@@ -454,7 +454,9 @@ i[34567]86-*-* | x86_64-*-*)
sm3intrin.h sha512intrin.h sm4intrin.h
usermsrintrin.h avx10_2roundingintrin.h
avx10_2mediaintrin.h avx10_2-512mediaintrin.h
- avx10_2bf16intrin.h avx10_2-512bf16intrin.h"
+ avx10_2convertintrin.h avx10_2-512convertintrin.h
+ avx10_2bf16intrin.h avx10_2-512bf16intrin.h
+ avx10_2satcvtintrin.h avx10_2-512satcvtintrin.h"
;;
ia64-*-*)
extra_headers=ia64intrin.h
new file mode 100644
@@ -0,0 +1,624 @@
+/* Copyright (C) 2024 Free Software Foundation, Inc.
+
+ This file is part of GCC.
+
+ GCC is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 3, or (at your option)
+ any later version.
+
+ GCC is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ Under Section 7 of GPL version 3, you are granted additional
+ permissions described in the GCC Runtime Library Exception, version
+ 3.1, as published by the Free Software Foundation.
+
+ You should have received a copy of the GNU General Public License and
+ a copy of the GCC Runtime Library Exception along with this program;
+ see the files COPYING3 and COPYING.RUNTIME respectively. If not, see
+ <http://www.gnu.org/licenses/>. */
+
+#if !defined _IMMINTRIN_H_INCLUDED
+#error "Never use <avx10_2-512satcvtintrin.h> directly; include <immintrin.h> instead."
+#endif
+
+#ifndef _AVX10_2_512SATCVTINTRIN_H_INCLUDED
+#define _AVX10_2_512SATCVTINTRIN_H_INCLUDED
+
+#if !defined (__AVX10_2_512__)
+#pragma GCC push_options
+#pragma GCC target("avx10.2-512")
+#define __DISABLE_AVX10_2_512__
+#endif /* __AVX10_2_512__ */
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_ipcvtnebf16_epi16 (__m512bh __A)
+{
+ return
+ (__m512i) __builtin_ia32_cvtnebf162ibs512_mask ((__v32bf) __A,
+ (__v32hi)
+ _mm512_undefined_si512 (),
+ (__mmask32) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_ipcvtnebf16_epi16 (__m512i __W, __mmask32 __U, __m512bh __A)
+{
+ return (__m512i) __builtin_ia32_cvtnebf162ibs512_mask ((__v32bf) __A,
+ (__v32hi) __W,
+ (__mmask32) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_ipcvtnebf16_epi16 (__mmask32 __U, __m512bh __A)
+{
+ return
+ (__m512i) __builtin_ia32_cvtnebf162ibs512_mask ((__v32bf) __A,
+ (__v32hi)
+ _mm512_setzero_si512 (),
+ (__mmask32) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_ipcvtnebf16_epu16 (__m512bh __A)
+{
+ return
+ (__m512i) __builtin_ia32_cvtnebf162iubs512_mask ((__v32bf) __A,
+ (__v32hi)
+ _mm512_undefined_si512 (),
+ (__mmask32) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_ipcvtnebf16_epu16 (__m512i __W, __mmask32 __U, __m512bh __A)
+{
+ return (__m512i) __builtin_ia32_cvtnebf162iubs512_mask ((__v32bf) __A,
+ (__v32hi) __W,
+ (__mmask32) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_ipcvtnebf16_epu16 (__mmask32 __U, __m512bh __A)
+{
+ return
+ (__m512i) __builtin_ia32_cvtnebf162iubs512_mask ((__v32bf) __A,
+ (__v32hi)
+ _mm512_setzero_si512 (),
+ (__mmask32) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_ipcvttnebf16_epi16 (__m512bh __A)
+{
+ return
+ (__m512i) __builtin_ia32_cvttnebf162ibs512_mask ((__v32bf) __A,
+ (__v32hi)
+ _mm512_undefined_si512 (),
+ (__mmask32) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_ipcvttnebf16_epi16 (__m512i __W, __mmask32 __U, __m512bh __A)
+{
+ return (__m512i) __builtin_ia32_cvttnebf162ibs512_mask ((__v32bf) __A,
+ (__v32hi) __W,
+ (__mmask32) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_ipcvttnebf16_epi16 (__mmask32 __U, __m512bh __A)
+{
+ return
+ (__m512i) __builtin_ia32_cvttnebf162ibs512_mask ((__v32bf) __A,
+ (__v32hi)
+ _mm512_setzero_si512 (),
+ (__mmask32) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_ipcvttnebf16_epu16 (__m512bh __A)
+{
+ return (__m512i)
+ __builtin_ia32_cvttnebf162iubs512_mask ((__v32bf) __A,
+ (__v32hi) _mm512_undefined_si512 (),
+ (__mmask32) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_ipcvttnebf16_epu16 (__m512i __W, __mmask32 __U, __m512bh __A)
+{
+ return (__m512i) __builtin_ia32_cvttnebf162iubs512_mask ((__v32bf) __A,
+ (__v32hi) __W,
+ (__mmask32)
+ __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_ipcvttnebf16_epu16 (__mmask32 __U, __m512bh __A)
+{
+ return (__m512i)
+ __builtin_ia32_cvttnebf162iubs512_mask ((__v32bf) __A,
+ (__v32hi)
+ _mm512_setzero_si512 (),
+ (__mmask32) __U);
+}
+
+#ifdef __OPTIMIZE__
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_ipcvt_roundph_epi16 (__m512h __A, const int __R)
+{
+ return
+ (__m512i) __builtin_ia32_cvtph2ibs512_mask_round ((__v32hf) __A,
+ (__v32hi)
+ _mm512_undefined_si512 (),
+ (__mmask32) -1,
+ __R);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_ipcvt_roundph_epi16 (__m512i __W, __mmask32 __U, __m512h __A,
+ const int __R)
+{
+ return (__m512i) __builtin_ia32_cvtph2ibs512_mask_round ((__v32hf) __A,
+ (__v32hi) __W,
+ (__mmask32) __U,
+ __R);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_ipcvt_roundph_epi16 (__mmask32 __U, __m512h __A, const int __R)
+{
+ return
+ (__m512i) __builtin_ia32_cvtph2ibs512_mask_round ((__v32hf) __A,
+ (__v32hi)
+ _mm512_setzero_si512 (),
+ (__mmask32) __U,
+ __R);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_ipcvt_roundph_epu16 (__m512h __A, const int __R)
+{
+ return
+ (__m512i) __builtin_ia32_cvtph2iubs512_mask_round ((__v32hf) __A,
+ (__v32hi)
+ _mm512_undefined_si512 (),
+ (__mmask32) -1,
+ __R);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_ipcvt_roundph_epu16 (__m512i __W, __mmask32 __U, __m512h __A,
+ const int __R)
+{
+ return (__m512i) __builtin_ia32_cvtph2iubs512_mask_round ((__v32hf) __A,
+ (__v32hi) __W,
+ (__mmask32) __U,
+ __R);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_ipcvt_roundph_epu16 (__mmask32 __U, __m512h __A, const int __R)
+{
+ return
+ (__m512i) __builtin_ia32_cvtph2iubs512_mask_round ((__v32hf) __A,
+ (__v32hi)
+ _mm512_setzero_si512 (),
+ (__mmask32) __U,
+ __R);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_ipcvt_roundps_epi32 (__m512 __A, const int __R)
+{
+ return
+ (__m512i) __builtin_ia32_cvtps2ibs512_mask_round ((__v16sf) __A,
+ (__v16si)
+ _mm512_undefined_si512 (),
+ (__mmask16) -1,
+ __R);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_ipcvt_roundps_epi32 (__m512i __W, __mmask16 __U, __m512 __A,
+ const int __R)
+{
+ return (__m512i) __builtin_ia32_cvtps2ibs512_mask_round ((__v16sf) __A,
+ (__v16si) __W,
+ (__mmask16) __U,
+ __R);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_ipcvt_roundps_epi32 (__mmask16 __U, __m512 __A, const int __R)
+{
+ return
+ (__m512i) __builtin_ia32_cvtps2ibs512_mask_round ((__v16sf) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U,
+ __R);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_ipcvt_roundps_epu32 (__m512 __A, const int __R)
+{
+ return
+ (__m512i) __builtin_ia32_cvtps2iubs512_mask_round ((__v16sf) __A,
+ (__v16si)
+ _mm512_undefined_si512 (),
+ (__mmask16) -1,
+ __R);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_ipcvt_roundps_epu32 (__m512i __W, __mmask16 __U, __m512 __A,
+ const int __R)
+{
+ return (__m512i) __builtin_ia32_cvtps2iubs512_mask_round ((__v16sf) __A,
+ (__v16si) __W,
+ (__mmask16) __U,
+ __R);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_ipcvt_roundps_epu32 (__mmask16 __U, __m512 __A, const int __R)
+{
+ return
+ (__m512i) __builtin_ia32_cvtps2iubs512_mask_round ((__v16sf) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U,
+ __R);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_ipcvtt_roundph_epi16 (__m512h __A, const int __R)
+{
+ return (__m512i)
+ __builtin_ia32_cvttph2ibs512_mask_round ((__v32hf) __A,
+ (__v32hi)
+ _mm512_undefined_si512 (),
+ (__mmask32) -1,
+ __R);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_ipcvtt_roundph_epi16 (__m512i __W, __mmask32 __U, __m512h __A,
+ const int __R)
+{
+ return (__m512i) __builtin_ia32_cvttph2ibs512_mask_round ((__v32hf) __A,
+ (__v32hi) __W,
+ (__mmask32) __U,
+ __R);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_ipcvtt_roundph_epi16 (__mmask32 __U, __m512h __A, const int __R)
+{
+ return
+ (__m512i) __builtin_ia32_cvttph2ibs512_mask_round ((__v32hf) __A,
+ (__v32hi)
+ _mm512_setzero_si512 (),
+ (__mmask32) __U,
+ __R);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_ipcvtt_roundph_epu16 (__m512h __A, const int __R)
+{
+ return (__m512i)
+ __builtin_ia32_cvttph2iubs512_mask_round ((__v32hf) __A,
+ (__v32hi)
+ _mm512_undefined_si512 (),
+ (__mmask32) -1,
+ __R);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_ipcvtt_roundph_epu16 (__m512i __W, __mmask32 __U, __m512h __A,
+ const int __R)
+{
+ return (__m512i) __builtin_ia32_cvttph2iubs512_mask_round ((__v32hf) __A,
+ (__v32hi) __W,
+ (__mmask32) __U,
+ __R);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_ipcvtt_roundph_epu16 (__mmask32 __U, __m512h __A, const int __R)
+{
+ return (__m512i)
+ __builtin_ia32_cvttph2iubs512_mask_round ((__v32hf) __A,
+ (__v32hi)
+ _mm512_setzero_si512 (),
+ (__mmask32) __U,
+ __R);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_ipcvtt_roundps_epi32 (__m512 __A, const int __R)
+{
+ return (__m512i)
+ __builtin_ia32_cvttps2ibs512_mask_round ((__v16sf) __A,
+ (__v16si)
+ _mm512_undefined_si512 (),
+ (__mmask16) -1,
+ __R);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_ipcvtt_roundps_epi32 (__m512i __W, __mmask16 __U, __m512 __A,
+ const int __R)
+{
+ return (__m512i) __builtin_ia32_cvttps2ibs512_mask_round ((__v16sf) __A,
+ (__v16si) __W,
+ (__mmask16) __U,
+ __R);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_ipcvtt_roundps_epi32 (__mmask16 __U, __m512 __A, const int __R)
+{
+ return (__m512i)
+ __builtin_ia32_cvttps2ibs512_mask_round ((__v16sf) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U,
+ __R);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_ipcvtt_roundps_epu32 (__m512 __A, const int __R)
+{
+ return (__m512i)
+ __builtin_ia32_cvttps2iubs512_mask_round ((__v16sf) __A,
+ (__v16si)
+ _mm512_undefined_si512 (),
+ (__mmask16) -1,
+ __R);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_ipcvtt_roundps_epu32 (__m512i __W, __mmask16 __U, __m512 __A,
+ const int __R)
+{
+ return (__m512i) __builtin_ia32_cvttps2iubs512_mask_round ((__v16sf) __A,
+ (__v16si) __W,
+ (__mmask16) __U,
+ __R);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_ipcvtt_roundps_epu32 (__mmask16 __U, __m512 __A, const int __R)
+{
+ return (__m512i)
+ __builtin_ia32_cvttps2iubs512_mask_round ((__v16sf) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U,
+ __R);
+}
+#else
+#define _mm512_ipcvt_roundph_epi16(A, R) \
+ ((__m512i) \
+ __builtin_ia32_cvtph2ibs512_mask_round ((__v32hf) (A), \
+ (__v32hi) \
+ (_mm512_undefined_si512 ()), \
+ (__mmask32) (-1), \
+ (R)))
+
+#define _mm512_mask_ipcvt_roundph_epi16(W, U, A, R) \
+ ((__m512i) __builtin_ia32_cvtph2ibs512_mask_round ((__v32hf) (A), \
+ (__v32hi) (W), \
+ (__mmask32) (U), \
+ (R)))
+
+#define _mm512_maskz_ipcvt_roundph_epi16(U, A, R) \
+ ((__m512i) \
+ __builtin_ia32_cvtph2ibs512_mask_round ((__v32hf) (A), \
+ (__v32hi) \
+ (_mm512_setzero_si512 ()), \
+ (__mmask32) (U), \
+ (R)))
+
+#define _mm512_ipcvt_roundph_epu16(A, R) \
+ ((__m512i) \
+ __builtin_ia32_cvtph2iubs512_mask_round ((__v32hf) (A), \
+ (__v32hi) \
+ (_mm512_undefined_si512 ()), \
+ (__mmask32) (-1), \
+ (R)))
+
+#define _mm512_mask_ipcvt_roundph_epu16(W, U, A, R) \
+ ((__m512i) __builtin_ia32_cvtph2iubs512_mask_round ((__v32hf) (A), \
+ (__v32hi) (W), \
+ (__mmask32) (U), \
+ (R)))
+
+#define _mm512_maskz_ipcvt_roundph_epu16(U, A, R) \
+ ((__m512i) \
+ __builtin_ia32_cvtph2iubs512_mask_round ((__v32hf) (A), \
+ (__v32hi) \
+ (_mm512_setzero_si512 ()), \
+ (__mmask32) (U), \
+ (R)))
+
+#define _mm512_ipcvt_roundps_epi32(A, R) \
+ ((__m512i) \
+ __builtin_ia32_cvtps2ibs512_mask_round ((__v16sf) (A), \
+ (__v16si) \
+ (_mm512_undefined_si512 ()), \
+ (__mmask16) (-1), \
+ (R)))
+
+#define _mm512_mask_ipcvt_roundps_epi32(W, U, A, R) \
+ ((__m512i) __builtin_ia32_cvtps2ibs512_mask_round ((__v16sf) (A), \
+ (__v16si) (W), \
+ (__mmask16) (U), \
+ (R)))
+
+#define _mm512_maskz_ipcvt_roundps_epi32(U, A, R) \
+ ((__m512i) \
+ __builtin_ia32_cvtps2ibs512_mask_round ((__v16sf) (A), \
+ (__v16si) \
+ (_mm512_setzero_si512 ()), \
+ (__mmask16) (U), \
+ (R)))
+
+#define _mm512_ipcvt_roundps_epu32(A, R) \
+ ((__m512i) \
+ __builtin_ia32_cvtps2iubs512_mask_round ((__v16sf) (A), \
+ (__v16si) \
+ (_mm512_undefined_si512 ()), \
+ (__mmask16) (-1), \
+ (R)))
+
+#define _mm512_mask_ipcvt_roundps_epu32(W, U, A, R) \
+ ((__m512i) __builtin_ia32_cvtps2iubs512_mask_round ((__v16sf) (A), \
+ (__v16si) (W), \
+ (__mmask16) (U), \
+ (R)))
+
+#define _mm512_maskz_ipcvt_roundps_epu32(U, A, R) \
+ ((__m512i) \
+ __builtin_ia32_cvtps2iubs512_mask_round ((__v16sf) (A), \
+ (__v16si) \
+ (_mm512_setzero_si512 ()), \
+ (__mmask16) (U), \
+ (R)))
+
+#define _mm512_ipcvtt_roundph_epi16(A, R) \
+ ((__m512i) \
+ __builtin_ia32_cvttph2ibs512_mask_round ((__v32hf) (A), \
+ (__v32hi) \
+ (_mm512_undefined_si512 ()), \
+ (__mmask32) (-1), \
+ (R)))
+
+#define _mm512_mask_ipcvtt_roundph_epi16(W, U, A, R) \
+ ((__m512i) __builtin_ia32_cvttph2ibs512_mask_round ((__v32hf) (A), \
+ (__v32hi) (W), \
+ (__mmask32) (U), \
+ (R)))
+
+#define _mm512_maskz_ipcvtt_roundph_epi16(U, A, R) \
+ ((__m512i) \
+ __builtin_ia32_cvttph2ibs512_mask_round ((__v32hf) (A), \
+ (__v32hi) \
+ (_mm512_setzero_si512 ()), \
+ (__mmask32) (U), \
+ (R)))
+
+#define _mm512_ipcvtt_roundph_epu16(A, R) \
+ ((__m512i) \
+ __builtin_ia32_cvttph2iubs512_mask_round ((__v32hf) (A), \
+ (__v32hi) \
+ (_mm512_undefined_si512 ()), \
+ (__mmask32) (-1), \
+ (R)))
+
+#define _mm512_mask_ipcvtt_roundph_epu16(W, U, A, R) \
+ ((__m512i) __builtin_ia32_cvttph2iubs512_mask_round ((__v32hf) (A), \
+ (__v32hi) (W), \
+ (__mmask32) (U), \
+ (R)))
+
+#define _mm512_maskz_ipcvtt_roundph_epu16(U, A, R) \
+ ((__m512i) \
+ __builtin_ia32_cvttph2iubs512_mask_round ((__v32hf) (A), \
+ (__v32hi) \
+ (_mm512_setzero_si512 ()), \
+ (__mmask32) (U), \
+ (R)))
+
+#define _mm512_ipcvtt_roundps_epi32(A, R) \
+ ((__m512i) \
+ __builtin_ia32_cvttps2ibs512_mask_round ((__v16sf) (A), \
+ (__v16si) \
+ (_mm512_undefined_si512 ()), \
+ (__mmask16) (-1), \
+ (R)))
+
+#define _mm512_mask_ipcvtt_roundps_epi32(W, U, A, R) \
+ ((__m512i) __builtin_ia32_cvttps2ibs512_mask_round ((__v16sf) (A), \
+ (__v16si) (W), \
+ (__mmask16) (U), \
+ (R)))
+
+#define _mm512_maskz_ipcvtt_roundps_epi32(U, A, R) \
+ ((__m512i) \
+ __builtin_ia32_cvttps2ibs512_mask_round ((__v16sf) (A), \
+ (__v16si) \
+ (_mm512_setzero_si512 ()), \
+ (__mmask16) (U), \
+ (R)))
+
+#define _mm512_ipcvtt_roundps_epu32(A, R) \
+ ((__m512i) \
+ __builtin_ia32_cvttps2iubs512_mask_round ((__v16sf) (A), \
+ (__v16si) \
+ (_mm512_undefined_si512 ()), \
+ (__mmask16) (-1), \
+ (R)))
+
+#define _mm512_mask_ipcvtt_roundps_epu32(W, U, A, R) \
+ ((__m512i) __builtin_ia32_cvttps2iubs512_mask_round ((__v16sf) (A), \
+ (__v16si) (W), \
+ (__mmask16) (U), \
+ (R)))
+
+#define _mm512_maskz_ipcvtt_roundps_epu32(U, A, R) \
+ ((__m512i) \
+ __builtin_ia32_cvttps2iubs512_mask_round ((__v16sf) (A), \
+ (__v16si) \
+ (_mm512_setzero_si512 ()), \
+ (__mmask16) (U), \
+ (R)))
+#endif
+
+#ifdef __DISABLE_AVX10_2_512__
+#undef __DISABLE_AVX10_2_512__
+#pragma GCC pop_options
+#endif /* __DISABLE_AVX10_2_512__ */
+
+#endif /* _AVX10_2_512SATCVTINTRIN_H_INCLUDED */
new file mode 100644
@@ -0,0 +1,1022 @@
+/* Copyright (C) 2024 Free Software Foundation, Inc.
+
+ This file is part of GCC.
+
+ GCC is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 3, or (at your option)
+ any later version.
+
+ GCC is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ Under Section 7 of GPL version 3, you are granted additional
+ permissions described in the GCC Runtime Library Exception, version
+ 3.1, as published by the Free Software Foundation.
+
+ You should have received a copy of the GNU General Public License and
+ a copy of the GCC Runtime Library Exception along with this program;
+ see the files COPYING3 and COPYING.RUNTIME respectively. If not, see
+ <http://www.gnu.org/licenses/>. */
+
+#if !defined _IMMINTRIN_H_INCLUDED
+#error "Never use <avx10_2satcvtintrin.h> directly; include <immintrin.h> instead."
+#endif
+
+#ifndef _AVX10_2SATCVTINTRIN_H_INCLUDED
+#define _AVX10_2SATCVTINTRIN_H_INCLUDED
+
+#if !defined (__AVX10_2_256__)
+#pragma GCC push_options
+#pragma GCC target("avx10.2")
+#define __DISABLE_AVX10_2_256__
+#endif /* __AVX10_2_256__ */
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_ipcvtnebf16_epi16 (__m128bh __A)
+{
+ return (__m128i) __builtin_ia32_cvtnebf162ibs128_mask ((__v8bf) __A,
+ (__v8hi)
+ _mm_undefined_si128 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_ipcvtnebf16_epi16 (__m128i __W, __mmask8 __U, __m128bh __A)
+{
+ return (__m128i) __builtin_ia32_cvtnebf162ibs128_mask ((__v8bf) __A,
+ (__v8hi) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_ipcvtnebf16_epi16 (__mmask8 __U, __m128bh __A)
+{
+ return (__m128i) __builtin_ia32_cvtnebf162ibs128_mask ((__v8bf) __A,
+ (__v8hi)
+ _mm_setzero_si128 (),
+ (__mmask8) __U);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_ipcvtnebf16_epi16 (__m256bh __A)
+{
+ return
+ (__m256i) __builtin_ia32_cvtnebf162ibs256_mask ((__v16bf) __A,
+ (__v16hi)
+ _mm256_undefined_si256 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_mask_ipcvtnebf16_epi16 (__m256i __W, __mmask16 __U, __m256bh __A)
+{
+ return (__m256i) __builtin_ia32_cvtnebf162ibs256_mask ((__v16bf) __A,
+ (__v16hi) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_maskz_ipcvtnebf16_epi16 (__mmask16 __U, __m256bh __A)
+{
+ return
+ (__m256i) __builtin_ia32_cvtnebf162ibs256_mask ((__v16bf) __A,
+ (__v16hi)
+ _mm256_setzero_si256 (),
+ (__mmask16) __U);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_ipcvtnebf16_epu16 (__m128bh __A)
+{
+ return
+ (__m128i) __builtin_ia32_cvtnebf162iubs128_mask ((__v8bf) __A,
+ (__v8hi)
+ _mm_undefined_si128 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_ipcvtnebf16_epu16 (__m128i __W, __mmask8 __U, __m128bh __A)
+{
+ return (__m128i) __builtin_ia32_cvtnebf162iubs128_mask ((__v8bf) __A,
+ (__v8hi) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_ipcvtnebf16_epu16 (__mmask8 __U, __m128bh __A)
+{
+ return
+ (__m128i) __builtin_ia32_cvtnebf162iubs128_mask ((__v8bf) __A,
+ (__v8hi)
+ _mm_setzero_si128 (),
+ (__mmask8) __U);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_ipcvtnebf16_epu16 (__m256bh __A)
+{
+ return
+ (__m256i) __builtin_ia32_cvtnebf162iubs256_mask ((__v16bf) __A,
+ (__v16hi)
+ _mm256_undefined_si256 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_mask_ipcvtnebf16_epu16 (__m256i __W, __mmask16 __U, __m256bh __A)
+{
+ return (__m256i) __builtin_ia32_cvtnebf162iubs256_mask ((__v16bf) __A,
+ (__v16hi) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_maskz_ipcvtnebf16_epu16 (__mmask16 __U, __m256bh __A)
+{
+ return
+ (__m256i) __builtin_ia32_cvtnebf162iubs256_mask ((__v16bf) __A,
+ (__v16hi)
+ _mm256_setzero_si256 (),
+ (__mmask16) __U);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_ipcvtph_epi16 (__m128h __A)
+{
+ return (__m128i) __builtin_ia32_cvtph2ibs128_mask ((__v8hf) __A,
+ (__v8hi)
+ _mm_undefined_si128 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_ipcvtph_epi16 (__m128i __W, __mmask8 __U, __m128h __A)
+{
+ return (__m128i) __builtin_ia32_cvtph2ibs128_mask ((__v8hf) __A,
+ (__v8hi) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_ipcvtph_epi16 (__mmask8 __U, __m128h __A)
+{
+ return (__m128i) __builtin_ia32_cvtph2ibs128_mask ((__v8hf) __A,
+ (__v8hi)
+ _mm_setzero_si128 (),
+ (__mmask8) __U);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_ipcvtph_epu16 (__m128h __A)
+{
+ return (__m128i) __builtin_ia32_cvtph2iubs128_mask ((__v8hf) __A,
+ (__v8hi)
+ _mm_undefined_si128 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_ipcvtph_epu16 (__m128i __W, __mmask8 __U, __m128h __A)
+{
+ return (__m128i) __builtin_ia32_cvtph2iubs128_mask ((__v8hf) __A,
+ (__v8hi) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_ipcvtph_epu16 (__mmask8 __U, __m128h __A)
+{
+ return (__m128i) __builtin_ia32_cvtph2iubs128_mask ((__v8hf) __A,
+ (__v8hi)
+ _mm_setzero_si128 (),
+ (__mmask8) __U);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_ipcvtps_epi32 (__m128 __A)
+{
+ return (__m128i) __builtin_ia32_cvtps2ibs128_mask ((__v4sf) __A,
+ (__v4si)
+ _mm_undefined_si128 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_ipcvtps_epi32 (__m128i __W, __mmask8 __U, __m128 __A)
+{
+ return (__m128i) __builtin_ia32_cvtps2ibs128_mask ((__v4sf) __A,
+ (__v4si) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_ipcvtps_epi32 (__mmask8 __U, __m128 __A)
+{
+ return (__m128i) __builtin_ia32_cvtps2ibs128_mask ((__v4sf) __A,
+ (__v4si)
+ _mm_setzero_si128 (),
+ (__mmask8) __U);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_ipcvtps_epu32 (__m128 __A)
+{
+ return (__m128i) __builtin_ia32_cvtps2iubs128_mask ((__v4sf) __A,
+ (__v4si)
+ _mm_undefined_si128 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_ipcvtps_epu32 (__m128i __W, __mmask8 __U, __m128 __A)
+{
+ return (__m128i) __builtin_ia32_cvtps2iubs128_mask ((__v4sf) __A,
+ (__v4si) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_ipcvtps_epu32 (__mmask8 __U, __m128 __A)
+{
+ return (__m128i) __builtin_ia32_cvtps2iubs128_mask ((__v4sf) __A,
+ (__v4si)
+ _mm_setzero_si128 (),
+ (__mmask8) __U);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_ipcvttnebf16_epi16 (__m128bh __A)
+{
+ return
+ (__m128i) __builtin_ia32_cvttnebf162ibs128_mask ((__v8bf) __A,
+ (__v8hi)
+ _mm_undefined_si128 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_ipcvttnebf16_epi16 (__m128i __W, __mmask8 __U, __m128bh __A)
+{
+ return (__m128i) __builtin_ia32_cvttnebf162ibs128_mask ((__v8bf) __A,
+ (__v8hi) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_ipcvttnebf16_epi16 (__mmask8 __U, __m128bh __A)
+{
+ return (__m128i) __builtin_ia32_cvttnebf162ibs128_mask ((__v8bf) __A,
+ (__v8hi)
+ _mm_setzero_si128 (),
+ (__mmask8) __U);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_ipcvttnebf16_epu16 (__m128bh __A)
+{
+ return
+ (__m128i) __builtin_ia32_cvttnebf162iubs128_mask ((__v8bf) __A,
+ (__v8hi)
+ _mm_undefined_si128 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_ipcvttnebf16_epu16 (__m128i __W, __mmask8 __U, __m128bh __A)
+{
+ return (__m128i) __builtin_ia32_cvttnebf162iubs128_mask ((__v8bf) __A,
+ (__v8hi) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_ipcvttnebf16_epu16 (__mmask8 __U, __m128bh __A)
+{
+ return (__m128i) __builtin_ia32_cvttnebf162iubs128_mask ((__v8bf) __A,
+ (__v8hi)
+ _mm_setzero_si128 (),
+ (__mmask8) __U);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_ipcvttnebf16_epi16 (__m256bh __A)
+{
+ return (__m256i)
+ __builtin_ia32_cvttnebf162ibs256_mask ((__v16bf) __A,
+ (__v16hi)
+ _mm256_undefined_si256 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_mask_ipcvttnebf16_epi16 (__m256i __W, __mmask16 __U, __m256bh __A)
+{
+ return (__m256i) __builtin_ia32_cvttnebf162ibs256_mask ((__v16bf) __A,
+ (__v16hi) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_maskz_ipcvttnebf16_epi16 (__mmask16 __U, __m256bh __A)
+{
+ return (__m256i)
+ __builtin_ia32_cvttnebf162ibs256_mask ((__v16bf) __A,
+ (__v16hi)
+ _mm256_setzero_si256 (),
+ (__mmask16) __U);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_ipcvttnebf16_epu16 (__m256bh __A)
+{
+ return (__m256i)
+ __builtin_ia32_cvttnebf162iubs256_mask ((__v16bf) __A,
+ (__v16hi)
+ _mm256_undefined_si256 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_mask_ipcvttnebf16_epu16 (__m256i __W, __mmask16 __U, __m256bh __A)
+{
+ return (__m256i) __builtin_ia32_cvttnebf162iubs256_mask ((__v16bf) __A,
+ (__v16hi) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_maskz_ipcvttnebf16_epu16 (__mmask16 __U, __m256bh __A)
+{
+ return (__m256i)
+ __builtin_ia32_cvttnebf162iubs256_mask ((__v16bf) __A,
+ (__v16hi)
+ _mm256_setzero_si256 (),
+ (__mmask16) __U);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_ipcvttph_epi16 (__m128h __A)
+{
+ return (__m128i) __builtin_ia32_cvttph2ibs128_mask ((__v8hf) __A,
+ (__v8hi)
+ _mm_undefined_si128 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_ipcvttph_epi16 (__m128i __W, __mmask8 __U, __m128h __A)
+{
+ return (__m128i) __builtin_ia32_cvttph2ibs128_mask ((__v8hf) __A,
+ (__v8hi) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_ipcvttph_epi16 (__mmask8 __U, __m128h __A)
+{
+ return (__m128i) __builtin_ia32_cvttph2ibs128_mask ((__v8hf) __A,
+ (__v8hi)
+ _mm_setzero_si128 (),
+ (__mmask8) __U);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_ipcvttph_epu16 (__m128h __A)
+{
+ return (__m128i) __builtin_ia32_cvttph2iubs128_mask ((__v8hf) __A,
+ (__v8hi)
+ _mm_undefined_si128 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_ipcvttph_epu16 (__m128i __W, __mmask8 __U, __m128h __A)
+{
+ return (__m128i) __builtin_ia32_cvttph2iubs128_mask ((__v8hf) __A,
+ (__v8hi) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_ipcvttph_epu16 (__mmask8 __U, __m128h __A)
+{
+ return (__m128i) __builtin_ia32_cvttph2iubs128_mask ((__v8hf) __A,
+ (__v8hi)
+ _mm_setzero_si128 (),
+ (__mmask8) __U);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_ipcvttps_epi32 (__m128 __A)
+{
+ return (__m128i) __builtin_ia32_cvttps2ibs128_mask ((__v4sf) __A,
+ (__v4si)
+ _mm_undefined_si128 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_ipcvttps_epi32 (__m128i __W, __mmask8 __U, __m128 __A)
+{
+ return (__m128i) __builtin_ia32_cvttps2ibs128_mask ((__v4sf) __A,
+ (__v4si) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_ipcvttps_epi32 (__mmask8 __U, __m128 __A)
+{
+ return (__m128i) __builtin_ia32_cvttps2ibs128_mask ((__v4sf) __A,
+ (__v4si)
+ _mm_setzero_si128 (),
+ (__mmask8) __U);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_ipcvttps_epu32 (__m128 __A)
+{
+ return (__m128i) __builtin_ia32_cvttps2iubs128_mask ((__v4sf) __A,
+ (__v4si)
+ _mm_undefined_si128 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_ipcvttps_epu32 (__m128i __W, __mmask8 __U, __m128 __A)
+{
+ return (__m128i) __builtin_ia32_cvttps2iubs128_mask ((__v4sf) __A,
+ (__v4si) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_ipcvttps_epu32 (__mmask8 __U, __m128 __A)
+{
+ return (__m128i) __builtin_ia32_cvttps2iubs128_mask ((__v4sf) __A,
+ (__v4si)
+ _mm_setzero_si128 (),
+ (__mmask8) __U);
+}
+
+#ifdef __OPTIMIZE__
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_ipcvt_roundph_epi16 (__m256h __A, const int __R)
+{
+ return
+ (__m256i) __builtin_ia32_cvtph2ibs256_mask_round ((__v16hf) __A,
+ (__v16hi)
+ _mm256_undefined_si256 (),
+ (__mmask16) -1,
+ __R);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_mask_ipcvt_roundph_epi16 (__m256i __W, __mmask16 __U, __m256h __A,
+ const int __R)
+{
+ return (__m256i) __builtin_ia32_cvtph2ibs256_mask_round ((__v16hf) __A,
+ (__v16hi) __W,
+ (__mmask16) __U,
+ __R);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_maskz_ipcvt_roundph_epi16 (__mmask16 __U, __m256h __A, const int __R)
+{
+ return
+ (__m256i) __builtin_ia32_cvtph2ibs256_mask_round ((__v16hf) __A,
+ (__v16hi)
+ _mm256_setzero_si256 (),
+ (__mmask16) __U,
+ __R);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_ipcvt_roundph_epu16 (__m256h __A, const int __R)
+{
+ return (__m256i)
+ __builtin_ia32_cvtph2iubs256_mask_round ((__v16hf) __A,
+ (__v16hi)
+ _mm256_undefined_si256 (),
+ (__mmask16) -1,
+ __R);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_mask_ipcvt_roundph_epu16 (__m256i __W, __mmask16 __U, __m256h __A,
+ const int __R)
+{
+ return (__m256i) __builtin_ia32_cvtph2iubs256_mask_round ((__v16hf) __A,
+ (__v16hi) __W,
+ (__mmask16) __U,
+ __R);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_maskz_ipcvt_roundph_epu16 (__mmask16 __U, __m256h __A, const int __R)
+{
+ return
+ (__m256i) __builtin_ia32_cvtph2iubs256_mask_round ((__v16hf) __A,
+ (__v16hi)
+ _mm256_setzero_si256 (),
+ (__mmask16) __U,
+ __R);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_ipcvt_roundps_epi32 (__m256 __A, const int __R)
+{
+ return
+ (__m256i) __builtin_ia32_cvtps2ibs256_mask_round ((__v8sf) __A,
+ (__v8si)
+ _mm256_undefined_si256 (),
+ (__mmask8) -1,
+ __R);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_mask_ipcvt_roundps_epi32 (__m256i __W, __mmask8 __U, __m256 __A,
+ const int __R)
+{
+ return (__m256i) __builtin_ia32_cvtps2ibs256_mask_round ((__v8sf) __A,
+ (__v8si) __W,
+ (__mmask8) __U,
+ __R);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_maskz_ipcvt_roundps_epi32 (__mmask8 __U, __m256 __A, const int __R)
+{
+ return
+ (__m256i) __builtin_ia32_cvtps2ibs256_mask_round ((__v8sf) __A,
+ (__v8si)
+ _mm256_setzero_si256 (),
+ (__mmask8) __U,
+ __R);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_ipcvt_roundps_epu32 (__m256 __A, const int __R)
+{
+ return (__m256i)
+ __builtin_ia32_cvtps2iubs256_mask_round ((__v8sf) __A,
+ (__v8si)
+ _mm256_undefined_si256 (),
+ (__mmask8) -1,
+ __R);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_mask_ipcvt_roundps_epu32 (__m256i __W, __mmask8 __U, __m256 __A,
+ const int __R)
+{
+ return (__m256i) __builtin_ia32_cvtps2iubs256_mask_round ((__v8sf) __A,
+ (__v8si) __W,
+ (__mmask8) __U,
+ __R);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_maskz_ipcvt_roundps_epu32 (__mmask8 __U, __m256 __A, const int __R)
+{
+ return
+ (__m256i) __builtin_ia32_cvtps2iubs256_mask_round ((__v8sf) __A,
+ (__v8si)
+ _mm256_setzero_si256 (),
+ (__mmask8) __U,
+ __R);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_ipcvtt_roundph_epi16 (__m256h __A, const int __R)
+{
+ return (__m256i)
+ __builtin_ia32_cvttph2ibs256_mask_round ((__v16hf) __A,
+ (__v16hi)
+ _mm256_undefined_si256 (),
+ (__mmask16) -1,
+ __R);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_mask_ipcvtt_roundph_epi16 (__m256i __W, __mmask16 __U, __m256h __A,
+ const int __R)
+{
+ return (__m256i) __builtin_ia32_cvttph2ibs256_mask_round ((__v16hf) __A,
+ (__v16hi) __W,
+ (__mmask16) __U,
+ __R);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_maskz_ipcvtt_roundph_epi16 (__mmask16 __U, __m256h __A, const int __R)
+{
+ return
+ (__m256i) __builtin_ia32_cvttph2ibs256_mask_round ((__v16hf) __A,
+ (__v16hi)
+ _mm256_setzero_si256 (),
+ (__mmask16) __U,
+ __R);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_ipcvtt_roundph_epu16 (__m256h __A, const int __R)
+{
+ return (__m256i)
+ __builtin_ia32_cvttph2iubs256_mask_round ((__v16hf) __A,
+ (__v16hi)
+ _mm256_undefined_si256 (),
+ (__mmask16) -1,
+ __R);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_mask_ipcvtt_roundph_epu16 (__m256i __W, __mmask16 __U, __m256h __A,
+ const int __R)
+{
+ return (__m256i) __builtin_ia32_cvttph2iubs256_mask_round ((__v16hf) __A,
+ (__v16hi) __W,
+ (__mmask16) __U,
+ __R);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_maskz_ipcvtt_roundph_epu16 (__mmask16 __U, __m256h __A, const int __R)
+{
+ return
+ (__m256i) __builtin_ia32_cvttph2iubs256_mask_round ((__v16hf) __A,
+ (__v16hi)
+ _mm256_setzero_si256 (),
+ (__mmask16) __U,
+ __R);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_ipcvtt_roundps_epi32 (__m256 __A, const int __R)
+{
+ return (__m256i)
+ __builtin_ia32_cvttps2ibs256_mask_round ((__v8sf) __A,
+ (__v8si)
+ _mm256_undefined_si256 (),
+ (__mmask8) -1,
+ __R);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_mask_ipcvtt_roundps_epi32 (__m256i __W, __mmask8 __U, __m256 __A,
+ const int __R)
+{
+ return (__m256i) __builtin_ia32_cvttps2ibs256_mask_round ((__v8sf) __A,
+ (__v8si) __W,
+ (__mmask8) __U,
+ __R);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_maskz_ipcvtt_roundps_epi32 (__mmask8 __U, __m256 __A, const int __R)
+{
+ return
+ (__m256i) __builtin_ia32_cvttps2ibs256_mask_round ((__v8sf) __A,
+ (__v8si)
+ _mm256_setzero_si256 (),
+ (__mmask8) __U,
+ __R);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_ipcvtt_roundps_epu32 (__m256 __A, const int __R)
+{
+ return (__m256i)
+ __builtin_ia32_cvttps2iubs256_mask_round ((__v8sf) __A,
+ (__v8si)
+ _mm256_undefined_si256 (),
+ (__mmask8) -1,
+ __R);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_mask_ipcvtt_roundps_epu32 (__m256i __W, __mmask8 __U, __m256 __A,
+ const int __R)
+{
+ return (__m256i) __builtin_ia32_cvttps2iubs256_mask_round ((__v8sf) __A,
+ (__v8si) __W,
+ (__mmask8) __U,
+ __R);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_maskz_ipcvtt_roundps_epu32 (__mmask8 __U, __m256 __A, const int __R)
+{
+ return
+ (__m256i) __builtin_ia32_cvttps2iubs256_mask_round ((__v8sf) __A,
+ (__v8si)
+ _mm256_setzero_si256 (),
+ (__mmask8) __U,
+ __R);
+}
+#else
+
+#define _mm256_ipcvt_roundph_epi16(A, R) \
+ ((__m256i) \
+ __builtin_ia32_cvtph2ibs256_mask_round ((__v16hf) (A), \
+ (__v16hi) \
+ (_mm256_undefined_si256 ()), \
+ (__mmask16) (-1), \
+ (R)))
+
+#define _mm256_mask_ipcvt_roundph_epi16(W, U, A, R) \
+ ((__m256i) __builtin_ia32_cvtph2ibs256_mask_round ((__v16hf) (A), \
+ (__v16hi) (W), \
+ (__mmask16) (U), \
+ (R)))
+
+#define _mm256_maskz_ipcvt_roundph_epi16(U, A, R) \
+ ((__m256i) \
+ __builtin_ia32_cvtph2ibs256_mask_round ((__v16hf) (A), \
+ (__v16hi) \
+ (_mm256_setzero_si256 ()), \
+ (__mmask16) (U), \
+ (R)))
+
+#define _mm256_ipcvt_roundph_epu16(A, R) \
+ ((__m256i) \
+ __builtin_ia32_cvtph2iubs256_mask_round ((__v16hf) (A), \
+ (__v16hi) \
+ (_mm256_undefined_si256 ()), \
+ (__mmask16) (-1), \
+ (R)))
+
+#define _mm256_mask_ipcvt_roundph_epu16(W, U, A, R) \
+ ((__m256i) __builtin_ia32_cvtph2iubs256_mask_round ((__v16hf) (A), \
+ (__v16hi) (W), \
+ (__mmask16) (U), \
+ (R)))
+
+#define _mm256_maskz_ipcvt_roundph_epu16(U, A, R) \
+ ((__m256i) \
+ __builtin_ia32_cvtph2iubs256_mask_round ((__v16hf) (A), \
+ (__v16hi) \
+ (_mm256_setzero_si256 ()), \
+ (__mmask16) (U), \
+ (R)))
+
+#define _mm256_ipcvt_roundps_epi32(A, R) \
+ ((__m256i) \
+ __builtin_ia32_cvtps2ibs256_mask_round ((__v8sf) (A), \
+ (__v8si) \
+ (_mm256_undefined_si256 ()), \
+ (__mmask8) (-1), \
+ (R)))
+
+#define _mm256_mask_ipcvt_roundps_epi32(W, U, A, R) \
+ ((__m256i) __builtin_ia32_cvtps2ibs256_mask_round ((__v8sf) (A), \
+ (__v8si) (W), \
+ (__mmask8) (U), \
+ (R)))
+
+#define _mm256_maskz_ipcvt_roundps_epi32(U, A, R) \
+ ((__m256i) \
+ __builtin_ia32_cvtps2ibs256_mask_round ((__v8sf) (A), \
+ (__v8si) \
+ (_mm256_setzero_si256 ()), \
+ (__mmask8) (U), \
+ (R)))
+
+#define _mm256_ipcvt_roundps_epu32(A, R) \
+ ((__m256i) \
+ __builtin_ia32_cvtps2iubs256_mask_round ((__v8sf) (A), \
+ (__v8si) \
+ (_mm256_undefined_si256 ()), \
+ (__mmask8) (-1), \
+ (R)))
+
+#define _mm256_mask_ipcvt_roundps_epu32(W, U, A, R) \
+ ((__m256i) __builtin_ia32_cvtps2iubs256_mask_round ((__v8sf) (A), \
+ (__v8si) (W), \
+ (__mmask8) (U), \
+ (R)))
+
+#define _mm256_maskz_ipcvt_roundps_epu32(U, A, R) \
+ ((__m256i) \
+ __builtin_ia32_cvtps2iubs256_mask_round ((__v8sf) (A), \
+ (__v8si) \
+ (_mm256_setzero_si256 ()), \
+ (__mmask8) (U), \
+ (R)))
+
+
+#define _mm256_ipcvttne_roundbf16_epi16(A, R) \
+ ((__m256i) \
+ __builtin_ia32_cvttnebf162ibs256_mask_round ((__v16bf) (A), \
+ (__v16hi) \
+ (_mm256_undefined_si256 ()), \
+ (__mmask16) (-1), \
+ (R)))
+
+#define _mm256_mask_ipcvttne_roundbf16_epi16(W, U, A, R) \
+ ((__m256i) __builtin_ia32_cvttnebf162ibs256_mask_round ((__v16bf) (A), \
+ (__v16hi) (W), \
+ (__mmask16) (U), \
+ (R)))
+
+#define _mm256_maskz_ipcvttne_roundbf16_epi16(U, A, R) \
+ ((__m256i) \
+ __builtin_ia32_cvttnebf162ibs256_mask_round ((__v16bf) (A), \
+ (__v16hi) \
+ (_mm256_setzero_si256 ()), \
+ (__mmask16) (U), \
+ (R)))
+
+#define _mm256_ipcvttne_roundbf16_epu16(A, R) \
+ ((__m256i) \
+ __builtin_ia32_cvttnebf162iubs256_mask_round ((__v16bf) (A), \
+ (__v16hi) \
+ (_mm256_undefined_si256 ()), \
+ (__mmask16) (-1), \
+ (R)))
+
+#define _mm256_mask_ipcvttne_roundbf16_epu16(W, U, A, R) \
+ ((__m256i) __builtin_ia32_cvttnebf162iubs256_mask_round ((__v16bf) (A), \
+ (__v16hi) (W), \
+ (__mmask16) (U), \
+ (R)))
+
+#define _mm256_maskz_ipcvttne_roundbf16_epu16(U, A, R) \
+ ((__m256i) \
+ __builtin_ia32_cvttnebf162iubs256_mask_round ((__v16bf) (A), \
+ (__v16hi) \
+ (_mm256_setzero_si256 ()), \
+ (__mmask16) (U), \
+ (R)))
+
+#define _mm256_ipcvtt_roundph_epi16(A, R) \
+ ((__m256i) \
+ __builtin_ia32_cvttph2ibs256_mask_round ((__v16hf) (A), \
+ (__v16hi) \
+ (_mm256_undefined_si256 ()), \
+ (__mmask16) (-1), \
+ (R)))
+
+#define _mm256_mask_ipcvtt_roundph_epi16(W, U, A, R) \
+ ((__m256i) __builtin_ia32_cvttph2ibs256_mask_round ((__v16hf) (A), \
+ (__v16hi) (W), \
+ (__mmask16) (U), \
+ (R)))
+
+#define _mm256_maskz_ipcvtt_roundph_epi16(U, A, R) \
+ ((__m256i) \
+ __builtin_ia32_cvttph2ibs256_mask_round ((__v16hf) (A), \
+ (__v16hi) \
+ (_mm256_setzero_si256 ()), \
+ (__mmask16) (U), \
+ (R)))
+
+#define _mm256_ipcvtt_roundph_epu16(A, R) \
+ ((__m256i) \
+ __builtin_ia32_cvttph2iubs256_mask_round ((__v16hf) (A), \
+ (__v16hi) \
+ (_mm256_undefined_si256 ()), \
+ (__mmask16) (-1), \
+ (R)))
+
+#define _mm256_mask_ipcvtt_roundph_epu16(W, U, A, R) \
+ ((__m256i) __builtin_ia32_cvttph2iubs256_mask_round ((__v16hf) (A), \
+ (__v16hi) (W), \
+ (__mmask16) (U), \
+ (R)))
+
+#define _mm256_maskz_ipcvtt_roundph_epu16(U, A, R) \
+ ((__m256i) \
+ __builtin_ia32_cvttph2iubs256_mask_round ((__v16hf) (A), \
+ (__v16hi) \
+ (_mm256_setzero_si256 ()), \
+ (__mmask16) (U), \
+ (R)))
+
+#define _mm256_ipcvtt_roundps_epi32(A, R) \
+ ((__m256i) \
+ __builtin_ia32_cvttps2ibs256_mask_round ((__v8sf) (A), \
+ (__v8si) \
+ (_mm256_undefined_si256 ()), \
+ (__mmask8) (-1), \
+ (R)))
+
+#define _mm256_mask_ipcvtt_roundps_epi32(W, U, A, R) \
+ ((__m256i) __builtin_ia32_cvttps2ibs256_mask_round ((__v8sf) (A), \
+ (__v8si) (W), \
+ (__mmask8) (U), \
+ (R)))
+
+#define _mm256_maskz_ipcvtt_roundps_epi32(U, A, R) \
+ ((__m256i) \
+ __builtin_ia32_cvttps2ibs256_mask_round ((__v8sf) (A), \
+ (__v8si) \
+ (_mm256_setzero_si256 ()), \
+ (__mmask8) (U), \
+ (R)))
+
+#define _mm256_ipcvtt_roundps_epu32(A, R) \
+ ((__m256i) \
+ __builtin_ia32_cvttps2iubs256_mask_round ((__v8sf) (A), \
+ (__v8si) \
+ (_mm256_undefined_si256 ()), \
+ (__mmask8) (-1), \
+ (R)))
+
+#define _mm256_mask_ipcvtt_roundps_epu32(W, U, A, R) \
+ ((__m256i) __builtin_ia32_cvttps2iubs256_mask_round ((__v8sf) (A), \
+ (__v8si) (W), \
+ (__mmask8) (U), \
+ (R)))
+
+#define _mm256_maskz_ipcvtt_roundps_epu32(U, A, R) \
+((__m256i) \
+ __builtin_ia32_cvttps2iubs256_mask_round ((__v8sf) (A), \
+ (__v8si) \
+ (_mm256_setzero_si256 ()), \
+ (__mmask8) (U), \
+ (R)))
+#endif
+
+#ifdef __DISABLE_AVX10_2_256__
+#undef __DISABLE_AVX10_2_256__
+#pragma GCC pop_options
+#endif /* __DISABLE_AVX10_2_256__ */
+
+#endif /* _AVX10_2SATCVTINTRIN_H_INCLUDED */
@@ -1493,3 +1493,9 @@ DEF_FUNCTION_TYPE (USI, V32BF, V32BF, INT, USI)
DEF_FUNCTION_TYPE (UHI, V16BF, V16BF, INT, UHI)
DEF_FUNCTION_TYPE (UQI, V8BF, V8BF, INT, UQI)
DEF_FUNCTION_TYPE (INT, V8BF, V8BF)
+DEF_FUNCTION_TYPE (V8HI, V8BF, V8HI, UQI)
+DEF_FUNCTION_TYPE (V16HI, V16BF, V16HI, UHI)
+DEF_FUNCTION_TYPE (V32HI, V32BF, V32HI, USI)
+DEF_FUNCTION_TYPE (V16SI, V16SF, V16SI, UHI, INT)
+DEF_FUNCTION_TYPE (V16HI, V16BF, V16HI, UHI, INT)
+DEF_FUNCTION_TYPE (V32HI, V32BF, V32HI, USI, INT)
@@ -3270,6 +3270,26 @@ BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx10_2_comsbf16_v8bf, "__built
BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx10_2_comsbf16_v8bf, "__builtin_ia32_vcomsbf16le", IX86_BUILTIN_VCOMSBF16LE, LE, (int) INT_FTYPE_V8BF_V8BF)
BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx10_2_comsbf16_v8bf, "__builtin_ia32_vcomsbf16lt", IX86_BUILTIN_VCOMSBF16LT, LT, (int) INT_FTYPE_V8BF_V8BF)
BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx10_2_comsbf16_v8bf, "__builtin_ia32_vcomsbf16neq", IX86_BUILTIN_VCOMSBF16NE, NE, (int) INT_FTYPE_V8BF_V8BF)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx10_2_cvtnebf162ibsv8bf_mask, "__builtin_ia32_cvtnebf162ibs128_mask", IX86_BUILTIN_CVTNEBF162IBS128_MASK, UNKNOWN, (int) V8HI_FTYPE_V8BF_V8HI_UQI)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx10_2_cvtnebf162ibsv16bf_mask, "__builtin_ia32_cvtnebf162ibs256_mask", IX86_BUILTIN_CVTNEBF162IBS256_MASK, UNKNOWN, (int) V16HI_FTYPE_V16BF_V16HI_UHI)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_512, CODE_FOR_avx10_2_cvtnebf162ibsv32bf_mask, "__builtin_ia32_cvtnebf162ibs512_mask", IX86_BUILTIN_CVTNEBF162IBS512_MASK, UNKNOWN, (int) V32HI_FTYPE_V32BF_V32HI_USI)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx10_2_cvtnebf162iubsv8bf_mask, "__builtin_ia32_cvtnebf162iubs128_mask", IX86_BUILTIN_CVTNEBF162IUBS128_MASK, UNKNOWN, (int) V8HI_FTYPE_V8BF_V8HI_UQI)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx10_2_cvtnebf162iubsv16bf_mask, "__builtin_ia32_cvtnebf162iubs256_mask", IX86_BUILTIN_CVTNEBF162IUBS256_MASK, UNKNOWN, (int) V16HI_FTYPE_V16BF_V16HI_UHI)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_512, CODE_FOR_avx10_2_cvtnebf162iubsv32bf_mask, "__builtin_ia32_cvtnebf162iubs512_mask", IX86_BUILTIN_CVTNEBF162IUBS512_MASK, UNKNOWN, (int) V32HI_FTYPE_V32BF_V32HI_USI)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx10_2_cvtph2ibsv8hf_mask, "__builtin_ia32_cvtph2ibs128_mask", IX86_BUILTIN_CVTPH2IBS128_MASK, UNKNOWN, (int) V8HI_FTYPE_V8HF_V8HI_UQI)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx10_2_cvtph2iubsv8hf_mask, "__builtin_ia32_cvtph2iubs128_mask", IX86_BUILTIN_CVTPH2IUBS128_MASK, UNKNOWN, (int) V8HI_FTYPE_V8HF_V8HI_UQI)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx10_2_cvtps2ibsv4sf_mask, "__builtin_ia32_cvtps2ibs128_mask", IX86_BUILTIN_CVTPS2IBS128_MASK, UNKNOWN, (int) V4SI_FTYPE_V4SF_V4SI_UQI)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx10_2_cvtps2iubsv4sf_mask, "__builtin_ia32_cvtps2iubs128_mask", IX86_BUILTIN_CVTPS2IUBS128_MASK, UNKNOWN, (int) V4SI_FTYPE_V4SF_V4SI_UQI)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx10_2_cvttnebf162ibsv8bf_mask, "__builtin_ia32_cvttnebf162ibs128_mask", IX86_BUILTIN_CVTTNEBF162IBS128_MASK, UNKNOWN, (int) V8HI_FTYPE_V8BF_V8HI_UQI)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx10_2_cvttnebf162ibsv16bf_mask, "__builtin_ia32_cvttnebf162ibs256_mask", IX86_BUILTIN_CVTTNEBF162IBS256_MASK, UNKNOWN, (int) V16HI_FTYPE_V16BF_V16HI_UHI)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_512, CODE_FOR_avx10_2_cvttnebf162ibsv32bf_mask, "__builtin_ia32_cvttnebf162ibs512_mask", IX86_BUILTIN_CVTTNEBF162IBS512_MASK, UNKNOWN, (int) V32HI_FTYPE_V32BF_V32HI_USI)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx10_2_cvttnebf162iubsv8bf_mask, "__builtin_ia32_cvttnebf162iubs128_mask", IX86_BUILTIN_CVTTNEBF162IUBS128_MASK, UNKNOWN, (int) V8HI_FTYPE_V8BF_V8HI_UQI)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx10_2_cvttnebf162iubsv16bf_mask, "__builtin_ia32_cvttnebf162iubs256_mask", IX86_BUILTIN_CVTTNEBF162IUBS256_MASK, UNKNOWN, (int) V16HI_FTYPE_V16BF_V16HI_UHI)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_512, CODE_FOR_avx10_2_cvttnebf162iubsv32bf_mask, "__builtin_ia32_cvttnebf162iubs512_mask", IX86_BUILTIN_CVTTNEBF162IUBS512_MASK, UNKNOWN, (int) V32HI_FTYPE_V32BF_V32HI_USI)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx10_2_cvttph2ibsv8hf_mask, "__builtin_ia32_cvttph2ibs128_mask", IX86_BUILTIN_CVTTPH2IBS128_MASK, UNKNOWN, (int) V8HI_FTYPE_V8HF_V8HI_UQI)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx10_2_cvttph2iubsv8hf_mask, "__builtin_ia32_cvttph2iubs128_mask", IX86_BUILTIN_CVTTPH2IUBS128_MASK, UNKNOWN, (int) V8HI_FTYPE_V8HF_V8HI_UQI)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx10_2_cvttps2ibsv4sf_mask, "__builtin_ia32_cvttps2ibs128_mask", IX86_BUILTIN_CVTTPS2IBS128_MASK, UNKNOWN, (int) V4SI_FTYPE_V4SF_V4SI_UQI)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx10_2_cvttps2iubsv4sf_mask, "__builtin_ia32_cvttps2iubs128_mask", IX86_BUILTIN_CVTTPS2IUBS128_MASK, UNKNOWN, (int) V4SI_FTYPE_V4SF_V4SI_UQI)
/* Builtins with rounding support. */
BDESC_END (ARGS, ROUND_ARGS)
@@ -3730,6 +3750,22 @@ BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_subv16hf3_mask_round, "__builti
BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_subv8sf3_mask_round, "__builtin_ia32_subps256_mask_round", IX86_BUILTIN_VSUBPS256_MASK_ROUND, UNKNOWN, (int) V8SF_FTYPE_V8SF_V8SF_V8SF_UQI_INT)
BDESC (0, OPTION_MASK_ISA2_AVX10_2_512, CODE_FOR_avx10_2_cvt2ps2phx_v32hf_mask_round, "__builtin_ia32_vcvt2ps2phx512_mask_round", IX86_BUILTIN_VCVT2PS2PHX_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V16SF_V16SF_V32HF_USI_INT)
BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx10_2_cvt2ps2phx_v16hf_mask_round, "__builtin_ia32_vcvt2ps2phx256_mask_round", IX86_BUILTIN_VCVT2PS2PHX_V16HF_MASK_ROUND, UNKNOWN, (int) V16HF_FTYPE_V8SF_V8SF_V16HF_UHI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx10_2_cvtph2ibsv16hf_mask_round, "__builtin_ia32_cvtph2ibs256_mask_round", IX86_BUILTIN_CVTPH2IBS256_MASK_ROUND, UNKNOWN, (int) V16HI_FTYPE_V16HF_V16HI_UHI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_512, CODE_FOR_avx10_2_cvtph2ibsv32hf_mask_round, "__builtin_ia32_cvtph2ibs512_mask_round", IX86_BUILTIN_CVTPH2IBS512_MASK_ROUND, UNKNOWN, (int) V32HI_FTYPE_V32HF_V32HI_USI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx10_2_cvtph2iubsv16hf_mask_round, "__builtin_ia32_cvtph2iubs256_mask_round", IX86_BUILTIN_CVTPH2IUBS256_MASK_ROUND, UNKNOWN, (int) V16HI_FTYPE_V16HF_V16HI_UHI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_512, CODE_FOR_avx10_2_cvtph2iubsv32hf_mask_round, "__builtin_ia32_cvtph2iubs512_mask_round", IX86_BUILTIN_CVTPH2IUBS512_MASK_ROUND, UNKNOWN, (int) V32HI_FTYPE_V32HF_V32HI_USI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx10_2_cvtps2ibsv8sf_mask_round, "__builtin_ia32_cvtps2ibs256_mask_round", IX86_BUILTIN_CVTPS2IBS256_MASK_ROUND, UNKNOWN, (int) V8SI_FTYPE_V8SF_V8SI_UQI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_512, CODE_FOR_avx10_2_cvtps2ibsv16sf_mask_round, "__builtin_ia32_cvtps2ibs512_mask_round", IX86_BUILTIN_CVTPS2IBS512_MASK_ROUND, UNKNOWN, (int) V16SI_FTYPE_V16SF_V16SI_UHI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx10_2_cvtps2iubsv8sf_mask_round, "__builtin_ia32_cvtps2iubs256_mask_round", IX86_BUILTIN_CVTPS2IUBS256_MASK_ROUND, UNKNOWN, (int) V8SI_FTYPE_V8SF_V8SI_UQI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_512, CODE_FOR_avx10_2_cvtps2iubsv16sf_mask_round, "__builtin_ia32_cvtps2iubs512_mask_round", IX86_BUILTIN_CVTPS2IUBS512_MASK_ROUND, UNKNOWN, (int) V16SI_FTYPE_V16SF_V16SI_UHI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx10_2_cvttph2ibsv16hf_mask_round, "__builtin_ia32_cvttph2ibs256_mask_round", IX86_BUILTIN_CVTTPH2IBS256_MASK_ROUND, UNKNOWN, (int) V16HI_FTYPE_V16HF_V16HI_UHI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_512, CODE_FOR_avx10_2_cvttph2ibsv32hf_mask_round, "__builtin_ia32_cvttph2ibs512_mask_round", IX86_BUILTIN_CVTTPH2IBS512_MASK_ROUND, UNKNOWN, (int) V32HI_FTYPE_V32HF_V32HI_USI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx10_2_cvttph2iubsv16hf_mask_round, "__builtin_ia32_cvttph2iubs256_mask_round", IX86_BUILTIN_CVTTPH2IUBS256_MASK_ROUND, UNKNOWN, (int) V16HI_FTYPE_V16HF_V16HI_UHI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_512, CODE_FOR_avx10_2_cvttph2iubsv32hf_mask_round, "__builtin_ia32_cvttph2iubs512_mask_round", IX86_BUILTIN_CVTTPH2IUBS512_MASK_ROUND, UNKNOWN, (int) V32HI_FTYPE_V32HF_V32HI_USI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx10_2_cvttps2ibsv8sf_mask_round, "__builtin_ia32_cvttps2ibs256_mask_round", IX86_BUILTIN_CVTTPS2IBS256_MASK_ROUND, UNKNOWN, (int) V8SI_FTYPE_V8SF_V8SI_UQI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_512, CODE_FOR_avx10_2_cvttps2ibsv16sf_mask_round, "__builtin_ia32_cvttps2ibs512_mask_round", IX86_BUILTIN_CVTTPS2IBS512_MASK_ROUND, UNKNOWN, (int) V16SI_FTYPE_V16SF_V16SI_UHI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx10_2_cvttps2iubsv8sf_mask_round, "__builtin_ia32_cvttps2iubs256_mask_round", IX86_BUILTIN_CVTTPS2IUBS256_MASK_ROUND, UNKNOWN, (int) V8SI_FTYPE_V8SF_V8SI_UQI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_512, CODE_FOR_avx10_2_cvttps2iubsv16sf_mask_round, "__builtin_ia32_cvttps2iubs512_mask_round", IX86_BUILTIN_CVTTPS2IUBS512_MASK_ROUND, UNKNOWN, (int) V16SI_FTYPE_V16SF_V16SI_UHI_INT)
BDESC_END (ROUND_ARGS, MULTI_ARG)
@@ -11496,10 +11496,13 @@ ix86_expand_args_builtin (const struct builtin_description *d,
case V16QI_FTYPE_V16QI_V16QI_UHI:
case V16QI_FTYPE_QI_V16QI_UHI:
case V32HI_FTYPE_V8HI_V32HI_USI:
+ case V32HI_FTYPE_V32BF_V32HI_USI:
case V32HI_FTYPE_HI_V32HI_USI:
case V16HI_FTYPE_V8HI_V16HI_UHI:
+ case V16HI_FTYPE_V16BF_V16HI_UHI:
case V16HI_FTYPE_HI_V16HI_UHI:
case V8HI_FTYPE_V8HI_V8HI_UQI:
+ case V8HI_FTYPE_V8BF_V8HI_UQI:
case V8BF_FTYPE_V8BF_V8BF_UQI:
case V8HI_FTYPE_HI_V8HI_UQI:
case V16HF_FTYPE_V16HF_V16HF_UHI:
@@ -12484,6 +12487,7 @@ ix86_expand_round_builtin (const struct builtin_description *d,
case V8SF_FTYPE_V8DF_V8SF_QI_INT:
case V8DF_FTYPE_V8DF_V8DF_QI_INT:
case V32HI_FTYPE_V32HF_V32HI_USI_INT:
+ case V32HI_FTYPE_V32BF_V32HI_USI_INT:
case V8SI_FTYPE_V8DF_V8SI_QI_INT:
case V8DI_FTYPE_V8HF_V8DI_UQI_INT:
case V8DI_FTYPE_V8DF_V8DI_QI_INT:
@@ -12498,6 +12502,7 @@ ix86_expand_round_builtin (const struct builtin_description *d,
case V8DI_FTYPE_V8SF_V8DI_QI_INT:
case V16SF_FTYPE_V16SI_V16SF_HI_INT:
case V16SI_FTYPE_V16SF_V16SI_HI_INT:
+ case V16SI_FTYPE_V16SF_V16SI_UHI_INT:
case V16SI_FTYPE_V16HF_V16SI_UHI_INT:
case V16HF_FTYPE_V16HF_V16HF_V16HF_INT:
case V16HF_FTYPE_V16SI_V16HF_UHI_INT:
@@ -12530,6 +12535,7 @@ ix86_expand_round_builtin (const struct builtin_description *d,
case V16HF_FTYPE_V16SF_V16HF_UHI_INT:
case V16HF_FTYPE_V16HF_V16HF_UHI_INT:
case V16HF_FTYPE_V16HI_V16HF_UHI_INT:
+ case V16HI_FTYPE_V16BF_V16HI_UHI_INT:
case V8HF_FTYPE_V8HF_V8HF_V8HF_INT:
nargs = 4;
break;
@@ -152,4 +152,7 @@
#include <avx10_2-512bf16intrin.h>
+#include <avx10_2satcvtintrin.h>
+
+#include <avx10_2-512satcvtintrin.h>
#endif /* _IMMINTRIN_H_INCLUDED */
@@ -235,6 +235,18 @@
UNSPEC_VGETMANTPBF16
UNSPEC_VFPCLASSPBF16
UNSPEC_VCOMSBF16
+ UNSPEC_VCVTNEBF162IBS
+ UNSPEC_VCVTNEBF162IUBS
+ UNSPEC_VCVTPH2IBS
+ UNSPEC_VCVTPH2IUBS
+ UNSPEC_VCVTPS2IBS
+ UNSPEC_VCVTPS2IUBS
+ UNSPEC_VCVTTNEBF162IBS
+ UNSPEC_VCVTTNEBF162IUBS
+ UNSPEC_VCVTTPH2IBS
+ UNSPEC_VCVTTPH2IUBS
+ UNSPEC_VCVTTPS2IBS
+ UNSPEC_VCVTTPS2IUBS
])
(define_c_enum "unspecv" [
@@ -32197,3 +32209,101 @@
"TARGET_AVX10_2_256"
"vcomsbf16\t{%1, %0|%0, %1}"
[(set_attr "prefix" "evex")])
+
+(define_int_iterator UNSPEC_CVTNE_BF16_IBS_ITER
+ [UNSPEC_VCVTNEBF162IBS
+ UNSPEC_VCVTNEBF162IUBS
+ UNSPEC_VCVTTNEBF162IBS
+ UNSPEC_VCVTTNEBF162IUBS])
+
+(define_int_attr sat_cvt_sign_prefix
+ [(UNSPEC_VCVTNEBF162IBS "")
+ (UNSPEC_VCVTNEBF162IUBS "u")
+ (UNSPEC_VCVTTNEBF162IBS "")
+ (UNSPEC_VCVTTNEBF162IUBS "u")
+ (UNSPEC_VCVTPH2IBS "")
+ (UNSPEC_VCVTPH2IUBS "u")
+ (UNSPEC_VCVTTPH2IBS "")
+ (UNSPEC_VCVTTPH2IUBS "u")
+ (UNSPEC_VCVTPS2IBS "")
+ (UNSPEC_VCVTPS2IUBS "u")
+ (UNSPEC_VCVTTPS2IBS "")
+ (UNSPEC_VCVTTPS2IUBS "u")])
+
+
+(define_int_attr sat_cvt_trunc_prefix
+ [(UNSPEC_VCVTNEBF162IBS "")
+ (UNSPEC_VCVTNEBF162IUBS "")
+ (UNSPEC_VCVTTNEBF162IBS "t")
+ (UNSPEC_VCVTTNEBF162IUBS "t")])
+
+(define_insn "avx10_2_cvt<sat_cvt_trunc_prefix>nebf162i<sat_cvt_sign_prefix>bs<mode><mask_name>"
+ [(set (match_operand:<sseintvecmode> 0 "register_operand" "=v")
+ (unspec:<sseintvecmode>
+ [(match_operand:VBF_AVX10_2 1 "vector_operand" "vm")]
+ UNSPEC_CVTNE_BF16_IBS_ITER))]
+ "TARGET_AVX10_2_256"
+ "vcvt<sat_cvt_trunc_prefix>nebf162i<sat_cvt_sign_prefix>bs\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
+ [(set_attr "type" "ssecvt")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "<sseinsnmode>")])
+
+(define_int_iterator UNSPEC_CVT_PH_IBS_ITER
+ [UNSPEC_VCVTPH2IBS
+ UNSPEC_VCVTPH2IUBS])
+
+(define_insn "avx10_2_cvtph2i<sat_cvt_sign_prefix>bs<mode><mask_name><round_name>"
+ [(set (match_operand:<sseintvecmode> 0 "register_operand" "=v")
+ (unspec:<sseintvecmode>
+ [(match_operand:VHF_AVX10_2 1 "<round_nimm_predicate>" "<round_constraint>")]
+ UNSPEC_CVT_PH_IBS_ITER))]
+ "TARGET_AVX10_2_256 && <round_mode_condition>"
+ "vcvtph2i<sat_cvt_sign_prefix>bs\t{<round_mask_op2>%1, %0<mask_operand2>|%0<mask_operand2>, %1<round_mask_op2>}"
+ [(set_attr "type" "ssecvt")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "<sseinsnmode>")])
+
+(define_int_iterator UNSPEC_CVTT_PH_IBS_ITER
+ [UNSPEC_VCVTTPH2IBS
+ UNSPEC_VCVTTPH2IUBS])
+
+(define_insn "avx10_2_cvttph2i<sat_cvt_sign_prefix>bs<mode><mask_name><round_saeonly_name>"
+ [(set (match_operand:<sseintvecmode> 0 "register_operand" "=v")
+ (unspec:<sseintvecmode>
+ [(match_operand:VHF_AVX10_2 1 "<round_saeonly_nimm_predicate>" "<round_saeonly_constraint>")]
+ UNSPEC_CVTT_PH_IBS_ITER))]
+ "TARGET_AVX10_2_256 && <round_saeonly_mode_condition>"
+ "vcvttph2i<sat_cvt_sign_prefix>bs\t{<round_saeonly_mask_op2>%1, %0<mask_operand2>|%0<mask_operand2>, %1<round_saeonly_mask_op2>}"
+ [(set_attr "type" "ssecvt")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "<sseinsnmode>")])
+
+(define_int_iterator UNSPEC_CVT_PS_IBS_ITER
+ [UNSPEC_VCVTPS2IBS
+ UNSPEC_VCVTPS2IUBS])
+
+(define_insn "avx10_2_cvtps2i<sat_cvt_sign_prefix>bs<mode><mask_name><round_name>"
+ [(set (match_operand:<sseintvecmode> 0 "register_operand" "=v")
+ (unspec:<sseintvecmode>
+ [(match_operand:VF1_AVX10_2 1 "<round_nimm_predicate>" "<round_constraint>")]
+ UNSPEC_CVT_PS_IBS_ITER))]
+ "TARGET_AVX10_2_256 && <round_mode_condition>"
+ "vcvtps2i<sat_cvt_sign_prefix>bs\t{<round_mask_op2>%1, %0<mask_operand2>|%0<mask_operand2>, %1<round_mask_op2>}"
+ [(set_attr "type" "ssecvt")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "<sseinsnmode>")])
+
+(define_int_iterator UNSPEC_CVTT_PS_IBS_ITER
+ [UNSPEC_VCVTTPS2IBS
+ UNSPEC_VCVTTPS2IUBS])
+
+(define_insn "avx10_2_cvttps2i<sat_cvt_sign_prefix>bs<mode><mask_name><round_saeonly_name>"
+ [(set (match_operand:<sseintvecmode> 0 "register_operand" "=v")
+ (unspec:<sseintvecmode>
+ [(match_operand:VF1_AVX10_2 1 "<round_saeonly_nimm_predicate>" "<round_saeonly_constraint>")]
+ UNSPEC_CVTT_PS_IBS_ITER))]
+ "TARGET_AVX10_2_256 && <round_saeonly_mode_condition>"
+ "vcvttps2i<sat_cvt_sign_prefix>bs\t{<round_saeonly_mask_op2>%1, %0<mask_operand2>|%0<mask_operand2>, %1<round_saeonly_mask_op2>}"
+ [(set_attr "type" "ssecvt")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "<sseinsnmode>")])
@@ -1035,6 +1035,26 @@
#define __builtin_ia32_cmppbf16256_mask(A, B, C, D) __builtin_ia32_cmppbf16256_mask(A, B, 1, D)
#define __builtin_ia32_cmppbf16128_mask(A, B, C, D) __builtin_ia32_cmppbf16128_mask(A, B, 1, D)
+/* avx10_2-512satcvtintrin.h */
+#define __builtin_ia32_cvtph2ibs512_mask_round(A, B, C, D) __builtin_ia32_cvtph2ibs512_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvtph2iubs512_mask_round(A, B, C, D) __builtin_ia32_cvtph2iubs512_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvtps2ibs512_mask_round(A, B, C, D) __builtin_ia32_cvtps2ibs512_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvtps2iubs512_mask_round(A, B, C, D) __builtin_ia32_cvtps2iubs512_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvttph2ibs512_mask_round(A, B, C, D) __builtin_ia32_cvttph2ibs512_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvttph2iubs512_mask_round(A, B, C, D) __builtin_ia32_cvttph2iubs512_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvttps2ibs512_mask_round(A, B, C, D) __builtin_ia32_cvttps2ibs512_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvttps2iubs512_mask_round(A, B, C, D) __builtin_ia32_cvttps2iubs512_mask_round(A, B, C, 8)
+
+/* avx10_2satcvtintrin.h */
+#define __builtin_ia32_cvtph2ibs256_mask_round(A, B, C, D) __builtin_ia32_cvtph2ibs256_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvtph2iubs256_mask_round(A, B, C, D) __builtin_ia32_cvtph2iubs256_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvtps2ibs256_mask_round(A, B, C, D) __builtin_ia32_cvtps2ibs256_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvtps2iubs256_mask_round(A, B, C, D) __builtin_ia32_cvtps2iubs256_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvttph2ibs256_mask_round(A, B, C, D) __builtin_ia32_cvttph2ibs256_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvttph2iubs256_mask_round(A, B, C, D) __builtin_ia32_cvttph2iubs256_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvttps2ibs256_mask_round(A, B, C, D) __builtin_ia32_cvttps2ibs256_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvttps2iubs256_mask_round(A, B, C, D) __builtin_ia32_cvttps2iubs256_mask_round(A, B, C, 8)
+
#include <wmmintrin.h>
#include <immintrin.h>
#include <mm3dnow.h>
new file mode 100644
@@ -0,0 +1,100 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mavx10.2 -mavx10.2-512" } */
+/* { dg-final { scan-assembler-times "vcvtph2ibs\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtph2ibs\[ \\t\]+\{rn-sae\}\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtph2ibs\[ \\t\]+\{rz-sae\}\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtph2iubs\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtph2iubs\[ \\t\]+\{rn-sae\}\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtph2iubs\[ \\t\]+\{rz-sae\}\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttph2ibs\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttph2ibs\[ \\t\]+\{sae\}\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttph2ibs\[ \\t\]+\{sae\}\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttph2iubs\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttph2iubs\[ \\t\]+\{sae\}\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttph2iubs\[ \\t\]+\{sae\}\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtps2ibs\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtps2ibs\[ \\t\]+\{rn-sae\}\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtps2ibs\[ \\t\]+\{rz-sae\}\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtps2iubs\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtps2iubs\[ \\t\]+\{rn-sae\}\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtps2iubs\[ \\t\]+\{rz-sae\}\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttps2ibs\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttps2ibs\[ \\t\]+\{sae\}\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttps2ibs\[ \\t\]+\{sae\}\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttps2iubs\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttps2iubs\[ \\t\]+\{sae\}\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttps2iubs\[ \\t\]+\{sae\}\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtnebf162ibs\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtnebf162ibs\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtnebf162ibs\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtnebf162iubs\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtnebf162iubs\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtnebf162iubs\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttnebf162ibs\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttnebf162ibs\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttnebf162ibs\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttnebf162iubs\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttnebf162iubs\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttnebf162iubs\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+
+#include <immintrin.h>
+
+volatile __m512 x;
+volatile __m512h xh;
+volatile __m512i xi;
+volatile __m512bh xbh;
+volatile __mmask8 m8;
+volatile __mmask16 m16;
+volatile __mmask32 m32;
+
+void extern
+avx10_2_test (void)
+{
+ xi = _mm512_ipcvt_roundph_epi16 (xh, 4);
+ xi = _mm512_mask_ipcvt_roundph_epi16 (xi, m32, xh, 8);
+ xi = _mm512_maskz_ipcvt_roundph_epi16 (m32, xh, 11);
+
+ xi = _mm512_ipcvt_roundph_epu16 (xh, 4);
+ xi = _mm512_mask_ipcvt_roundph_epu16 (xi, m32, xh, 8);
+ xi = _mm512_maskz_ipcvt_roundph_epu16 (m32, xh, 11);
+
+ xi = _mm512_ipcvtt_roundph_epi16 (xh, 4);
+ xi = _mm512_mask_ipcvtt_roundph_epi16 (xi, m32, xh, 8);
+ xi = _mm512_maskz_ipcvtt_roundph_epi16 (m32, xh, 8);
+
+ xi = _mm512_ipcvtt_roundph_epu16 (xh, 4);
+ xi = _mm512_mask_ipcvtt_roundph_epu16 (xi, m32, xh, 8);
+ xi = _mm512_maskz_ipcvtt_roundph_epu16 (m32, xh, 8);
+
+ xi = _mm512_ipcvt_roundps_epi32 (x, 4);
+ xi = _mm512_mask_ipcvt_roundps_epi32 (xi, m16, x, 8);
+ xi = _mm512_maskz_ipcvt_roundps_epi32 (m16, x, 11);
+
+ xi = _mm512_ipcvt_roundps_epu32 (x, 4);
+ xi = _mm512_mask_ipcvt_roundps_epu32 (xi, m16, x, 8);
+ xi = _mm512_maskz_ipcvt_roundps_epu32 (m16, x, 11);
+
+ xi = _mm512_ipcvtt_roundps_epi32 (x, 4);
+ xi = _mm512_mask_ipcvtt_roundps_epi32 (xi, m16, x, 8);
+ xi = _mm512_maskz_ipcvtt_roundps_epi32 (m16, x, 8);
+
+ xi = _mm512_ipcvtt_roundps_epu32 (x, 4);
+ xi = _mm512_mask_ipcvtt_roundps_epu32 (xi, m16, x, 8);
+ xi = _mm512_maskz_ipcvtt_roundps_epu32 (m16, x, 8);
+
+ xi = _mm512_ipcvtnebf16_epi16 (xbh);
+ xi = _mm512_mask_ipcvtnebf16_epi16 (xi, m32, xbh);
+ xi = _mm512_maskz_ipcvtnebf16_epi16 (m32, xbh);
+
+ xi = _mm512_ipcvtnebf16_epu16 (xbh);
+ xi = _mm512_mask_ipcvtnebf16_epu16 (xi, m32, xbh);
+ xi = _mm512_maskz_ipcvtnebf16_epu16 (m32, xbh);
+
+ xi = _mm512_ipcvttnebf16_epi16 (xbh);
+ xi = _mm512_mask_ipcvttnebf16_epi16 (xi, m32, xbh);
+ xi = _mm512_maskz_ipcvttnebf16_epi16 (m32, xbh);
+
+ xi = _mm512_ipcvttnebf16_epu16 (xbh);
+ xi = _mm512_mask_ipcvttnebf16_epu16 (xi, m32, xbh);
+ xi = _mm512_maskz_ipcvttnebf16_epu16 (m32, xbh);
+}
new file mode 100644
@@ -0,0 +1,69 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx10.2-512" } */
+/* { dg-require-effective-target avx10_2_512 } */
+
+#ifndef AVX10_2
+#define AVX10_2
+#define AVX10_2_512
+#define AVX10_512BIT
+#endif
+#include "avx10-helper.h"
+#include <math.h>
+#include <limits.h>
+
+#define SRC_SIZE ((AVX512F_LEN) / 16)
+#define DST_SIZE ((AVX512F_LEN) / 16)
+
+static void
+CALC (__bf16 *s, short *r)
+{
+ int i;
+ unsigned char tmp;
+
+ for (i = 0; i < SRC_SIZE; i++)
+ {
+ if (s[i] > SCHAR_MAX)
+ tmp = SCHAR_MAX;
+ else if (s[i] < SCHAR_MIN)
+ tmp = SCHAR_MIN;
+ else
+ tmp = nearbyint(_mm_cvtsbh_ss(s[i]));
+ r[i] = (unsigned short)tmp;
+ }
+}
+
+void
+TEST (void)
+{
+ UNION_TYPE (AVX512F_LEN, bf16_bf) s;
+ UNION_TYPE (AVX512F_LEN, i_w) res1, res2, res3;
+ MASK_TYPE mask = MASK_VALUE;
+ short res_ref[DST_SIZE] = { 0 };
+ int i, sign = 1;
+
+ for (i = 0; i < SRC_SIZE; i++)
+ {
+ s.a[i] = 1.23 * (i + 2) * sign;
+ sign = -sign;
+ }
+
+ for (i = 0; i < DST_SIZE; i++)
+ res2.a[i] = DEFAULT_VALUE;
+
+ res1.x = INTRINSIC (_ipcvtnebf16_epi16) (s.x);
+ res2.x = INTRINSIC (_mask_ipcvtnebf16_epi16) (res2.x, mask, s.x);
+ res3.x = INTRINSIC (_maskz_ipcvtnebf16_epi16) (mask, s.x);
+
+ CALC (s.a, res_ref);
+
+ if (UNION_CHECK (AVX512F_LEN, i_w) (res1, res_ref))
+ abort ();
+
+ MASK_MERGE (i_w) (res_ref, mask, SRC_SIZE);
+ if (UNION_CHECK (AVX512F_LEN, i_w) (res2, res_ref))
+ abort ();
+
+ MASK_ZERO (i_w) (res_ref, mask, SRC_SIZE);
+ if (UNION_CHECK (AVX512F_LEN, i_w) (res3, res_ref))
+ abort ();
+}
new file mode 100644
@@ -0,0 +1,69 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx10.2-512" } */
+/* { dg-require-effective-target avx10_2_512 } */
+
+#ifndef AVX10_2
+#define AVX10_2
+#define AVX10_2_512
+#define AVX10_512BIT
+#endif
+#include "avx10-helper.h"
+#include <math.h>
+#include <limits.h>
+
+#define SRC_SIZE ((AVX512F_LEN) / 16)
+#define DST_SIZE ((AVX512F_LEN) / 16)
+
+static void
+CALC (__bf16 *s, unsigned short *r)
+{
+ int i;
+ unsigned char tmp;
+
+ for (i = 0; i < SRC_SIZE; i++)
+ {
+ if (s[i] > UCHAR_MAX)
+ tmp = UCHAR_MAX;
+ else if (s[i] < 0)
+ tmp = 0;
+ else
+ tmp = nearbyint(_mm_cvtsbh_ss(s[i]));
+ r[i] = (unsigned short)tmp;
+ }
+}
+
+void
+TEST (void)
+{
+ UNION_TYPE (AVX512F_LEN, bf16_bf) s;
+ UNION_TYPE (AVX512F_LEN, i_uw) res1, res2, res3;
+ MASK_TYPE mask = MASK_VALUE;
+ unsigned short res_ref[DST_SIZE] = { 0 };
+ int i, sign = 1;
+
+ for (i = 0; i < SRC_SIZE; i++)
+ {
+ s.a[i] = 1.23 * (i + 2) * sign;
+ sign = -sign;
+ }
+
+ for (i = 0; i < DST_SIZE; i++)
+ res2.a[i] = DEFAULT_VALUE;
+
+ res1.x = INTRINSIC (_ipcvtnebf16_epu16) (s.x);
+ res2.x = INTRINSIC (_mask_ipcvtnebf16_epu16) (res2.x, mask, s.x);
+ res3.x = INTRINSIC (_maskz_ipcvtnebf16_epu16) (mask, s.x);
+
+ CALC (s.a, res_ref);
+
+ if (UNION_CHECK (AVX512F_LEN, i_uw) (res1, res_ref))
+ abort ();
+
+ MASK_MERGE (i_uw) (res_ref, mask, SRC_SIZE);
+ if (UNION_CHECK (AVX512F_LEN, i_uw) (res2, res_ref))
+ abort ();
+
+ MASK_ZERO (i_uw) (res_ref, mask, SRC_SIZE);
+ if (UNION_CHECK (AVX512F_LEN, i_uw) (res3, res_ref))
+ abort ();
+}
new file mode 100644
@@ -0,0 +1,74 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx10.2-512" } */
+/* { dg-require-effective-target avx10_2_512 } */
+
+#ifndef AVX10_2
+#define AVX10_2
+#define AVX10_2_512
+#define AVX10_512BIT
+#endif
+#include "avx10-helper.h"
+#include <limits.h>
+
+#define SRC_SIZE ((AVX512F_LEN) / 16)
+#define DST_SIZE ((AVX512F_LEN) / 16)
+
+static void
+CALC (_Float16 *s, short *r)
+{
+ int i;
+ unsigned char tmp;
+
+ for (i = 0; i < SRC_SIZE; i++)
+ {
+ if (s[i] > SCHAR_MAX)
+ tmp = SCHAR_MAX;
+ else if (s[i] < SCHAR_MIN)
+ tmp = SCHAR_MIN;
+ else
+ tmp = __builtin_nearbyintf16(s[i]);
+ r[i] = (unsigned short) tmp;
+ }
+}
+
+void
+TEST (void)
+{
+ UNION_TYPE (AVX512F_LEN, h) s;
+ UNION_TYPE (AVX512F_LEN, i_w) res1, res2, res3;
+ MASK_TYPE mask = MASK_VALUE;
+ short res_ref[DST_SIZE] = { 0 };
+ int i, sign = 1;
+
+ for (i = 0; i < SRC_SIZE; i++)
+ {
+ s.a[i] = 1.23 * (i + 2) * sign;
+ sign = -sign;
+ }
+
+ for (i = 0; i < DST_SIZE; i++)
+ res2.a[i] = DEFAULT_VALUE;
+
+#if AVX512F_LEN == 128
+ res1.x = INTRINSIC (_ipcvtph_epi16) (s.x);
+ res2.x = INTRINSIC (_mask_ipcvtph_epi16) (res2.x, mask, s.x);
+ res3.x = INTRINSIC (_maskz_ipcvtph_epi16) (mask, s.x);
+#else
+ res1.x = INTRINSIC (_ipcvt_roundph_epi16) (s.x, 8);
+ res2.x = INTRINSIC (_mask_ipcvt_roundph_epi16) (res2.x, mask, s.x, 8);
+ res3.x = INTRINSIC (_maskz_ipcvt_roundph_epi16) (mask, s.x, 8);
+#endif
+
+ CALC (s.a, res_ref);
+
+ if (UNION_CHECK (AVX512F_LEN, i_w) (res1, res_ref))
+ abort ();
+
+ MASK_MERGE (i_w) (res_ref, mask, SRC_SIZE);
+ if (UNION_CHECK (AVX512F_LEN, i_w) (res2, res_ref))
+ abort ();
+
+ MASK_ZERO (i_w) (res_ref, mask, SRC_SIZE);
+ if (UNION_CHECK (AVX512F_LEN, i_w) (res3, res_ref))
+ abort ();
+}
new file mode 100644
@@ -0,0 +1,74 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx10.2-512" } */
+/* { dg-require-effective-target avx10_2_512 } */
+
+#ifndef AVX10_2
+#define AVX10_2
+#define AVX10_2_512
+#define AVX10_512BIT
+#endif
+#include "avx10-helper.h"
+#include <limits.h>
+
+#define SRC_SIZE ((AVX512F_LEN) / 16)
+#define DST_SIZE ((AVX512F_LEN) / 16)
+
+static void
+CALC (_Float16 *s, short *r)
+{
+ int i;
+ unsigned char tmp;
+
+ for (i = 0; i < SRC_SIZE; i++)
+ {
+ if (s[i] > UCHAR_MAX)
+ tmp = UCHAR_MAX;
+ else if (s[i] < 0)
+ tmp = 0;
+ else
+ tmp = __builtin_nearbyintf16(s[i]);
+ r[i] = (unsigned short) tmp;
+ }
+}
+
+void
+TEST (void)
+{
+ UNION_TYPE (AVX512F_LEN, h) s;
+ UNION_TYPE (AVX512F_LEN, i_w) res1, res2, res3;
+ MASK_TYPE mask = MASK_VALUE;
+ short res_ref[DST_SIZE] = { 0 };
+ int i, sign = 1;
+
+ for (i = 0; i < SRC_SIZE; i++)
+ {
+ s.a[i] = 1.23 * (i + 2) * sign;
+ sign = -sign;
+ }
+
+ for (i = 0; i < DST_SIZE; i++)
+ res2.a[i] = DEFAULT_VALUE;
+
+#if AVX512F_LEN == 128
+ res1.x = INTRINSIC (_ipcvtph_epu16) (s.x);
+ res2.x = INTRINSIC (_mask_ipcvtph_epu16) (res2.x, mask, s.x);
+ res3.x = INTRINSIC (_maskz_ipcvtph_epu16) (mask, s.x);
+#else
+ res1.x = INTRINSIC (_ipcvt_roundph_epu16) (s.x, 8);
+ res2.x = INTRINSIC (_mask_ipcvt_roundph_epu16) (res2.x, mask, s.x, 8);
+ res3.x = INTRINSIC (_maskz_ipcvt_roundph_epu16) (mask, s.x, 8);
+#endif
+
+ CALC (s.a, res_ref);
+
+ if (UNION_CHECK (AVX512F_LEN, i_w) (res1, res_ref))
+ abort ();
+
+ MASK_MERGE (i_w) (res_ref, mask, SRC_SIZE);
+ if (UNION_CHECK (AVX512F_LEN, i_w) (res2, res_ref))
+ abort ();
+
+ MASK_ZERO (i_w) (res_ref, mask, SRC_SIZE);
+ if (UNION_CHECK (AVX512F_LEN, i_w) (res3, res_ref))
+ abort ();
+}
new file mode 100644
@@ -0,0 +1,75 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx10.2-512" } */
+/* { dg-require-effective-target avx10_2_512 } */
+
+#ifndef AVX10_2
+#define AVX10_2
+#define AVX10_2_512
+#define AVX10_512BIT
+#endif
+#include "avx10-helper.h"
+#include <limits.h>
+#include <math.h>
+
+#define SRC_SIZE ((AVX512F_LEN) / 32)
+#define DST_SIZE ((AVX512F_LEN) / 32)
+
+static void
+CALC (float *s, int *r)
+{
+ int i;
+ unsigned char tmp;
+
+ for (i = 0; i < SRC_SIZE; i++)
+ {
+ if (s[i] > SCHAR_MAX)
+ tmp = SCHAR_MAX;
+ else if (s[i] < SCHAR_MIN)
+ tmp = SCHAR_MIN;
+ else
+ tmp = nearbyint(s[i]);
+ r[i] = (unsigned int) tmp;
+ }
+}
+
+void
+TEST (void)
+{
+ UNION_TYPE (AVX512F_LEN, ) s;
+ UNION_TYPE (AVX512F_LEN, i_d) res1, res2, res3;
+ MASK_TYPE mask = MASK_VALUE;
+ int res_ref[DST_SIZE] = { 0 };
+ int i, sign = 1;
+
+ for (i = 0; i < SRC_SIZE; i++)
+ {
+ s.a[i] = 1.23 * (i + 2) * sign;
+ sign = -sign;
+ }
+
+ for (i = 0; i < DST_SIZE; i++)
+ res2.a[i] = DEFAULT_VALUE;
+
+#if AVX512F_LEN == 128
+ res1.x = INTRINSIC (_ipcvtps_epi32) (s.x);
+ res2.x = INTRINSIC (_mask_ipcvtps_epi32) (res2.x, mask, s.x);
+ res3.x = INTRINSIC (_maskz_ipcvtps_epi32) (mask, s.x);
+#else
+ res1.x = INTRINSIC (_ipcvt_roundps_epi32) (s.x, 8);
+ res2.x = INTRINSIC (_mask_ipcvt_roundps_epi32) (res2.x, mask, s.x, 8);
+ res3.x = INTRINSIC (_maskz_ipcvt_roundps_epi32) (mask, s.x, 8);
+#endif
+
+ CALC (s.a, res_ref);
+
+ if (UNION_CHECK (AVX512F_LEN, i_d) (res1, res_ref))
+ abort ();
+
+ MASK_MERGE (i_d) (res_ref, mask, SRC_SIZE);
+ if (UNION_CHECK (AVX512F_LEN, i_d) (res2, res_ref))
+ abort ();
+
+ MASK_ZERO (i_d) (res_ref, mask, SRC_SIZE);
+ if (UNION_CHECK (AVX512F_LEN, i_d) (res3, res_ref))
+ abort ();
+}
new file mode 100644
@@ -0,0 +1,73 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx10.2-512" } */
+/* { dg-require-effective-target avx10_2_512 } */
+
+#ifndef AVX10_2
+#define AVX10_2
+#define AVX10_2_512
+#define AVX10_512BIT
+#endif
+#include "avx10-helper.h"
+#include <limits.h>
+#include <math.h>
+
+#define SRC_SIZE ((AVX512F_LEN) / 32)
+#define DST_SIZE ((AVX512F_LEN) / 32)
+
+static void
+CALC (float *s, int *r)
+{
+ int i;
+
+ for (i = 0; i < SRC_SIZE; i++)
+ {
+ if (s[i] > UCHAR_MAX)
+ r[i] = UCHAR_MAX;
+ else if (s[i] < 0)
+ r[i] = 0;
+ else
+ r[i] = nearbyint(s[i]);
+ }
+}
+
+void
+TEST (void)
+{
+ UNION_TYPE (AVX512F_LEN, ) s;
+ UNION_TYPE (AVX512F_LEN, i_d) res1, res2, res3;
+ MASK_TYPE mask = MASK_VALUE;
+ int res_ref[DST_SIZE] = { 0 };
+ int i, sign = 1;
+
+ for (i = 0; i < SRC_SIZE; i++)
+ {
+ s.a[i] = 1.23 * (i + 2) * sign;
+ sign = -sign;
+ }
+
+ for (i = 0; i < DST_SIZE; i++)
+ res2.a[i] = DEFAULT_VALUE;
+
+#if AVX512F_LEN == 128
+ res1.x = INTRINSIC (_ipcvtps_epu32) (s.x);
+ res2.x = INTRINSIC (_mask_ipcvtps_epu32) (res2.x, mask, s.x);
+ res3.x = INTRINSIC (_maskz_ipcvtps_epu32) (mask, s.x);
+#else
+ res1.x = INTRINSIC (_ipcvt_roundps_epu32) (s.x, 8);
+ res2.x = INTRINSIC (_mask_ipcvt_roundps_epu32) (res2.x, mask, s.x, 8);
+ res3.x = INTRINSIC (_maskz_ipcvt_roundps_epu32) (mask, s.x, 8);
+#endif
+
+ CALC (s.a, res_ref);
+
+ if (UNION_CHECK (AVX512F_LEN, i_d) (res1, res_ref))
+ abort ();
+
+ MASK_MERGE (i_d) (res_ref, mask, SRC_SIZE);
+ if (UNION_CHECK (AVX512F_LEN, i_d) (res2, res_ref))
+ abort ();
+
+ MASK_ZERO (i_d) (res_ref, mask, SRC_SIZE);
+ if (UNION_CHECK (AVX512F_LEN, i_d) (res3, res_ref))
+ abort ();
+}
new file mode 100644
@@ -0,0 +1,69 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx10.2-512" } */
+/* { dg-require-effective-target avx10_2_512 } */
+
+#ifndef AVX10_2
+#define AVX10_2
+#define AVX10_2_512
+#define AVX10_512BIT
+#endif
+#include "avx10-helper.h"
+#include <math.h>
+#include <limits.h>
+
+#define SRC_SIZE ((AVX512F_LEN) / 16)
+#define DST_SIZE ((AVX512F_LEN) / 16)
+
+static void
+CALC (__bf16 *s, short *r)
+{
+ int i;
+ unsigned char tmp;
+
+ for (i = 0; i < SRC_SIZE; i++)
+ {
+ if (s[i] > SCHAR_MAX)
+ tmp = SCHAR_MAX;
+ else if (s[i] < SCHAR_MIN)
+ tmp = SCHAR_MIN;
+ else
+ tmp = s[i];
+ r[i] = (unsigned short)tmp;
+ }
+}
+
+void
+TEST (void)
+{
+ UNION_TYPE (AVX512F_LEN, bf16_bf) s;
+ UNION_TYPE (AVX512F_LEN, i_w) res1, res2, res3;
+ MASK_TYPE mask = MASK_VALUE;
+ short res_ref[DST_SIZE] = { 0 };
+ int i, sign = 1;
+
+ for (i = 0; i < SRC_SIZE; i++)
+ {
+ s.a[i] = 1.23 * (i + 2) * sign;
+ sign = -sign;
+ }
+
+ for (i = 0; i < DST_SIZE; i++)
+ res2.a[i] = DEFAULT_VALUE;
+
+ res1.x = INTRINSIC (_ipcvttnebf16_epi16) (s.x);
+ res2.x = INTRINSIC (_mask_ipcvttnebf16_epi16) (res2.x, mask, s.x);
+ res3.x = INTRINSIC (_maskz_ipcvttnebf16_epi16) (mask, s.x);
+
+ CALC (s.a, res_ref);
+
+ if (UNION_CHECK (AVX512F_LEN, i_w) (res1, res_ref))
+ abort ();
+
+ MASK_MERGE (i_w) (res_ref, mask, SRC_SIZE);
+ if (UNION_CHECK (AVX512F_LEN, i_w) (res2, res_ref))
+ abort ();
+
+ MASK_ZERO (i_w) (res_ref, mask, SRC_SIZE);
+ if (UNION_CHECK (AVX512F_LEN, i_w) (res3, res_ref))
+ abort ();
+}
new file mode 100644
@@ -0,0 +1,69 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx10.2-512" } */
+/* { dg-require-effective-target avx10_2_512 } */
+
+#ifndef AVX10_2
+#define AVX10_2
+#define AVX10_2_512
+#define AVX10_512BIT
+#endif
+#include "avx10-helper.h"
+#include <math.h>
+#include <limits.h>
+
+#define SRC_SIZE ((AVX512F_LEN) / 16)
+#define DST_SIZE ((AVX512F_LEN) / 16)
+
+static void
+CALC (__bf16 *s, short *r)
+{
+ int i;
+ unsigned char tmp;
+
+ for (i = 0; i < SRC_SIZE; i++)
+ {
+ if (s[i] > UCHAR_MAX)
+ tmp = UCHAR_MAX;
+ else if (s[i] < 0)
+ tmp = 0;
+ else
+ tmp = s[i];
+ r[i] = (unsigned short) tmp;
+ }
+}
+
+void
+TEST (void)
+{
+ UNION_TYPE (AVX512F_LEN, bf16_bf) s;
+ UNION_TYPE (AVX512F_LEN, i_uw) res1, res2, res3;
+ MASK_TYPE mask = MASK_VALUE;
+ unsigned short res_ref[DST_SIZE] = { 0 };
+ int i, sign = 1;
+
+ for (i = 0; i < SRC_SIZE; i++)
+ {
+ s.a[i] = 1.23 * (i + 2) * sign;
+ sign = -sign;
+ }
+
+ for (i = 0; i < DST_SIZE; i++)
+ res2.a[i] = DEFAULT_VALUE;
+
+ res1.x = INTRINSIC (_ipcvttnebf16_epu16) (s.x);
+ res2.x = INTRINSIC (_mask_ipcvttnebf16_epu16) (res2.x, mask, s.x);
+ res3.x = INTRINSIC (_maskz_ipcvttnebf16_epu16) (mask, s.x);
+
+ CALC (s.a, res_ref);
+
+ if (UNION_CHECK (AVX512F_LEN, i_uw) (res1, res_ref))
+ abort ();
+
+ MASK_MERGE (i_uw) (res_ref, mask, SRC_SIZE);
+ if (UNION_CHECK (AVX512F_LEN, i_uw) (res2, res_ref))
+ abort ();
+
+ MASK_ZERO (i_uw) (res_ref, mask, SRC_SIZE);
+ if (UNION_CHECK (AVX512F_LEN, i_uw) (res3, res_ref))
+ abort ();
+}
new file mode 100644
@@ -0,0 +1,74 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx10.2-512" } */
+/* { dg-require-effective-target avx10_2_512 } */
+
+#ifndef AVX10_2
+#define AVX10_2
+#define AVX10_2_512
+#define AVX10_512BIT
+#endif
+#include "avx10-helper.h"
+#include <limits.h>
+
+#define SRC_SIZE ((AVX512F_LEN) / 16)
+#define DST_SIZE ((AVX512F_LEN) / 16)
+
+static void
+CALC (_Float16 *s, short *r)
+{
+ int i;
+ char tmp;
+
+ for (i = 0; i < SRC_SIZE; i++)
+ {
+ if (s[i] > SCHAR_MAX)
+ tmp = SCHAR_MAX;
+ else if (s[i] < SCHAR_MIN)
+ tmp = SCHAR_MIN;
+ else
+ tmp = s[i];
+ r[i] = (unsigned char) tmp;
+ }
+}
+
+void
+TEST (void)
+{
+ UNION_TYPE (AVX512F_LEN, h) s;
+ UNION_TYPE (AVX512F_LEN, i_w) res1, res2, res3;
+ MASK_TYPE mask = MASK_VALUE;
+ short res_ref[DST_SIZE] = { 0 };
+ int i, sign = 1;
+
+ for (i = 0; i < SRC_SIZE; i++)
+ {
+ s.a[i] = 1.23 * (i + 2) * sign;
+ sign = -sign;
+ }
+
+ for (i = 0; i < DST_SIZE; i++)
+ res2.a[i] = DEFAULT_VALUE;
+
+#if AVX512F_LEN == 128
+ res1.x = INTRINSIC (_ipcvttph_epi16) (s.x);
+ res2.x = INTRINSIC (_mask_ipcvttph_epi16) (res2.x, mask, s.x);
+ res3.x = INTRINSIC (_maskz_ipcvttph_epi16) (mask, s.x);
+#else
+ res1.x = INTRINSIC (_ipcvtt_roundph_epi16) (s.x, 8);
+ res2.x = INTRINSIC (_mask_ipcvtt_roundph_epi16) (res2.x, mask, s.x, 8);
+ res3.x = INTRINSIC (_maskz_ipcvtt_roundph_epi16) (mask, s.x, 8);
+#endif
+
+ CALC (s.a, res_ref);
+
+ if (UNION_CHECK (AVX512F_LEN, i_w) (res1, res_ref))
+ abort ();
+
+ MASK_MERGE (i_w) (res_ref, mask, SRC_SIZE);
+ if (UNION_CHECK (AVX512F_LEN, i_w) (res2, res_ref))
+ abort ();
+
+ MASK_ZERO (i_w) (res_ref, mask, SRC_SIZE);
+ if (UNION_CHECK (AVX512F_LEN, i_w) (res3, res_ref))
+ abort ();
+}
new file mode 100644
@@ -0,0 +1,74 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx10.2-512" } */
+/* { dg-require-effective-target avx10_2_512 } */
+
+#ifndef AVX10_2
+#define AVX10_2
+#define AVX10_2_512
+#define AVX10_512BIT
+#endif
+#include "avx10-helper.h"
+#include <limits.h>
+
+#define SRC_SIZE ((AVX512F_LEN) / 16)
+#define DST_SIZE ((AVX512F_LEN) / 16)
+
+static void
+CALC (_Float16 *s, short *r)
+{
+ int i;
+ unsigned char tmp;
+
+ for (i = 0; i < SRC_SIZE; i++)
+ {
+ if (s[i] > UCHAR_MAX)
+ tmp = UCHAR_MAX;
+ else if (s[i] < 0)
+ tmp = 0;
+ else
+ tmp = s[i];
+ r[i] = (unsigned short) tmp;
+ }
+}
+
+void
+TEST (void)
+{
+ UNION_TYPE (AVX512F_LEN, h) s;
+ UNION_TYPE (AVX512F_LEN, i_w) res1, res2, res3;
+ MASK_TYPE mask = MASK_VALUE;
+ short res_ref[DST_SIZE] = { 0 };
+ int i, sign = 1;
+
+ for (i = 0; i < SRC_SIZE; i++)
+ {
+ s.a[i] = 1.23 * (i + 2) * sign;
+ sign = -sign;
+ }
+
+ for (i = 0; i < DST_SIZE; i++)
+ res2.a[i] = DEFAULT_VALUE;
+
+#if AVX512F_LEN == 128
+ res1.x = INTRINSIC (_ipcvttph_epu16) (s.x);
+ res2.x = INTRINSIC (_mask_ipcvttph_epu16) (res2.x, mask, s.x);
+ res3.x = INTRINSIC (_maskz_ipcvttph_epu16) (mask, s.x);
+#else
+ res1.x = INTRINSIC (_ipcvtt_roundph_epu16) (s.x, 8);
+ res2.x = INTRINSIC (_mask_ipcvtt_roundph_epu16) (res2.x, mask, s.x, 8);
+ res3.x = INTRINSIC (_maskz_ipcvtt_roundph_epu16) (mask, s.x, 8);
+#endif
+
+ CALC (s.a, res_ref);
+
+ if (UNION_CHECK (AVX512F_LEN, i_w) (res1, res_ref))
+ abort ();
+
+ MASK_MERGE (i_w) (res_ref, mask, SRC_SIZE);
+ if (UNION_CHECK (AVX512F_LEN, i_w) (res2, res_ref))
+ abort ();
+
+ MASK_ZERO (i_w) (res_ref, mask, SRC_SIZE);
+ if (UNION_CHECK (AVX512F_LEN, i_w) (res3, res_ref))
+ abort ();
+}
new file mode 100644
@@ -0,0 +1,75 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx10.2-512" } */
+/* { dg-require-effective-target avx10_2_512 } */
+
+#ifndef AVX10_2
+#define AVX10_2
+#define AVX10_2_512
+#define AVX10_512BIT
+#endif
+#include "avx10-helper.h"
+#include <limits.h>
+#include <math.h>
+
+#define SRC_SIZE ((AVX512F_LEN) / 32)
+#define DST_SIZE ((AVX512F_LEN) / 32)
+
+static void
+CALC (float *s, int *r)
+{
+ int i;
+ unsigned char tmp;
+
+ for (i = 0; i < SRC_SIZE; i++)
+ {
+ if (s[i] > SCHAR_MAX)
+ tmp = SCHAR_MAX;
+ else if (s[i] < SCHAR_MIN)
+ tmp = SCHAR_MIN;
+ else
+ tmp = s[i];
+ r[i] = (unsigned int)tmp;
+ }
+}
+
+void
+TEST (void)
+{
+ UNION_TYPE (AVX512F_LEN, ) s;
+ UNION_TYPE (AVX512F_LEN, i_d) res1, res2, res3;
+ MASK_TYPE mask = MASK_VALUE;
+ int res_ref[DST_SIZE] = { 0 };
+ int i, sign = 1;
+
+ for (i = 0; i < SRC_SIZE; i++)
+ {
+ s.a[i] = 1.23 * (i + 2) * sign;
+ sign = -sign;
+ }
+
+ for (i = 0; i < DST_SIZE; i++)
+ res2.a[i] = DEFAULT_VALUE;
+
+#if AVX512F_LEN == 128
+ res1.x = INTRINSIC (_ipcvttps_epi32) (s.x);
+ res2.x = INTRINSIC (_mask_ipcvttps_epi32) (res2.x, mask, s.x);
+ res3.x = INTRINSIC (_maskz_ipcvttps_epi32) (mask, s.x);
+#else
+ res1.x = INTRINSIC (_ipcvtt_roundps_epi32) (s.x, 8);
+ res2.x = INTRINSIC (_mask_ipcvtt_roundps_epi32) (res2.x, mask, s.x, 8);
+ res3.x = INTRINSIC (_maskz_ipcvtt_roundps_epi32) (mask, s.x, 8);
+#endif
+
+ CALC (s.a, res_ref);
+
+ if (UNION_CHECK (AVX512F_LEN, i_d) (res1, res_ref))
+ abort ();
+
+ MASK_MERGE (i_d) (res_ref, mask, SRC_SIZE);
+ if (UNION_CHECK (AVX512F_LEN, i_d) (res2, res_ref))
+ abort ();
+
+ MASK_ZERO (i_d) (res_ref, mask, SRC_SIZE);
+ if (UNION_CHECK (AVX512F_LEN, i_d) (res3, res_ref))
+ abort ();
+}
new file mode 100644
@@ -0,0 +1,73 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx10.2-512" } */
+/* { dg-require-effective-target avx10_2_512 } */
+
+#ifndef AVX10_2
+#define AVX10_2
+#define AVX10_2_512
+#define AVX10_512BIT
+#endif
+#include "avx10-helper.h"
+#include <limits.h>
+#include <math.h>
+
+#define SRC_SIZE ((AVX512F_LEN) / 32)
+#define DST_SIZE ((AVX512F_LEN) / 32)
+
+static void
+CALC (float *s, int *r)
+{
+ int i;
+
+ for (i = 0; i < SRC_SIZE; i++)
+ {
+ if (s[i] > UCHAR_MAX)
+ r[i] = UCHAR_MAX;
+ else if (s[i] < 0)
+ r[i] = 0;
+ else
+ r[i] = s[i];
+ }
+}
+
+void
+TEST (void)
+{
+ UNION_TYPE (AVX512F_LEN, ) s;
+ UNION_TYPE (AVX512F_LEN, i_d) res1, res2, res3;
+ MASK_TYPE mask = MASK_VALUE;
+ int res_ref[DST_SIZE] = { 0 };
+ int i, sign = 1;
+
+ for (i = 0; i < SRC_SIZE; i++)
+ {
+ s.a[i] = 1.23 * (i + 2) * sign;
+ sign = -sign;
+ }
+
+ for (i = 0; i < DST_SIZE; i++)
+ res2.a[i] = DEFAULT_VALUE;
+
+#if AVX512F_LEN == 128
+ res1.x = INTRINSIC (_ipcvttps_epu32) (s.x);
+ res2.x = INTRINSIC (_mask_ipcvttps_epu32) (res2.x, mask, s.x);
+ res3.x = INTRINSIC (_maskz_ipcvttps_epu32) (mask, s.x);
+#else
+ res1.x = INTRINSIC (_ipcvtt_roundps_epu32) (s.x, 8);
+ res2.x = INTRINSIC (_mask_ipcvtt_roundps_epu32) (res2.x, mask, s.x, 8);
+ res3.x = INTRINSIC (_maskz_ipcvtt_roundps_epu32) (mask, s.x, 8);
+#endif
+
+ CALC (s.a, res_ref);
+
+ if (UNION_CHECK (AVX512F_LEN, i_d) (res1, res_ref))
+ abort ();
+
+ MASK_MERGE (i_d) (res_ref, mask, SRC_SIZE);
+ if (UNION_CHECK (AVX512F_LEN, i_d) (res2, res_ref))
+ abort ();
+
+ MASK_ZERO (i_d) (res_ref, mask, SRC_SIZE);
+ if (UNION_CHECK (AVX512F_LEN, i_d) (res3, res_ref))
+ abort ();
+}
new file mode 100644
@@ -0,0 +1,187 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mavx10.2" } */
+/* { dg-final { scan-assembler-times "vcvtph2ibs\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtph2ibs\[ \\t\]+\{rn-sae\}\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtph2ibs\[ \\t\]+\{rz-sae\}\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtph2iubs\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtph2iubs\[ \\t\]+\{rn-sae\}\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtph2iubs\[ \\t\]+\{rz-sae\}\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttph2ibs\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttph2ibs\[ \\t\]+\{sae\}\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttph2ibs\[ \\t\]+\{sae\}\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttph2iubs\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttph2iubs\[ \\t\]+\{sae\}\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttph2iubs\[ \\t\]+\{sae\}\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtps2ibs\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtps2ibs\[ \\t\]+\{rn-sae\}\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtps2ibs\[ \\t\]+\{rz-sae\}\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtps2iubs\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtps2iubs\[ \\t\]+\{rn-sae\}\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtps2iubs\[ \\t\]+\{rz-sae\}\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttps2ibs\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttps2ibs\[ \\t\]+\{sae\}\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttps2ibs\[ \\t\]+\{sae\}\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttps2iubs\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttps2iubs\[ \\t\]+\{sae\}\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttps2iubs\[ \\t\]+\{sae\}\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtnebf162ibs\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtnebf162ibs\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtnebf162ibs\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtnebf162iubs\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtnebf162iubs\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtnebf162iubs\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttnebf162ibs\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttnebf162ibs\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttnebf162ibs\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttnebf162iubs\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttnebf162iubs\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttnebf162iubs\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtph2ibs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtph2ibs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtph2ibs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtph2iubs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtph2iubs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtph2iubs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttph2ibs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttph2ibs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttph2ibs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttph2iubs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttph2iubs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttph2iubs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtps2ibs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtps2ibs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtps2ibs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtps2iubs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtps2iubs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtps2iubs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttps2ibs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttps2ibs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttps2ibs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttps2iubs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttps2iubs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttps2iubs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtnebf162ibs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtnebf162ibs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtnebf162ibs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtnebf162iubs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtnebf162iubs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtnebf162iubs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttnebf162ibs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttnebf162ibs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttnebf162ibs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttnebf162iubs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttnebf162iubs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvttnebf162iubs\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+
+#include <immintrin.h>
+
+volatile __m128 hx;
+volatile __m128i hxi;
+volatile __m128h hxh;
+volatile __m128bh hxbh;
+volatile __m256 x;
+volatile __m256h xh;
+volatile __m256i xi;
+volatile __m256bh xbh;
+volatile __mmask8 m8;
+volatile __mmask16 m16;
+
+void extern
+avx10_2_test (void)
+{
+ xi = _mm256_ipcvt_roundph_epi16 (xh, 4);
+ xi = _mm256_mask_ipcvt_roundph_epi16 (xi, m16, xh, 8);
+ xi = _mm256_maskz_ipcvt_roundph_epi16 (m16, xh, 11);
+
+ xi = _mm256_ipcvt_roundph_epu16 (xh, 4);
+ xi = _mm256_mask_ipcvt_roundph_epu16 (xi, m16, xh, 8);
+ xi = _mm256_maskz_ipcvt_roundph_epu16 (m16, xh, 11);
+
+ xi = _mm256_ipcvtt_roundph_epi16 (xh, 4);
+ xi = _mm256_mask_ipcvtt_roundph_epi16 (xi, m16, xh, 8);
+ xi = _mm256_maskz_ipcvtt_roundph_epi16 (m16, xh, 8);
+
+ xi = _mm256_ipcvtt_roundph_epu16 (xh, 4);
+ xi = _mm256_mask_ipcvtt_roundph_epu16 (xi, m16, xh, 8);
+ xi = _mm256_maskz_ipcvtt_roundph_epu16 (m16, xh, 8);
+
+ xi = _mm256_ipcvt_roundps_epi32 (x, 4);
+ xi = _mm256_mask_ipcvt_roundps_epi32 (xi, m8, x, 8);
+ xi = _mm256_maskz_ipcvt_roundps_epi32 (m8, x, 11);
+
+ xi = _mm256_ipcvt_roundps_epu32 (x, 4);
+ xi = _mm256_mask_ipcvt_roundps_epu32 (xi, m8, x, 8);
+ xi = _mm256_maskz_ipcvt_roundps_epu32 (m8, x, 11);
+
+ xi = _mm256_ipcvtt_roundps_epi32 (x, 4);
+ xi = _mm256_mask_ipcvtt_roundps_epi32 (xi, m8, x, 8);
+ xi = _mm256_maskz_ipcvtt_roundps_epi32 (m8, x, 8);
+
+ xi = _mm256_ipcvtt_roundps_epu32 (x, 4);
+ xi = _mm256_mask_ipcvtt_roundps_epu32 (xi, m8, x, 8);
+ xi = _mm256_maskz_ipcvtt_roundps_epu32 (m8, x, 8);
+
+ xi = _mm256_ipcvtnebf16_epi16 (xbh);
+ xi = _mm256_mask_ipcvtnebf16_epi16 (xi, m16, xbh);
+ xi = _mm256_maskz_ipcvtnebf16_epi16 (m16, xbh);
+
+ xi = _mm256_ipcvtnebf16_epu16 (xbh);
+ xi = _mm256_mask_ipcvtnebf16_epu16 (xi, m16, xbh);
+ xi = _mm256_maskz_ipcvtnebf16_epu16 (m16, xbh);
+
+ xi = _mm256_ipcvttnebf16_epi16 (xbh);
+ xi = _mm256_mask_ipcvttnebf16_epi16 (xi, m16, xbh);
+ xi = _mm256_maskz_ipcvttnebf16_epi16 (m16, xbh);
+
+ xi = _mm256_ipcvttnebf16_epu16 (xbh);
+ xi = _mm256_mask_ipcvttnebf16_epu16 (xi, m16, xbh);
+ xi = _mm256_maskz_ipcvttnebf16_epu16 (m16, xbh);
+
+ hxi = _mm_ipcvtph_epi16 (hxh);
+ hxi = _mm_mask_ipcvtph_epi16 (hxi, m8, hxh);
+ hxi = _mm_maskz_ipcvtph_epi16 (m8, hxh);
+
+ hxi = _mm_ipcvtph_epu16 (hxh);
+ hxi = _mm_mask_ipcvtph_epu16 (hxi, m8, hxh);
+ hxi = _mm_maskz_ipcvtph_epu16 (m8, hxh);
+
+ hxi = _mm_ipcvttph_epi16 (hxh);
+ hxi = _mm_mask_ipcvttph_epi16 (hxi, m8, hxh);
+ hxi = _mm_maskz_ipcvttph_epi16 (m8, hxh);
+
+ hxi = _mm_ipcvttph_epu16 (hxh);
+ hxi = _mm_mask_ipcvttph_epu16 (hxi, m8, hxh);
+ hxi = _mm_maskz_ipcvttph_epu16 (m8, hxh);
+
+ hxi = _mm_ipcvtps_epi32 (hx);
+ hxi = _mm_mask_ipcvtps_epi32 (hxi, m8, hx);
+ hxi = _mm_maskz_ipcvtps_epi32 (m8, hx);
+
+ hxi = _mm_ipcvtps_epu32 (hx);
+ hxi = _mm_mask_ipcvtps_epu32 (hxi, m8, hx);
+ hxi = _mm_maskz_ipcvtps_epu32 (m8, hx);
+
+ hxi = _mm_ipcvttps_epi32 (hx);
+ hxi = _mm_mask_ipcvttps_epi32 (hxi, m8, hx);
+ hxi = _mm_maskz_ipcvttps_epi32 (m8, hx);
+
+ hxi = _mm_ipcvttps_epu32 (hx);
+ hxi = _mm_mask_ipcvttps_epu32 (hxi, m8, hx);
+ hxi = _mm_maskz_ipcvttps_epu32 (m8, hx);
+
+ hxi = _mm_ipcvtnebf16_epi16 (hxbh);
+ hxi = _mm_mask_ipcvtnebf16_epi16 (hxi, m8, hxbh);
+ hxi = _mm_maskz_ipcvtnebf16_epi16 (m8, hxbh);
+
+ hxi = _mm_ipcvtnebf16_epu16 (hxbh);
+ hxi = _mm_mask_ipcvtnebf16_epu16 (hxi, m8, hxbh);
+ hxi = _mm_maskz_ipcvtnebf16_epu16 (m8, hxbh);
+
+ hxi = _mm_ipcvttnebf16_epi16 (hxbh);
+ hxi = _mm_mask_ipcvttnebf16_epi16 (hxi, m8, hxbh);
+ hxi = _mm_maskz_ipcvttnebf16_epi16 (m8, hxbh);
+
+ hxi = _mm_ipcvttnebf16_epu16 (hxbh);
+ hxi = _mm_mask_ipcvttnebf16_epu16 (hxi, m8, hxbh);
+ hxi = _mm_maskz_ipcvttnebf16_epu16 (m8, hxbh);
+}
new file mode 100644
@@ -0,0 +1,16 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx10.2" } */
+/* { dg-require-effective-target avx10_2 } */
+
+#define AVX10_2
+#define AVX512VL
+#define AVX512F_LEN 256
+#define AVX512F_LEN_HALF 128
+#include "avx10_2-512-vcvtnebf162ibs-2.c"
+
+#undef AVX512F_LEN
+#undef AVX512F_LEN_HALF
+
+#define AVX512F_LEN 128
+#define AVX512F_LEN_HALF 128
+#include "avx10_2-512-vcvtnebf162ibs-2.c"
new file mode 100644
@@ -0,0 +1,16 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx10.2" } */
+/* { dg-require-effective-target avx10_2 } */
+
+#define AVX10_2
+#define AVX512VL
+#define AVX512F_LEN 256
+#define AVX512F_LEN_HALF 128
+#include "avx10_2-512-vcvtnebf162iubs-2.c"
+
+#undef AVX512F_LEN
+#undef AVX512F_LEN_HALF
+
+#define AVX512F_LEN 128
+#define AVX512F_LEN_HALF 128
+#include "avx10_2-512-vcvtnebf162iubs-2.c"
new file mode 100644
@@ -0,0 +1,16 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx10.2" } */
+/* { dg-require-effective-target avx10_2 } */
+
+#define AVX10_2
+#define AVX512VL
+#define AVX512F_LEN 256
+#define AVX512F_LEN_HALF 128
+#include "avx10_2-512-vcvtph2ibs-2.c"
+
+#undef AVX512F_LEN
+#undef AVX512F_LEN_HALF
+
+#define AVX512F_LEN 128
+#define AVX512F_LEN_HALF 128
+#include "avx10_2-512-vcvtph2ibs-2.c"
new file mode 100644
@@ -0,0 +1,16 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx10.2" } */
+/* { dg-require-effective-target avx10_2 } */
+
+#define AVX10_2
+#define AVX512VL
+#define AVX512F_LEN 256
+#define AVX512F_LEN_HALF 128
+#include "avx10_2-512-vcvtph2iubs-2.c"
+
+#undef AVX512F_LEN
+#undef AVX512F_LEN_HALF
+
+#define AVX512F_LEN 128
+#define AVX512F_LEN_HALF 128
+#include "avx10_2-512-vcvtph2iubs-2.c"
new file mode 100644
@@ -0,0 +1,16 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx10.2" } */
+/* { dg-require-effective-target avx10_2 } */
+
+#define AVX10_2
+#define AVX512VL
+#define AVX512F_LEN 256
+#define AVX512F_LEN_HALF 128
+#include "avx10_2-512-vcvtps2ibs-2.c"
+
+#undef AVX512F_LEN
+#undef AVX512F_LEN_HALF
+
+#define AVX512F_LEN 128
+#define AVX512F_LEN_HALF 128
+#include "avx10_2-512-vcvtps2ibs-2.c"
new file mode 100644
@@ -0,0 +1,16 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx10.2" } */
+/* { dg-require-effective-target avx10_2 } */
+
+#define AVX10_2
+#define AVX512VL
+#define AVX512F_LEN 256
+#define AVX512F_LEN_HALF 128
+#include "avx10_2-512-vcvttnebf162ibs-2.c"
+
+#undef AVX512F_LEN
+#undef AVX512F_LEN_HALF
+
+#define AVX512F_LEN 128
+#define AVX512F_LEN_HALF 128
+#include "avx10_2-512-vcvttnebf162ibs-2.c"
new file mode 100644
@@ -0,0 +1,16 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx10.2" } */
+/* { dg-require-effective-target avx10_2 } */
+
+#define AVX10_2
+#define AVX512VL
+#define AVX512F_LEN 256
+#define AVX512F_LEN_HALF 128
+#include "avx10_2-512-vcvttnebf162iubs-2.c"
+
+#undef AVX512F_LEN
+#undef AVX512F_LEN_HALF
+
+#define AVX512F_LEN 128
+#define AVX512F_LEN_HALF 128
+#include "avx10_2-512-vcvttnebf162iubs-2.c"
new file mode 100644
@@ -0,0 +1,16 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx10.2" } */
+/* { dg-require-effective-target avx10_2 } */
+
+#define AVX10_2
+#define AVX512VL
+#define AVX512F_LEN 256
+#define AVX512F_LEN_HALF 128
+#include "avx10_2-512-vcvttph2ibs-2.c"
+
+#undef AVX512F_LEN
+#undef AVX512F_LEN_HALF
+
+#define AVX512F_LEN 128
+#define AVX512F_LEN_HALF 128
+#include "avx10_2-512-vcvttph2ibs-2.c"
new file mode 100644
@@ -0,0 +1,16 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx10.2" } */
+/* { dg-require-effective-target avx10_2 } */
+
+#define AVX10_2
+#define AVX512VL
+#define AVX512F_LEN 256
+#define AVX512F_LEN_HALF 128
+#include "avx10_2-512-vcvttph2iubs-2.c"
+
+#undef AVX512F_LEN
+#undef AVX512F_LEN_HALF
+
+#define AVX512F_LEN 128
+#define AVX512F_LEN_HALF 128
+#include "avx10_2-512-vcvttph2iubs-2.c"
new file mode 100644
@@ -0,0 +1,16 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx10.2" } */
+/* { dg-require-effective-target avx10_2 } */
+
+#define AVX10_2
+#define AVX512VL
+#define AVX512F_LEN 256
+#define AVX512F_LEN_HALF 128
+#include "avx10_2-512-vcvttps2ibs-2.c"
+
+#undef AVX512F_LEN
+#undef AVX512F_LEN_HALF
+
+#define AVX512F_LEN 128
+#define AVX512F_LEN_HALF 128
+#include "avx10_2-512-vcvttps2ibs-2.c"
new file mode 100644
@@ -0,0 +1,16 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx10.2" } */
+/* { dg-require-effective-target avx10_2 } */
+
+#define AVX10_2
+#define AVX512VL
+#define AVX512F_LEN 256
+#define AVX512F_LEN_HALF 128
+#include "avx10_2-512-vcvttps2iubs-2.c"
+
+#undef AVX512F_LEN
+#undef AVX512F_LEN_HALF
+
+#define AVX512F_LEN 128
+#define AVX512F_LEN_HALF 128
+#include "avx10_2-512-vcvttps2iubs-2.c"
@@ -48,6 +48,7 @@ MAKE_MASK_MERGE(i_uw, unsigned short)
MAKE_MASK_MERGE(bf16_uw, unsigned short)
MAKE_MASK_MERGE(i_ud, unsigned int)
MAKE_MASK_MERGE(i_uq, unsigned long long)
+MAKE_MASK_MERGE(bf16_bf, __bf16)
#define MASK_MERGE(TYPE) merge_masking_##TYPE
@@ -74,6 +75,7 @@ MAKE_MASK_ZERO(i_uw, unsigned short)
MAKE_MASK_ZERO(bf16_uw, unsigned short)
MAKE_MASK_ZERO(i_ud, unsigned int)
MAKE_MASK_ZERO(i_uq, unsigned long long)
+MAKE_MASK_ZERO(bf16_bf, __bf16)
#define MASK_ZERO(TYPE) zero_masking_##TYPE
@@ -73,6 +73,12 @@ typedef union
unsigned short a[32];
} union512bf16_uw;
+typedef union
+{
+ __m512bh x;
+ __bf16 a[32];
+} union512bf16_bf;
+
typedef union
{
__m128h x;
@@ -97,6 +103,18 @@ typedef union
unsigned short a[16];
} union256bf16_uw;
+typedef union
+{
+ __m128bh x;
+ __bf16 a[8];
+} union128bf16_bf;
+
+typedef union
+{
+ __m256bh x;
+ __bf16 a[16];
+} union256bf16_bf;
+
#define CHECK_ROUGH_EXP(UNION_TYPE, VALUE_TYPE, FMT) \
static int \
__attribute__((noinline, unused)) \
@@ -176,9 +194,12 @@ CHECK_ROUGH_EXP (union256h, _Float16, "%f")
#if defined(AVX512BF16)
CHECK_EXP (union512bf16_uw, unsigned short, "%d")
+CHECK_EXP (union512bf16_bf, __bf16, "%f")
#endif
#if defined(AVX512BF16)
CHECK_EXP (union128bf16_uw, unsigned short, "%d")
CHECK_EXP (union256bf16_uw, unsigned short, "%d")
+CHECK_EXP (union128bf16_bf, __bf16, "%f")
+CHECK_EXP (union256bf16_bf, __bf16, "%f")
#endif
@@ -1043,4 +1043,24 @@
#define __builtin_ia32_cmppbf16256_mask(A, B, C, D) __builtin_ia32_cmppbf16256_mask(A, B, 1, D)
#define __builtin_ia32_cmppbf16128_mask(A, B, C, D) __builtin_ia32_cmppbf16128_mask(A, B, 1, D)
+/* avx10_2-512satcvtintrin.h */
+#define __builtin_ia32_cvtph2ibs512_mask_round(A, B, C, D) __builtin_ia32_cvtph2ibs512_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvtph2iubs512_mask_round(A, B, C, D) __builtin_ia32_cvtph2iubs512_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvtps2ibs512_mask_round(A, B, C, D) __builtin_ia32_cvtps2ibs512_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvtps2iubs512_mask_round(A, B, C, D) __builtin_ia32_cvtps2iubs512_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvttph2ibs512_mask_round(A, B, C, D) __builtin_ia32_cvttph2ibs512_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvttph2iubs512_mask_round(A, B, C, D) __builtin_ia32_cvttph2iubs512_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvttps2ibs512_mask_round(A, B, C, D) __builtin_ia32_cvttps2ibs512_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvttps2iubs512_mask_round(A, B, C, D) __builtin_ia32_cvttps2iubs512_mask_round(A, B, C, 8)
+
+/* avx10_2satcvtintrin.h */
+#define __builtin_ia32_cvtph2ibs256_mask_round(A, B, C, D) __builtin_ia32_cvtph2ibs256_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvtph2iubs256_mask_round(A, B, C, D) __builtin_ia32_cvtph2iubs256_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvtps2ibs256_mask_round(A, B, C, D) __builtin_ia32_cvtps2ibs256_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvtps2iubs256_mask_round(A, B, C, D) __builtin_ia32_cvtps2iubs256_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvttph2ibs256_mask_round(A, B, C, D) __builtin_ia32_cvttph2ibs256_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvttph2iubs256_mask_round(A, B, C, D) __builtin_ia32_cvttph2iubs256_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvttps2ibs256_mask_round(A, B, C, D) __builtin_ia32_cvttps2ibs256_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvttps2iubs256_mask_round(A, B, C, D) __builtin_ia32_cvttps2iubs256_mask_round(A, B, C, 8)
+
#include <x86intrin.h>
@@ -1431,3 +1431,55 @@ test_2 (_mm256_cmp_pbh_mask, __mmask16, __m256bh, __m256bh, 1)
test_2 (_mm_cmp_pbh_mask, __mmask8, __m128bh, __m128bh, 1)
test_3 (_mm256_mask_cmp_pbh_mask, __mmask16, __mmask16, __m256bh, __m256bh, 1)
test_3 (_mm_mask_cmp_pbh_mask, __mmask8, __mmask8, __m128bh, __m128bh, 1)
+
+/* avx10_2-512satcvtintrin.h */
+test_1 (_mm512_ipcvt_roundph_epi16, __m512i, __m512h, 8)
+test_1 (_mm512_ipcvt_roundph_epu16, __m512i, __m512h, 8)
+test_1 (_mm512_ipcvt_roundps_epi32, __m512i, __m512, 8)
+test_1 (_mm512_ipcvt_roundps_epu32, __m512i, __m512, 8)
+test_1 (_mm512_ipcvtt_roundph_epi16, __m512i, __m512h, 8)
+test_1 (_mm512_ipcvtt_roundph_epu16, __m512i, __m512h, 8)
+test_1 (_mm512_ipcvtt_roundps_epi32, __m512i, __m512, 8)
+test_1 (_mm512_ipcvtt_roundps_epu32, __m512i, __m512, 8)
+test_2 (_mm512_maskz_ipcvt_roundph_epi16, __m512i, __mmask32, __m512h, 8)
+test_2 (_mm512_maskz_ipcvt_roundph_epu16, __m512i, __mmask32, __m512h, 8)
+test_2 (_mm512_maskz_ipcvt_roundps_epi32, __m512i, __mmask16, __m512, 8)
+test_2 (_mm512_maskz_ipcvt_roundps_epu32, __m512i, __mmask16, __m512, 8)
+test_2 (_mm512_maskz_ipcvtt_roundph_epi16, __m512i, __mmask32, __m512h, 8)
+test_2 (_mm512_maskz_ipcvtt_roundph_epu16, __m512i, __mmask32, __m512h, 8)
+test_2 (_mm512_maskz_ipcvtt_roundps_epi32, __m512i, __mmask16, __m512, 8)
+test_2 (_mm512_maskz_ipcvtt_roundps_epu32, __m512i, __mmask16, __m512, 8)
+test_3 (_mm512_mask_ipcvt_roundph_epi16, __m512i, __m512i, __mmask32, __m512h, 8)
+test_3 (_mm512_mask_ipcvt_roundph_epu16, __m512i, __m512i, __mmask32, __m512h, 8)
+test_3 (_mm512_mask_ipcvt_roundps_epi32, __m512i, __m512i, __mmask16, __m512, 8)
+test_3 (_mm512_mask_ipcvt_roundps_epu32, __m512i, __m512i, __mmask16, __m512, 8)
+test_3 (_mm512_mask_ipcvtt_roundph_epi16, __m512i, __m512i, __mmask32, __m512h, 8)
+test_3 (_mm512_mask_ipcvtt_roundph_epu16, __m512i, __m512i, __mmask32, __m512h, 8)
+test_3 (_mm512_mask_ipcvtt_roundps_epi32, __m512i, __m512i, __mmask16, __m512, 8)
+test_3 (_mm512_mask_ipcvtt_roundps_epu32, __m512i, __m512i, __mmask16, __m512, 8)
+
+/* avx10_2satcvtintrin.h */
+test_1 (_mm256_ipcvt_roundph_epi16, __m256i, __m256h, 8)
+test_1 (_mm256_ipcvt_roundph_epu16, __m256i, __m256h, 8)
+test_1 (_mm256_ipcvt_roundps_epi32, __m256i, __m256, 8)
+test_1 (_mm256_ipcvt_roundps_epu32, __m256i, __m256, 8)
+test_1 (_mm256_ipcvtt_roundph_epi16, __m256i, __m256h, 8)
+test_1 (_mm256_ipcvtt_roundph_epu16, __m256i, __m256h, 8)
+test_1 (_mm256_ipcvtt_roundps_epi32, __m256i, __m256, 8)
+test_1 (_mm256_ipcvtt_roundps_epu32, __m256i, __m256, 8)
+test_2 (_mm256_maskz_ipcvt_roundph_epi16, __m256i, __mmask16, __m256h, 8)
+test_2 (_mm256_maskz_ipcvt_roundph_epu16, __m256i, __mmask16, __m256h, 8)
+test_2 (_mm256_maskz_ipcvt_roundps_epi32, __m256i, __mmask8, __m256, 8)
+test_2 (_mm256_maskz_ipcvt_roundps_epu32, __m256i, __mmask8, __m256, 8)
+test_2 (_mm256_maskz_ipcvtt_roundph_epi16, __m256i, __mmask16, __m256h, 8)
+test_2 (_mm256_maskz_ipcvtt_roundph_epu16, __m256i, __mmask16, __m256h, 8)
+test_2 (_mm256_maskz_ipcvtt_roundps_epi32, __m256i, __mmask8, __m256, 8)
+test_2 (_mm256_maskz_ipcvtt_roundps_epu32, __m256i, __mmask8, __m256, 8)
+test_3 (_mm256_mask_ipcvt_roundph_epi16, __m256i, __m256i, __mmask16, __m256h, 8)
+test_3 (_mm256_mask_ipcvt_roundph_epu16, __m256i, __m256i, __mmask16, __m256h, 8)
+test_3 (_mm256_mask_ipcvt_roundps_epi32, __m256i, __m256i, __mmask8, __m256, 8)
+test_3 (_mm256_mask_ipcvt_roundps_epu32, __m256i, __m256i, __mmask8, __m256, 8)
+test_3 (_mm256_mask_ipcvtt_roundph_epi16, __m256i, __m256i, __mmask16, __m256h, 8)
+test_3 (_mm256_mask_ipcvtt_roundph_epu16, __m256i, __m256i, __mmask16, __m256h, 8)
+test_3 (_mm256_mask_ipcvtt_roundps_epi32, __m256i, __m256i, __mmask8, __m256, 8)
+test_3 (_mm256_mask_ipcvtt_roundps_epu32, __m256i, __m256i, __mmask8, __m256, 8)
@@ -1470,3 +1470,55 @@ test_2 (_mm256_cmp_pbh_mask, __mmask16, __m256bh, __m256bh, 1)
test_2 (_mm_cmp_pbh_mask, __mmask8, __m128bh, __m128bh, 1)
test_3 (_mm256_mask_cmp_pbh_mask, __mmask16, __mmask16, __m256bh, __m256bh, 1)
test_3 (_mm_mask_cmp_pbh_mask, __mmask8, __mmask8, __m128bh, __m128bh, 1)
+
+/* avx10_2-512satcvtintrin.h */
+test_1 (_mm512_ipcvt_roundph_epi16, __m512i, __m512h, 8)
+test_1 (_mm512_ipcvt_roundph_epu16, __m512i, __m512h, 8)
+test_1 (_mm512_ipcvt_roundps_epi32, __m512i, __m512, 8)
+test_1 (_mm512_ipcvt_roundps_epu32, __m512i, __m512, 8)
+test_1 (_mm512_ipcvtt_roundph_epi16, __m512i, __m512h, 8)
+test_1 (_mm512_ipcvtt_roundph_epu16, __m512i, __m512h, 8)
+test_1 (_mm512_ipcvtt_roundps_epi32, __m512i, __m512, 8)
+test_1 (_mm512_ipcvtt_roundps_epu32, __m512i, __m512, 8)
+test_2 (_mm512_maskz_ipcvt_roundph_epi16, __m512i, __mmask32, __m512h, 8)
+test_2 (_mm512_maskz_ipcvt_roundph_epu16, __m512i, __mmask32, __m512h, 8)
+test_2 (_mm512_maskz_ipcvt_roundps_epi32, __m512i, __mmask16, __m512, 8)
+test_2 (_mm512_maskz_ipcvt_roundps_epu32, __m512i, __mmask16, __m512, 8)
+test_2 (_mm512_maskz_ipcvtt_roundph_epi16, __m512i, __mmask32, __m512h, 8)
+test_2 (_mm512_maskz_ipcvtt_roundph_epu16, __m512i, __mmask32, __m512h, 8)
+test_2 (_mm512_maskz_ipcvtt_roundps_epi32, __m512i, __mmask16, __m512, 8)
+test_2 (_mm512_maskz_ipcvtt_roundps_epu32, __m512i, __mmask16, __m512, 8)
+test_3 (_mm512_mask_ipcvt_roundph_epi16, __m512i, __m512i, __mmask32, __m512h, 8)
+test_3 (_mm512_mask_ipcvt_roundph_epu16, __m512i, __m512i, __mmask32, __m512h, 8)
+test_3 (_mm512_mask_ipcvt_roundps_epi32, __m512i, __m512i, __mmask16, __m512, 8)
+test_3 (_mm512_mask_ipcvt_roundps_epu32, __m512i, __m512i, __mmask16, __m512, 8)
+test_3 (_mm512_mask_ipcvtt_roundph_epi16, __m512i, __m512i, __mmask32, __m512h, 8)
+test_3 (_mm512_mask_ipcvtt_roundph_epu16, __m512i, __m512i, __mmask32, __m512h, 8)
+test_3 (_mm512_mask_ipcvtt_roundps_epi32, __m512i, __m512i, __mmask16, __m512, 8)
+test_3 (_mm512_mask_ipcvtt_roundps_epu32, __m512i, __m512i, __mmask16, __m512, 8)
+
+/* avx10_2satcvtintrin.h */
+test_1 (_mm256_ipcvt_roundph_epi16, __m256i, __m256h, 8)
+test_1 (_mm256_ipcvt_roundph_epu16, __m256i, __m256h, 8)
+test_1 (_mm256_ipcvt_roundps_epi32, __m256i, __m256, 8)
+test_1 (_mm256_ipcvt_roundps_epu32, __m256i, __m256, 8)
+test_1 (_mm256_ipcvtt_roundph_epi16, __m256i, __m256h, 8)
+test_1 (_mm256_ipcvtt_roundph_epu16, __m256i, __m256h, 8)
+test_1 (_mm256_ipcvtt_roundps_epi32, __m256i, __m256, 8)
+test_1 (_mm256_ipcvtt_roundps_epu32, __m256i, __m256, 8)
+test_2 (_mm256_maskz_ipcvt_roundph_epi16, __m256i, __mmask16, __m256h, 8)
+test_2 (_mm256_maskz_ipcvt_roundph_epu16, __m256i, __mmask16, __m256h, 8)
+test_2 (_mm256_maskz_ipcvt_roundps_epi32, __m256i, __mmask8, __m256, 8)
+test_2 (_mm256_maskz_ipcvt_roundps_epu32, __m256i, __mmask8, __m256, 8)
+test_2 (_mm256_maskz_ipcvtt_roundph_epi16, __m256i, __mmask16, __m256h, 8)
+test_2 (_mm256_maskz_ipcvtt_roundph_epu16, __m256i, __mmask16, __m256h, 8)
+test_2 (_mm256_maskz_ipcvtt_roundps_epi32, __m256i, __mmask8, __m256, 8)
+test_2 (_mm256_maskz_ipcvtt_roundps_epu32, __m256i, __mmask8, __m256, 8)
+test_3 (_mm256_mask_ipcvt_roundph_epi16, __m256i, __m256i, __mmask16, __m256h, 8)
+test_3 (_mm256_mask_ipcvt_roundph_epu16, __m256i, __m256i, __mmask16, __m256h, 8)
+test_3 (_mm256_mask_ipcvt_roundps_epi32, __m256i, __m256i, __mmask8, __m256, 8)
+test_3 (_mm256_mask_ipcvt_roundps_epu32, __m256i, __m256i, __mmask8, __m256, 8)
+test_3 (_mm256_mask_ipcvtt_roundph_epi16, __m256i, __m256i, __mmask16, __m256h, 8)
+test_3 (_mm256_mask_ipcvtt_roundph_epu16, __m256i, __m256i, __mmask16, __m256h, 8)
+test_3 (_mm256_mask_ipcvtt_roundps_epi32, __m256i, __m256i, __mmask8, __m256, 8)
+test_3 (_mm256_mask_ipcvtt_roundps_epu32, __m256i, __m256i, __mmask8, __m256, 8)
@@ -1017,6 +1017,26 @@
#define __builtin_ia32_cmppbf16256_mask(A, B, C, D) __builtin_ia32_cmppbf16256_mask(A, B, 1, D)
#define __builtin_ia32_cmppbf16128_mask(A, B, C, D) __builtin_ia32_cmppbf16128_mask(A, B, 1, D)
+/* avx10_2-512satcvtintrin.h */
+#define __builtin_ia32_cvtph2ibs512_mask_round(A, B, C, D) __builtin_ia32_cvtph2ibs512_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvtph2iubs512_mask_round(A, B, C, D) __builtin_ia32_cvtph2iubs512_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvtps2ibs512_mask_round(A, B, C, D) __builtin_ia32_cvtps2ibs512_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvtps2iubs512_mask_round(A, B, C, D) __builtin_ia32_cvtps2iubs512_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvttph2ibs512_mask_round(A, B, C, D) __builtin_ia32_cvttph2ibs512_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvttph2iubs512_mask_round(A, B, C, D) __builtin_ia32_cvttph2iubs512_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvttps2ibs512_mask_round(A, B, C, D) __builtin_ia32_cvttps2ibs512_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvttps2iubs512_mask_round(A, B, C, D) __builtin_ia32_cvttps2iubs512_mask_round(A, B, C, 8)
+
+/* avx10_2satcvtintrin.h */
+#define __builtin_ia32_cvtph2ibs256_mask_round(A, B, C, D) __builtin_ia32_cvtph2ibs256_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvtph2iubs256_mask_round(A, B, C, D) __builtin_ia32_cvtph2iubs256_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvtps2ibs256_mask_round(A, B, C, D) __builtin_ia32_cvtps2ibs256_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvtps2iubs256_mask_round(A, B, C, D) __builtin_ia32_cvtps2iubs256_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvttph2ibs256_mask_round(A, B, C, D) __builtin_ia32_cvttph2ibs256_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvttph2iubs256_mask_round(A, B, C, D) __builtin_ia32_cvttph2iubs256_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvttps2ibs256_mask_round(A, B, C, D) __builtin_ia32_cvttps2ibs256_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvttps2iubs256_mask_round(A, B, C, D) __builtin_ia32_cvttps2iubs256_mask_round(A, B, C, 8)
+
#pragma GCC target ("sse4a,3dnow,avx,avx2,fma4,xop,aes,pclmul,popcnt,abm,lzcnt,bmi,bmi2,tbm,lwp,fsgsbase,rdrnd,f16c,fma,rtm,rdseed,prfchw,adx,fxsr,xsaveopt,sha,xsavec,xsaves,clflushopt,clwb,mwaitx,clzero,pku,sgx,rdpid,gfni,vpclmulqdq,pconfig,wbnoinvd,enqcmd,avx512vp2intersect,serialize,tsxldtrk,amx-tile,amx-int8,amx-bf16,kl,widekl,avxvnni,avxifma,avxvnniint8,avxneconvert,cmpccxadd,amx-fp16,prefetchi,raoint,amx-complex,avxvnniint16,sm3,sha512,sm4,avx10.2-512")
#include <x86intrin.h>
From: "Hu, Lin1" <lin1.hu@intel.com> gcc/ChangeLog: * config.gcc: Add avx10_2satcvtintrin.h and avx10_2-512satcvtintrin.h. * config/i386/i386-builtin-types.def: Add DEF_FUNCTION_TYPE (V8HI, V8BF, V8HI, UQI), (V16HI, V16BF, V16HI, UHI), (V32HI, V32BF, V32HI, USI), (V16SI, V16SF, V16SI, UHI, INT), (V16HI, V16BF, V16HI, UHI, INT), (V32HI, V32BF, V32HI, USI, INT). * config/i386/i386-builtin.def (BDESC): Add new builtins. * config/i386/i386-expand.cc (ix86_expand_args_builtin): Handle V32HI_FTYPE_V32BF_V32HI_USI, V16HI_FTYPE_V16BF_V16HI_UHI, V8HI_FTYPE_V8BF_V8HI_UQI. (ix86_expand_round_builtin): Handle V32HI_FTYPE_V32BF_V32HI_USI_INT, V16SI_FTYPE_V16SF_V16SI_UHI_INT, V16HI_FTYPE_V16BF_V16HI_UHI_INT. * config/i386/immintrin.h: Include avx10_2satcvtintrin.h and avx10_2-512savcvtintrin.h. * config/i386/sse.md: (avx10_2_cvt<cvtnebf162ibs_trunc_or_notrunc>nebf162i<cvtnebf162ibs_signorunsign>bs<mode><mask_name>): New. (avx10_2_cvtph2i<cvtph2ibs_signorunsign>bs<mode><mask_name><round_name>): Ditto. (avx10_2_cvttph2i<cvttph2ibs_signorunsign>bs<mode><mask_name><round_saeonly_name>): Ditto. (avx10_2_cvtps2i<cvtps2ibs_signorunsign>bs<mode><mask_name><round_name>): Ditto. (avx10_2_cvttps2i<cvttps2ibs_signorunsign>bs<mode><mask_name><round_saeonly_name>): Ditto. * config/i386/avx10_2-512satcvtintrin.h: New file. * config/i386/avx10_2satcvtintrin.h: Ditto. gcc/testsuite/ChangeLog: * gcc.target/i386/avx-1.c: Add macros. * gcc.target/i386/sse-13.c: Ditto. * gcc.target/i386/sse-14.c: Ditto. * gcc.target/i386/sse-22.c: Ditto. * gcc.target/i386/sse-23.c: Ditto. * gcc.target/i386/avx10_2-512-satcvt-1.c: New test. * gcc.target/i386/avx10_2-512-vcvtnebf162ibs-2.c: Ditto. * gcc.target/i386/avx10_2-512-vcvtnebf162iubs-2.c: Ditto. * gcc.target/i386/avx10_2-512-vcvtph2ibs-2.c: Ditto. * gcc.target/i386/avx10_2-512-vcvtph2iubs-2.c: Ditto. * gcc.target/i386/avx10_2-512-vcvtps2ibs-2.c: Ditto. * gcc.target/i386/avx10_2-512-vcvtps2iubs-2.c: Ditto. * gcc.target/i386/avx10_2-512-vcvttnebf162ibs-2.c: Ditto. * gcc.target/i386/avx10_2-512-vcvttnebf162iubs-2.c: Ditto. * gcc.target/i386/avx10_2-512-vcvttph2ibs-2.c: Ditto. * gcc.target/i386/avx10_2-512-vcvttph2iubs-2.c: Ditto. * gcc.target/i386/avx10_2-512-vcvttps2ibs-2.c: Ditto. * gcc.target/i386/avx10_2-512-vcvttps2iubs-2.c: Ditto. * gcc.target/i386/avx10_2-satcvt-1.c: Ditto. * gcc.target/i386/avx10_2-vcvtnebf162ibs-2.c: Ditto. * gcc.target/i386/avx10_2-vcvtnebf162iubs-2.c: Ditto. * gcc.target/i386/avx10_2-vcvtph2ibs-2.c: Ditto. * gcc.target/i386/avx10_2-vcvtph2iubs-2.c: Ditto. * gcc.target/i386/avx10_2-vcvtps2ibs-2.c: Ditto. * gcc.target/i386/avx10_2-vcvttnebf162ibs-2.c: Ditto. * gcc.target/i386/avx10_2-vcvttnebf162iubs-2.c: Ditto. * gcc.target/i386/avx10_2-vcvttph2ibs-2.c: Ditto. * gcc.target/i386/avx10_2-vcvttph2iubs-2.c: Ditto. * gcc.target/i386/avx10_2-vcvttps2ibs-2.c: Ditto. * gcc.target/i386/avx10_2-vcvttps2iubs-2.c: Ditto. --- gcc/config.gcc | 4 +- gcc/config/i386/avx10_2-512satcvtintrin.h | 624 ++++++++++ gcc/config/i386/avx10_2satcvtintrin.h | 1022 +++++++++++++++++ gcc/config/i386/i386-builtin-types.def | 6 + gcc/config/i386/i386-builtin.def | 36 + gcc/config/i386/i386-expand.cc | 6 + gcc/config/i386/immintrin.h | 3 + gcc/config/i386/sse.md | 110 ++ gcc/testsuite/gcc.target/i386/avx-1.c | 20 + .../gcc.target/i386/avx10_2-512-satcvt-1.c | 100 ++ .../i386/avx10_2-512-vcvtnebf162ibs-2.c | 69 ++ .../i386/avx10_2-512-vcvtnebf162iubs-2.c | 69 ++ .../i386/avx10_2-512-vcvtph2ibs-2.c | 74 ++ .../i386/avx10_2-512-vcvtph2iubs-2.c | 74 ++ .../i386/avx10_2-512-vcvtps2ibs-2.c | 75 ++ .../i386/avx10_2-512-vcvtps2iubs-2.c | 73 ++ .../i386/avx10_2-512-vcvttnebf162ibs-2.c | 69 ++ .../i386/avx10_2-512-vcvttnebf162iubs-2.c | 69 ++ .../i386/avx10_2-512-vcvttph2ibs-2.c | 74 ++ .../i386/avx10_2-512-vcvttph2iubs-2.c | 74 ++ .../i386/avx10_2-512-vcvttps2ibs-2.c | 75 ++ .../i386/avx10_2-512-vcvttps2iubs-2.c | 73 ++ .../gcc.target/i386/avx10_2-satcvt-1.c | 187 +++ .../i386/avx10_2-vcvtnebf162ibs-2.c | 16 + .../i386/avx10_2-vcvtnebf162iubs-2.c | 16 + .../gcc.target/i386/avx10_2-vcvtph2ibs-2.c | 16 + .../gcc.target/i386/avx10_2-vcvtph2iubs-2.c | 16 + .../gcc.target/i386/avx10_2-vcvtps2ibs-2.c | 16 + .../i386/avx10_2-vcvttnebf162ibs-2.c | 16 + .../i386/avx10_2-vcvttnebf162iubs-2.c | 16 + .../gcc.target/i386/avx10_2-vcvttph2ibs-2.c | 16 + .../gcc.target/i386/avx10_2-vcvttph2iubs-2.c | 16 + .../gcc.target/i386/avx10_2-vcvttps2ibs-2.c | 16 + .../gcc.target/i386/avx10_2-vcvttps2iubs-2.c | 16 + .../gcc.target/i386/avx512f-helper.h | 2 + gcc/testsuite/gcc.target/i386/m512-check.h | 21 + gcc/testsuite/gcc.target/i386/sse-13.c | 20 + gcc/testsuite/gcc.target/i386/sse-14.c | 52 + gcc/testsuite/gcc.target/i386/sse-22.c | 52 + gcc/testsuite/gcc.target/i386/sse-23.c | 20 + 40 files changed, 3328 insertions(+), 1 deletion(-) create mode 100644 gcc/config/i386/avx10_2-512satcvtintrin.h create mode 100644 gcc/config/i386/avx10_2satcvtintrin.h create mode 100644 gcc/testsuite/gcc.target/i386/avx10_2-512-satcvt-1.c create mode 100644 gcc/testsuite/gcc.target/i386/avx10_2-512-vcvtnebf162ibs-2.c create mode 100644 gcc/testsuite/gcc.target/i386/avx10_2-512-vcvtnebf162iubs-2.c create mode 100644 gcc/testsuite/gcc.target/i386/avx10_2-512-vcvtph2ibs-2.c create mode 100644 gcc/testsuite/gcc.target/i386/avx10_2-512-vcvtph2iubs-2.c create mode 100644 gcc/testsuite/gcc.target/i386/avx10_2-512-vcvtps2ibs-2.c create mode 100644 gcc/testsuite/gcc.target/i386/avx10_2-512-vcvtps2iubs-2.c create mode 100644 gcc/testsuite/gcc.target/i386/avx10_2-512-vcvttnebf162ibs-2.c create mode 100644 gcc/testsuite/gcc.target/i386/avx10_2-512-vcvttnebf162iubs-2.c create mode 100644 gcc/testsuite/gcc.target/i386/avx10_2-512-vcvttph2ibs-2.c create mode 100644 gcc/testsuite/gcc.target/i386/avx10_2-512-vcvttph2iubs-2.c create mode 100644 gcc/testsuite/gcc.target/i386/avx10_2-512-vcvttps2ibs-2.c create mode 100644 gcc/testsuite/gcc.target/i386/avx10_2-512-vcvttps2iubs-2.c create mode 100644 gcc/testsuite/gcc.target/i386/avx10_2-satcvt-1.c create mode 100644 gcc/testsuite/gcc.target/i386/avx10_2-vcvtnebf162ibs-2.c create mode 100644 gcc/testsuite/gcc.target/i386/avx10_2-vcvtnebf162iubs-2.c create mode 100644 gcc/testsuite/gcc.target/i386/avx10_2-vcvtph2ibs-2.c create mode 100644 gcc/testsuite/gcc.target/i386/avx10_2-vcvtph2iubs-2.c create mode 100644 gcc/testsuite/gcc.target/i386/avx10_2-vcvtps2ibs-2.c create mode 100644 gcc/testsuite/gcc.target/i386/avx10_2-vcvttnebf162ibs-2.c create mode 100644 gcc/testsuite/gcc.target/i386/avx10_2-vcvttnebf162iubs-2.c create mode 100644 gcc/testsuite/gcc.target/i386/avx10_2-vcvttph2ibs-2.c create mode 100644 gcc/testsuite/gcc.target/i386/avx10_2-vcvttph2iubs-2.c create mode 100644 gcc/testsuite/gcc.target/i386/avx10_2-vcvttps2ibs-2.c create mode 100644 gcc/testsuite/gcc.target/i386/avx10_2-vcvttps2iubs-2.c