--- a/gcc/config/i386/smmintrin.h	Sun Feb 07 18:28:00 2010 +0900
+++ b/gcc/config/i386/smmintrin.h	Fri Feb 12 23:39:51 2010 +0900
@@ -35,7 +35,125 @@
 /* We need definitions from the SSSE3, SSE3, SSE2 and SSE header
    files.  */
 #include <tmmintrin.h>
-#include <mmintrin-common.h>
+
+/* Rounding mode macros. */
+#define _MM_FROUND_TO_NEAREST_INT	0x00
+#define _MM_FROUND_TO_NEG_INF		0x01
+#define _MM_FROUND_TO_POS_INF		0x02
+#define _MM_FROUND_TO_ZERO		0x03
+#define _MM_FROUND_CUR_DIRECTION	0x04
+
+#define _MM_FROUND_RAISE_EXC		0x00
+#define _MM_FROUND_NO_EXC		0x08
+
+#define _MM_FROUND_NINT		\
+  (_MM_FROUND_TO_NEAREST_INT | _MM_FROUND_RAISE_EXC)
+#define _MM_FROUND_FLOOR	\
+  (_MM_FROUND_TO_NEG_INF | _MM_FROUND_RAISE_EXC)
+#define _MM_FROUND_CEIL		\
+  (_MM_FROUND_TO_POS_INF | _MM_FROUND_RAISE_EXC)
+#define _MM_FROUND_TRUNC	\
+  (_MM_FROUND_TO_ZERO | _MM_FROUND_RAISE_EXC)
+#define _MM_FROUND_RINT		\
+  (_MM_FROUND_CUR_DIRECTION | _MM_FROUND_RAISE_EXC)
+#define _MM_FROUND_NEARBYINT	\
+  (_MM_FROUND_CUR_DIRECTION | _MM_FROUND_NO_EXC)
+
+/* Test Instruction */
+/* Packed integer 128-bit bitwise comparison. Return 1 if
+   (__V & __M) == 0.  */
+extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_testz_si128 (__m128i __M, __m128i __V)
+{
+  return __builtin_ia32_ptestz128 ((__v2di)__M, (__v2di)__V);
+}
+
+/* Packed integer 128-bit bitwise comparison. Return 1 if
+   (__V & ~__M) == 0.  */
+extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_testc_si128 (__m128i __M, __m128i __V)
+{
+  return __builtin_ia32_ptestc128 ((__v2di)__M, (__v2di)__V);
+}
+
+/* Packed integer 128-bit bitwise comparison. Return 1 if
+   (__V & __M) != 0 && (__V & ~__M) != 0.  */
+extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_testnzc_si128 (__m128i __M, __m128i __V)
+{
+  return __builtin_ia32_ptestnzc128 ((__v2di)__M, (__v2di)__V);
+}
+
+/* Macros for packed integer 128-bit comparison intrinsics.  */
+#define _mm_test_all_zeros(M, V) _mm_testz_si128 ((M), (V))
+
+#define _mm_test_all_ones(V) \
+  _mm_testc_si128 ((V), _mm_cmpeq_epi32 ((V), (V)))
+
+#define _mm_test_mix_ones_zeros(M, V) _mm_testnzc_si128 ((M), (V))
+
+/* Packed/scalar double precision floating point rounding.  */
+
+#ifdef __OPTIMIZE__
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_round_pd (__m128d __V, const int __M)
+{
+  return (__m128d) __builtin_ia32_roundpd ((__v2df)__V, __M);
+}
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_round_sd(__m128d __D, __m128d __V, const int __M)
+{
+  return (__m128d) __builtin_ia32_roundsd ((__v2df)__D,
+					   (__v2df)__V,
+					   __M);
+}
+#else
+#define _mm_round_pd(V, M) \
+  ((__m128d) __builtin_ia32_roundpd ((__v2df)(__m128d)(V), (int)(M)))
+
+#define _mm_round_sd(D, V, M)						\
+  ((__m128d) __builtin_ia32_roundsd ((__v2df)(__m128d)(D),		\
+				     (__v2df)(__m128d)(V), (int)(M)))
+#endif
+
+/* Packed/scalar single precision floating point rounding.  */
+
+#ifdef __OPTIMIZE__
+extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_round_ps (__m128 __V, const int __M)
+{
+  return (__m128) __builtin_ia32_roundps ((__v4sf)__V, __M);
+}
+
+extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_round_ss (__m128 __D, __m128 __V, const int __M)
+{
+  return (__m128) __builtin_ia32_roundss ((__v4sf)__D,
+					  (__v4sf)__V,
+					  __M);
+}
+#else
+#define _mm_round_ps(V, M) \
+  ((__m128) __builtin_ia32_roundps ((__v4sf)(__m128)(V), (int)(M)))
+
+#define _mm_round_ss(D, V, M)						\
+  ((__m128) __builtin_ia32_roundss ((__v4sf)(__m128)(D),		\
+				    (__v4sf)(__m128)(V), (int)(M)))
+#endif
+
+/* Macros for ceil/floor intrinsics.  */
+#define _mm_ceil_pd(V)	   _mm_round_pd ((V), _MM_FROUND_CEIL)
+#define _mm_ceil_sd(D, V)  _mm_round_sd ((D), (V), _MM_FROUND_CEIL)
+
+#define _mm_floor_pd(V)	   _mm_round_pd((V), _MM_FROUND_FLOOR)
+#define _mm_floor_sd(D, V) _mm_round_sd ((D), (V), _MM_FROUND_FLOOR)
+
+#define _mm_ceil_ps(V)	   _mm_round_ps ((V), _MM_FROUND_CEIL)
+#define _mm_ceil_ss(D, V)  _mm_round_ss ((D), (V), _MM_FROUND_CEIL)
+
+#define _mm_floor_ps(V)	   _mm_round_ps ((V), _MM_FROUND_FLOOR)
+#define _mm_floor_ss(D, V) _mm_round_ss ((D), (V), _MM_FROUND_FLOOR)
 
 /* SSE4.1 */
 
@@ -675,19 +793,8 @@
   return (__m128i) __builtin_ia32_pcmpgtq ((__v2di)__X, (__v2di)__Y);
 }
 
-/* Calculate a number of bits set to 1.  */
-extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_popcnt_u32 (unsigned int __X)
-{
-  return __builtin_popcount (__X);
-}
-
-#ifdef __x86_64__
-extern __inline long long  __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_popcnt_u64 (unsigned long long __X)
-{
-  return __builtin_popcountll (__X);
-}
+#ifdef __POPCNT__
+#include <popcntintrin.h>
 #endif
 
 /* Accumulate CRC32 (polynomial 0x11EDC6F41) value.  */