gccxml_gem 0.9.3-x86-darwin-10

data/share/gccxml-0.9/GCC/4.4/emmintrin.h

@@ -0,0 +1,1041 @@
+/* Copyright (C) 2003, 2004, 2005, 2006, 2007, 2008, 2009
+   Free Software Foundation, Inc.
+
+   This file is part of GCC.
+
+   GCC is free software; you can redistribute it and/or modify
+   it under the terms of the GNU General Public License as published by
+   the Free Software Foundation; either version 3, or (at your option)
+   any later version.
+
+   GCC is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+
+   Under Section 7 of GPL version 3, you are granted additional
+   permissions described in the GCC Runtime Library Exception, version
+   3.1, as published by the Free Software Foundation.
+
+   You should have received a copy of the GNU General Public License and
+   a copy of the GCC Runtime Library Exception along with this program;
+   see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
+   <http://www.gnu.org/licenses/>.  */
+
+/* Implemented from the specification included in the Intel C++ Compiler
+   User Guide and Reference, version 9.0.  */
+
+#ifndef _EMMINTRIN_H_INCLUDED
+#define _EMMINTRIN_H_INCLUDED
+
+#ifndef __SSE2__
+# error "SSE2 instruction set not enabled"
+#else
+
+/* We need definitions from the SSE header files*/
+#include <xmmintrin.h>
+
+/* SSE2 */
+typedef double __v2df __attribute__ ((__vector_size__ (16)));
+typedef long long __v2di __attribute__ ((__vector_size__ (16)));
+typedef int __v4si __attribute__ ((__vector_size__ (16)));
+typedef short __v8hi __attribute__ ((__vector_size__ (16)));
+typedef char __v16qi __attribute__ ((__vector_size__ (16)));
+
+/* The Intel API is flexible enough that we must allow aliasing with other
+   vector types, and their scalar components.  */
+typedef long long __m128i __attribute__ ((__vector_size__ (16), __may_alias__));
+typedef double __m128d __attribute__ ((__vector_size__ (16), __may_alias__));
+
+/* Create a selector for use with the SHUFPD instruction.  */
+#define _MM_SHUFFLE2(fp1,fp0) \
+ (((fp1) << 1) | (fp0))
+
+/* Create a vector with element 0 as F and the rest zero.  */
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_set_sd (double __F)
+;
+
+/* Create a vector with both elements equal to F.  */
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_set1_pd (double __F)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_set_pd1 (double __F)
+;
+
+/* Create a vector with the lower value X and upper value W.  */
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_set_pd (double __W, double __X)
+;
+
+/* Create a vector with the lower value W and upper value X.  */
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_setr_pd (double __W, double __X)
+;
+
+/* Create a vector of zeros.  */
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_setzero_pd (void)
+;
+
+/* Sets the low DPFP value of A from the low value of B.  */
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_move_sd (__m128d __A, __m128d __B)
+;
+
+/* Load two DPFP values from P.  The address must be 16-byte aligned.  */
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_load_pd (double const *__P)
+;
+
+/* Load two DPFP values from P.  The address need not be 16-byte aligned.  */
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_loadu_pd (double const *__P)
+;
+
+/* Create a vector with all two elements equal to *P.  */
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_load1_pd (double const *__P)
+;
+
+/* Create a vector with element 0 as *P and the rest zero.  */
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_load_sd (double const *__P)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_load_pd1 (double const *__P)
+;
+
+/* Load two DPFP values in reverse order.  The address must be aligned.  */
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_loadr_pd (double const *__P)
+;
+
+/* Store two DPFP values.  The address must be 16-byte aligned.  */
+extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_store_pd (double *__P, __m128d __A)
+;
+
+/* Store two DPFP values.  The address need not be 16-byte aligned.  */
+extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_storeu_pd (double *__P, __m128d __A)
+;
+
+/* Stores the lower DPFP value.  */
+extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_store_sd (double *__P, __m128d __A)
+;
+
+extern __inline double __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtsd_f64 (__m128d __A)
+;
+
+extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_storel_pd (double *__P, __m128d __A)
+;
+
+/* Stores the upper DPFP value.  */
+extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_storeh_pd (double *__P, __m128d __A)
+;
+
+/* Store the lower DPFP value across two words.
+   The address must be 16-byte aligned.  */
+extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_store1_pd (double *__P, __m128d __A)
+;
+
+extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_store_pd1 (double *__P, __m128d __A)
+;
+
+/* Store two DPFP values in reverse order.  The address must be aligned.  */
+extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_storer_pd (double *__P, __m128d __A)
+;
+
+extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtsi128_si32 (__m128i __A)
+;
+
+#ifdef __x86_64__
+/* Intel intrinsic.  */
+extern __inline long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtsi128_si64 (__m128i __A)
+;
+
+/* Microsoft intrinsic.  */
+extern __inline long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtsi128_si64x (__m128i __A)
+;
+#endif
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_add_pd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_add_sd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_sub_pd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_sub_sd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mul_pd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mul_sd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_div_pd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_div_sd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_sqrt_pd (__m128d __A)
+;
+
+/* Return pair {sqrt (A[0), B[1]}.  */
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_sqrt_sd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_min_pd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_min_sd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_max_pd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_max_sd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_and_pd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_andnot_pd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_or_pd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_xor_pd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmpeq_pd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmplt_pd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmple_pd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmpgt_pd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmpge_pd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmpneq_pd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmpnlt_pd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmpnle_pd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmpngt_pd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmpnge_pd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmpord_pd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmpunord_pd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmpeq_sd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmplt_sd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmple_sd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmpgt_sd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmpge_sd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmpneq_sd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmpnlt_sd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmpnle_sd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmpngt_sd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmpnge_sd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmpord_sd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmpunord_sd (__m128d __A, __m128d __B)
+;
+
+extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comieq_sd (__m128d __A, __m128d __B)
+;
+
+extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comilt_sd (__m128d __A, __m128d __B)
+;
+
+extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comile_sd (__m128d __A, __m128d __B)
+;
+
+extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comigt_sd (__m128d __A, __m128d __B)
+;
+
+extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comige_sd (__m128d __A, __m128d __B)
+;
+
+extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comineq_sd (__m128d __A, __m128d __B)
+;
+
+extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_ucomieq_sd (__m128d __A, __m128d __B)
+;
+
+extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_ucomilt_sd (__m128d __A, __m128d __B)
+;
+
+extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_ucomile_sd (__m128d __A, __m128d __B)
+;
+
+extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_ucomigt_sd (__m128d __A, __m128d __B)
+;
+
+extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_ucomige_sd (__m128d __A, __m128d __B)
+;
+
+extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_ucomineq_sd (__m128d __A, __m128d __B)
+;
+
+/* Create a vector of Qi, where i is the element number.  */
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_set_epi64x (long long __q1, long long __q0)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_set_epi64 (__m64 __q1,  __m64 __q0)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_set_epi32 (int __q3, int __q2, int __q1, int __q0)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_set_epi16 (short __q7, short __q6, short __q5, short __q4,
+               short __q3, short __q2, short __q1, short __q0)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_set_epi8 (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)
+;
+
+/* Set all of the elements of the vector to A.  */
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_set1_epi64x (long long __A)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_set1_epi64 (__m64 __A)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_set1_epi32 (int __A)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_set1_epi16 (short __A)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_set1_epi8 (char __A)
+;
+
+/* Create a vector of Qi, where i is the element number.
+   The parameter order is reversed from the _mm_set_epi* functions.  */
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_setr_epi64 (__m64 __q0, __m64 __q1)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_setr_epi32 (int __q0, int __q1, int __q2, int __q3)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_setr_epi16 (short __q0, short __q1, short __q2, short __q3,
+                short __q4, short __q5, short __q6, short __q7)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_setr_epi8 (char __q00, char __q01, char __q02, char __q03,
+               char __q04, char __q05, char __q06, char __q07,
+               char __q08, char __q09, char __q10, char __q11,
+               char __q12, char __q13, char __q14, char __q15)
+;
+
+/* Create a vector with element 0 as *P and the rest zero.  */
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_load_si128 (__m128i const *__P)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_loadu_si128 (__m128i const *__P)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_loadl_epi64 (__m128i const *__P)
+;
+
+extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_store_si128 (__m128i *__P, __m128i __B)
+;
+
+extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_storeu_si128 (__m128i *__P, __m128i __B)
+;
+
+extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_storel_epi64 (__m128i *__P, __m128i __B)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_movepi64_pi64 (__m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_movpi64_epi64 (__m64 __A)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_move_epi64 (__m128i __A)
+;
+
+/* Create a vector of zeros.  */
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_setzero_si128 (void)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtepi32_pd (__m128i __A)
+;
+
+extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtepi32_ps (__m128i __A)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtpd_epi32 (__m128d __A)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtpd_pi32 (__m128d __A)
+;
+
+extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtpd_ps (__m128d __A)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvttpd_epi32 (__m128d __A)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvttpd_pi32 (__m128d __A)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtpi32_pd (__m64 __A)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtps_epi32 (__m128 __A)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvttps_epi32 (__m128 __A)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtps_pd (__m128 __A)
+;
+
+extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtsd_si32 (__m128d __A)
+;
+
+#ifdef __x86_64__
+/* Intel intrinsic.  */
+extern __inline long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtsd_si64 (__m128d __A)
+;
+
+/* Microsoft intrinsic.  */
+extern __inline long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtsd_si64x (__m128d __A)
+;
+#endif
+
+extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvttsd_si32 (__m128d __A)
+;
+
+#ifdef __x86_64__
+/* Intel intrinsic.  */
+extern __inline long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvttsd_si64 (__m128d __A)
+;
+
+/* Microsoft intrinsic.  */
+extern __inline long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvttsd_si64x (__m128d __A)
+;
+#endif
+
+extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtsd_ss (__m128 __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtsi32_sd (__m128d __A, int __B)
+;
+
+#ifdef __x86_64__
+/* Intel intrinsic.  */
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtsi64_sd (__m128d __A, long long __B)
+;
+
+/* Microsoft intrinsic.  */
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtsi64x_sd (__m128d __A, long long __B)
+;
+#endif
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtss_sd (__m128d __A, __m128 __B)
+;
+
+#ifdef __OPTIMIZE__
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_shuffle_pd(__m128d __A, __m128d __B, const int __mask)
+;
+#else
+#define _mm_shuffle_pd(A, B, N)                                         \
+  ((__m128d)__builtin_ia32_shufpd ((__v2df)(__m128d)(A),                \
+                                   (__v2df)(__m128d)(B), (int)(N)))
+#endif
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_unpackhi_pd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_unpacklo_pd (__m128d __A, __m128d __B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_loadh_pd (__m128d __A, double const *__B)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_loadl_pd (__m128d __A, double const *__B)
+;
+
+extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_movemask_pd (__m128d __A)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_packs_epi16 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_packs_epi32 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_packus_epi16 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_unpackhi_epi8 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_unpackhi_epi16 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_unpackhi_epi32 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_unpackhi_epi64 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_unpacklo_epi8 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_unpacklo_epi16 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_unpacklo_epi32 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_unpacklo_epi64 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_add_epi8 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_add_epi16 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_add_epi32 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_add_epi64 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_adds_epi8 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_adds_epi16 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_adds_epu8 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_adds_epu16 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_sub_epi8 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_sub_epi16 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_sub_epi32 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_sub_epi64 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_subs_epi8 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_subs_epi16 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_subs_epu8 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_subs_epu16 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_madd_epi16 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mulhi_epi16 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mullo_epi16 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mul_su32 (__m64 __A, __m64 __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mul_epu32 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_slli_epi16 (__m128i __A, int __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_slli_epi32 (__m128i __A, int __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_slli_epi64 (__m128i __A, int __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_srai_epi16 (__m128i __A, int __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_srai_epi32 (__m128i __A, int __B)
+;
+
+#ifdef __OPTIMIZE__
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_srli_si128 (__m128i __A, const int __N)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_slli_si128 (__m128i __A, const int __N)
+;
+#else
+#define _mm_srli_si128(A, N) \
+  ((__m128i)__builtin_ia32_psrldqi128 ((__m128i)(A), (int)(N) * 8))
+#define _mm_slli_si128(A, N) \
+  ((__m128i)__builtin_ia32_pslldqi128 ((__m128i)(A), (int)(N) * 8))
+#endif
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_srli_epi16 (__m128i __A, int __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_srli_epi32 (__m128i __A, int __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_srli_epi64 (__m128i __A, int __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_sll_epi16 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_sll_epi32 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_sll_epi64 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_sra_epi16 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_sra_epi32 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_srl_epi16 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_srl_epi32 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_srl_epi64 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_and_si128 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_andnot_si128 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_or_si128 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_xor_si128 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmpeq_epi8 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmpeq_epi16 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmpeq_epi32 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmplt_epi8 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmplt_epi16 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmplt_epi32 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmpgt_epi8 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmpgt_epi16 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmpgt_epi32 (__m128i __A, __m128i __B)
+;
+
+#ifdef __OPTIMIZE__
+extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_extract_epi16 (__m128i const __A, int const __N)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_insert_epi16 (__m128i const __A, int const __D, int const __N)
+;
+#else
+#define _mm_extract_epi16(A, N) \
+  ((int) __builtin_ia32_vec_ext_v8hi ((__v8hi)(__m128i)(A), (int)(N)))
+#define _mm_insert_epi16(A, D, N)                               \
+  ((__m128i) __builtin_ia32_vec_set_v8hi ((__v8hi)(__m128i)(A), \
+                                          (int)(D), (int)(N)))
+#endif
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_max_epi16 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_max_epu8 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_min_epi16 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_min_epu8 (__m128i __A, __m128i __B)
+;
+
+extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_movemask_epi8 (__m128i __A)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mulhi_epu16 (__m128i __A, __m128i __B)
+;
+
+#ifdef __OPTIMIZE__
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_shufflehi_epi16 (__m128i __A, const int __mask)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_shufflelo_epi16 (__m128i __A, const int __mask)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_shuffle_epi32 (__m128i __A, const int __mask)
+;
+#else
+#define _mm_shufflehi_epi16(A, N) \
+  ((__m128i)__builtin_ia32_pshufhw ((__v8hi)(__m128i)(A), (int)(N)))
+#define _mm_shufflelo_epi16(A, N) \
+  ((__m128i)__builtin_ia32_pshuflw ((__v8hi)(__m128i)(A), (int)(N)))
+#define _mm_shuffle_epi32(A, N) \
+  ((__m128i)__builtin_ia32_pshufd ((__v4si)(__m128i)(A), (int)(N)))
+#endif
+
+extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskmoveu_si128 (__m128i __A, __m128i __B, char *__C)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_avg_epu8 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_avg_epu16 (__m128i __A, __m128i __B)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_sad_epu8 (__m128i __A, __m128i __B)
+;
+
+extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_stream_si32 (int *__A, int __B)
+;
+
+extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_stream_si128 (__m128i *__A, __m128i __B)
+;
+
+extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_stream_pd (double *__A, __m128d __B)
+;
+
+extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_clflush (void const *__A)
+;
+
+extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_lfence (void)
+;
+
+extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mfence (void)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtsi32_si128 (int __A)
+;
+
+#ifdef __x86_64__
+/* Intel intrinsic.  */
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtsi64_si128 (long long __A)
+;
+
+/* Microsoft intrinsic.  */
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtsi64x_si128 (long long __A)
+;
+#endif
+
+/* Casts between various SP, DP, INT vector types.  Note that these do no
+   conversion of values, they just change the type.  */
+extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_castpd_ps(__m128d __A)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_castpd_si128(__m128d __A)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_castps_pd(__m128 __A)
+;
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_castps_si128(__m128 __A)
+;
+
+extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_castsi128_ps(__m128i __A)
+;
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_castsi128_pd(__m128i __A)
+;
+
+#endif /* __SSE2__  */
+
+#endif /* _EMMINTRIN_H_INCLUDED */