gccxml_gem 0.9.3-x86-darwin-10

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

@@ -0,0 +1,153 @@
+#define __builtin_apply(x,y,z) ((void*)0)
+#define __builtin_nan(x) (0.0)
+#define __builtin_nanf(x) (0.0f)
+#define __builtin_nanl(x) (0.0l)
+#define __builtin_huge_val(x) (0.0)
+#define __builtin_huge_valf(x) (0.0f)
+#define __builtin_huge_vall(x) (0.0l)
+#define __builtin_apply_args(x) ((void*)0)
+#define __builtin_types_compatible_p(x,y) 0
+#define __builtin_choose_expr(x,y,z) int
+#define __builtin_constant_p(x) 0
+void* __builtin_memchr(void const*, int, unsigned int);
+void __builtin_return (void *RESULT);
+void * __builtin_return_address (unsigned int LEVEL);
+void * __builtin_frame_address (unsigned int LEVEL);
+long __builtin_expect (long EXP, long C);
+void __builtin_prefetch (const void *ADDR, ...);
+double __builtin_inf (void);
+float __builtin_inff (void);
+long double __builtin_infl (void);
+double __builtin_nans (const char *str);
+float __builtin_nansf (const char *str);
+long double __builtin_nansl (const char *str);
+double      __builtin_acos(double);
+float       __builtin_acosf(float);
+long double __builtin_acosl(long double);
+double      __builtin_asin(double);
+float       __builtin_asinf(float);
+long double __builtin_asinl(long double);
+double      __builtin_atan(double);
+double      __builtin_atan2(double, double);
+float       __builtin_atan2f(float, float);
+long double __builtin_atan2l(long double, long double);
+float       __builtin_atanf(float);
+long double __builtin_atanl(long double);
+double      __builtin_ceil(double);
+float       __builtin_ceilf(float);
+long double __builtin_ceill(long double);
+double      __builtin_cos(double);
+float       __builtin_cosf(float);
+double      __builtin_cosh(double);
+float       __builtin_coshf(float);
+long double __builtin_coshl(long double);
+long double __builtin_cosl(long double);
+double      __builtin_exp(double);
+float       __builtin_expf(float);
+long double __builtin_expl(long double);
+double      __builtin_fabs(double);
+float       __builtin_fabsf(float);
+long double __builtin_fabsl(long double);
+double      __builtin_floor(double);
+float       __builtin_floorf(float);
+long double __builtin_floorl(long double);
+float       __builtin_fmodf(float, float);
+long double __builtin_fmodl(long double, long double);
+double      __builtin_frexp(double, int*);
+float       __builtin_frexpf(float, int*);
+long double __builtin_frexpl(long double, int*);
+double      __builtin_ldexp(double, int);
+float       __builtin_ldexpf(float, int);
+long double __builtin_ldexpl(long double, int);
+double      __builtin_log(double);
+double      __builtin_log10(double);
+float       __builtin_log10f(float);
+long double __builtin_log10l(long double);
+float       __builtin_logf(float);
+long double __builtin_logl(long double);
+float       __builtin_modff(float, float*);
+long double __builtin_modfl(long double, long double*);
+float       __builtin_powf(float, float);
+long double __builtin_powl(long double, long double);
+double      __builtin_powi(double, int);
+float       __builtin_powif(float, int);
+long double __builtin_powil(long double, int);
+double      __builtin_sin(double);
+float       __builtin_sinf(float);
+double      __builtin_sinh(double);
+float       __builtin_sinhf(float);
+long double __builtin_sinhl(long double);
+long double __builtin_sinl(long double);
+double      __builtin_sqrt(double);
+float       __builtin_sqrtf(float);
+long double __builtin_sqrtl(long double);
+double      __builtin_tan(double);
+float       __builtin_tanf(float);
+double      __builtin_tanh(double);
+float       __builtin_tanhf(float);
+long double __builtin_tanhl(long double);
+long double __builtin_tanl(long double);
+float       __builtin_cabsf(float __complex__);
+double      __builtin_cabs(double __complex__);
+long double __builtin_cabsl(long double __complex__);
+float       __builtin_cargf(float __complex__);
+double      __builtin_carg(double __complex__);
+long double __builtin_cargl(long double __complex__);
+int         __builtin_ctz(int);
+int         __builtin_ctzl(long);
+int         __builtin_ctzll(long long);
+int         __builtin_popcount(int);
+int         __builtin_popcountl(long);
+int         __builtin_popcountll(long long);
+float       __complex__ __builtin_ccosf(float __complex__);
+double      __complex__ __builtin_ccos(double __complex__);
+long double __complex__ __builtin_ccosl(long double __complex__);
+float       __complex__ __builtin_ccoshf(float __complex__);
+double      __complex__ __builtin_ccosh(double __complex__);
+long double __complex__ __builtin_ccoshl(long double __complex__);
+float       __complex__ __builtin_cexpf(float __complex__);
+double      __complex__ __builtin_cexp(double __complex__);
+long double __complex__ __builtin_cexpl(long double __complex__);
+float       __complex__ __builtin_clogf(float __complex__);
+double      __complex__ __builtin_clog(double __complex__);
+long double __complex__ __builtin_clogl(long double __complex__);
+float       __complex__ __builtin_csinf(float __complex__);
+double      __complex__ __builtin_csin(double __complex__);
+long double __complex__ __builtin_csinl(long double __complex__);
+float       __complex__ __builtin_csinhf(float __complex__);
+double      __complex__ __builtin_csinh(double __complex__);
+long double __complex__ __builtin_csinhl(long double __complex__);
+float       __complex__ __builtin_csqrtf(float __complex__);
+double      __complex__ __builtin_csqrt(double __complex__);
+long double __complex__ __builtin_csqrtl(long double __complex__);
+float       __complex__ __builtin_ctanf(float __complex__);
+double      __complex__ __builtin_ctan(double __complex__);
+long double __complex__ __builtin_ctanl(long double __complex__);
+float       __complex__ __builtin_ctanhf(float __complex__);
+double      __complex__ __builtin_ctanh(double __complex__);
+long double __complex__ __builtin_ctanhl(long double __complex__);
+float       __complex__ __builtin_cpowf(float __complex__, float __complex__);
+double      __complex__ __builtin_cpow(double __complex__, double __complex__);
+long double __complex__ __builtin_cpowl(long double __complex__, long double __complex__);
+
+/* The GCC 4.4 parser hard-codes handling of these, so they do not
+   have real signatures.  */
+bool __builtin_fpclassify(...);
+bool __builtin_isfinite(...);
+bool __builtin_isgreater(...);
+bool __builtin_isgreaterequal(...);
+bool __builtin_isinf(...);
+bool __builtin_isinf_sign(...);
+bool __builtin_isless(...);
+bool __builtin_islessequal(...);
+bool __builtin_islessgreater(...);
+bool __builtin_isnan(...);
+bool __builtin_isnormal(...);
+bool __builtin_isunordered(...);
+bool __builtin_va_arg_pack(...);
+int  __builtin_va_arg_pack_len(...);
+
+/* We fake some constant expressions from GCC 4.4 parser.  */
+#define __is_pod(x) false
+#define __is_empty(x) false
+#define __has_trivial_destructor(x) false

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

@@ -0,0 +1,662 @@
+/* Copyright (C) 2002, 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 _MMINTRIN_H_INCLUDED
+#define _MMINTRIN_H_INCLUDED
+
+#ifndef __MMX__
+# error "MMX instruction set not enabled"
+#else
+/* The Intel API is flexible enough that we must allow aliasing with other
+   vector types, and their scalar components.  */
+typedef int __m64 __attribute__ ((__vector_size__ (8), __may_alias__));
+
+/* Internal data types for implementing the intrinsics.  */
+typedef int __v2si __attribute__ ((__vector_size__ (8)));
+typedef short __v4hi __attribute__ ((__vector_size__ (8)));
+typedef char __v8qi __attribute__ ((__vector_size__ (8)));
+typedef long long __v1di __attribute__ ((__vector_size__ (8)));
+typedef float __v2sf __attribute__ ((__vector_size__ (8)));
+
+/* Empty the multimedia state.  */
+extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_empty (void)
+;
+
+extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_empty (void)
+;
+
+/* Convert I to a __m64 object.  The integer is zero-extended to 64-bits.  */
+extern __inline __m64  __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtsi32_si64 (int __i)
+;
+
+extern __inline __m64  __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_from_int (int __i)
+;
+
+#ifdef __x86_64__
+/* Convert I to a __m64 object.  */
+
+/* Intel intrinsic.  */
+extern __inline __m64  __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_from_int64 (long long __i)
+;
+
+extern __inline __m64  __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtsi64_m64 (long long __i)
+;
+
+/* Microsoft intrinsic.  */
+extern __inline __m64  __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtsi64x_si64 (long long __i)
+;
+
+extern __inline __m64  __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_set_pi64x (long long __i)
+;
+#endif
+
+/* Convert the lower 32 bits of the __m64 object into an integer.  */
+extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtsi64_si32 (__m64 __i)
+;
+
+extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_to_int (__m64 __i)
+;
+
+#ifdef __x86_64__
+/* Convert the __m64 object to a 64bit integer.  */
+
+/* Intel intrinsic.  */
+extern __inline long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_to_int64 (__m64 __i)
+;
+
+extern __inline long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtm64_si64 (__m64 __i)
+;
+
+/* Microsoft intrinsic.  */
+extern __inline long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtsi64_si64x (__m64 __i)
+;
+#endif
+
+/* Pack the four 16-bit values from M1 into the lower four 8-bit values of
+   the result, and the four 16-bit values from M2 into the upper four 8-bit
+   values of the result, all with signed saturation.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_packs_pi16 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_packsswb (__m64 __m1, __m64 __m2)
+;
+
+/* Pack the two 32-bit values from M1 in to the lower two 16-bit values of
+   the result, and the two 32-bit values from M2 into the upper two 16-bit
+   values of the result, all with signed saturation.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_packs_pi32 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_packssdw (__m64 __m1, __m64 __m2)
+;
+
+/* Pack the four 16-bit values from M1 into the lower four 8-bit values of
+   the result, and the four 16-bit values from M2 into the upper four 8-bit
+   values of the result, all with unsigned saturation.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_packs_pu16 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_packuswb (__m64 __m1, __m64 __m2)
+;
+
+/* Interleave the four 8-bit values from the high half of M1 with the four
+   8-bit values from the high half of M2.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_unpackhi_pi8 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_punpckhbw (__m64 __m1, __m64 __m2)
+;
+
+/* Interleave the two 16-bit values from the high half of M1 with the two
+   16-bit values from the high half of M2.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_unpackhi_pi16 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_punpckhwd (__m64 __m1, __m64 __m2)
+;
+
+/* Interleave the 32-bit value from the high half of M1 with the 32-bit
+   value from the high half of M2.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_unpackhi_pi32 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_punpckhdq (__m64 __m1, __m64 __m2)
+;
+
+/* Interleave the four 8-bit values from the low half of M1 with the four
+   8-bit values from the low half of M2.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_unpacklo_pi8 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_punpcklbw (__m64 __m1, __m64 __m2)
+;
+
+/* Interleave the two 16-bit values from the low half of M1 with the two
+   16-bit values from the low half of M2.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_unpacklo_pi16 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_punpcklwd (__m64 __m1, __m64 __m2)
+;
+
+/* Interleave the 32-bit value from the low half of M1 with the 32-bit
+   value from the low half of M2.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_unpacklo_pi32 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_punpckldq (__m64 __m1, __m64 __m2)
+;
+
+/* Add the 8-bit values in M1 to the 8-bit values in M2.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_add_pi8 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_paddb (__m64 __m1, __m64 __m2)
+;
+
+/* Add the 16-bit values in M1 to the 16-bit values in M2.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_add_pi16 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_paddw (__m64 __m1, __m64 __m2)
+;
+
+/* Add the 32-bit values in M1 to the 32-bit values in M2.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_add_pi32 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_paddd (__m64 __m1, __m64 __m2)
+;
+
+/* Add the 64-bit values in M1 to the 64-bit values in M2.  */
+#ifdef __SSE2__
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_add_si64 (__m64 __m1, __m64 __m2)
+;
+#endif
+
+/* Add the 8-bit values in M1 to the 8-bit values in M2 using signed
+   saturated arithmetic.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_adds_pi8 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_paddsb (__m64 __m1, __m64 __m2)
+;
+
+/* Add the 16-bit values in M1 to the 16-bit values in M2 using signed
+   saturated arithmetic.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_adds_pi16 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_paddsw (__m64 __m1, __m64 __m2)
+;
+
+/* Add the 8-bit values in M1 to the 8-bit values in M2 using unsigned
+   saturated arithmetic.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_adds_pu8 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_paddusb (__m64 __m1, __m64 __m2)
+;
+
+/* Add the 16-bit values in M1 to the 16-bit values in M2 using unsigned
+   saturated arithmetic.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_adds_pu16 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_paddusw (__m64 __m1, __m64 __m2)
+;
+
+/* Subtract the 8-bit values in M2 from the 8-bit values in M1.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_sub_pi8 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_psubb (__m64 __m1, __m64 __m2)
+;
+
+/* Subtract the 16-bit values in M2 from the 16-bit values in M1.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_sub_pi16 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_psubw (__m64 __m1, __m64 __m2)
+;
+
+/* Subtract the 32-bit values in M2 from the 32-bit values in M1.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_sub_pi32 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_psubd (__m64 __m1, __m64 __m2)
+;
+
+/* Add the 64-bit values in M1 to the 64-bit values in M2.  */
+#ifdef __SSE2__
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_sub_si64 (__m64 __m1, __m64 __m2)
+;
+#endif
+
+/* Subtract the 8-bit values in M2 from the 8-bit values in M1 using signed
+   saturating arithmetic.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_subs_pi8 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_psubsb (__m64 __m1, __m64 __m2)
+;
+
+/* Subtract the 16-bit values in M2 from the 16-bit values in M1 using
+   signed saturating arithmetic.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_subs_pi16 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_psubsw (__m64 __m1, __m64 __m2)
+;
+
+/* Subtract the 8-bit values in M2 from the 8-bit values in M1 using
+   unsigned saturating arithmetic.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_subs_pu8 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_psubusb (__m64 __m1, __m64 __m2)
+;
+
+/* Subtract the 16-bit values in M2 from the 16-bit values in M1 using
+   unsigned saturating arithmetic.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_subs_pu16 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_psubusw (__m64 __m1, __m64 __m2)
+;
+
+/* Multiply four 16-bit values in M1 by four 16-bit values in M2 producing
+   four 32-bit intermediate results, which are then summed by pairs to
+   produce two 32-bit results.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_madd_pi16 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_pmaddwd (__m64 __m1, __m64 __m2)
+;
+
+/* Multiply four signed 16-bit values in M1 by four signed 16-bit values in
+   M2 and produce the high 16 bits of the 32-bit results.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mulhi_pi16 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_pmulhw (__m64 __m1, __m64 __m2)
+;
+
+/* Multiply four 16-bit values in M1 by four 16-bit values in M2 and produce
+   the low 16 bits of the results.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mullo_pi16 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_pmullw (__m64 __m1, __m64 __m2)
+;
+
+/* Shift four 16-bit values in M left by COUNT.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_sll_pi16 (__m64 __m, __m64 __count)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_psllw (__m64 __m, __m64 __count)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_slli_pi16 (__m64 __m, int __count)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_psllwi (__m64 __m, int __count)
+;
+
+/* Shift two 32-bit values in M left by COUNT.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_sll_pi32 (__m64 __m, __m64 __count)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_pslld (__m64 __m, __m64 __count)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_slli_pi32 (__m64 __m, int __count)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_pslldi (__m64 __m, int __count)
+;
+
+/* Shift the 64-bit value in M left by COUNT.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_sll_si64 (__m64 __m, __m64 __count)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_psllq (__m64 __m, __m64 __count)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_slli_si64 (__m64 __m, int __count)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_psllqi (__m64 __m, int __count)
+;
+
+/* Shift four 16-bit values in M right by COUNT; shift in the sign bit.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_sra_pi16 (__m64 __m, __m64 __count)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_psraw (__m64 __m, __m64 __count)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_srai_pi16 (__m64 __m, int __count)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_psrawi (__m64 __m, int __count)
+;
+
+/* Shift two 32-bit values in M right by COUNT; shift in the sign bit.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_sra_pi32 (__m64 __m, __m64 __count)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_psrad (__m64 __m, __m64 __count)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_srai_pi32 (__m64 __m, int __count)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_psradi (__m64 __m, int __count)
+;
+
+/* Shift four 16-bit values in M right by COUNT; shift in zeros.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_srl_pi16 (__m64 __m, __m64 __count)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_psrlw (__m64 __m, __m64 __count)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_srli_pi16 (__m64 __m, int __count)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_psrlwi (__m64 __m, int __count)
+;
+
+/* Shift two 32-bit values in M right by COUNT; shift in zeros.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_srl_pi32 (__m64 __m, __m64 __count)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_psrld (__m64 __m, __m64 __count)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_srli_pi32 (__m64 __m, int __count)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_psrldi (__m64 __m, int __count)
+;
+
+/* Shift the 64-bit value in M left by COUNT; shift in zeros.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_srl_si64 (__m64 __m, __m64 __count)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_psrlq (__m64 __m, __m64 __count)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_srli_si64 (__m64 __m, int __count)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_psrlqi (__m64 __m, int __count)
+;
+
+/* Bit-wise AND the 64-bit values in M1 and M2.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_and_si64 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_pand (__m64 __m1, __m64 __m2)
+;
+
+/* Bit-wise complement the 64-bit value in M1 and bit-wise AND it with the
+   64-bit value in M2.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_andnot_si64 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_pandn (__m64 __m1, __m64 __m2)
+;
+
+/* Bit-wise inclusive OR the 64-bit values in M1 and M2.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_or_si64 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_por (__m64 __m1, __m64 __m2)
+;
+
+/* Bit-wise exclusive OR the 64-bit values in M1 and M2.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_xor_si64 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_pxor (__m64 __m1, __m64 __m2)
+;
+
+/* Compare eight 8-bit values.  The result of the comparison is 0xFF if the
+   test is true and zero if false.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmpeq_pi8 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_pcmpeqb (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmpgt_pi8 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_pcmpgtb (__m64 __m1, __m64 __m2)
+;
+
+/* Compare four 16-bit values.  The result of the comparison is 0xFFFF if
+   the test is true and zero if false.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmpeq_pi16 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_pcmpeqw (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmpgt_pi16 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_pcmpgtw (__m64 __m1, __m64 __m2)
+;
+
+/* Compare two 32-bit values.  The result of the comparison is 0xFFFFFFFF if
+   the test is true and zero if false.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmpeq_pi32 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_pcmpeqd (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmpgt_pi32 (__m64 __m1, __m64 __m2)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_m_pcmpgtd (__m64 __m1, __m64 __m2)
+;
+
+/* Creates a 64-bit zero.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_setzero_si64 (void)
+;
+
+/* Creates a vector of two 32-bit values; I0 is least significant.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_set_pi32 (int __i1, int __i0)
+;
+
+/* Creates a vector of four 16-bit values; W0 is least significant.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_set_pi16 (short __w3, short __w2, short __w1, short __w0)
+;
+
+/* Creates a vector of eight 8-bit values; B0 is least significant.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_set_pi8 (char __b7, char __b6, char __b5, char __b4,
+             char __b3, char __b2, char __b1, char __b0)
+;
+
+/* Similar, but with the arguments in reverse order.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_setr_pi32 (int __i0, int __i1)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_setr_pi16 (short __w0, short __w1, short __w2, short __w3)
+;
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_setr_pi8 (char __b0, char __b1, char __b2, char __b3,
+              char __b4, char __b5, char __b6, char __b7)
+;
+
+/* Creates a vector of two 32-bit values, both elements containing I.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_set1_pi32 (int __i)
+;
+
+/* Creates a vector of four 16-bit values, all elements containing W.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_set1_pi16 (short __w)
+;
+
+/* Creates a vector of eight 8-bit values, all elements containing B.  */
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_set1_pi8 (char __b)
+;
+
+#endif /* __MMX__ */
+#endif /* _MMINTRIN_H_INCLUDED */