v8hi)(__m128i)(W), \ (__mmask8)(U))) -#define _mm_maskz_slli_epi16(U, X, C) \ - ((__m128i)__builtin_ia32_psllwi128_mask ((__v8hi)(__m128i)(X), (int)(C),\ - (__v8hi)(__m128i)_mm_setzero_si128 (),\ +#define _mm_maskz_slli_epi16(U, X, C) \ + ((__m128i)__builtin_ia32_psllwi128_mask ((__v8hi)(__m128i)(X), \ + (unsigned int)(C), \ + (__v8hi)(__m128i)_mm_setzero_si128 (), \ (__mmask8)(U))) #define _mm256_dbsad_epu8(X, Y, C) \ @@ -1946,14 +1948,16 @@ _mm_maskz_slli_epi16 (__mmask8 __U, __m128i __A, int __B) (__v16hi)(__m256i)_mm256_setzero_si256(),\ (__mmask16)-1)) -#define _mm256_mask_slli_epi16(W, U, X, C) \ - ((__m256i)__builtin_ia32_psllwi256_mask ((__v16hi)(__m256i)(X), (int)(C),\ - (__v16hi)(__m256i)(W),\ +#define _mm256_mask_slli_epi16(W, U, X, C) \ + ((__m256i)__builtin_ia32_psllwi256_mask ((__v16hi)(__m256i)(X), \ + (unsigned int)(C), \ + (__v16hi)(__m256i)(W), \ (__mmask16)(U))) -#define _mm256_maskz_slli_epi16(U, X, C) \ - ((__m256i)__builtin_ia32_psllwi256_mask ((__v16hi)(__m256i)(X), (int)(C),\ - (__v16hi)(__m256i)_mm256_setzero_si256 (),\ +#define _mm256_maskz_slli_epi16(U, X, C) \ + ((__m256i)__builtin_ia32_psllwi256_mask ((__v16hi)(__m256i)(X), \ + (unsigned int)(C), \ + (__v16hi)(__m256i)_mm256_setzero_si256 (), \ (__mmask16)(U))) #define _mm256_mask_dbsad_epu8(W, U, X, Y, C) \ diff --git a/gcc/config/i386/avx512vlintrin.h b/gcc/config/i386/avx512vlintrin.h index 4a717a7e52f..08e49e8d8ab 100644 --- a/gcc/config/i386/avx512vlintrin.h +++ b/gcc/config/i386/avx512vlintrin.h @@ -10565,7 +10565,7 @@ _mm_maskz_fixupimm_ps (__mmask8 __U, __m128 __A, __m128 __B, extern __inline __m256i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) _mm256_mask_srli_epi32 (__m256i __W, __mmask8 __U, __m256i __A, - const int __imm) + const unsigned int __imm) { return (__m256i) __builtin_ia32_psrldi256_mask ((__v8si) __A, __imm, (__v8si) __W, @@ -10574,7 +10574,7 @@ _mm256_mask_srli_epi32 (__m256i __W, __mmask8 __U, __m256i __A, extern __inline __m256i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm256_maskz_srli_epi32 (__mmask8 __U, __m256i __A, const int __imm) +_mm256_maskz_srli_epi32 (__mmask8 __U, __m256i __A, const unsigned int __imm) { return (__m256i) __builtin_ia32_psrldi256_mask ((__v8si) __A, __imm, (__v8si) @@ -10585,7 +10585,7 @@ _mm256_maskz_srli_epi32 (__mmask8 __U, __m256i __A, const int __imm) extern __inline __m128i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) _mm_mask_srli_epi32 (__m128i __W, __mmask8 __U, __m128i __A, - const int __imm) + const unsigned int __imm) { return (__m128i) __builtin_ia32_psrldi128_mask ((__v4si) __A, __imm, (__v4si) __W, @@ -10594,7 +10594,7 @@ _mm_mask_srli_epi32 (__m128i __W, __mmask8 __U, __m128i __A, extern __inline __m128i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm_maskz_srli_epi32 (__mmask8 __U, __m128i __A, const int __imm) +_mm_maskz_srli_epi32 (__mmask8 __U, __m128i __A, const unsigned int __imm) { return (__m128i) __builtin_ia32_psrldi128_mask ((__v4si) __A, __imm, (__v4si) @@ -10605,7 +10605,7 @@ _mm_maskz_srli_epi32 (__mmask8 __U, __m128i __A, const int __imm) extern __inline __m256i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) _mm256_mask_srli_epi64 (__m256i __W, __mmask8 __U, __m256i __A, - const int __imm) + const unsigned int __imm) { return (__m256i) __builtin_ia32_psrlqi256_mask ((__v4di) __A, __imm, (__v4di) __W, @@ -10614,7 +10614,7 @@ _mm256_mask_srli_epi64 (__m256i __W, __mmask8 __U, __m256i __A, extern __inline __m256i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm256_maskz_srli_epi64 (__mmask8 __U, __m256i __A, const int __imm) +_mm256_maskz_srli_epi64 (__mmask8 __U, __m256i __A, const unsigned int __imm) { return (__m256i) __builtin_ia32_psrlqi256_mask ((__v4di) __A, __imm, (__v4di) @@ -10625,7 +10625,7 @@ _mm256_maskz_srli_epi64 (__mmask8 __U, __m256i __A, const int __imm) extern __inline __m128i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) _mm_mask_srli_epi64 (__m128i __W, __mmask8 __U, __m128i __A, - const int __imm) + const unsigned int __imm) { return (__m128i) __builtin_ia32_psrlqi128_mask ((__v2di) __A, __imm, (__v2di) __W, @@ -10634,7 +10634,7 @@ _mm_mask_srli_epi64 (__m128i __W, __mmask8 __U, __m128i __A, extern __inline __m128i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm_maskz_srli_epi64 (__mmask8 __U, __m128i __A, const int __imm) +_mm_maskz_srli_epi64 (__mmask8 __U, __m128i __A, const unsigned int __imm) { return (__m128i) __builtin_ia32_psrlqi128_mask ((__v2di) __A, __imm, (__v2di) @@ -12059,7 +12059,7 @@ _mm256_maskz_cvtps_ph (__mmask8 __U, __m256 __A, const int __I) extern __inline __m256i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) _mm256_mask_srai_epi32 (__m256i __W, __mmask8 __U, __m256i __A, - const int __imm) + const unsigned int __imm) { return (__m256i) __builtin_ia32_psradi256_mask ((__v8si) __A, __imm, (__v8si) __W, @@ -12068,7 +12068,7 @@ _mm256_mask_srai_epi32 (__m256i __W, __mmask8 __U, __m256i __A, extern __inline __m256i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm256_maskz_srai_epi32 (__mmask8 __U, __m256i __A, const int __imm) +_mm256_maskz_srai_epi32 (__mmask8 __U, __m256i __A, const unsigned int __imm) { return (__m256i) __builtin_ia32_psradi256_mask ((__v8si) __A, __imm, (__v8si) @@ -12079,7 +12079,7 @@ _mm256_maskz_srai_epi32 (__mmask8 __U, __m256i __A, const int __imm) extern __inline __m128i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) _mm_mask_srai_epi32 (__m128i __W, __mmask8 __U, __m128i __A, - const int __imm) + const unsigned int __imm) { return (__m128i) __builtin_ia32_psradi128_mask ((__v4si) __A, __imm, (__v4si) __W, @@ -12088,7 +12088,7 @@ _mm_mask_srai_epi32 (__m128i __W, __mmask8 __U, __m128i __A, extern __inline __m128i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm_maskz_srai_epi32 (__mmask8 __U, __m128i __A, const int __imm) +_mm_maskz_srai_epi32 (__mmask8 __U, __m128i __A, const unsigned int __imm) { return (__m128i) __builtin_ia32_psradi128_mask ((__v4si) __A, __imm, (__v4si) @@ -12098,7 +12098,7 @@ _mm_maskz_srai_epi32 (__mmask8 __U, __m128i __A, const int __imm) extern __inline __m256i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm256_srai_epi64 (__m256i __A, const int __imm) +_mm256_srai_epi64 (__m256i __A, const unsigned int __imm) { return (__m256i) __builtin_ia32_psraqi256_mask ((__v4di) __A, __imm, (__v4di) @@ -12109,7 +12109,7 @@ _mm256_srai_epi64 (__m256i __A, const int __imm) extern __inline __m256i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) _mm256_mask_srai_epi64 (__m256i __W, __mmask8 __U, __m256i __A, - const int __imm) + const unsigned int __imm) { return (__m256i) __builtin_ia32_psraqi256_mask ((__v4di) __A, __imm, (__v4di) __W, @@ -12118,7 +12118,7 @@ _mm256_mask_srai_epi64 (__m256i __W, __mmask8 __U, __m256i __A, extern __inline __m256i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm256_maskz_srai_epi64 (__mmask8 __U, __m256i __A, const int __imm) +_mm256_maskz_srai_epi64 (__mmask8 __U, __m256i __A, const unsigned int __imm) { return (__m256i) __builtin_ia32_psraqi256_mask ((__v4di) __A, __imm, (__v4di) @@ -12128,7 +12128,7 @@ _mm256_maskz_srai_epi64 (__mmask8 __U, __m256i __A, const int __imm) extern __inline __m128i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm_srai_epi64 (__m128i __A, const int __imm) +_mm_srai_epi64 (__m128i __A, const unsigned int __imm) { return (__m128i) __builtin_ia32_psraqi128_mask ((__v2di) __A, __imm, (__v2di) @@ -12139,7 +12139,7 @@ _mm_srai_epi64 (__m128i __A, const int __imm) extern __inline __m128i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) _mm_mask_srai_epi64 (__m128i __W, __mmask8 __U, __m128i __A, - const int __imm) + const unsigned int __imm) { return (__m128i) __builtin_ia32_psraqi128_mask ((__v2di) __A, __imm, (__v2di) __W, @@ -12148,7 +12148,7 @@ _mm_mask_srai_epi64 (__m128i __W, __mmask8 __U, __m128i __A, extern __inline __m128i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm_maskz_srai_epi64 (__mmask8 __U, __m128i __A, const int __imm) +_mm_maskz_srai_epi64 (__mmask8 __U, __m128i __A, const unsigned int __imm) { return (__m128i) __builtin_ia32_psraqi128_mask ((__v2di) __A, __imm, (__v2di) @@ -12158,7 +12158,7 @@ _mm_maskz_srai_epi64 (__mmask8 __U, __m128i __A, const int __imm) extern __inline __m128i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm_mask_slli_epi32 (__m128i __W, __mmask8 __U, __m128i __A, int __B) +_mm_mask_slli_epi32 (__m128i __W, __mmask8 __U, __m128i __A, unsigned int __B) { return (__m128i) __builtin_ia32_pslldi128_mask ((__v4si) __A, __B, (__v4si) __W, @@ -12167,7 +12167,7 @@ _mm_mask_slli_epi32 (__m128i __W, __mmask8 __U, __m128i __A, int __B) extern __inline __m128i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm_maskz_slli_epi32 (__mmask8 __U, __m128i __A, int __B) +_mm_maskz_slli_epi32 (__mmask8 __U, __m128i __A, unsigned int __B) { return (__m128i) __builtin_ia32_pslldi128_mask ((__v4si) __A, __B, (__v4si) @@ -12177,7 +12177,7 @@ _mm_maskz_slli_epi32 (__mmask8 __U, __m128i __A, int __B) extern __inline __m128i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm_mask_slli_epi64 (__m128i __W, __mmask8 __U, __m128i __A, int __B) +_mm_mask_slli_epi64 (__m128i __W, __mmask8 __U, __m128i __A, unsigned int __B) { return (__m128i) __builtin_ia32_psllqi128_mask ((__v2di) __A, __B, (__v2di) __W, @@ -12186,7 +12186,7 @@ _mm_mask_slli_epi64 (__m128i __W, __mmask8 __U, __m128i __A, int __B) extern __inline __m128i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm_maskz_slli_epi64 (__mmask8 __U, __m128i __A, int __B) +_mm_maskz_slli_epi64 (__mmask8 __U, __m128i __A, unsigned int __B) { return (__m128i) __builtin_ia32_psllqi128_mask ((__v2di) __A, __B, (__v2di) @@ -12197,7 +12197,7 @@ _mm_maskz_slli_epi64 (__mmask8 __U, __m128i __A, int __B) extern __inline __m256i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) _mm256_mask_slli_epi32 (__m256i __W, __mmask8 __U, __m256i __A, - int __B) + unsigned int __B) { return (__m256i) __builtin_ia32_pslldi256_mask ((__v8si) __A, __B, (__v8si) __W, @@ -12206,7 +12206,7 @@ _mm256_mask_slli_epi32 (__m256i __W, __mmask8 __U, __m256i __A, extern __inline __m256i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm256_maskz_slli_epi32 (__mmask8 __U, __m256i __A, int __B) +_mm256_maskz_slli_epi32 (__mmask8 __U, __m256i __A, unsigned int __B) { return (__m256i) __builtin_ia32_pslldi256_mask ((__v8si) __A, __B, (__v8si) @@ -12217,7 +12217,7 @@ _mm256_maskz_slli_epi32 (__mmask8 __U, __m256i __A, int __B) extern __inline __m256i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) _mm256_mask_slli_epi64 (__m256i __W, __mmask8 __U, __m256i __A, - int __B) + unsigned int __B) { return (__m256i) __builtin_ia32_psllqi256_mask ((__v4di) __A, __B, (__v4di) __W, @@ -12226,7 +12226,7 @@ _mm256_mask_slli_epi64 (__m256i __W, __mmask8 __U, __m256i __A, extern __inline __m256i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm256_maskz_slli_epi64 (__mmask8 __U, __m256i __A, int __B) +_mm256_maskz_slli_epi64 (__mmask8 __U, __m256i __A, unsigned int __B) { return (__m256i) __builtin_ia32_psllqi256_mask ((__v4di) __A, __B, (__v4di) @@ -12864,74 +12864,82 @@ _mm256_permutex_pd (__m256d __X, const int __M) #define _mm256_mask_srli_epi32(W, U, A, B) \ ((__m256i) __builtin_ia32_psrldi256_mask ((__v8si)(__m256i)(A), \ - (int)(B), (__v8si)(__m256i)(W), (__mmask8)(U))) + (unsigned int)(B), (__v8si)(__m256i)(W), (__mmask8)(U))) #define _mm256_maskz_srli_epi32(U, A, B) \ ((__m256i) __builtin_ia32_psrldi256_mask ((__v8si)(__m256i)(A), \ - (int)(B), (__v8si)_mm256_setzero_si256 (), (__mmask8)(U))) + (unsigned int)(B), (__v8si)_mm256_setzero_si256 (), (__mmask8)(U))) #define _mm_mask_srli_epi32(W, U, A, B) \ ((__m128i) __builtin_ia32_psrldi128_mask ((__v4si)(__m128i)(A), \ - (int)(B), (__v4si)(__m128i)(W), (__mmask8)(U))) + (unsigned int)(B), (__v4si)(__m128i)(W), (__mmask8)(U))) #define _mm_maskz_srli_epi32(U, A, B) \ ((__m128i) __builtin_ia32_psrldi128_mask ((__v4si)(__m128i)(A), \ - (int)(B), (__v4si)_mm_setzero_si128 (), (__mmask8)(U))) + (unsigned int)(B), (__v4si)_mm_setzero_si128 (), (__mmask8)(U))) #define _mm256_mask_srli_epi64(W, U, A, B) \ ((__m256i) __builtin_ia32_psrlqi256_mask ((__v4di)(__m256i)(A), \ - (int)(B), (__v4di)(__m256i)(W), (__mmask8)(U))) + (unsigned int)(B), (__v4di)(__m256i)(W), (__mmask8)(U))) #define _mm256_maskz_srli_epi64(U, A, B) \ ((__m256i) __builtin_ia32_psrlqi256_mask ((__v4di)(__m256i)(A), \ - (int)(B), (__v4di)_mm256_setzero_si256 (), (__mmask8)(U))) + (unsigned int)(B), (__v4di)_mm256_setzero_si256 (), (__mmask8)(U))) #define _mm_mask_srli_epi64(W, U, A, B) \ ((__m128i) __builtin_ia32_psrlqi128_mask ((__v2di)(__m128i)(A), \ - (int)(B), (__v2di)(__m128i)(W), (__mmask8)(U))) + (unsigned int)(B), (__v2di)(__m128i)(W), (__mmask8)(U))) #define _mm_maskz_srli_epi64(U, A, B) \ ((__m128i) __builtin_ia32_psrlqi128_mask ((__v2di)(__m128i)(A), \ - (int)(B), (__v2di)_mm_setzero_si128 (), (__mmask8)(U))) + (unsigned int)(B), (__v2di)_mm_setzero_si128 (), (__mmask8)(U))) -#define _mm256_mask_slli_epi32(W, U, X, C) \ - ((__m256i)__builtin_ia32_pslldi256_mask ((__v8si)(__m256i)(X), (int)(C),\ - (__v8si)(__m256i)(W), \ +#define _mm256_mask_slli_epi32(W, U, X, C) \ + ((__m256i)__builtin_ia32_pslldi256_mask ((__v8si)(__m256i)(X), \ + (unsigned int)(C), \ + (__v8si)(__m256i)(W), \ (__mmask8)(U))) -#define _mm256_maskz_slli_epi32(U, X, C) \ - ((__m256i)__builtin_ia32_pslldi256_mask ((__v8si)(__m256i)(X), (int)(C),\ - (__v8si)(__m256i)_mm256_setzero_si256 (), \ +#define _mm256_maskz_slli_epi32(U, X, C) \ + ((__m256i)__builtin_ia32_pslldi256_mask ((__v8si)(__m256i)(X), \ + (unsigned int)(C), \ + (__v8si)(__m256i)_mm256_setzero_si256 (), \ (__mmask8)(U))) -#define _mm256_mask_slli_epi64(W, U, X, C) \ - ((__m256i)__builtin_ia32_psllqi256_mask ((__v4di)(__m256i)(X), (int)(C),\ - (__v4di)(__m256i)(W), \ +#define _mm256_mask_slli_epi64(W, U, X, C) \ + ((__m256i)__builtin_ia32_psllqi256_mask ((__v4di)(__m256i)(X), \ + (unsigned int)(C), \ + (__v4di)(__m256i)(W), \ (__mmask8)(U))) -#define _mm256_maskz_slli_epi64(U, X, C) \ - ((__m256i)__builtin_ia32_psllqi256_mask ((__v4di)(__m256i)(X), (int)(C),\ - (__v4di)(__m256i)_mm256_setzero_si256 (), \ +#define _mm256_maskz_slli_epi64(U, X, C) \ + ((__m256i)__builtin_ia32_psllqi256_mask ((__v4di)(__m256i)(X), \ + (unsigned int)(C), \ + (__v4di)(__m256i)_mm256_setzero_si256 (), \ (__mmask8)(U))) -#define _mm_mask_slli_epi32(W, U, X, C) \ - ((__m128i)__builtin_ia32_pslldi128_mask ((__v4si)(__m128i)(X), (int)(C),\ - (__v4si)(__m128i)(W),\ +#define _mm_mask_slli_epi32(W, U, X, C) \ + ((__m128i)__builtin_ia32_pslldi128_mask ((__v4si)(__m128i)(X), \ + (unsigned int)(C), \ + (__v4si)(__m128i)(W), \ (__mmask8)(U))) -#define _mm_maskz_slli_epi32(U, X, C) \ - ((__m128i)__builtin_ia32_pslldi128_mask ((__v4si)(__m128i)(X), (int)(C),\ - (__v4si)(__m128i)_mm_setzero_si128 (),\ +#define _mm_maskz_slli_epi32(U, X, C) \ + ((__m128i)__builtin_ia32_pslldi128_mask ((__v4si)(__m128i)(X), \ + (unsigned int)(C), \ + (__v4si)(__m128i)_mm_setzero_si128 (), \ (__mmask8)(U))) -#define _mm_mask_slli_epi64(W, U, X, C) \ - ((__m128i)__builtin_ia32_psllqi128_mask ((__v2di)(__m128i)(X), (int)(C),\ - (__v2di)(__m128i)(W),\ +#define _mm_mask_slli_epi64(W, U, X, C) \ + ((__m128i)__builtin_ia32_psllqi128_mask ((__v2di)(__m128i)(X), \ + (unsigned int)(C), \ + (__v2di)(__m128i)(W), \ (__mmask8)(U))) -#define _mm_maskz_slli_epi64(U, X, C) \ - ((__m128i)__builtin_ia32_psllqi128_mask ((__v2di)(__m128i)(X), (int)(C),\ - (__v2di)(__m128i)_mm_setzero_si128 (),\ +#define _mm_maskz_slli_epi64(U, X, C) \ + ((__m128i)__builtin_ia32_psllqi128_mask ((__v2di)(__m128i)(X), \ + (unsigned int)(C), \ + (__v2di)(__m128i)_mm_setzero_si128 (), \ (__mmask8)(U))) #define _mm256_ternarylogic_epi64(A, B, C, I) \ @@ -13634,43 +13642,43 @@ _mm256_permutex_pd (__m256d __X, const int __M) #define _mm256_mask_srai_epi32(W, U, A, B) \ ((__m256i) __builtin_ia32_psradi256_mask ((__v8si)(__m256i)(A), \ - (int)(B), (__v8si)(__m256i)(W), (__mmask8)(U))) + (unsigned int)(B), (__v8si)(__m256i)(W), (__mmask8)(U))) #define _mm256_maskz_srai_epi32(U, A, B) \ ((__m256i) __builtin_ia32_psradi256_mask ((__v8si)(__m256i)(A), \ - (int)(B), (__v8si)_mm256_setzero_si256 (), (__mmask8)(U))) + (unsigned int)(B), (__v8si)_mm256_setzero_si256 (), (__mmask8)(U))) #define _mm_mask_srai_epi32(W, U, A, B) \ ((__m128i) __builtin_ia32_psradi128_mask ((__v4si)(__m128i)(A), \ - (int)(B), (__v4si)(__m128i)(W), (__mmask8)(U))) + (unsigned int)(B), (__v4si)(__m128i)(W), (__mmask8)(U))) #define _mm_maskz_srai_epi32(U, A, B) \ ((__m128i) __builtin_ia32_psradi128_mask ((__v4si)(__m128i)(A), \ - (int)(B), (__v4si)_mm_setzero_si128 (), (__mmask8)(U))) + (unsigned int)(B), (__v4si)_mm_setzero_si128 (), (__mmask8)(U))) #define _mm256_srai_epi64(A, B) \ ((__m256i) __builtin_ia32_psraqi256_mask ((__v4di)(__m256i)(A), \ - (int)(B), (__v4di)_mm256_setzero_si256 (), (__mmask8)-1)) + (unsigned int)(B), (__v4di)_mm256_setzero_si256 (), (__mmask8)-1)) #define _mm256_mask_srai_epi64(W, U, A, B) \ ((__m256i) __builtin_ia32_psraqi256_mask ((__v4di)(__m256i)(A), \ - (int)(B), (__v4di)(__m256i)(W), (__mmask8)(U))) + (unsigned int)(B), (__v4di)(__m256i)(W), (__mmask8)(U))) #define _mm256_maskz_srai_epi64(U, A, B) \ ((__m256i) __builtin_ia32_psraqi256_mask ((__v4di)(__m256i)(A), \ - (int)(B), (__v4di)_mm256_setzero_si256 (), (__mmask8)(U))) + (unsigned int)(B), (__v4di)_mm256_setzero_si256 (), (__mmask8)(U))) #define _mm_srai_epi64(A, B) \ ((__m128i) __builtin_ia32_psraqi128_mask ((__v2di)(__m128i)(A), \ - (int)(B), (__v2di)_mm_setzero_si128 (), (__mmask8)-1)) + (unsigned int)(B), (__v2di)_mm_setzero_si128 (), (__mmask8)-1)) #define _mm_mask_srai_epi64(W, U, A, B) \ ((__m128i) __builtin_ia32_psraqi128_mask ((__v2di)(__m128i)(A), \ - (int)(B), (__v2di)(__m128i)(W), (__mmask8)(U))) + (unsigned int)(B), (__v2di)(__m128i)(W), (__mmask8)(U))) #define _mm_maskz_srai_epi64(U, A, B) \ ((__m128i) __builtin_ia32_psraqi128_mask ((__v2di)(__m128i)(A), \ - (int)(B), (__v2di)_mm_setzero_si128 (), (__mmask8)(U))) + (unsigned int)(B), (__v2di)_mm_setzero_si128 (), (__mmask8)(U))) #define _mm256_mask_permutex_pd(W, U, A, B) \ ((__m256d) __builtin_ia32_permdf256_mask ((__v4df)(__m256d)(A), \ diff --git a/gcc/testsuite/gcc.target/i386/pr109173-1.c b/gcc/testsuite/gcc.target/i386/pr109173-1.c new file mode 100644 index 00000000000..286939e56be --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/pr109173-1.c @@ -0,0 +1,57 @@ +/* PR target/109173 */ +/* { dg-do compile } */ +/* { dg-options "-c -Wsign-conversion -Werror -mavx512bw -mavx512vl -O2" } */ + +#include <immintrin.h> + +extern unsigned int bar(); + +void foo() +{ + __m128i a1, w1; + __m256i a2, w2; + __mmask8 u; + + _mm256_mask_srli_epi32(w2, u, a2, bar()); + _mm256_maskz_srli_epi32(u, a2, bar()); + _mm_mask_srli_epi32(w1, u, a1, bar()); + _mm_maskz_srli_epi32(u, a1, bar()); + + _mm256_mask_srli_epi64(w2, u, a2, bar()); + _mm256_maskz_srli_epi64(u, a2, bar()); + _mm_mask_srli_epi64(w1, u, a1, bar()); + _mm_maskz_srli_epi64(u, a1, bar()); + + _mm256_mask_srai_epi32(w2, u, a2, bar()); + _mm256_maskz_srai_epi32(u, a2, bar()); + _mm_mask_srai_epi32(w1, u, a1, bar()); + _mm_maskz_srai_epi32(u, a1, bar()); + + _mm256_srai_epi64(a2, bar()); + _mm256_mask_srai_epi64(w2, u, a2, bar()); + _mm256_maskz_srai_epi64(u, a2, bar()); + _mm_srai_epi64(a1, bar()); + _mm_mask_srai_epi64(w1, u, a1, bar()); + _mm_maskz_srai_epi64(u, a1, bar()); + + _mm256_mask_slli_epi32(w2, u, a2, bar()); + _mm256_maskz_slli_epi32(u, a2, bar()); + _mm_mask_slli_epi32(w1, u, a1, bar()); + _mm_maskz_slli_epi32(u, a1, bar()); + + _mm256_mask_slli_epi64(w2, u, a2, bar()); + _mm256_maskz_slli_epi64(u, a2, bar()); + _mm_mask_slli_epi64(w1, u, a1, bar()); + _mm_maskz_slli_epi64(u, a1, bar()); + + _mm256_mask_srai_epi16(w2, u, a2, bar()); + _mm256_maskz_srai_epi16(u, a2, bar()); + _mm_mask_srai_epi16(w1, u, a1, bar()); + _mm_maskz_srai_epi16(u, a1, bar()); + + _mm256_mask_slli_epi16(w2, u, a2, bar()); + _mm256_maskz_slli_epi16(u, a2, bar()); + _mm_mask_slli_epi16(w1, u, a1, bar()); + _mm_maskz_slli_epi16(u, a1, bar()); +} + diff --git a/gcc/testsuite/gcc.target/i386/pr109174-1.c b/gcc/testsuite/gcc.target/i386/pr109174-1.c new file mode 100644 index 00000000000..119721bccf0 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/pr109174-1.c @@ -0,0 +1,45 @@ +/* PR target/109174 */ +/* { dg-do compile } */ +/* { dg-options "-c -Wsign-conversion -Werror -mavx512bw -O2" } */ + +#include <immintrin.h> + +extern unsigned int bar(); + +void foo() +{ + __m512i a, w; + __mmask32 u1; + __mmask16 u2; + __mmask8 u3; + + _mm512_slli_epi64(a, bar()); + _mm512_mask_slli_epi64(w, u3, a, bar()); + _mm512_maskz_slli_epi64(u3, a, bar()); + _mm512_slli_epi32(a, bar()); + _mm512_mask_slli_epi32(w, u2, a, bar()); + _mm512_maskz_slli_epi32(u2, a, bar()); + _mm512_slli_epi16(a, bar()); + _mm512_mask_slli_epi16(w, u1, a, bar()); + _mm512_maskz_slli_epi16(u1, a, bar()); + + _mm512_srai_epi64(a, bar()); + _mm512_mask_srai_epi64(w, u3, a, bar()); + _mm512_maskz_srai_epi64(u3, a, bar()); + _mm512_srai_epi32(a, bar()); + _mm512_mask_srai_epi32(w, u2, a, bar()); + _mm512_maskz_srai_epi32(u2, a, bar()); + _mm512_srai_epi16(a, bar()); + _mm512_mask_srai_epi16(w, u1, a, bar()); + _mm512_maskz_srai_epi16(u1, a, bar()); + + _mm512_srli_epi64(a, bar()); + _mm512_mask_srli_epi64(w, u3, a, bar()); + _mm512_maskz_srli_epi64(u3, a, bar()); + _mm512_srli_epi32(a, bar()); + _mm512_mask_srli_epi32(w, u2, a, bar()); + _mm512_maskz_srli_epi32(u2, a, bar()); + _mm512_srli_epi16(a, bar()); + _mm512_mask_srli_epi16(w, u1, a, bar()); +} +
reply other threads:[~2023-05-25 8:08 UTC|newest] Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=20230525080818.4C16E388217A@sourceware.org \ --to=jianghc@gcc.gnu.org \ --cc=gcc-cvs@gcc.gnu.org \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox; as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).