Update copyright years.

[thirdparty/gcc.git] / gcc / config / i386 / avx512fintrin.h

diff --git a/gcc/config/i386/avx512fintrin.h b/gcc/config/i386/avx512fintrin.h
index 71e36a5e514321a0af8678ff42aaeae6b652858f..e979b7e8622cb8be62d90fc4645f11e82d9b58da 100644 (file)
--- a/gcc/config/i386/avx512fintrin.h
+++ b/gcc/config/i386/avx512fintrin.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2013-2018 Free Software Foundation, Inc.
+/* Copyright (C) 2013-2020 Free Software Foundation, Inc.
 
    This file is part of GCC.
 
@@ -97,6 +97,56 @@ _mm512_set_epi32 (int __A, int __B, int __C, int __D,
           __H, __G, __F, __E, __D, __C, __B, __A };
 }
 
+extern __inline __m512i
+__attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_set_epi16 (short __q31, short __q30, short __q29, short __q28,
+                 short __q27, short __q26, short __q25, short __q24,
+                 short __q23, short __q22, short __q21, short __q20,
+                 short __q19, short __q18, short __q17, short __q16,
+                 short __q15, short __q14, short __q13, short __q12,
+                 short __q11, short __q10, short __q09, short __q08,
+                 short __q07, short __q06, short __q05, short __q04,
+                 short __q03, short __q02, short __q01, short __q00)
+{
+  return __extension__ (__m512i)(__v32hi){
+    __q00, __q01, __q02, __q03, __q04, __q05, __q06, __q07,
+    __q08, __q09, __q10, __q11, __q12, __q13, __q14, __q15,
+    __q16, __q17, __q18, __q19, __q20, __q21, __q22, __q23,
+    __q24, __q25, __q26, __q27, __q28, __q29, __q30, __q31
+  };
+}
+
+extern __inline __m512i
+__attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_set_epi8 (char __q63, char __q62, char __q61, char __q60,
+                char __q59, char __q58, char __q57, char __q56,
+                char __q55, char __q54, char __q53, char __q52,
+                char __q51, char __q50, char __q49, char __q48,
+                char __q47, char __q46, char __q45, char __q44,
+                char __q43, char __q42, char __q41, char __q40,
+                char __q39, char __q38, char __q37, char __q36,
+                char __q35, char __q34, char __q33, char __q32,
+                char __q31, char __q30, char __q29, char __q28,
+                char __q27, char __q26, char __q25, char __q24,
+                char __q23, char __q22, char __q21, char __q20,
+                char __q19, char __q18, char __q17, char __q16,
+                char __q15, char __q14, char __q13, char __q12,
+                char __q11, char __q10, char __q09, char __q08,
+                char __q07, char __q06, char __q05, char __q04,
+                char __q03, char __q02, char __q01, char __q00)
+{
+  return __extension__ (__m512i)(__v64qi){
+    __q00, __q01, __q02, __q03, __q04, __q05, __q06, __q07,
+    __q08, __q09, __q10, __q11, __q12, __q13, __q14, __q15,
+    __q16, __q17, __q18, __q19, __q20, __q21, __q22, __q23,
+    __q24, __q25, __q26, __q27, __q28, __q29, __q30, __q31,
+    __q32, __q33, __q34, __q35, __q36, __q37, __q38, __q39,
+    __q40, __q41, __q42, __q43, __q44, __q45, __q46, __q47,
+    __q48, __q49, __q50, __q51, __q52, __q53, __q54, __q55,
+    __q56, __q57, __q58, __q59, __q60, __q61, __q62, __q63
+  };
+}
+
 extern __inline __m512d
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_set_pd (double __A, double __B, double __C, double __D,
@@ -263,6 +313,13 @@ _mm512_setzero_ps (void)
                                 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 };
 }
 
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_setzero (void)
+{
+  return _mm512_setzero_ps ();
+}
+
 extern __inline __m512d
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_setzero_pd (void)
@@ -565,6 +622,20 @@ _mm512_mask_mullo_epi32 (__m512i __W, __mmask16 __M, __m512i __A, __m512i __B)
                                                  (__v16si) __W, __M);
 }
 
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mullox_epi64 (__m512i __A, __m512i __B)
+{
+  return (__m512i) ((__v8du) __A * (__v8du) __B);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_mullox_epi64 (__m512i __W, __mmask8 __M, __m512i __A, __m512i __B)
+{
+  return _mm512_mask_mov_epi64 (__W, __M, _mm512_mullox_epi64 (__A, __B));
+}
+
 extern __inline __m512i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_sllv_epi32 (__m512i __X, __m512i __Y)
@@ -1955,18 +2026,66 @@ extern __inline __m128d
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm_sqrt_round_sd (__m128d __A, __m128d __B, const int __R)
 {
-  return (__m128d) __builtin_ia32_sqrtsd_round ((__v2df) __B,
-                                               (__v2df) __A,
-                                               __R);
+  return (__m128d) __builtin_ia32_sqrtsd_mask_round ((__v2df) __B,
+                                                    (__v2df) __A,
+                                                    (__v2df)
+                                                    _mm_setzero_pd (),
+                                                    (__mmask8) -1, __R);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_sqrt_round_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B,
+                       const int __R)
+{
+  return (__m128d) __builtin_ia32_sqrtsd_mask_round ((__v2df) __B,
+                                                    (__v2df) __A,
+                                                    (__v2df) __W,
+                                                    (__mmask8) __U, __R);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_sqrt_round_sd (__mmask8 __U, __m128d __A, __m128d __B, const int __R)
+{
+  return (__m128d) __builtin_ia32_sqrtsd_mask_round ((__v2df) __B,
+                                                    (__v2df) __A,
+                                                    (__v2df)
+                                                    _mm_setzero_pd (),
+                                                    (__mmask8) __U, __R);
 }
 
 extern __inline __m128
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm_sqrt_round_ss (__m128 __A, __m128 __B, const int __R)
 {
-  return (__m128) __builtin_ia32_sqrtss_round ((__v4sf) __B,
-                                              (__v4sf) __A,
-                                              __R);
+  return (__m128) __builtin_ia32_sqrtss_mask_round ((__v4sf) __B,
+                                                   (__v4sf) __A,
+                                                   (__v4sf)
+                                                   _mm_setzero_ps (),
+                                                   (__mmask8) -1, __R);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_sqrt_round_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B,
+                       const int __R)
+{
+  return (__m128) __builtin_ia32_sqrtss_mask_round ((__v4sf) __B,
+                                                   (__v4sf) __A,
+                                                   (__v4sf) __W,
+                                                   (__mmask8) __U, __R);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_sqrt_round_ss (__mmask8 __U, __m128 __A, __m128 __B, const int __R)
+{
+  return (__m128) __builtin_ia32_sqrtss_mask_round ((__v4sf) __B,
+                                                   (__v4sf) __A,
+                                                   (__v4sf)
+                                                   _mm_setzero_ps (),
+                                                   (__mmask8) __U, __R);
 }
 #else
 #define _mm512_sqrt_round_pd(A, C)            \
@@ -1987,11 +2106,27 @@ _mm_sqrt_round_ss (__m128 __A, __m128 __B, const int __R)
 #define _mm512_maskz_sqrt_round_ps(U, A, C)   \
     (__m512)__builtin_ia32_sqrtps512_mask(A, (__v16sf)_mm512_setzero_ps(), U, C)
 
-#define _mm_sqrt_round_sd(A, B, C)            \
-    (__m128d)__builtin_ia32_sqrtsd_round(A, B, C)
+#define _mm_sqrt_round_sd(A, B, C)           \
+    (__m128d)__builtin_ia32_sqrtsd_mask_round (B, A, \
+       (__v2df) _mm_setzero_pd (), -1, C)
+
+#define _mm_mask_sqrt_round_sd(W, U, A, B, C) \
+    (__m128d)__builtin_ia32_sqrtsd_mask_round (B, A, W, U, C)
 
-#define _mm_sqrt_round_ss(A, B, C)            \
-    (__m128)__builtin_ia32_sqrtss_round(A, B, C)
+#define _mm_maskz_sqrt_round_sd(U, A, B, C)   \
+    (__m128d)__builtin_ia32_sqrtsd_mask_round (B, A, \
+       (__v2df) _mm_setzero_pd (), U, C)
+
+#define _mm_sqrt_round_ss(A, B, C)           \
+    (__m128)__builtin_ia32_sqrtss_mask_round (B, A, \
+       (__v4sf) _mm_setzero_ps (), -1, C)
+
+#define _mm_mask_sqrt_round_ss(W, U, A, B, C) \
+    (__m128)__builtin_ia32_sqrtss_mask_round (B, A, W, U, C)
+
+#define _mm_maskz_sqrt_round_ss(U, A, B, C)   \
+    (__m128)__builtin_ia32_sqrtss_mask_round (B, A, \
+       (__v4sf) _mm_setzero_ps (), U, C)
 #endif
 
 extern __inline __m512i
@@ -3039,18 +3174,67 @@ extern __inline __m128d
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm_scalef_round_sd (__m128d __A, __m128d __B, const int __R)
 {
-  return (__m128d) __builtin_ia32_scalefsd_round ((__v2df) __A,
-                                                 (__v2df) __B,
-                                                 __R);
+  return (__m128d) __builtin_ia32_scalefsd_mask_round ((__v2df) __A,
+                                                      (__v2df) __B,
+                                                      (__v2df)
+                                                      _mm_setzero_pd (),
+                                                      (__mmask8) -1, __R);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_scalef_round_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B,
+                         const int __R)
+{
+  return (__m128d) __builtin_ia32_scalefsd_mask_round ((__v2df) __A,
+                                                      (__v2df) __B,
+                                                      (__v2df) __W,
+                                                      (__mmask8) __U, __R);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_scalef_round_sd (__mmask8 __U, __m128d __A, __m128d __B,
+                          const int __R)
+{
+  return (__m128d) __builtin_ia32_scalefsd_mask_round ((__v2df) __A,
+                                                      (__v2df) __B,
+                                                      (__v2df)
+                                                      _mm_setzero_pd (),
+                                                      (__mmask8) __U, __R);
 }
 
 extern __inline __m128
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm_scalef_round_ss (__m128 __A, __m128 __B, const int __R)
 {
-  return (__m128) __builtin_ia32_scalefss_round ((__v4sf) __A,
-                                                (__v4sf) __B,
-                                                __R);
+  return (__m128) __builtin_ia32_scalefss_mask_round ((__v4sf) __A,
+                                                     (__v4sf) __B,
+                                                     (__v4sf)
+                                                     _mm_setzero_ps (),
+                                                     (__mmask8) -1, __R);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_scalef_round_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B,
+                        const int __R)
+{
+  return (__m128) __builtin_ia32_scalefss_mask_round ((__v4sf) __A,
+                                                     (__v4sf) __B,
+                                                     (__v4sf) __W,
+                                                     (__mmask8) __U, __R);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_scalef_round_ss (__mmask8 __U, __m128 __A, __m128 __B, const int __R)
+{
+  return (__m128) __builtin_ia32_scalefss_mask_round ((__v4sf) __A,
+                                                     (__v4sf) __B,
+                                                     (__v4sf)
+                                                     _mm_setzero_ps (),
+                                                     (__mmask8) __U, __R);
 }
 #else
 #define _mm512_scalef_round_pd(A, B, C)            \
@@ -3072,10 +3256,12 @@ _mm_scalef_round_ss (__m128 __A, __m128 __B, const int __R)
     (__m512)__builtin_ia32_scalefps512_mask(A, B, (__v16sf)_mm512_setzero_ps(), U, C)
 
 #define _mm_scalef_round_sd(A, B, C)            \
-    (__m128d)__builtin_ia32_scalefsd_round(A, B, C)
+    (__m128d)__builtin_ia32_scalefsd_mask_round (A, B, \
+       (__v2df)_mm_setzero_pd (), -1, C)
 
 #define _mm_scalef_round_ss(A, B, C)            \
-    (__m128)__builtin_ia32_scalefss_round(A, B, C)
+    (__m128)__builtin_ia32_scalefss_mask_round (A, B, \
+       (__v4sf)_mm_setzero_ps (), -1, C)
 #endif
 
 #ifdef __OPTIMIZE__
@@ -3169,9 +3355,9 @@ extern __inline __m512d
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_fmsub_round_pd (__m512d __A, __m512d __B, __m512d __C, const int __R)
 {
-  return (__m512d) __builtin_ia32_vfmaddpd512_mask ((__v8df) __A,
+  return (__m512d) __builtin_ia32_vfmsubpd512_mask ((__v8df) __A,
                                                    (__v8df) __B,
-                                                   -(__v8df) __C,
+                                                   (__v8df) __C,
                                                    (__mmask8) -1, __R);
 }
 
@@ -3180,9 +3366,9 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_mask_fmsub_round_pd (__m512d __A, __mmask8 __U, __m512d __B,
                            __m512d __C, const int __R)
 {
-  return (__m512d) __builtin_ia32_vfmaddpd512_mask ((__v8df) __A,
+  return (__m512d) __builtin_ia32_vfmsubpd512_mask ((__v8df) __A,
                                                    (__v8df) __B,
-                                                   -(__v8df) __C,
+                                                   (__v8df) __C,
                                                    (__mmask8) __U, __R);
 }
 
@@ -3202,9 +3388,9 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_maskz_fmsub_round_pd (__mmask8 __U, __m512d __A, __m512d __B,
                             __m512d __C, const int __R)
 {
-  return (__m512d) __builtin_ia32_vfmaddpd512_maskz ((__v8df) __A,
+  return (__m512d) __builtin_ia32_vfmsubpd512_maskz ((__v8df) __A,
                                                     (__v8df) __B,
-                                                    -(__v8df) __C,
+                                                    (__v8df) __C,
                                                     (__mmask8) __U, __R);
 }
 
@@ -3212,9 +3398,9 @@ extern __inline __m512
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_fmsub_round_ps (__m512 __A, __m512 __B, __m512 __C, const int __R)
 {
-  return (__m512) __builtin_ia32_vfmaddps512_mask ((__v16sf) __A,
+  return (__m512) __builtin_ia32_vfmsubps512_mask ((__v16sf) __A,
                                                   (__v16sf) __B,
-                                                  -(__v16sf) __C,
+                                                  (__v16sf) __C,
                                                   (__mmask16) -1, __R);
 }
 
@@ -3223,9 +3409,9 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_mask_fmsub_round_ps (__m512 __A, __mmask16 __U, __m512 __B,
                            __m512 __C, const int __R)
 {
-  return (__m512) __builtin_ia32_vfmaddps512_mask ((__v16sf) __A,
+  return (__m512) __builtin_ia32_vfmsubps512_mask ((__v16sf) __A,
                                                   (__v16sf) __B,
-                                                  -(__v16sf) __C,
+                                                  (__v16sf) __C,
                                                   (__mmask16) __U, __R);
 }
 
@@ -3245,9 +3431,9 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_maskz_fmsub_round_ps (__mmask16 __U, __m512 __A, __m512 __B,
                             __m512 __C, const int __R)
 {
-  return (__m512) __builtin_ia32_vfmaddps512_maskz ((__v16sf) __A,
+  return (__m512) __builtin_ia32_vfmsubps512_maskz ((__v16sf) __A,
                                                    (__v16sf) __B,
-                                                   -(__v16sf) __C,
+                                                   (__v16sf) __C,
                                                    (__mmask16) __U, __R);
 }
 
@@ -3427,10 +3613,10 @@ extern __inline __m512d
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_fnmadd_round_pd (__m512d __A, __m512d __B, __m512d __C, const int __R)
 {
-  return (__m512d) __builtin_ia32_vfmaddpd512_mask (-(__v8df) __A,
-                                                   (__v8df) __B,
-                                                   (__v8df) __C,
-                                                   (__mmask8) -1, __R);
+  return (__m512d) __builtin_ia32_vfnmaddpd512_mask ((__v8df) __A,
+                                                    (__v8df) __B,
+                                                    (__v8df) __C,
+                                                    (__mmask8) -1, __R);
 }
 
 extern __inline __m512d
@@ -3449,10 +3635,10 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_mask3_fnmadd_round_pd (__m512d __A, __m512d __B, __m512d __C,
                              __mmask8 __U, const int __R)
 {
-  return (__m512d) __builtin_ia32_vfmaddpd512_mask3 (-(__v8df) __A,
-                                                    (__v8df) __B,
-                                                    (__v8df) __C,
-                                                    (__mmask8) __U, __R);
+  return (__m512d) __builtin_ia32_vfnmaddpd512_mask3 ((__v8df) __A,
+                                                     (__v8df) __B,
+                                                     (__v8df) __C,
+                                                     (__mmask8) __U, __R);
 }
 
 extern __inline __m512d
@@ -3460,20 +3646,20 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_maskz_fnmadd_round_pd (__mmask8 __U, __m512d __A, __m512d __B,
                              __m512d __C, const int __R)
 {
-  return (__m512d) __builtin_ia32_vfmaddpd512_maskz (-(__v8df) __A,
-                                                    (__v8df) __B,
-                                                    (__v8df) __C,
-                                                    (__mmask8) __U, __R);
+  return (__m512d) __builtin_ia32_vfnmaddpd512_maskz ((__v8df) __A,
+                                                     (__v8df) __B,
+                                                     (__v8df) __C,
+                                                     (__mmask8) __U, __R);
 }
 
 extern __inline __m512
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_fnmadd_round_ps (__m512 __A, __m512 __B, __m512 __C, const int __R)
 {
-  return (__m512) __builtin_ia32_vfmaddps512_mask (-(__v16sf) __A,
-                                                  (__v16sf) __B,
-                                                  (__v16sf) __C,
-                                                  (__mmask16) -1, __R);
+  return (__m512) __builtin_ia32_vfnmaddps512_mask ((__v16sf) __A,
+                                                   (__v16sf) __B,
+                                                   (__v16sf) __C,
+                                                   (__mmask16) -1, __R);
 }
 
 extern __inline __m512
@@ -3492,10 +3678,10 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_mask3_fnmadd_round_ps (__m512 __A, __m512 __B, __m512 __C,
                              __mmask16 __U, const int __R)
 {
-  return (__m512) __builtin_ia32_vfmaddps512_mask3 (-(__v16sf) __A,
-                                                   (__v16sf) __B,
-                                                   (__v16sf) __C,
-                                                   (__mmask16) __U, __R);
+  return (__m512) __builtin_ia32_vfnmaddps512_mask3 ((__v16sf) __A,
+                                                    (__v16sf) __B,
+                                                    (__v16sf) __C,
+                                                    (__mmask16) __U, __R);
 }
 
 extern __inline __m512
@@ -3503,20 +3689,20 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_maskz_fnmadd_round_ps (__mmask16 __U, __m512 __A, __m512 __B,
                              __m512 __C, const int __R)
 {
-  return (__m512) __builtin_ia32_vfmaddps512_maskz (-(__v16sf) __A,
-                                                   (__v16sf) __B,
-                                                   (__v16sf) __C,
-                                                   (__mmask16) __U, __R);
+  return (__m512) __builtin_ia32_vfnmaddps512_maskz ((__v16sf) __A,
+                                                    (__v16sf) __B,
+                                                    (__v16sf) __C,
+                                                    (__mmask16) __U, __R);
 }
 
 extern __inline __m512d
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_fnmsub_round_pd (__m512d __A, __m512d __B, __m512d __C, const int __R)
 {
-  return (__m512d) __builtin_ia32_vfmaddpd512_mask (-(__v8df) __A,
-                                                   (__v8df) __B,
-                                                   -(__v8df) __C,
-                                                   (__mmask8) -1, __R);
+  return (__m512d) __builtin_ia32_vfnmsubpd512_mask ((__v8df) __A,
+                                                    (__v8df) __B,
+                                                    (__v8df) __C,
+                                                    (__mmask8) -1, __R);
 }
 
 extern __inline __m512d
@@ -3546,20 +3732,20 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_maskz_fnmsub_round_pd (__mmask8 __U, __m512d __A, __m512d __B,
                              __m512d __C, const int __R)
 {
-  return (__m512d) __builtin_ia32_vfmaddpd512_maskz (-(__v8df) __A,
-                                                    (__v8df) __B,
-                                                    -(__v8df) __C,
-                                                    (__mmask8) __U, __R);
+  return (__m512d) __builtin_ia32_vfnmsubpd512_maskz ((__v8df) __A,
+                                                     (__v8df) __B,
+                                                     (__v8df) __C,
+                                                     (__mmask8) __U, __R);
 }
 
 extern __inline __m512
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_fnmsub_round_ps (__m512 __A, __m512 __B, __m512 __C, const int __R)
 {
-  return (__m512) __builtin_ia32_vfmaddps512_mask (-(__v16sf) __A,
-                                                  (__v16sf) __B,
-                                                  -(__v16sf) __C,
-                                                  (__mmask16) -1, __R);
+  return (__m512) __builtin_ia32_vfnmsubps512_mask ((__v16sf) __A,
+                                                   (__v16sf) __B,
+                                                   (__v16sf) __C,
+                                                   (__mmask16) -1, __R);
 }
 
 extern __inline __m512
@@ -3589,10 +3775,10 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_maskz_fnmsub_round_ps (__mmask16 __U, __m512 __A, __m512 __B,
                              __m512 __C, const int __R)
 {
-  return (__m512) __builtin_ia32_vfmaddps512_maskz (-(__v16sf) __A,
-                                                   (__v16sf) __B,
-                                                   -(__v16sf) __C,
-                                                   (__mmask16) __U, __R);
+  return (__m512) __builtin_ia32_vfnmsubps512_maskz ((__v16sf) __A,
+                                                    (__v16sf) __B,
+                                                    (__v16sf) __C,
+                                                    (__mmask16) __U, __R);
 }
 #else
 #define _mm512_fmadd_round_pd(A, B, C, R)            \
@@ -3620,34 +3806,34 @@ _mm512_maskz_fnmsub_round_ps (__mmask16 __U, __m512 __A, __m512 __B,
     (__m512)__builtin_ia32_vfmaddps512_maskz(A, B, C, U, R)
 
 #define _mm512_fmsub_round_pd(A, B, C, R)            \
-    (__m512d)__builtin_ia32_vfmaddpd512_mask(A, B, -(C), -1, R)
+    (__m512d)__builtin_ia32_vfmsubpd512_mask(A, B, C, -1, R)
 
 #define _mm512_mask_fmsub_round_pd(A, U, B, C, R)    \
-    (__m512d)__builtin_ia32_vfmaddpd512_mask(A, B, -(C), U, R)
+    (__m512d)__builtin_ia32_vfmsubpd512_mask(A, B, C, U, R)
 
 #define _mm512_mask3_fmsub_round_pd(A, B, C, U, R)   \
     (__m512d)__builtin_ia32_vfmsubpd512_mask3(A, B, C, U, R)
 
 #define _mm512_maskz_fmsub_round_pd(U, A, B, C, R)   \
-    (__m512d)__builtin_ia32_vfmaddpd512_maskz(A, B, -(C), U, R)
+    (__m512d)__builtin_ia32_vfmsubpd512_maskz(A, B, C, U, R)
 
 #define _mm512_fmsub_round_ps(A, B, C, R)            \
-    (__m512)__builtin_ia32_vfmaddps512_mask(A, B, -(C), -1, R)
+    (__m512)__builtin_ia32_vfmsubps512_mask(A, B, C, -1, R)
 
 #define _mm512_mask_fmsub_round_ps(A, U, B, C, R)    \
-    (__m512)__builtin_ia32_vfmaddps512_mask(A, B, -(C), U, R)
+    (__m512)__builtin_ia32_vfmsubps512_mask(A, B, C, U, R)
 
 #define _mm512_mask3_fmsub_round_ps(A, B, C, U, R)   \
     (__m512)__builtin_ia32_vfmsubps512_mask3(A, B, C, U, R)
 
 #define _mm512_maskz_fmsub_round_ps(U, A, B, C, R)   \
-    (__m512)__builtin_ia32_vfmaddps512_maskz(A, B, -(C), U, R)
+    (__m512)__builtin_ia32_vfmsubps512_maskz(A, B, C, U, R)
 
 #define _mm512_fmaddsub_round_pd(A, B, C, R)            \
     (__m512d)__builtin_ia32_vfmaddsubpd512_mask(A, B, C, -1, R)
 
 #define _mm512_mask_fmaddsub_round_pd(A, U, B, C, R)    \
-    (__m512d)__builtin_ia32_vfmaddpd512_mask(A, B, C, U, R)
+    (__m512d)__builtin_ia32_vfmaddsubpd512_mask(A, B, C, U, R)
 
 #define _mm512_mask3_fmaddsub_round_pd(A, B, C, U, R)   \
     (__m512d)__builtin_ia32_vfmaddsubpd512_mask3(A, B, C, U, R)
@@ -3692,31 +3878,31 @@ _mm512_maskz_fnmsub_round_ps (__mmask16 __U, __m512 __A, __m512 __B,
     (__m512)__builtin_ia32_vfmaddsubps512_maskz(A, B, -(C), U, R)
 
 #define _mm512_fnmadd_round_pd(A, B, C, R)            \
-    (__m512d)__builtin_ia32_vfmaddpd512_mask(-(A), B, C, -1, R)
+    (__m512d)__builtin_ia32_vfnmaddpd512_mask(A, B, C, -1, R)
 
 #define _mm512_mask_fnmadd_round_pd(A, U, B, C, R)    \
-    (__m512d)__builtin_ia32_vfnmaddpd512_mask(-(A), B, C, U, R)
+    (__m512d)__builtin_ia32_vfnmaddpd512_mask(A, B, C, U, R)
 
 #define _mm512_mask3_fnmadd_round_pd(A, B, C, U, R)   \
-    (__m512d)__builtin_ia32_vfmaddpd512_mask3(-(A), B, C, U, R)
+    (__m512d)__builtin_ia32_vfnmaddpd512_mask3(A, B, C, U, R)
 
 #define _mm512_maskz_fnmadd_round_pd(U, A, B, C, R)   \
-    (__m512d)__builtin_ia32_vfmaddpd512_maskz(-(A), B, C, U, R)
+    (__m512d)__builtin_ia32_vfnmaddpd512_maskz(A, B, C, U, R)
 
 #define _mm512_fnmadd_round_ps(A, B, C, R)            \
-    (__m512)__builtin_ia32_vfmaddps512_mask(-(A), B, C, -1, R)
+    (__m512)__builtin_ia32_vfnmaddps512_mask(A, B, C, -1, R)
 
 #define _mm512_mask_fnmadd_round_ps(A, U, B, C, R)    \
-    (__m512)__builtin_ia32_vfnmaddps512_mask(-(A), B, C, U, R)
+    (__m512)__builtin_ia32_vfnmaddps512_mask(A, B, C, U, R)
 
 #define _mm512_mask3_fnmadd_round_ps(A, B, C, U, R)   \
-    (__m512)__builtin_ia32_vfmaddps512_mask3(-(A), B, C, U, R)
+    (__m512)__builtin_ia32_vfnmaddps512_mask3(A, B, C, U, R)
 
 #define _mm512_maskz_fnmadd_round_ps(U, A, B, C, R)   \
-    (__m512)__builtin_ia32_vfmaddps512_maskz(-(A), B, C, U, R)
+    (__m512)__builtin_ia32_vfnmaddps512_maskz(A, B, C, U, R)
 
 #define _mm512_fnmsub_round_pd(A, B, C, R)            \
-    (__m512d)__builtin_ia32_vfmaddpd512_mask(-(A), B, -(C), -1, R)
+    (__m512d)__builtin_ia32_vfnmsubpd512_mask(A, B, C, -1, R)
 
 #define _mm512_mask_fnmsub_round_pd(A, U, B, C, R)    \
     (__m512d)__builtin_ia32_vfnmsubpd512_mask(A, B, C, U, R)
@@ -3725,10 +3911,10 @@ _mm512_maskz_fnmsub_round_ps (__mmask16 __U, __m512 __A, __m512 __B,
     (__m512d)__builtin_ia32_vfnmsubpd512_mask3(A, B, C, U, R)
 
 #define _mm512_maskz_fnmsub_round_pd(U, A, B, C, R)   \
-    (__m512d)__builtin_ia32_vfmaddpd512_maskz(-(A), B, -(C), U, R)
+    (__m512d)__builtin_ia32_vfnmsubpd512_maskz(A, B, C, U, R)
 
 #define _mm512_fnmsub_round_ps(A, B, C, R)            \
-    (__m512)__builtin_ia32_vfmaddps512_mask(-(A), B, -(C), -1, R)
+    (__m512)__builtin_ia32_vfnmsubps512_mask(A, B, C, -1, R)
 
 #define _mm512_mask_fnmsub_round_ps(A, U, B, C, R)    \
     (__m512)__builtin_ia32_vfnmsubps512_mask(A, B, C, U, R)
@@ -3737,7 +3923,7 @@ _mm512_maskz_fnmsub_round_ps (__mmask16 __U, __m512 __A, __m512 __B,
     (__m512)__builtin_ia32_vfnmsubps512_mask3(A, B, C, U, R)
 
 #define _mm512_maskz_fnmsub_round_ps(U, A, B, C, R)   \
-    (__m512)__builtin_ia32_vfmaddps512_maskz(-(A), B, -(C), U, R)
+    (__m512)__builtin_ia32_vfnmsubps512_maskz(A, B, C, U, R)
 #endif
 
 extern __inline __m512i
@@ -6087,6 +6273,90 @@ _mm512_mask_storeu_ps (void *__P, __mmask16 __U, __m512 __A)
                                   (__mmask16) __U);
 }
 
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_load_ss (__m128 __W, __mmask8 __U, const float *__P)
+{
+  return (__m128) __builtin_ia32_loadss_mask (__P, (__v4sf) __W, __U);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_load_ss (__mmask8 __U, const float *__P)
+{
+  return (__m128) __builtin_ia32_loadss_mask (__P, (__v4sf) _mm_setzero_ps (),
+                                             __U);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_load_sd (__m128d __W, __mmask8 __U, const double *__P)
+{
+  return (__m128d) __builtin_ia32_loadsd_mask (__P, (__v2df) __W, __U);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_load_sd (__mmask8 __U, const double *__P)
+{
+  return (__m128d) __builtin_ia32_loadsd_mask (__P, (__v2df) _mm_setzero_pd (),
+                                              __U);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_move_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B)
+{
+  return (__m128) __builtin_ia32_movess_mask ((__v4sf) __A, (__v4sf) __B,
+                                             (__v4sf) __W, __U);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_move_ss (__mmask8 __U, __m128 __A, __m128 __B)
+{
+  return (__m128) __builtin_ia32_movess_mask ((__v4sf) __A, (__v4sf) __B,
+                                             (__v4sf) _mm_setzero_ps (), __U);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_move_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B)
+{
+  return (__m128d) __builtin_ia32_movesd_mask ((__v2df) __A, (__v2df) __B,
+                                              (__v2df) __W, __U);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_move_sd (__mmask8 __U, __m128d __A, __m128d __B)
+{
+  return (__m128d) __builtin_ia32_movesd_mask ((__v2df) __A, (__v2df) __B,
+                                              (__v2df) _mm_setzero_pd (),
+                                              __U);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_store_ss (float *__P, __mmask8 __U, __m128 __A)
+{
+  __builtin_ia32_storess_mask (__P, (__v4sf) __A, (__mmask8) __U);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_store_sd (double *__P, __mmask8 __U, __m128d __A)
+{
+  __builtin_ia32_storesd_mask (__P, (__v2df) __A, (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_loadu_epi64 (void const *__P)
+{
+  return *(__m512i_u *) __P;
+}
+
 extern __inline __m512i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_mask_loadu_epi64 (__m512i __W, __mmask8 __U, void const *__P)
@@ -6106,6 +6376,13 @@ _mm512_maskz_loadu_epi64 (__mmask8 __U, void const *__P)
                                                     (__mmask8) __U);
 }
 
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_storeu_epi64 (void *__P, __m512i __A)
+{
+  *(__m512i_u *) __P = (__m512i_u) __A;
+}
+
 extern __inline void
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_mask_storeu_epi64 (void *__P, __mmask8 __U, __m512i __A)
@@ -6121,6 +6398,13 @@ _mm512_loadu_si512 (void const *__P)
   return *(__m512i_u *)__P;
 }
 
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_loadu_epi32 (void const *__P)
+{
+  return *(__m512i_u *) __P;
+}
+
 extern __inline __m512i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_mask_loadu_epi32 (__m512i __W, __mmask16 __U, void const *__P)
@@ -6147,6 +6431,13 @@ _mm512_storeu_si512 (void *__P, __m512i __A)
   *(__m512i_u *)__P = __A;
 }
 
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_storeu_epi32 (void *__P, __m512i __A)
+{
+  *(__m512i_u *) __P = (__m512i_u) __A;
+}
+
 extern __inline void
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_mask_storeu_epi32 (void *__P, __mmask16 __U, __m512i __A)
@@ -7191,7 +7482,7 @@ _mm512_xor_epi64 (__m512i __A, __m512i __B)
 
 extern __inline __m512i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm512_mask_xor_epi64 (__m512i __W, __mmask16 __U, __m512i __A, __m512i __B)
+_mm512_mask_xor_epi64 (__m512i __W, __mmask8 __U, __m512i __A, __m512i __B)
 {
   return (__m512i) __builtin_ia32_pxorq512_mask ((__v8di) __A,
                                                 (__v8di) __B,
@@ -7201,7 +7492,7 @@ _mm512_mask_xor_epi64 (__m512i __W, __mmask16 __U, __m512i __A, __m512i __B)
 
 extern __inline __m512i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm512_maskz_xor_epi64 (__mmask16 __U, __m512i __A, __m512i __B)
+_mm512_maskz_xor_epi64 (__mmask8 __U, __m512i __A, __m512i __B)
 {
   return (__m512i) __builtin_ia32_pxorq512_mask ((__v8di) __A,
                                                 (__v8di) __B,
@@ -7612,7 +7903,7 @@ _mm512_mask_abs_ps (__m512 __W, __mmask16 __U, __m512 __A)
 
 extern __inline __m512d
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm512_abs_pd (__m512 __A)
+_mm512_abs_pd (__m512d __A)
 {
   return (__m512d) _mm512_and_epi64 ((__m512i) __A,
                                     _mm512_set1_epi64 (0x7fffffffffffffffLL));
@@ -7620,7 +7911,7 @@ _mm512_abs_pd (__m512 __A)
 
 extern __inline __m512d
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm512_mask_abs_pd (__m512d __W, __mmask8 __U, __m512 __A)
+_mm512_mask_abs_pd (__m512d __W, __mmask8 __U, __m512d __A)
 {
   return (__m512d)
         _mm512_mask_and_epi64 ((__m512i) __W, __U, (__m512i) __A,
@@ -8878,10 +9169,43 @@ _mm512_maskz_roundscale_round_pd (__mmask8 __A, __m512d __B,
 
 extern __inline __m128
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_roundscale_round_ss (__m128 __A, __m128 __B, const int __imm, const int __R)
+_mm_roundscale_round_ss (__m128 __A, __m128 __B, const int __imm,
+                        const int __R)
+{
+  return (__m128)
+    __builtin_ia32_rndscaless_mask_round ((__v4sf) __A,
+                                         (__v4sf) __B, __imm,
+                                         (__v4sf)
+                                         _mm_setzero_ps (),
+                                         (__mmask8) -1,
+                                         __R);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_roundscale_round_ss (__m128 __A, __mmask8 __B, __m128 __C,
+                             __m128 __D, const int __imm, const int __R)
+{
+  return (__m128)
+    __builtin_ia32_rndscaless_mask_round ((__v4sf) __C,
+                                         (__v4sf) __D, __imm,
+                                         (__v4sf) __A,
+                                         (__mmask8) __B,
+                                         __R);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_roundscale_round_ss (__mmask8 __A, __m128 __B, __m128 __C,
+                              const int __imm, const int __R)
 {
-  return (__m128) __builtin_ia32_rndscaless_round ((__v4sf) __A,
-                                                  (__v4sf) __B, __imm, __R);
+  return (__m128)
+    __builtin_ia32_rndscaless_mask_round ((__v4sf) __B,
+                                         (__v4sf) __C, __imm,
+                                         (__v4sf)
+                                         _mm_setzero_ps (),
+                                         (__mmask8) __A,
+                                         __R);
 }
 
 extern __inline __m128d
@@ -8889,8 +9213,40 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm_roundscale_round_sd (__m128d __A, __m128d __B, const int __imm,
                         const int __R)
 {
-  return (__m128d) __builtin_ia32_rndscalesd_round ((__v2df) __A,
-                                                   (__v2df) __B, __imm, __R);
+  return (__m128d)
+    __builtin_ia32_rndscalesd_mask_round ((__v2df) __A,
+                                         (__v2df) __B, __imm,
+                                         (__v2df)
+                                         _mm_setzero_pd (),
+                                         (__mmask8) -1,
+                                         __R);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_roundscale_round_sd (__m128d __A, __mmask8 __B, __m128d __C,
+                             __m128d __D, const int __imm, const int __R)
+{
+  return (__m128d)
+    __builtin_ia32_rndscalesd_mask_round ((__v2df) __C,
+                                         (__v2df) __D, __imm,
+                                         (__v2df) __A,
+                                         (__mmask8) __B,
+                                         __R);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_roundscale_round_sd (__mmask8 __A, __m128d __B, __m128d __C,
+                              const int __imm, const int __R)
+{
+  return (__m128d)
+    __builtin_ia32_rndscalesd_mask_round ((__v2df) __B,
+                                         (__v2df) __C, __imm,
+                                         (__v2df)
+                                         _mm_setzero_pd (),
+                                         (__mmask8) __A,
+                                         __R);
 }
 
 #else
@@ -8920,12 +9276,54 @@ _mm_roundscale_round_sd (__m128d __A, __m128d __B, const int __imm,
                                             (int)(C),                  \
                                             (__v8df)_mm512_setzero_pd(),\
                                             (__mmask8)(A), R))
-#define _mm_roundscale_round_ss(A, B, C, R)                                    \
-  ((__m128) __builtin_ia32_rndscaless_round ((__v4sf)(__m128)(A),      \
-    (__v4sf)(__m128)(B), (int)(C), R))
-#define _mm_roundscale_round_sd(A, B, C, R)                                    \
-  ((__m128d) __builtin_ia32_rndscalesd_round ((__v2df)(__m128d)(A),    \
-    (__v2df)(__m128d)(B), (int)(C), R))
+#define _mm_roundscale_round_ss(A, B, I, R)                            \
+  ((__m128)                                                            \
+   __builtin_ia32_rndscaless_mask_round ((__v4sf) (__m128) (A),                \
+                                        (__v4sf) (__m128) (B),         \
+                                        (int) (I),                     \
+                                        (__v4sf) _mm_setzero_ps (),    \
+                                        (__mmask8) (-1),               \
+                                        (int) (R)))
+#define _mm_mask_roundscale_round_ss(A, U, B, C, I, R)         \
+  ((__m128)                                                    \
+   __builtin_ia32_rndscaless_mask_round ((__v4sf) (__m128) (B),        \
+                                        (__v4sf) (__m128) (C), \
+                                        (int) (I),             \
+                                        (__v4sf) (__m128) (A), \
+                                        (__mmask8) (U),        \
+                                        (int) (R)))
+#define _mm_maskz_roundscale_round_ss(U, A, B, I, R)                   \
+  ((__m128)                                                            \
+   __builtin_ia32_rndscaless_mask_round ((__v4sf) (__m128) (A),                \
+                                        (__v4sf) (__m128) (B),         \
+                                        (int) (I),                     \
+                                        (__v4sf) _mm_setzero_ps (),    \
+                                        (__mmask8) (U),                \
+                                        (int) (R)))
+#define _mm_roundscale_round_sd(A, B, I, R)                            \
+  ((__m128d)                                                           \
+   __builtin_ia32_rndscalesd_mask_round ((__v2df) (__m128d) (A),       \
+                                        (__v2df) (__m128d) (B),        \
+                                        (int) (I),                     \
+                                        (__v2df) _mm_setzero_pd (),    \
+                                        (__mmask8) (-1),               \
+                                        (int) (R)))
+#define _mm_mask_roundscale_round_sd(A, U, B, C, I, R)                 \
+  ((__m128d)                                                           \
+   __builtin_ia32_rndscalesd_mask_round ((__v2df) (__m128d) (B),       \
+                                        (__v2df) (__m128d) (C),        \
+                                        (int) (I),                     \
+                                        (__v2df) (__m128d) (A),        \
+                                        (__mmask8) (U),                \
+                                        (int) (R)))
+#define _mm_maskz_roundscale_round_sd(U, A, B, I, R)                   \
+  ((__m128d)                                                           \
+   __builtin_ia32_rndscalesd_mask_round ((__v2df) (__m128d) (A),       \
+                                        (__v2df) (__m128d) (B),        \
+                                        (int) (I),                     \
+                                        (__v2df) _mm_setzero_pd (),    \
+                                        (__mmask8) (U),                \
+                                        (int) (R)))
 #endif
 
 extern __inline __m512
@@ -9429,7 +9827,7 @@ _mm512_cmpneq_epu32_mask (__m512i __X, __m512i __Y)
 
 extern __inline __mmask8
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm512_mask_cmpneq_epi64_mask (__mmask16 __M, __m512i __X, __m512i __Y)
+_mm512_mask_cmpneq_epi64_mask (__mmask8 __M, __m512i __X, __m512i __Y)
 {
   return (__mmask8) __builtin_ia32_cmpq512_mask ((__v8di) __X,
                                                    (__v8di) __Y, 4,
@@ -10691,22 +11089,22 @@ _mm512_mask_insertf32x4 (__m512 __A, __mmask16 __B, __m512 __C,
 #define _mm512_maskz_insertf32x4(A, X, Y, C)                            \
   ((__m512) __builtin_ia32_insertf32x4_mask ((__v16sf)(__m512) (X),     \
     (__v4sf)(__m128) (Y), (int) (C), (__v16sf)_mm512_setzero_ps(),      \
-    (__mmask8)(A)))
+    (__mmask16)(A)))
 
 #define _mm512_maskz_inserti32x4(A, X, Y, C)                            \
   ((__m512i) __builtin_ia32_inserti32x4_mask ((__v16si)(__m512i) (X),   \
     (__v4si)(__m128i) (Y), (int) (C), (__v16si)_mm512_setzero_si512 (),     \
-    (__mmask8)(A)))
+    (__mmask16)(A)))
 
 #define _mm512_mask_insertf32x4(A, B, X, Y, C)                          \
   ((__m512) __builtin_ia32_insertf32x4_mask ((__v16sf)(__m512) (X),     \
     (__v4sf)(__m128) (Y), (int) (C), (__v16sf)(__m512) (A),             \
-                                            (__mmask8)(B)))
+                                            (__mmask16)(B)))
 
 #define _mm512_mask_inserti32x4(A, B, X, Y, C)                          \
   ((__m512i) __builtin_ia32_inserti32x4_mask ((__v16si)(__m512i) (X),   \
     (__v4si)(__m128i) (Y), (int) (C), (__v16si)(__m512i) (A),           \
-                                             (__mmask8)(B)))
+                                             (__mmask16)(B)))
 #endif
 
 extern __inline __m512i
@@ -11299,10 +11697,612 @@ _mm_fnmsub_round_ss (__m128 __W, __m128 __A, __m128 __B, const int __R)
     (__m128)__builtin_ia32_vfmaddss3_round(A, -(B), -(C), R)
 #endif
 
-#ifdef __OPTIMIZE__
-extern __inline int
+extern __inline __m128d
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comi_round_ss (__m128 __A, __m128 __B, const int __P, const int __R)
+_mm_mask_fmadd_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B)
+{
+  return (__m128d) __builtin_ia32_vfmaddsd3_mask ((__v2df) __W,
+                                                 (__v2df) __A,
+                                                 (__v2df) __B,
+                                                 (__mmask8) __U,
+                                                 _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_fmadd_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B)
+{
+  return (__m128) __builtin_ia32_vfmaddss3_mask ((__v4sf) __W,
+                                                (__v4sf) __A,
+                                                (__v4sf) __B,
+                                                (__mmask8) __U,
+                                                _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask3_fmadd_sd (__m128d __W, __m128d __A, __m128d __B, __mmask8 __U)
+{
+  return (__m128d) __builtin_ia32_vfmaddsd3_mask3 ((__v2df) __W,
+                                                  (__v2df) __A,
+                                                  (__v2df) __B,
+                                                  (__mmask8) __U,
+                                                  _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask3_fmadd_ss (__m128 __W, __m128 __A, __m128 __B, __mmask8 __U)
+{
+  return (__m128) __builtin_ia32_vfmaddss3_mask3 ((__v4sf) __W,
+                                                 (__v4sf) __A,
+                                                 (__v4sf) __B,
+                                                 (__mmask8) __U,
+                                                 _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_fmadd_sd (__mmask8 __U, __m128d __W, __m128d __A, __m128d __B)
+{
+  return (__m128d) __builtin_ia32_vfmaddsd3_maskz ((__v2df) __W,
+                                                  (__v2df) __A,
+                                                  (__v2df) __B,
+                                                  (__mmask8) __U,
+                                                  _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_fmadd_ss (__mmask8 __U, __m128 __W, __m128 __A, __m128 __B)
+{
+  return (__m128) __builtin_ia32_vfmaddss3_maskz ((__v4sf) __W,
+                                                 (__v4sf) __A,
+                                                 (__v4sf) __B,
+                                                 (__mmask8) __U,
+                                                 _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_fmsub_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B)
+{
+  return (__m128d) __builtin_ia32_vfmaddsd3_mask ((__v2df) __W,
+                                                 (__v2df) __A,
+                                                 -(__v2df) __B,
+                                                 (__mmask8) __U,
+                                                 _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_fmsub_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B)
+{
+  return (__m128) __builtin_ia32_vfmaddss3_mask ((__v4sf) __W,
+                                                (__v4sf) __A,
+                                                -(__v4sf) __B,
+                                                (__mmask8) __U,
+                                                _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask3_fmsub_sd (__m128d __W, __m128d __A, __m128d __B, __mmask8 __U)
+{
+  return (__m128d) __builtin_ia32_vfmsubsd3_mask3 ((__v2df) __W,
+                                                  (__v2df) __A,
+                                                  (__v2df) __B,
+                                                  (__mmask8) __U,
+                                                  _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask3_fmsub_ss (__m128 __W, __m128 __A, __m128 __B, __mmask8 __U)
+{
+  return (__m128) __builtin_ia32_vfmsubss3_mask3 ((__v4sf) __W,
+                                                 (__v4sf) __A,
+                                                 (__v4sf) __B,
+                                                 (__mmask8) __U,
+                                                 _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_fmsub_sd (__mmask8 __U, __m128d __W, __m128d __A, __m128d __B)
+{
+  return (__m128d) __builtin_ia32_vfmaddsd3_maskz ((__v2df) __W,
+                                                  (__v2df) __A,
+                                                  -(__v2df) __B,
+                                                  (__mmask8) __U,
+                                                  _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_fmsub_ss (__mmask8 __U, __m128 __W, __m128 __A, __m128 __B)
+{
+  return (__m128) __builtin_ia32_vfmaddss3_maskz ((__v4sf) __W,
+                                                 (__v4sf) __A,
+                                                 -(__v4sf) __B,
+                                                 (__mmask8) __U,
+                                                 _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_fnmadd_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B)
+{
+  return (__m128d) __builtin_ia32_vfmaddsd3_mask ((__v2df) __W,
+                                                 -(__v2df) __A,
+                                                 (__v2df) __B,
+                                                 (__mmask8) __U,
+                                                 _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_fnmadd_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B)
+{
+  return (__m128) __builtin_ia32_vfmaddss3_mask ((__v4sf) __W,
+                                                -(__v4sf) __A,
+                                                (__v4sf) __B,
+                                                (__mmask8) __U,
+                                                _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask3_fnmadd_sd (__m128d __W, __m128d __A, __m128d __B, __mmask8 __U)
+{
+  return (__m128d) __builtin_ia32_vfmaddsd3_mask3 ((__v2df) __W,
+                                                  -(__v2df) __A,
+                                                  (__v2df) __B,
+                                                  (__mmask8) __U,
+                                                  _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask3_fnmadd_ss (__m128 __W, __m128 __A, __m128 __B, __mmask8 __U)
+{
+  return (__m128) __builtin_ia32_vfmaddss3_mask3 ((__v4sf) __W,
+                                                 -(__v4sf) __A,
+                                                 (__v4sf) __B,
+                                                 (__mmask8) __U,
+                                                 _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_fnmadd_sd (__mmask8 __U, __m128d __W, __m128d __A, __m128d __B)
+{
+  return (__m128d) __builtin_ia32_vfmaddsd3_maskz ((__v2df) __W,
+                                                  -(__v2df) __A,
+                                                  (__v2df) __B,
+                                                  (__mmask8) __U,
+                                                  _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_fnmadd_ss (__mmask8 __U, __m128 __W, __m128 __A, __m128 __B)
+{
+  return (__m128) __builtin_ia32_vfmaddss3_maskz ((__v4sf) __W,
+                                                 -(__v4sf) __A,
+                                                 (__v4sf) __B,
+                                                 (__mmask8) __U,
+                                                 _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_fnmsub_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B)
+{
+  return (__m128d) __builtin_ia32_vfmaddsd3_mask ((__v2df) __W,
+                                                 -(__v2df) __A,
+                                                 -(__v2df) __B,
+                                                 (__mmask8) __U,
+                                                 _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_fnmsub_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B)
+{
+  return (__m128) __builtin_ia32_vfmaddss3_mask ((__v4sf) __W,
+                                                -(__v4sf) __A,
+                                                -(__v4sf) __B,
+                                                (__mmask8) __U,
+                                                _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask3_fnmsub_sd (__m128d __W, __m128d __A, __m128d __B, __mmask8 __U)
+{
+  return (__m128d) __builtin_ia32_vfmsubsd3_mask3 ((__v2df) __W,
+                                                  -(__v2df) __A,
+                                                  (__v2df) __B,
+                                                  (__mmask8) __U,
+                                                  _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask3_fnmsub_ss (__m128 __W, __m128 __A, __m128 __B, __mmask8 __U)
+{
+  return (__m128) __builtin_ia32_vfmsubss3_mask3 ((__v4sf) __W,
+                                                 -(__v4sf) __A,
+                                                 (__v4sf) __B,
+                                                 (__mmask8) __U,
+                                                 _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_fnmsub_sd (__mmask8 __U, __m128d __W, __m128d __A, __m128d __B)
+{
+  return (__m128d) __builtin_ia32_vfmaddsd3_maskz ((__v2df) __W,
+                                                  -(__v2df) __A,
+                                                  -(__v2df) __B,
+                                                  (__mmask8) __U,
+                                                  _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_fnmsub_ss (__mmask8 __U, __m128 __W, __m128 __A, __m128 __B)
+{
+  return (__m128) __builtin_ia32_vfmaddss3_maskz ((__v4sf) __W,
+                                                 -(__v4sf) __A,
+                                                 -(__v4sf) __B,
+                                                 (__mmask8) __U,
+                                                 _MM_FROUND_CUR_DIRECTION);
+}
+
+#ifdef __OPTIMIZE__
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_fmadd_round_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B,
+                        const int __R)
+{
+  return (__m128d) __builtin_ia32_vfmaddsd3_mask ((__v2df) __W,
+                                                 (__v2df) __A,
+                                                 (__v2df) __B,
+                                                 (__mmask8) __U, __R);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_fmadd_round_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B,
+                        const int __R)
+{
+  return (__m128) __builtin_ia32_vfmaddss3_mask ((__v4sf) __W,
+                                                (__v4sf) __A,
+                                                (__v4sf) __B,
+                                                (__mmask8) __U, __R);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask3_fmadd_round_sd (__m128d __W, __m128d __A, __m128d __B, __mmask8 __U,
+                         const int __R)
+{
+  return (__m128d) __builtin_ia32_vfmaddsd3_mask3 ((__v2df) __W,
+                                                  (__v2df) __A,
+                                                  (__v2df) __B,
+                                                  (__mmask8) __U, __R);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask3_fmadd_round_ss (__m128 __W, __m128 __A, __m128 __B, __mmask8 __U,
+                         const int __R)
+{
+  return (__m128) __builtin_ia32_vfmaddss3_mask3 ((__v4sf) __W,
+                                                 (__v4sf) __A,
+                                                 (__v4sf) __B,
+                                                 (__mmask8) __U, __R);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_fmadd_round_sd (__mmask8 __U, __m128d __W, __m128d __A, __m128d __B,
+                         const int __R)
+{
+  return (__m128d) __builtin_ia32_vfmaddsd3_maskz ((__v2df) __W,
+                                                  (__v2df) __A,
+                                                  (__v2df) __B,
+                                                  (__mmask8) __U, __R);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_fmadd_round_ss (__mmask8 __U, __m128 __W, __m128 __A, __m128 __B,
+                         const int __R)
+{
+  return (__m128) __builtin_ia32_vfmaddss3_maskz ((__v4sf) __W,
+                                                 (__v4sf) __A,
+                                                 (__v4sf) __B,
+                                                 (__mmask8) __U, __R);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_fmsub_round_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B,
+                        const int __R)
+{
+  return (__m128d) __builtin_ia32_vfmaddsd3_mask ((__v2df) __W,
+                                                 (__v2df) __A,
+                                                 -(__v2df) __B,
+                                                 (__mmask8) __U, __R);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_fmsub_round_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B,
+                        const int __R)
+{
+  return (__m128) __builtin_ia32_vfmaddss3_mask ((__v4sf) __W,
+                                                (__v4sf) __A,
+                                                -(__v4sf) __B,
+                                                (__mmask8) __U, __R);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask3_fmsub_round_sd (__m128d __W, __m128d __A, __m128d __B, __mmask8 __U,
+                         const int __R)
+{
+  return (__m128d) __builtin_ia32_vfmsubsd3_mask3 ((__v2df) __W,
+                                                  (__v2df) __A,
+                                                  (__v2df) __B,
+                                                  (__mmask8) __U, __R);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask3_fmsub_round_ss (__m128 __W, __m128 __A, __m128 __B, __mmask8 __U,
+                         const int __R)
+{
+  return (__m128) __builtin_ia32_vfmsubss3_mask3 ((__v4sf) __W,
+                                                 (__v4sf) __A,
+                                                 (__v4sf) __B,
+                                                 (__mmask8) __U, __R);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_fmsub_round_sd (__mmask8 __U, __m128d __W, __m128d __A, __m128d __B,
+                         const int __R)
+{
+  return (__m128d) __builtin_ia32_vfmaddsd3_maskz ((__v2df) __W,
+                                                  (__v2df) __A,
+                                                  -(__v2df) __B,
+                                                  (__mmask8) __U, __R);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_fmsub_round_ss (__mmask8 __U, __m128 __W, __m128 __A, __m128 __B,
+                         const int __R)
+{
+  return (__m128) __builtin_ia32_vfmaddss3_maskz ((__v4sf) __W,
+                                                 (__v4sf) __A,
+                                                 -(__v4sf) __B,
+                                                 (__mmask8) __U, __R);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_fnmadd_round_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B,
+                        const int __R)
+{
+  return (__m128d) __builtin_ia32_vfmaddsd3_mask ((__v2df) __W,
+                                                 -(__v2df) __A,
+                                                 (__v2df) __B,
+                                                 (__mmask8) __U, __R);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_fnmadd_round_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B,
+                        const int __R)
+{
+  return (__m128) __builtin_ia32_vfmaddss3_mask ((__v4sf) __W,
+                                                -(__v4sf) __A,
+                                                (__v4sf) __B,
+                                                (__mmask8) __U, __R);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask3_fnmadd_round_sd (__m128d __W, __m128d __A, __m128d __B, __mmask8 __U,
+                         const int __R)
+{
+  return (__m128d) __builtin_ia32_vfmaddsd3_mask3 ((__v2df) __W,
+                                                  -(__v2df) __A,
+                                                  (__v2df) __B,
+                                                  (__mmask8) __U, __R);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask3_fnmadd_round_ss (__m128 __W, __m128 __A, __m128 __B, __mmask8 __U,
+                         const int __R)
+{
+  return (__m128) __builtin_ia32_vfmaddss3_mask3 ((__v4sf) __W,
+                                                 -(__v4sf) __A,
+                                                 (__v4sf) __B,
+                                                 (__mmask8) __U, __R);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_fnmadd_round_sd (__mmask8 __U, __m128d __W, __m128d __A, __m128d __B,
+                         const int __R)
+{
+  return (__m128d) __builtin_ia32_vfmaddsd3_maskz ((__v2df) __W,
+                                                  -(__v2df) __A,
+                                                  (__v2df) __B,
+                                                  (__mmask8) __U, __R);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_fnmadd_round_ss (__mmask8 __U, __m128 __W, __m128 __A, __m128 __B,
+                         const int __R)
+{
+  return (__m128) __builtin_ia32_vfmaddss3_maskz ((__v4sf) __W,
+                                                 -(__v4sf) __A,
+                                                 (__v4sf) __B,
+                                                 (__mmask8) __U, __R);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_fnmsub_round_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B,
+                        const int __R)
+{
+  return (__m128d) __builtin_ia32_vfmaddsd3_mask ((__v2df) __W,
+                                                 -(__v2df) __A,
+                                                 -(__v2df) __B,
+                                                 (__mmask8) __U, __R);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_fnmsub_round_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B,
+                        const int __R)
+{
+  return (__m128) __builtin_ia32_vfmaddss3_mask ((__v4sf) __W,
+                                                -(__v4sf) __A,
+                                                -(__v4sf) __B,
+                                                (__mmask8) __U, __R);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask3_fnmsub_round_sd (__m128d __W, __m128d __A, __m128d __B, __mmask8 __U,
+                         const int __R)
+{
+  return (__m128d) __builtin_ia32_vfmsubsd3_mask3 ((__v2df) __W,
+                                                  -(__v2df) __A,
+                                                  (__v2df) __B,
+                                                  (__mmask8) __U, __R);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask3_fnmsub_round_ss (__m128 __W, __m128 __A, __m128 __B, __mmask8 __U,
+                         const int __R)
+{
+  return (__m128) __builtin_ia32_vfmsubss3_mask3 ((__v4sf) __W,
+                                                 -(__v4sf) __A,
+                                                 (__v4sf) __B,
+                                                 (__mmask8) __U, __R);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_fnmsub_round_sd (__mmask8 __U, __m128d __W, __m128d __A, __m128d __B,
+                         const int __R)
+{
+  return (__m128d) __builtin_ia32_vfmaddsd3_maskz ((__v2df) __W,
+                                                  -(__v2df) __A,
+                                                  -(__v2df) __B,
+                                                  (__mmask8) __U, __R);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_fnmsub_round_ss (__mmask8 __U, __m128 __W, __m128 __A, __m128 __B,
+                         const int __R)
+{
+  return (__m128) __builtin_ia32_vfmaddss3_maskz ((__v4sf) __W,
+                                                 -(__v4sf) __A,
+                                                 -(__v4sf) __B,
+                                                 (__mmask8) __U, __R);
+}
+#else
+#define _mm_mask_fmadd_round_sd(A, U, B, C, R)            \
+    (__m128d) __builtin_ia32_vfmaddsd3_mask (A, B, C, U, R)
+
+#define _mm_mask_fmadd_round_ss(A, U, B, C, R)            \
+    (__m128) __builtin_ia32_vfmaddss3_mask (A, B, C, U, R)
+
+#define _mm_mask3_fmadd_round_sd(A, B, C, U, R)            \
+    (__m128d) __builtin_ia32_vfmaddsd3_mask3 (A, B, C, U, R)
+
+#define _mm_mask3_fmadd_round_ss(A, B, C, U, R)            \
+    (__m128) __builtin_ia32_vfmaddss3_mask3 (A, B, C, U, R)
+
+#define _mm_maskz_fmadd_round_sd(U, A, B, C, R)            \
+    (__m128d) __builtin_ia32_vfmaddsd3_maskz (A, B, C, U, R)
+
+#define _mm_maskz_fmadd_round_ss(U, A, B, C, R)            \
+    (__m128) __builtin_ia32_vfmaddss3_maskz (A, B, C, U, R)
+
+#define _mm_mask_fmsub_round_sd(A, U, B, C, R)            \
+    (__m128d) __builtin_ia32_vfmaddsd3_mask (A, B, -(C), U, R)
+
+#define _mm_mask_fmsub_round_ss(A, U, B, C, R)            \
+    (__m128) __builtin_ia32_vfmaddss3_mask (A, B, -(C), U, R)
+
+#define _mm_mask3_fmsub_round_sd(A, B, C, U, R)            \
+    (__m128d) __builtin_ia32_vfmsubsd3_mask3 (A, B, C, U, R)
+
+#define _mm_mask3_fmsub_round_ss(A, B, C, U, R)            \
+    (__m128) __builtin_ia32_vfmsubss3_mask3 (A, B, C, U, R)
+
+#define _mm_maskz_fmsub_round_sd(U, A, B, C, R)            \
+    (__m128d) __builtin_ia32_vfmaddsd3_maskz (A, B, -(C), U, R)
+
+#define _mm_maskz_fmsub_round_ss(U, A, B, C, R)            \
+    (__m128) __builtin_ia32_vfmaddss3_maskz (A, B, -(C), U, R)
+
+#define _mm_mask_fnmadd_round_sd(A, U, B, C, R)            \
+    (__m128d) __builtin_ia32_vfmaddsd3_mask (A, -(B), C, U, R)
+
+#define _mm_mask_fnmadd_round_ss(A, U, B, C, R)            \
+    (__m128) __builtin_ia32_vfmaddss3_mask (A, -(B), C, U, R)
+
+#define _mm_mask3_fnmadd_round_sd(A, B, C, U, R)            \
+    (__m128d) __builtin_ia32_vfmaddsd3_mask3 (A, -(B), C, U, R)
+
+#define _mm_mask3_fnmadd_round_ss(A, B, C, U, R)            \
+    (__m128) __builtin_ia32_vfmaddss3_mask3 (A, -(B), C, U, R)
+
+#define _mm_maskz_fnmadd_round_sd(U, A, B, C, R)            \
+    (__m128d) __builtin_ia32_vfmaddsd3_maskz (A, -(B), C, U, R)
+
+#define _mm_maskz_fnmadd_round_ss(U, A, B, C, R)            \
+    (__m128) __builtin_ia32_vfmaddss3_maskz (A, -(B), C, U, R)
+
+#define _mm_mask_fnmsub_round_sd(A, U, B, C, R)            \
+    (__m128d) __builtin_ia32_vfmaddsd3_mask (A, -(B), -(C), U, R)
+
+#define _mm_mask_fnmsub_round_ss(A, U, B, C, R)            \
+    (__m128) __builtin_ia32_vfmaddss3_mask (A, -(B), -(C), U, R)
+
+#define _mm_mask3_fnmsub_round_sd(A, B, C, U, R)            \
+    (__m128d) __builtin_ia32_vfmsubsd3_mask3 (A, -(B), C, U, R)
+
+#define _mm_mask3_fnmsub_round_ss(A, B, C, U, R)            \
+    (__m128) __builtin_ia32_vfmsubss3_mask3 (A, -(B), C, U, R)
+
+#define _mm_maskz_fnmsub_round_sd(U, A, B, C, R)            \
+    (__m128d) __builtin_ia32_vfmaddsd3_maskz (A, -(B), -(C), U, R)
+
+#define _mm_maskz_fnmsub_round_ss(U, A, B, C, R)            \
+    (__m128) __builtin_ia32_vfmaddss3_maskz (A, -(B), -(C), U, R)
+#endif
+
+#ifdef __OPTIMIZE__
+extern __inline int
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comi_round_ss (__m128 __A, __m128 __B, const int __P, const int __R)
 {
   return __builtin_ia32_vcomiss ((__v4sf) __A, (__v4sf) __B, __P, __R);
 }
@@ -12118,18 +13118,24 @@ extern __inline __m128d
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm_scalef_sd (__m128d __A, __m128d __B)
 {
-  return (__m128d) __builtin_ia32_scalefsd_round ((__v2df) __A,
-                                                 (__v2df) __B,
-                                                 _MM_FROUND_CUR_DIRECTION);
+  return (__m128d) __builtin_ia32_scalefsd_mask_round ((__v2df) __A,
+                                                   (__v2df) __B,
+                                                   (__v2df)
+                                                   _mm_setzero_pd (),
+                                                   (__mmask8) -1,
+                                                   _MM_FROUND_CUR_DIRECTION);
 }
 
 extern __inline __m128
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm_scalef_ss (__m128 __A, __m128 __B)
 {
-  return (__m128) __builtin_ia32_scalefss_round ((__v4sf) __A,
-                                                (__v4sf) __B,
-                                                _MM_FROUND_CUR_DIRECTION);
+  return (__m128) __builtin_ia32_scalefss_mask_round ((__v4sf) __A,
+                                                  (__v4sf) __B,
+                                                  (__v4sf)
+                                                  _mm_setzero_ps (),
+                                                  (__mmask8) -1,
+                                                  _MM_FROUND_CUR_DIRECTION);
 }
 
 extern __inline __m512d
@@ -12224,9 +13230,9 @@ extern __inline __m512d
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_fmsub_pd (__m512d __A, __m512d __B, __m512d __C)
 {
-  return (__m512d) __builtin_ia32_vfmaddpd512_mask ((__v8df) __A,
+  return (__m512d) __builtin_ia32_vfmsubpd512_mask ((__v8df) __A,
                                                    (__v8df) __B,
-                                                   -(__v8df) __C,
+                                                   (__v8df) __C,
                                                    (__mmask8) -1,
                                                    _MM_FROUND_CUR_DIRECTION);
 }
@@ -12235,9 +13241,9 @@ extern __inline __m512d
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_mask_fmsub_pd (__m512d __A, __mmask8 __U, __m512d __B, __m512d __C)
 {
-  return (__m512d) __builtin_ia32_vfmaddpd512_mask ((__v8df) __A,
+  return (__m512d) __builtin_ia32_vfmsubpd512_mask ((__v8df) __A,
                                                    (__v8df) __B,
-                                                   -(__v8df) __C,
+                                                   (__v8df) __C,
                                                    (__mmask8) __U,
                                                    _MM_FROUND_CUR_DIRECTION);
 }
@@ -12257,9 +13263,9 @@ extern __inline __m512d
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_maskz_fmsub_pd (__mmask8 __U, __m512d __A, __m512d __B, __m512d __C)
 {
-  return (__m512d) __builtin_ia32_vfmaddpd512_maskz ((__v8df) __A,
+  return (__m512d) __builtin_ia32_vfmsubpd512_maskz ((__v8df) __A,
                                                     (__v8df) __B,
-                                                    -(__v8df) __C,
+                                                    (__v8df) __C,
                                                     (__mmask8) __U,
                                                     _MM_FROUND_CUR_DIRECTION);
 }
@@ -12268,9 +13274,9 @@ extern __inline __m512
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_fmsub_ps (__m512 __A, __m512 __B, __m512 __C)
 {
-  return (__m512) __builtin_ia32_vfmaddps512_mask ((__v16sf) __A,
+  return (__m512) __builtin_ia32_vfmsubps512_mask ((__v16sf) __A,
                                                   (__v16sf) __B,
-                                                  -(__v16sf) __C,
+                                                  (__v16sf) __C,
                                                   (__mmask16) -1,
                                                   _MM_FROUND_CUR_DIRECTION);
 }
@@ -12279,9 +13285,9 @@ extern __inline __m512
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_mask_fmsub_ps (__m512 __A, __mmask16 __U, __m512 __B, __m512 __C)
 {
-  return (__m512) __builtin_ia32_vfmaddps512_mask ((__v16sf) __A,
+  return (__m512) __builtin_ia32_vfmsubps512_mask ((__v16sf) __A,
                                                   (__v16sf) __B,
-                                                  -(__v16sf) __C,
+                                                  (__v16sf) __C,
                                                   (__mmask16) __U,
                                                   _MM_FROUND_CUR_DIRECTION);
 }
@@ -12301,9 +13307,9 @@ extern __inline __m512
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_maskz_fmsub_ps (__mmask16 __U, __m512 __A, __m512 __B, __m512 __C)
 {
-  return (__m512) __builtin_ia32_vfmaddps512_maskz ((__v16sf) __A,
+  return (__m512) __builtin_ia32_vfmsubps512_maskz ((__v16sf) __A,
                                                    (__v16sf) __B,
-                                                   -(__v16sf) __C,
+                                                   (__v16sf) __C,
                                                    (__mmask16) __U,
                                                    _MM_FROUND_CUR_DIRECTION);
 }
@@ -12488,11 +13494,11 @@ extern __inline __m512d
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_fnmadd_pd (__m512d __A, __m512d __B, __m512d __C)
 {
-  return (__m512d) __builtin_ia32_vfmaddpd512_mask (-(__v8df) __A,
-                                                   (__v8df) __B,
-                                                   (__v8df) __C,
-                                                   (__mmask8) -1,
-                                                   _MM_FROUND_CUR_DIRECTION);
+  return (__m512d) __builtin_ia32_vfnmaddpd512_mask ((__v8df) __A,
+                                                    (__v8df) __B,
+                                                    (__v8df) __C,
+                                                    (__mmask8) -1,
+                                                    _MM_FROUND_CUR_DIRECTION);
 }
 
 extern __inline __m512d
@@ -12510,33 +13516,33 @@ extern __inline __m512d
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_mask3_fnmadd_pd (__m512d __A, __m512d __B, __m512d __C, __mmask8 __U)
 {
-  return (__m512d) __builtin_ia32_vfmaddpd512_mask3 (-(__v8df) __A,
-                                                    (__v8df) __B,
-                                                    (__v8df) __C,
-                                                    (__mmask8) __U,
-                                                    _MM_FROUND_CUR_DIRECTION);
+  return (__m512d) __builtin_ia32_vfnmaddpd512_mask3 ((__v8df) __A,
+                                                     (__v8df) __B,
+                                                     (__v8df) __C,
+                                                     (__mmask8) __U,
+                                                     _MM_FROUND_CUR_DIRECTION);
 }
 
 extern __inline __m512d
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_maskz_fnmadd_pd (__mmask8 __U, __m512d __A, __m512d __B, __m512d __C)
 {
-  return (__m512d) __builtin_ia32_vfmaddpd512_maskz (-(__v8df) __A,
-                                                    (__v8df) __B,
-                                                    (__v8df) __C,
-                                                    (__mmask8) __U,
-                                                    _MM_FROUND_CUR_DIRECTION);
+  return (__m512d) __builtin_ia32_vfnmaddpd512_maskz ((__v8df) __A,
+                                                     (__v8df) __B,
+                                                     (__v8df) __C,
+                                                     (__mmask8) __U,
+                                                     _MM_FROUND_CUR_DIRECTION);
 }
 
 extern __inline __m512
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_fnmadd_ps (__m512 __A, __m512 __B, __m512 __C)
 {
-  return (__m512) __builtin_ia32_vfmaddps512_mask (-(__v16sf) __A,
-                                                  (__v16sf) __B,
-                                                  (__v16sf) __C,
-                                                  (__mmask16) -1,
-                                                  _MM_FROUND_CUR_DIRECTION);
+  return (__m512) __builtin_ia32_vfnmaddps512_mask ((__v16sf) __A,
+                                                   (__v16sf) __B,
+                                                   (__v16sf) __C,
+                                                   (__mmask16) -1,
+                                                   _MM_FROUND_CUR_DIRECTION);
 }
 
 extern __inline __m512
@@ -12554,33 +13560,33 @@ extern __inline __m512
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_mask3_fnmadd_ps (__m512 __A, __m512 __B, __m512 __C, __mmask16 __U)
 {
-  return (__m512) __builtin_ia32_vfmaddps512_mask3 (-(__v16sf) __A,
-                                                   (__v16sf) __B,
-                                                   (__v16sf) __C,
-                                                   (__mmask16) __U,
-                                                   _MM_FROUND_CUR_DIRECTION);
+  return (__m512) __builtin_ia32_vfnmaddps512_mask3 ((__v16sf) __A,
+                                                    (__v16sf) __B,
+                                                    (__v16sf) __C,
+                                                    (__mmask16) __U,
+                                                    _MM_FROUND_CUR_DIRECTION);
 }
 
 extern __inline __m512
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_maskz_fnmadd_ps (__mmask16 __U, __m512 __A, __m512 __B, __m512 __C)
 {
-  return (__m512) __builtin_ia32_vfmaddps512_maskz (-(__v16sf) __A,
-                                                   (__v16sf) __B,
-                                                   (__v16sf) __C,
-                                                   (__mmask16) __U,
-                                                   _MM_FROUND_CUR_DIRECTION);
+  return (__m512) __builtin_ia32_vfnmaddps512_maskz ((__v16sf) __A,
+                                                    (__v16sf) __B,
+                                                    (__v16sf) __C,
+                                                    (__mmask16) __U,
+                                                    _MM_FROUND_CUR_DIRECTION);
 }
 
 extern __inline __m512d
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_fnmsub_pd (__m512d __A, __m512d __B, __m512d __C)
 {
-  return (__m512d) __builtin_ia32_vfmaddpd512_mask (-(__v8df) __A,
-                                                   (__v8df) __B,
-                                                   -(__v8df) __C,
-                                                   (__mmask8) -1,
-                                                   _MM_FROUND_CUR_DIRECTION);
+  return (__m512d) __builtin_ia32_vfnmsubpd512_mask ((__v8df) __A,
+                                                    (__v8df) __B,
+                                                    (__v8df) __C,
+                                                    (__mmask8) -1,
+                                                    _MM_FROUND_CUR_DIRECTION);
 }
 
 extern __inline __m512d
@@ -12609,22 +13615,22 @@ extern __inline __m512d
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_maskz_fnmsub_pd (__mmask8 __U, __m512d __A, __m512d __B, __m512d __C)
 {
-  return (__m512d) __builtin_ia32_vfmaddpd512_maskz (-(__v8df) __A,
-                                                    (__v8df) __B,
-                                                    -(__v8df) __C,
-                                                    (__mmask8) __U,
-                                                    _MM_FROUND_CUR_DIRECTION);
+  return (__m512d) __builtin_ia32_vfnmsubpd512_maskz ((__v8df) __A,
+                                                     (__v8df) __B,
+                                                     (__v8df) __C,
+                                                     (__mmask8) __U,
+                                                     _MM_FROUND_CUR_DIRECTION);
 }
 
 extern __inline __m512
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_fnmsub_ps (__m512 __A, __m512 __B, __m512 __C)
 {
-  return (__m512) __builtin_ia32_vfmaddps512_mask (-(__v16sf) __A,
-                                                  (__v16sf) __B,
-                                                  -(__v16sf) __C,
-                                                  (__mmask16) -1,
-                                                  _MM_FROUND_CUR_DIRECTION);
+  return (__m512) __builtin_ia32_vfnmsubps512_mask ((__v16sf) __A,
+                                                   (__v16sf) __B,
+                                                   (__v16sf) __C,
+                                                   (__mmask16) -1,
+                                                   _MM_FROUND_CUR_DIRECTION);
 }
 
 extern __inline __m512
@@ -12653,11 +13659,11 @@ extern __inline __m512
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_maskz_fnmsub_ps (__mmask16 __U, __m512 __A, __m512 __B, __m512 __C)
 {
-  return (__m512) __builtin_ia32_vfmaddps512_maskz (-(__v16sf) __A,
-                                                   (__v16sf) __B,
-                                                   -(__v16sf) __C,
-                                                   (__mmask16) __U,
-                                                   _MM_FROUND_CUR_DIRECTION);
+  return (__m512) __builtin_ia32_vfnmsubps512_maskz ((__v16sf) __A,
+                                                    (__v16sf) __B,
+                                                    (__v16sf) __C,
+                                                    (__mmask16) __U,
+                                                    _MM_FROUND_CUR_DIRECTION);
 }
 
 extern __inline __m256i
@@ -13913,18 +14919,81 @@ extern __inline __m128
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm_roundscale_ss (__m128 __A, __m128 __B, const int __imm)
 {
-  return (__m128) __builtin_ia32_rndscaless_round ((__v4sf) __A,
-                                                  (__v4sf) __B, __imm,
-                                                  _MM_FROUND_CUR_DIRECTION);
+  return (__m128)
+    __builtin_ia32_rndscaless_mask_round ((__v4sf) __A,
+                                         (__v4sf) __B, __imm,
+                                         (__v4sf)
+                                         _mm_setzero_ps (),
+                                         (__mmask8) -1,
+                                         _MM_FROUND_CUR_DIRECTION);
+}
+
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_roundscale_ss (__m128 __A, __mmask8 __B, __m128 __C, __m128 __D,
+                       const int __imm)
+{
+  return (__m128)
+    __builtin_ia32_rndscaless_mask_round ((__v4sf) __C,
+                                         (__v4sf) __D, __imm,
+                                         (__v4sf) __A,
+                                         (__mmask8) __B,
+                                         _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_roundscale_ss (__mmask8 __A, __m128 __B, __m128 __C,
+                        const int __imm)
+{
+  return (__m128)
+    __builtin_ia32_rndscaless_mask_round ((__v4sf) __B,
+                                         (__v4sf) __C, __imm,
+                                         (__v4sf)
+                                         _mm_setzero_ps (),
+                                         (__mmask8) __A,
+                                         _MM_FROUND_CUR_DIRECTION);
 }
 
 extern __inline __m128d
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm_roundscale_sd (__m128d __A, __m128d __B, const int __imm)
 {
-  return (__m128d) __builtin_ia32_rndscalesd_round ((__v2df) __A,
-                                                   (__v2df) __B, __imm,
-                                                  _MM_FROUND_CUR_DIRECTION);
+  return (__m128d)
+    __builtin_ia32_rndscalesd_mask_round ((__v2df) __A,
+                                         (__v2df) __B, __imm,
+                                         (__v2df)
+                                         _mm_setzero_pd (),
+                                         (__mmask8) -1,
+                                         _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_roundscale_sd (__m128d __A, __mmask8 __B, __m128d __C, __m128d __D,
+                       const int __imm)
+{
+  return (__m128d)
+    __builtin_ia32_rndscalesd_mask_round ((__v2df) __C,
+                                         (__v2df) __D, __imm,
+                                         (__v2df) __A,
+                                         (__mmask8) __B,
+                                         _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_roundscale_sd (__mmask8 __A, __m128d __B, __m128d __C,
+                        const int __imm)
+{
+  return (__m128d)
+    __builtin_ia32_rndscalesd_mask_round ((__v2df) __B,
+                                         (__v2df) __C, __imm,
+                                         (__v2df)
+                                         _mm_setzero_pd (),
+                                         (__mmask8) __A,
+                                         _MM_FROUND_CUR_DIRECTION);
 }
 
 #else
@@ -13954,12 +15023,54 @@ _mm_roundscale_sd (__m128d __A, __m128d __B, const int __imm)
                                             (int)(C),                  \
                                             (__v8df)_mm512_setzero_pd(),\
                                             (__mmask8)(A), _MM_FROUND_CUR_DIRECTION))
-#define _mm_roundscale_ss(A, B, C)                                     \
-  ((__m128) __builtin_ia32_rndscaless_round ((__v4sf)(__m128)(A),      \
-  (__v4sf)(__m128)(B), (int)(C), _MM_FROUND_CUR_DIRECTION))
-#define _mm_roundscale_sd(A, B, C)                                     \
-  ((__m128d) __builtin_ia32_rndscalesd_round ((__v2df)(__m128d)(A),    \
-    (__v2df)(__m128d)(B), (int)(C), _MM_FROUND_CUR_DIRECTION))
+#define _mm_roundscale_ss(A, B, I)                                     \
+  ((__m128)                                                            \
+   __builtin_ia32_rndscaless_mask_round ((__v4sf) (__m128) (A),                \
+                                        (__v4sf) (__m128) (B),         \
+                                        (int) (I),                     \
+                                        (__v4sf) _mm_setzero_ps (),    \
+                                        (__mmask8) (-1),               \
+                                        _MM_FROUND_CUR_DIRECTION))
+#define _mm_mask_roundscale_ss(A, U, B, C, I)                          \
+  ((__m128)                                                            \
+   __builtin_ia32_rndscaless_mask_round ((__v4sf) (__m128) (B),                \
+                                        (__v4sf) (__m128) (C),         \
+                                        (int) (I),                     \
+                                        (__v4sf) (__m128) (A),         \
+                                        (__mmask8) (U),                \
+                                        _MM_FROUND_CUR_DIRECTION))
+#define _mm_maskz_roundscale_ss(U, A, B, I)                            \
+  ((__m128)                                                            \
+   __builtin_ia32_rndscaless_mask_round ((__v4sf) (__m128) (A),                \
+                                        (__v4sf) (__m128) (B),         \
+                                        (int) (I),                     \
+                                        (__v4sf) _mm_setzero_ps (),    \
+                                        (__mmask8) (U),                \
+                                        _MM_FROUND_CUR_DIRECTION))
+#define _mm_roundscale_sd(A, B, I)                                     \
+  ((__m128d)                                                           \
+   __builtin_ia32_rndscalesd_mask_round ((__v2df) (__m128d) (A),       \
+                                        (__v2df) (__m128d) (B),        \
+                                        (int) (I),                     \
+                                        (__v2df) _mm_setzero_pd (),    \
+                                        (__mmask8) (-1),               \
+                                        _MM_FROUND_CUR_DIRECTION))
+#define _mm_mask_roundscale_sd(A, U, B, C, I)                          \
+  ((__m128d)                                                           \
+   __builtin_ia32_rndscalesd_mask_round ((__v2df) (__m128d) (B),       \
+                                        (__v2df) (__m128d) (C),        \
+                                        (int) (I),                     \
+                                        (__v2df) (__m128d) (A),        \
+                                        (__mmask8) (U),                \
+                                        _MM_FROUND_CUR_DIRECTION))
+#define _mm_maskz_roundscale_sd(U, A, B, I)                            \
+  ((__m128d)                                                           \
+   __builtin_ia32_rndscalesd_mask_round ((__v2df) (__m128d) (A),       \
+                                        (__v2df) (__m128d) (B),        \
+                                        (int) (I),                     \
+                                        (__v2df) _mm_setzero_pd (),    \
+                                        (__mmask8) (U),                \
+                                        _MM_FROUND_CUR_DIRECTION))
 #endif
 
 #ifdef __OPTIMIZE__
@@ -14538,6 +15649,48 @@ _mm512_castsi256_si512 (__m256i __A)
   return (__m512i)__builtin_ia32_si512_256si ((__v8si)__A);
 }
 
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_zextpd128_pd512 (__m128d __A)
+{
+  return (__m512d) _mm512_insertf32x4 (_mm512_setzero_ps (), (__m128) __A, 0);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_zextps128_ps512 (__m128 __A)
+{
+  return _mm512_insertf32x4 (_mm512_setzero_ps (), __A, 0);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_zextsi128_si512 (__m128i __A)
+{
+  return _mm512_inserti32x4 (_mm512_setzero_si512 (), __A, 0);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_zextpd256_pd512 (__m256d __A)
+{
+  return _mm512_insertf64x4 (_mm512_setzero_pd (), __A, 0);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_zextps256_ps512 (__m256 __A)
+{
+  return (__m512) _mm512_insertf64x4 (_mm512_setzero_pd (), (__m256d) __A, 0);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_zextsi256_si512 (__m256i __A)
+{
+  return _mm512_inserti64x4 (_mm512_setzero_si512 (), __A, 0);
+}
+
 extern __inline __mmask16
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_cmpeq_epu32_mask (__m512i __A, __m512i __B)