2009-08-29 Basile Starynkevitch <basile@starynkevitch.net>

	MELT branch merged with trunk rev 151199



git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/branches/melt-branch@151206 138bc75d-0d04-0410-961f-82ee72b054a4

22 files changed, 358 insertions, 5317 deletions

diff --git a/gcc/config/i386/att.h b/gcc/config/i386/att.h
index 6586ddd3d87..30616904fe2 100644
--- a/gcc/config/i386/att.h
+++ b/gcc/config/i386/att.h
@@ -31,6 +31,7 @@ see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
 
 /* Assembler pseudos to introduce constants of various size.  */
 
+#define ASM_BYTE "\t.byte\t"
 #define ASM_SHORT "\t.value\t"
 #define ASM_LONG "\t.long\t"
 #define ASM_QUAD "\t.quad\t"  /* Should not be used for 32bit compilation.  */
@@ -43,7 +44,7 @@ do								\
 { size_t i = 0, limit = (SIZE); 				\
   while (i < limit)						\
     { if (i%10 == 0) { if (i!=0) putc ('\n', (FILE));		\
-		       fputs ("\t.byte\t", (FILE)); }		\
+		       fputs (ASM_BYTE, (FILE)); }		\
       else putc (',', (FILE));					\
 	fprintf ((FILE), "0x%x", ((PTR)[i++] & 0377)) ;}	\
       putc ('\n', (FILE));					\
diff --git a/gcc/config/i386/bmmintrin.h b/gcc/config/i386/bmmintrin.h
index e92768c25dc..91d4e774246 100644
--- a/gcc/config/i386/bmmintrin.h
+++ b/gcc/config/i386/bmmintrin.h
@@ -24,1238 +24,6 @@
 #ifndef _BMMINTRIN_H_INCLUDED
 #define _BMMINTRIN_H_INCLUDED
 
-#ifndef __SSE5__
-# error "SSE5 instruction set not enabled"
-#else
-
-/* We need definitions from the SSE4A, SSE3, SSE2 and SSE header files.  */
-#include <ammintrin.h>
-#include <mmintrin-common.h>
-
-/* Floating point multiply/add type instructions */
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_macc_ps(__m128 __A, __m128 __B, __m128 __C)
-{
-  return (__m128) __builtin_ia32_fmaddps ((__v4sf)__A, (__v4sf)__B, (__v4sf)__C);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_macc_pd(__m128d __A, __m128d __B, __m128d __C)
-{
-  return (__m128d) __builtin_ia32_fmaddpd ((__v2df)__A, (__v2df)__B, (__v2df)__C);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_macc_ss(__m128 __A, __m128 __B, __m128 __C)
-{
-  return  (__m128) __builtin_ia32_fmaddss ((__v4sf)__A, (__v4sf)__B, (__v4sf)__C);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_macc_sd(__m128d __A, __m128d __B, __m128d __C)
-{
-  return (__m128d) __builtin_ia32_fmaddsd ((__v2df)__A, (__v2df)__B, (__v2df)__C);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_msub_ps(__m128 __A, __m128 __B, __m128 __C)
-{
-  return (__m128) __builtin_ia32_fmsubps ((__v4sf)__A, (__v4sf)__B, (__v4sf)__C);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_msub_pd(__m128d __A, __m128d __B, __m128d __C)
-{
-  return (__m128d) __builtin_ia32_fmsubpd ((__v2df)__A, (__v2df)__B, (__v2df)__C);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_msub_ss(__m128 __A, __m128 __B, __m128 __C)
-{
-  return (__m128) __builtin_ia32_fmsubss ((__v4sf)__A, (__v4sf)__B, (__v4sf)__C);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_msub_sd(__m128d __A, __m128d __B, __m128d __C)
-{
-  return (__m128d) __builtin_ia32_fmsubsd ((__v2df)__A, (__v2df)__B, (__v2df)__C);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_nmacc_ps(__m128 __A, __m128 __B, __m128 __C)
-{
-  return (__m128) __builtin_ia32_fnmaddps ((__v4sf)__A, (__v4sf)__B, (__v4sf)__C);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_nmacc_pd(__m128d __A, __m128d __B, __m128d __C)
-{
-  return (__m128d) __builtin_ia32_fnmaddpd ((__v2df)__A, (__v2df)__B, (__v2df)__C);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_nmacc_ss(__m128 __A, __m128 __B, __m128 __C)
-{
-  return (__m128) __builtin_ia32_fnmaddss ((__v4sf)__A, (__v4sf)__B, (__v4sf)__C);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_nmacc_sd(__m128d __A, __m128d __B, __m128d __C)
-{
-  return (__m128d) __builtin_ia32_fnmaddsd ((__v2df)__A, (__v2df)__B, (__v2df)__C);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_nmsub_ps(__m128 __A, __m128 __B, __m128 __C)
-{
-  return (__m128) __builtin_ia32_fnmsubps ((__v4sf)__A, (__v4sf)__B, (__v4sf)__C);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_nmsub_pd(__m128d __A, __m128d __B, __m128d __C)
-{
-  return (__m128d) __builtin_ia32_fnmsubpd ((__v2df)__A, (__v2df)__B, (__v2df)__C);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_nmsub_ss(__m128 __A, __m128 __B, __m128 __C)
-{
-  return (__m128) __builtin_ia32_fnmsubss ((__v4sf)__A, (__v4sf)__B, (__v4sf)__C);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_nmsub_sd(__m128d __A, __m128d __B, __m128d __C)
-{
-  return (__m128d) __builtin_ia32_fnmsubsd ((__v2df)__A, (__v2df)__B, (__v2df)__C);
-}
-
-/* Integer multiply/add intructions. */
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_maccs_epi16(__m128i __A, __m128i __B, __m128i __C)
-{
-  return (__m128i) __builtin_ia32_pmacssww ((__v8hi)__A,(__v8hi)__B, (__v8hi)__C);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_macc_epi16(__m128i __A, __m128i __B, __m128i __C)
-{
-  return (__m128i) __builtin_ia32_pmacsww ((__v8hi)__A, (__v8hi)__B, (__v8hi)__C);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_maccsd_epi16(__m128i __A, __m128i __B, __m128i __C)
-{
-  return  (__m128i) __builtin_ia32_pmacsswd ((__v8hi)__A, (__v8hi)__B, (__v4si)__C);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_maccd_epi16(__m128i __A, __m128i __B, __m128i __C)
-{
-  return  (__m128i) __builtin_ia32_pmacswd ((__v8hi)__A, (__v8hi)__B, (__v4si)__C);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_maccs_epi32(__m128i __A, __m128i __B, __m128i __C)
-{
-  return  (__m128i) __builtin_ia32_pmacssdd ((__v4si)__A, (__v4si)__B, (__v4si)__C);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_macc_epi32(__m128i __A, __m128i __B, __m128i __C)
-{
-  return  (__m128i) __builtin_ia32_pmacsdd ((__v4si)__A, (__v4si)__B, (__v4si)__C);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_maccslo_epi32(__m128i __A, __m128i __B, __m128i __C)
-{
-  return  (__m128i) __builtin_ia32_pmacssdql ((__v4si)__A, (__v4si)__B, (__v2di)__C);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_macclo_epi32(__m128i __A, __m128i __B, __m128i __C)
-{
-  return  (__m128i) __builtin_ia32_pmacsdql ((__v4si)__A, (__v4si)__B, (__v2di)__C);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_maccshi_epi32(__m128i __A, __m128i __B, __m128i __C)
-{
-  return  (__m128i) __builtin_ia32_pmacssdqh ((__v4si)__A, (__v4si)__B, (__v2di)__C);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_macchi_epi32(__m128i __A, __m128i __B, __m128i __C)
-{
-  return  (__m128i) __builtin_ia32_pmacsdqh ((__v4si)__A, (__v4si)__B, (__v2di)__C);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_maddsd_epi16(__m128i __A, __m128i __B, __m128i __C)
-{
-  return  (__m128i) __builtin_ia32_pmadcsswd ((__v8hi)__A,(__v8hi)__B,(__v4si)__C);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_maddd_epi16(__m128i __A, __m128i __B, __m128i __C)
-{
-  return  (__m128i) __builtin_ia32_pmadcswd ((__v8hi)__A,(__v8hi)__B,(__v4si)__C);
-}
-
-/* Packed Integer Horizontal Add and Subtract */
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_haddw_epi8(__m128i __A)
-{
-  return  (__m128i) __builtin_ia32_phaddbw ((__v16qi)__A);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_haddd_epi8(__m128i __A)
-{
-  return  (__m128i) __builtin_ia32_phaddbd ((__v16qi)__A);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_haddq_epi8(__m128i __A)
-{
-  return  (__m128i) __builtin_ia32_phaddbq ((__v16qi)__A);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_haddd_epi16(__m128i __A)
-{
-  return  (__m128i) __builtin_ia32_phaddwd ((__v8hi)__A);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_haddq_epi16(__m128i __A)
-{
-  return  (__m128i) __builtin_ia32_phaddwq ((__v8hi)__A);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_haddq_epi32(__m128i __A)
-{
-  return  (__m128i) __builtin_ia32_phadddq ((__v4si)__A);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_haddw_epu8(__m128i __A)
-{
-  return  (__m128i) __builtin_ia32_phaddubw ((__v16qi)__A);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_haddd_epu8(__m128i __A)
-{
-  return  (__m128i) __builtin_ia32_phaddubd ((__v16qi)__A);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_haddq_epu8(__m128i __A)
-{
-  return  (__m128i) __builtin_ia32_phaddubq ((__v16qi)__A);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_haddd_epu16(__m128i __A)
-{
-  return  (__m128i) __builtin_ia32_phadduwd ((__v8hi)__A);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_haddq_epu16(__m128i __A)
-{
-  return  (__m128i) __builtin_ia32_phadduwq ((__v8hi)__A);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_haddq_epu32(__m128i __A)
-{
-  return  (__m128i) __builtin_ia32_phaddudq ((__v4si)__A);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_hsubw_epi8(__m128i __A)
-{
-  return  (__m128i) __builtin_ia32_phsubbw ((__v16qi)__A);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_hsubd_epi16(__m128i __A)
-{
-  return  (__m128i) __builtin_ia32_phsubwd ((__v8hi)__A);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_hsubq_epi32(__m128i __A)
-{
-  return  (__m128i) __builtin_ia32_phsubdq ((__v4si)__A);
-}
-
-/* Vector conditional move and permute */
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_cmov_si128(__m128i __A, __m128i __B, __m128i __C)
-{
-  return  (__m128i) __builtin_ia32_pcmov (__A, __B, __C);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_perm_epi8(__m128i __A, __m128i __B, __m128i __C)
-{
-  return  (__m128i) __builtin_ia32_pperm ((__v16qi)__A, (__v16qi)__B, (__v16qi)__C);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_perm_ps(__m128 __A, __m128 __B, __m128i __C)
-{
-  return  (__m128) __builtin_ia32_permps ((__m128)__A, (__m128)__B, (__v16qi)__C);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_perm_pd(__m128d __A, __m128d __B, __m128i __C)
-{
-  return  (__m128d) __builtin_ia32_permpd ((__m128d)__A, (__m128d)__B, (__v16qi)__C);
-}
-
-/* Packed Integer Rotates and Shifts */
-
-/* Rotates - Non-Immediate form */
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_rot_epi8(__m128i __A,  __m128i __B)
-{
-  return  (__m128i) __builtin_ia32_protb ((__v16qi)__A, (__v16qi)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_rot_epi16(__m128i __A,  __m128i __B)
-{
-  return  (__m128i) __builtin_ia32_protw ((__v8hi)__A, (__v8hi)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_rot_epi32(__m128i __A,  __m128i __B)
-{
-  return  (__m128i) __builtin_ia32_protd ((__v4si)__A, (__v4si)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_rot_epi64(__m128i __A,  __m128i __B)
-{
-  return (__m128i)  __builtin_ia32_protq ((__v2di)__A, (__v2di)__B);
-}
-
-
-/* Rotates - Immediate form */
-#ifdef __OPTIMIZE__
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_roti_epi8(__m128i __A, const int __B)
-{
-  return  (__m128i) __builtin_ia32_protbi ((__v16qi)__A, __B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_roti_epi16(__m128i __A, const int __B)
-{
-  return  (__m128i) __builtin_ia32_protwi ((__v8hi)__A, __B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_roti_epi32(__m128i __A, const int __B)
-{
-  return  (__m128i) __builtin_ia32_protdi ((__v4si)__A, __B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_roti_epi64(__m128i __A, const int __B)
-{
-  return  (__m128i) __builtin_ia32_protqi ((__v2di)__A, __B);
-}
-#else
-#define _mm_roti_epi8(A, N) \
-  ((__m128i) __builtin_ia32_protbi ((__v16qi)(__m128i)(A), (int)(N)))
-#define _mm_roti_epi16(A, N) \
-  ((__m128i) __builtin_ia32_protwi ((__v8hi)(__m128i)(A), (int)(N)))
-#define _mm_roti_epi32(A, N) \
-  ((__m128i) __builtin_ia32_protdi ((__v4si)(__m128i)(A), (int)(N)))
-#define _mm_roti_epi64(A, N) \
-  ((__m128i) __builtin_ia32_protqi ((__v2di)(__m128i)(A), (int)(N)))
-#endif
-
-/* pshl */
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_shl_epi8(__m128i __A,  __m128i __B)
-{
-  return  (__m128i) __builtin_ia32_pshlb ((__v16qi)__A, (__v16qi)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_shl_epi16(__m128i __A,  __m128i __B)
-{
-  return  (__m128i) __builtin_ia32_pshlw ((__v8hi)__A, (__v8hi)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_shl_epi32(__m128i __A,  __m128i __B)
-{
-  return  (__m128i) __builtin_ia32_pshld ((__v4si)__A, (__v4si)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_shl_epi64(__m128i __A,  __m128i __B)
-{
-  return  (__m128i) __builtin_ia32_pshlq ((__v2di)__A, (__v2di)__B);
-}
-
-/* psha */
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_sha_epi8(__m128i __A,  __m128i __B)
-{
-  return  (__m128i) __builtin_ia32_pshab ((__v16qi)__A, (__v16qi)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_sha_epi16(__m128i __A,  __m128i __B)
-{
-  return  (__m128i) __builtin_ia32_pshaw ((__v8hi)__A, (__v8hi)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_sha_epi32(__m128i __A,  __m128i __B)
-{
-  return  (__m128i) __builtin_ia32_pshad ((__v4si)__A, (__v4si)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_sha_epi64(__m128i __A,  __m128i __B)
-{
-  return  (__m128i) __builtin_ia32_pshaq ((__v2di)__A, (__v2di)__B);
-}
-
-/* Compare and Predicate Generation */
-
-/* com (floating point, packed single) */
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comeq_ps(__m128 __A, __m128 __B)
-{
-  return  (__m128) __builtin_ia32_comeqps ((__v4sf)__A, (__v4sf)__B);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comlt_ps(__m128 __A, __m128 __B)
-{
-  return  (__m128) __builtin_ia32_comltps ((__v4sf)__A, (__v4sf)__B);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comle_ps(__m128 __A, __m128 __B)
-{
-  return (__m128) __builtin_ia32_comleps ((__v4sf)__A, (__v4sf)__B);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comunord_ps(__m128 __A, __m128 __B)
-{
-  return (__m128) __builtin_ia32_comunordps ((__v4sf)__A, (__v4sf)__B);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comneq_ps(__m128 __A, __m128 __B)
-{
-  return (__m128) __builtin_ia32_comuneqps ((__v4sf)__A, (__v4sf)__B);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comnlt_ps(__m128 __A, __m128 __B)
-{
-  return (__m128) __builtin_ia32_comunltps ((__v4sf)__A, (__v4sf)__B);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comnle_ps(__m128 __A, __m128 __B)
-{
-  return (__m128)  __builtin_ia32_comunleps ((__v4sf)__A, (__v4sf)__B);
-}
-
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comord_ps(__m128 __A, __m128 __B)
-{
-  return (__m128) __builtin_ia32_comordps ((__v4sf)__A, (__v4sf)__B);
-}
-
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comueq_ps(__m128 __A, __m128 __B)
-{
-  return (__m128) __builtin_ia32_comueqps ((__v4sf)__A, (__v4sf)__B);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comnge_ps(__m128 __A, __m128 __B)
-{
-  return (__m128) __builtin_ia32_comungeps ((__v4sf)__A, (__v4sf)__B);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comngt_ps(__m128 __A, __m128 __B)
-{
-  return (__m128) __builtin_ia32_comungtps ((__v4sf)__A, (__v4sf)__B);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comfalse_ps(__m128 __A, __m128 __B)
-{
-  return (__m128) __builtin_ia32_comfalseps ((__v4sf)__A, (__v4sf)__B);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comoneq_ps(__m128 __A, __m128 __B)
-{
-  return (__m128) __builtin_ia32_comneqps ((__v4sf)__A, (__v4sf)__B);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comge_ps(__m128 __A, __m128 __B)
-{
-  return (__m128) __builtin_ia32_comgeps ((__v4sf)__A, (__v4sf)__B);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comgt_ps(__m128 __A, __m128 __B)
-{
-  return (__m128) __builtin_ia32_comgtps ((__v4sf)__A, (__v4sf)__B);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comtrue_ps(__m128 __A, __m128 __B)
-{
-  return (__m128) __builtin_ia32_comtrueps ((__v4sf)__A, (__v4sf)__B);
-}
-
-/* com (floating point, packed double) */
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comeq_pd(__m128d __A, __m128d __B)
-{
-  return (__m128d) __builtin_ia32_comeqpd ((__v2df)__A, (__v2df)__B);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comlt_pd(__m128d __A, __m128d __B)
-{
-  return (__m128d) __builtin_ia32_comltpd ((__v2df)__A, (__v2df)__B);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comle_pd(__m128d __A, __m128d __B)
-{
-  return (__m128d) __builtin_ia32_comlepd ((__v2df)__A, (__v2df)__B);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comunord_pd(__m128d __A, __m128d __B)
-{
-  return (__m128d) __builtin_ia32_comunordpd ((__v2df)__A, (__v2df)__B);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comneq_pd(__m128d __A, __m128d __B)
-{
-  return (__m128d) __builtin_ia32_comuneqpd ((__v2df)__A, (__v2df)__B);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comnlt_pd(__m128d __A, __m128d __B)
-{
-  return (__m128d) __builtin_ia32_comunltpd ((__v2df)__A, (__v2df)__B);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comnle_pd(__m128d __A, __m128d __B)
-{
-  return (__m128d) __builtin_ia32_comunlepd ((__v2df)__A, (__v2df)__B);
-}
-
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comord_pd(__m128d __A, __m128d __B)
-{
-  return (__m128d) __builtin_ia32_comordpd ((__v2df)__A, (__v2df)__B);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comueq_pd(__m128d __A, __m128d __B)
-{
-  return (__m128d) __builtin_ia32_comueqpd ((__v2df)__A, (__v2df)__B);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comnge_pd(__m128d __A, __m128d __B)
-{
-  return (__m128d) __builtin_ia32_comungepd ((__v2df)__A, (__v2df)__B);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comngt_pd(__m128d __A, __m128d __B)
-{
-  return (__m128d) __builtin_ia32_comungtpd ((__v2df)__A, (__v2df)__B);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comfalse_pd(__m128d __A, __m128d __B)
-{
-  return (__m128d) __builtin_ia32_comfalsepd ((__v2df)__A, (__v2df)__B);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comoneq_pd(__m128d __A, __m128d __B)
-{
-  return (__m128d) __builtin_ia32_comneqpd ((__v2df)__A, (__v2df)__B);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comge_pd(__m128d __A, __m128d __B)
-{
-  return (__m128d) __builtin_ia32_comgepd ((__v2df)__A, (__v2df)__B);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comgt_pd(__m128d __A, __m128d __B)
-{
-  return (__m128d) __builtin_ia32_comgtpd ((__v2df)__A, (__v2df)__B);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comtrue_pd(__m128d __A, __m128d __B)
-{
-  return (__m128d) __builtin_ia32_comtruepd ((__v2df)__A, (__v2df)__B);
-}
-
-/* com (floating point, scalar single) */
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comeq_ss(__m128 __A, __m128 __B)
-{
-  return (__m128)  __builtin_ia32_comeqss ((__v4sf)__A, (__v4sf)__B);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comlt_ss(__m128 __A, __m128 __B)
-{
-  return (__m128) __builtin_ia32_comltss ((__v4sf)__A, (__v4sf)__B);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comle_ss(__m128 __A, __m128 __B)
-{
-  return (__m128) __builtin_ia32_comless ((__v4sf)__A, (__v4sf)__B);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comunord_ss(__m128 __A, __m128 __B)
-{
-  return (__m128) __builtin_ia32_comunordss ((__v4sf)__A, (__v4sf)__B);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comneq_ss(__m128 __A, __m128 __B)
-{
-  return (__m128) __builtin_ia32_comuneqss ((__v4sf)__A, (__v4sf)__B);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comnlt_ss(__m128 __A, __m128 __B)
-{
-  return (__m128) __builtin_ia32_comunltss ((__v4sf)__A, (__v4sf)__B);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comnle_ss(__m128 __A, __m128 __B)
-{
-  return (__m128) __builtin_ia32_comunless ((__v4sf)__A, (__v4sf)__B);
-}
-
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comord_ss(__m128 __A, __m128 __B)
-{
-  return (__m128) __builtin_ia32_comordss ((__v4sf)__A, (__v4sf)__B);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comueq_ss(__m128 __A, __m128 __B)
-{
-  return (__m128) __builtin_ia32_comueqss ((__v4sf)__A, (__v4sf)__B);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comnge_ss(__m128 __A, __m128 __B)
-{
-  return (__m128) __builtin_ia32_comungess ((__v4sf)__A, (__v4sf)__B);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comngt_ss(__m128 __A, __m128 __B)
-{
-  return (__m128) __builtin_ia32_comungtss ((__v4sf)__A, (__v4sf)__B);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comfalse_ss(__m128 __A, __m128 __B)
-{
-  return (__m128) __builtin_ia32_comfalsess ((__v4sf)__A, (__v4sf)__B);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comoneq_ss(__m128 __A, __m128 __B)
-{
-  return (__m128) __builtin_ia32_comneqss ((__v4sf)__A, (__v4sf)__B);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comge_ss(__m128 __A, __m128 __B)
-{
-  return (__m128) __builtin_ia32_comgess ((__v4sf)__A, (__v4sf)__B);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comgt_ss(__m128 __A, __m128 __B)
-{
-  return (__m128) __builtin_ia32_comgtss ((__v4sf)__A, (__v4sf)__B);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comtrue_ss(__m128 __A, __m128 __B)
-{
-  return (__m128) __builtin_ia32_comtruess ((__v4sf)__A, (__v4sf)__B);
-}
-
-/* com (floating point, scalar double) */
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comeq_sd(__m128d __A, __m128d __B)
-{
-  return (__m128d) __builtin_ia32_comeqsd ((__v2df)__A, (__v2df)__B);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comlt_sd(__m128d __A, __m128d __B)
-{
-  return (__m128d) __builtin_ia32_comltsd ((__v2df)__A, (__v2df)__B);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comle_sd(__m128d __A, __m128d __B)
-{
-  return (__m128d) __builtin_ia32_comlesd ((__v2df)__A, (__v2df)__B);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comunord_sd(__m128d __A, __m128d __B)
-{
-  return (__m128d) __builtin_ia32_comunordsd ((__v2df)__A, (__v2df)__B);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comneq_sd(__m128d __A, __m128d __B)
-{
-  return (__m128d) __builtin_ia32_comuneqsd ((__v2df)__A, (__v2df)__B);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comnlt_sd(__m128d __A, __m128d __B)
-{
-  return (__m128d) __builtin_ia32_comunltsd ((__v2df)__A, (__v2df)__B);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comnle_sd(__m128d __A, __m128d __B)
-{
-  return (__m128d) __builtin_ia32_comunlesd ((__v2df)__A, (__v2df)__B);
-}
-
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comord_sd(__m128d __A, __m128d __B)
-{
-  return (__m128d) __builtin_ia32_comordsd ((__v2df)__A, (__v2df)__B);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comueq_sd(__m128d __A, __m128d __B)
-{
-  return (__m128d) __builtin_ia32_comueqsd ((__v2df)__A, (__v2df)__B);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comnge_sd(__m128d __A, __m128d __B)
-{
-  return (__m128d) __builtin_ia32_comungesd ((__v2df)__A, (__v2df)__B);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comngt_sd(__m128d __A, __m128d __B)
-{
-  return (__m128d) __builtin_ia32_comungtsd ((__v2df)__A, (__v2df)__B);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comfalse_sd(__m128d __A, __m128d __B)
-{
-  return (__m128d) __builtin_ia32_comfalsesd ((__v2df)__A, (__v2df)__B);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comoneq_sd(__m128d __A, __m128d __B)
-{
-  return (__m128d) __builtin_ia32_comneqsd ((__v2df)__A, (__v2df)__B);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comge_sd(__m128d __A, __m128d __B)
-{
-  return (__m128d) __builtin_ia32_comgesd ((__v2df)__A, (__v2df)__B);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comgt_sd(__m128d __A, __m128d __B)
-{
-  return (__m128d) __builtin_ia32_comgtsd ((__v2df)__A, (__v2df)__B);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comtrue_sd(__m128d __A, __m128d __B)
-{
-  return (__m128d) __builtin_ia32_comtruesd ((__v2df)__A, (__v2df)__B);
-}
-
-
-/*pcom (integer, unsinged bytes) */
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comlt_epu8(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomltub ((__v16qi)__A, (__v16qi)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comle_epu8(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomleub ((__v16qi)__A, (__v16qi)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comgt_epu8(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomgtub ((__v16qi)__A, (__v16qi)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comge_epu8(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomgeub ((__v16qi)__A, (__v16qi)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comeq_epu8(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomequb ((__v16qi)__A, (__v16qi)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comneq_epu8(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomnequb ((__v16qi)__A, (__v16qi)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comfalse_epu8(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomfalseub ((__v16qi)__A, (__v16qi)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comtrue_epu8(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomtrueub ((__v16qi)__A, (__v16qi)__B);
-}
-
-/*pcom (integer, unsinged words) */
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comlt_epu16(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomltuw ((__v8hi)__A, (__v8hi)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comle_epu16(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomleuw ((__v8hi)__A, (__v8hi)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comgt_epu16(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomgtuw ((__v8hi)__A, (__v8hi)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comge_epu16(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomgeuw ((__v8hi)__A, (__v8hi)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comeq_epu16(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomequw ((__v8hi)__A, (__v8hi)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comneq_epu16(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomnequw ((__v8hi)__A, (__v8hi)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comfalse_epu16(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomfalseuw ((__v8hi)__A, (__v8hi)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comtrue_epu16(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomtrueuw ((__v8hi)__A, (__v8hi)__B);
-}
-
-/*pcom (integer, unsinged double words) */
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comlt_epu32(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomltud ((__v4si)__A, (__v4si)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comle_epu32(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomleud ((__v4si)__A, (__v4si)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comgt_epu32(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomgtud ((__v4si)__A, (__v4si)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comge_epu32(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomgeud ((__v4si)__A, (__v4si)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comeq_epu32(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomequd ((__v4si)__A, (__v4si)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comneq_epu32(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomnequd ((__v4si)__A, (__v4si)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comfalse_epu32(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomfalseud ((__v4si)__A, (__v4si)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comtrue_epu32(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomtrueud ((__v4si)__A, (__v4si)__B);
-}
-
-/*pcom (integer, unsinged quad words) */
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comlt_epu64(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomltuq ((__v2di)__A, (__v2di)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comle_epu64(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomleuq ((__v2di)__A, (__v2di)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comgt_epu64(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomgtuq ((__v2di)__A, (__v2di)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comge_epu64(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomgeuq ((__v2di)__A, (__v2di)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comeq_epu64(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomequq ((__v2di)__A, (__v2di)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comneq_epu64(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomnequq ((__v2di)__A, (__v2di)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comfalse_epu64(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomfalseuq ((__v2di)__A, (__v2di)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comtrue_epu64(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomtrueuq ((__v2di)__A, (__v2di)__B);
-}
-
-/*pcom (integer, signed bytes) */
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comlt_epi8(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomltb ((__v16qi)__A, (__v16qi)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comle_epi8(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomleb ((__v16qi)__A, (__v16qi)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comgt_epi8(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomgtb ((__v16qi)__A, (__v16qi)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comge_epi8(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomgeb ((__v16qi)__A, (__v16qi)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comeq_epi8(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomeqb ((__v16qi)__A, (__v16qi)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comneq_epi8(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomneqb ((__v16qi)__A, (__v16qi)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comfalse_epi8(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomfalseb ((__v16qi)__A, (__v16qi)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comtrue_epi8(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomtrueb ((__v16qi)__A, (__v16qi)__B);
-}
-
-/*pcom (integer, signed words) */
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comlt_epi16(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomltw ((__v8hi)__A, (__v8hi)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comle_epi16(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomlew ((__v8hi)__A, (__v8hi)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comgt_epi16(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomgtw ((__v8hi)__A, (__v8hi)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comge_epi16(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomgew ((__v8hi)__A, (__v8hi)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comeq_epi16(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomeqw ((__v8hi)__A, (__v8hi)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comneq_epi16(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomneqw ((__v8hi)__A, (__v8hi)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comfalse_epi16(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomfalsew ((__v8hi)__A, (__v8hi)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comtrue_epi16(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomtruew ((__v8hi)__A, (__v8hi)__B);
-}
-
-/*pcom (integer, signed double words) */
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comlt_epi32(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomltd ((__v4si)__A, (__v4si)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comle_epi32(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomled ((__v4si)__A, (__v4si)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comgt_epi32(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomgtd ((__v4si)__A, (__v4si)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comge_epi32(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomged ((__v4si)__A, (__v4si)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comeq_epi32(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomeqd ((__v4si)__A, (__v4si)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comneq_epi32(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomneqd ((__v4si)__A, (__v4si)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comfalse_epi32(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomfalsed ((__v4si)__A, (__v4si)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comtrue_epi32(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomtrued ((__v4si)__A, (__v4si)__B);
-}
-
-/*pcom (integer, signed quad words) */
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comlt_epi64(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomltq ((__v2di)__A, (__v2di)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comle_epi64(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomleq ((__v2di)__A, (__v2di)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comgt_epi64(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomgtq ((__v2di)__A, (__v2di)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comge_epi64(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomgeq ((__v2di)__A, (__v2di)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comeq_epi64(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomeqq ((__v2di)__A, (__v2di)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comneq_epi64(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomneqq ((__v2di)__A, (__v2di)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comfalse_epi64(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomfalseq ((__v2di)__A, (__v2di)__B);
-}
-
-extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_comtrue_epi64(__m128i __A, __m128i __B)
-{
-  return (__m128i) __builtin_ia32_pcomtrueq ((__v2di)__A, (__v2di)__B);
-}
-
-/* FRCZ */
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_frcz_ps (__m128 __A)
-{
-  return (__m128) __builtin_ia32_frczps ((__v4sf)__A);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_frcz_pd (__m128d __A)
-{
-  return (__m128d) __builtin_ia32_frczpd ((__v2df)__A);
-}
-
-extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_frcz_ss (__m128 __A, __m128 __B)
-{
-  return (__m128) __builtin_ia32_frczss ((__v4sf)__A, (__v4sf)__B);
-}
-
-extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_frcz_sd (__m128d __A, __m128d __B)
-{
-  return (__m128d) __builtin_ia32_frczsd ((__v2df)__A, (__v2df)__B);
-}
-
-#endif /* __SSE5__ */
+# error "SSE5 instruction set removed from compiler"
 
 #endif /* _BMMINTRIN_H_INCLUDED */
diff --git a/gcc/config/i386/bsd.h b/gcc/config/i386/bsd.h
index 229777a4640..e408ccdb032 100644
--- a/gcc/config/i386/bsd.h
+++ b/gcc/config/i386/bsd.h
@@ -32,6 +32,7 @@ along with GCC; see the file COPYING3.  If not see
 
 /* Assembler pseudos to introduce constants of various size.  */
 
+#define ASM_BYTE "\t.byte\t"
 #define ASM_SHORT "\t.word\t"
 #define ASM_LONG "\t.long\t"
 #define ASM_QUAD "\t.quad\t"  /* Should not be used for 32bit compilation.  */
diff --git a/gcc/config/i386/cygwin.h b/gcc/config/i386/cygwin.h
index 02d059f7628..d1d00f7a79b 100644
--- a/gcc/config/i386/cygwin.h
+++ b/gcc/config/i386/cygwin.h
@@ -91,7 +91,7 @@ along with GCC; see the file COPYING3.  If not see
   %{shared: %{mdll: %eshared and mdll are not compatible}} \
   %{shared: --shared} %{mdll:--dll} \
   %{static:-Bstatic} %{!static:-Bdynamic} \
-  %{shared|mdll: -e \
+  %{shared|mdll: --enable-auto-image-base -e \
     %{mno-cygwin:_DllMainCRTStartup@12} \
     %{!mno-cygwin:__cygwin_dll_entry@12}}\
   %{!mno-cygwin:--dll-search-prefix=cyg}"
diff --git a/gcc/config/i386/darwin.h b/gcc/config/i386/darwin.h
index 039f52f77ba..eb9ee70a04d 100644
--- a/gcc/config/i386/darwin.h
+++ b/gcc/config/i386/darwin.h
@@ -189,7 +189,7 @@ extern void darwin_x86_file_end (void);
 
 /* Assembler pseudos to introduce constants of various size.  */
 
-#define ASM_BYTE_OP "\t.byte\t"
+#define ASM_BYTE "\t.byte\t"
 #define ASM_SHORT "\t.word\t"
 #define ASM_LONG "\t.long\t"
 #define ASM_QUAD "\t.quad\t"
diff --git a/gcc/config/i386/djgpp-stdint.h b/gcc/config/i386/djgpp-stdint.h
new file mode 100644
index 00000000000..8fd3a25653d
--- /dev/null
+++ b/gcc/config/i386/djgpp-stdint.h
@@ -0,0 +1,62 @@
+/* Definitions for <stdint.h> types on systems using DJGPP.
+   Copyright (C) 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.
+
+You should have received a copy of the GNU General Public License
+along with GCC; see the file COPYING3.  If not see
+<http://www.gnu.org/licenses/>.  */
+
+#define SIG_ATOMIC_TYPE "int"
+
+/* Exact-width integer types */
+
+#define INT8_TYPE "signed char"
+#define INT16_TYPE "signed short int"
+#define INT32_TYPE "signed long int"
+#define INT64_TYPE "signed long long int"
+
+#define UINT8_TYPE "unsigned char"
+#define UINT16_TYPE "short unsigned int"
+#define UINT32_TYPE "long unsigned int"
+#define UINT64_TYPE "long long unsigned int"
+
+/* Minimum-width integer types */
+
+#define INT_LEAST8_TYPE "signed char"
+#define INT_LEAST16_TYPE "signed short int"
+#define INT_LEAST32_TYPE "signed int"
+#define INT_LEAST64_TYPE "signed long long int"
+
+#define UINT_LEAST8_TYPE "unsigned char"
+#define UINT_LEAST16_TYPE "short unsigned int"
+#define UINT_LEAST32_TYPE "unsigned int"
+#define UINT_LEAST64_TYPE "long long unsigned int"
+
+/* Fastest minimum-width integer types */
+
+#define INT_FAST8_TYPE "signed char"
+#define INT_FAST16_TYPE "signed int"
+#define INT_FAST32_TYPE "signed int"
+#define INT_FAST64_TYPE "long long signed int"
+
+#define UINT_FAST8_TYPE "unsigned char"
+#define UINT_FAST16_TYPE "unsigned int"
+#define UINT_FAST32_TYPE "unsigned int"
+#define UINT_FAST64_TYPE "long long unsigned int"
+
+/* Integer types capable of holding object pointers */
+
+#define INTPTR_TYPE "long int"
+#define UINTPTR_TYPE "long unsigned int"
+
diff --git a/gcc/config/i386/i386-c.c b/gcc/config/i386/i386-c.c
index e11ddc2819f..4c960e7d444 100644
--- a/gcc/config/i386/i386-c.c
+++ b/gcc/config/i386/i386-c.c
@@ -230,8 +230,6 @@ ix86_target_macros_internal (int isa_flag,
     def_or_undef (parse_in, "__FMA__");
   if (isa_flag & OPTION_MASK_ISA_SSE4A)
     def_or_undef (parse_in, "__SSE4A__");
-  if (isa_flag & OPTION_MASK_ISA_SSE5)
-    def_or_undef (parse_in, "__SSE5__");
   if ((fpmath & FPMATH_SSE) && (isa_flag & OPTION_MASK_ISA_SSE))
     def_or_undef (parse_in, "__SSE_MATH__");
   if ((fpmath & FPMATH_SSE) && (isa_flag & OPTION_MASK_ISA_SSE2))
diff --git a/gcc/config/i386/i386-interix.h b/gcc/config/i386/i386-interix.h
index 380b46c3d3c..060b82ca245 100644
--- a/gcc/config/i386/i386-interix.h
+++ b/gcc/config/i386/i386-interix.h
@@ -209,7 +209,7 @@ along with GCC; see the file COPYING3.  If not see
 	  else								\
 	    {								\
 	      if (bytes_in_chunk == 0)					\
-		fprintf ((FILE), "\t.byte\t");				\
+		fputs (ASM_BYTE, (FILE));				\
 	      else							\
 		fputc (',', (FILE));					\
 	      fprintf ((FILE), "0x%02x", *_ascii_bytes);		\
@@ -217,7 +217,7 @@ along with GCC; see the file COPYING3.  If not see
 	    }								\
 	}								\
       if (bytes_in_chunk > 0)						\
-        fprintf ((FILE), "\n");						\
+        fputc ('\n', (FILE));						\
     }									\
   while (0)
 
@@ -277,11 +277,11 @@ do {									\
 #define ASM_OUTPUT_DEF(FILE,LABEL1,LABEL2)				\
 do									\
 {									\
-    fprintf ((FILE), "%s", SET_ASM_OP);					\
+    fputs (SET_ASM_OP, (FILE));						\
     assemble_name (FILE, LABEL1);					\
-    fprintf (FILE, ",");						\
+    fputc (',', (FILE));						\
     assemble_name (FILE, LABEL2);					\
-    fprintf (FILE, "\n");						\
+    fputc ('\n', (FILE));						\
     }									\
 while (0)
 
@@ -359,4 +359,4 @@ extern void i386_pe_unique_section (tree, int);
 
 #define SUBTARGET_RETURN_IN_MEMORY(TYPE, FNTYPE) \
 	(TYPE_MODE (TYPE) == BLKmode \
-	 || (AGGREGATE_TYPE_P (TYPE) && int_size_in_bytes (TYPE) > 8 ))
\ No newline at end of file
+	 || (AGGREGATE_TYPE_P (TYPE) && int_size_in_bytes (TYPE) > 8 ))
diff --git a/gcc/config/i386/i386-protos.h b/gcc/config/i386/i386-protos.h
index 324062ec7df..389fc3cddd7 100644
--- a/gcc/config/i386/i386-protos.h
+++ b/gcc/config/i386/i386-protos.h
@@ -28,7 +28,6 @@ extern int ix86_can_use_return_insn_p (void);
 extern void ix86_setup_frame_addresses (void);
 
 extern void ix86_file_end (void);
-extern int ix86_can_eliminate (int, int);
 extern HOST_WIDE_INT ix86_initial_elimination_offset (int, int);
 extern void ix86_expand_prologue (void);
 extern void ix86_expand_epilogue (int);
@@ -114,8 +113,6 @@ extern bool ix86_expand_fp_vcond (rtx[]);
 extern bool ix86_expand_int_vcond (rtx[]);
 extern void ix86_expand_sse_unpack (rtx[], bool, bool);
 extern void ix86_expand_sse4_unpack (rtx[], bool, bool);
-extern void ix86_expand_sse5_unpack (rtx[], bool, bool);
-extern void ix86_expand_sse5_pack (rtx[]);
 extern int ix86_expand_int_addcc (rtx[]);
 extern void ix86_expand_call (rtx, rtx, rtx, rtx, rtx, int);
 extern void x86_initialize_trampoline (rtx, rtx, rtx);
@@ -217,9 +214,6 @@ extern void ix86_expand_vector_set (bool, rtx, rtx, int);
 extern void ix86_expand_vector_extract (bool, rtx, rtx, int);
 extern void ix86_expand_reduc_v4sf (rtx (*)(rtx, rtx, rtx), rtx, rtx);
 
-extern bool ix86_sse5_valid_op_p (rtx [], rtx, int, bool, int, bool);
-extern void ix86_expand_sse5_multiple_memory (rtx [], int, enum machine_mode);
-
 /* In i386-c.c  */
 extern void ix86_target_macros (void);
 extern void ix86_register_pragmas (void);
diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index 042ff4419f6..3a12c27a2ea 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -1954,8 +1954,6 @@ static int ix86_isa_flags_explicit;
 
 #define OPTION_MASK_ISA_SSE4A_SET \
   (OPTION_MASK_ISA_SSE4A | OPTION_MASK_ISA_SSE3_SET)
-#define OPTION_MASK_ISA_SSE5_SET \
-  (OPTION_MASK_ISA_SSE5 | OPTION_MASK_ISA_SSE4A_SET)
 
 /* AES and PCLMUL need SSE2 because they use xmm registers */
 #define OPTION_MASK_ISA_AES_SET \
@@ -2004,8 +2002,7 @@ static int ix86_isa_flags_explicit;
 #define OPTION_MASK_ISA_SSE4_UNSET OPTION_MASK_ISA_SSE4_1_UNSET
 
 #define OPTION_MASK_ISA_SSE4A_UNSET \
-  (OPTION_MASK_ISA_SSE4A | OPTION_MASK_ISA_SSE5_UNSET)
-#define OPTION_MASK_ISA_SSE5_UNSET OPTION_MASK_ISA_SSE5
+  (OPTION_MASK_ISA_SSE4A)
 #define OPTION_MASK_ISA_AES_UNSET OPTION_MASK_ISA_AES
 #define OPTION_MASK_ISA_PCLMUL_UNSET OPTION_MASK_ISA_PCLMUL
 #define OPTION_MASK_ISA_ABM_UNSET OPTION_MASK_ISA_ABM
@@ -2239,19 +2236,6 @@ ix86_handle_option (size_t code, const char *arg ATTRIBUTE_UNUSED, int value)
 	}
       return true;
 
-    case OPT_msse5:
-      if (value)
-	{
-	  ix86_isa_flags |= OPTION_MASK_ISA_SSE5_SET;
-	  ix86_isa_flags_explicit |= OPTION_MASK_ISA_SSE5_SET;
-	}
-      else
-	{
-	  ix86_isa_flags &= ~OPTION_MASK_ISA_SSE5_UNSET;
-	  ix86_isa_flags_explicit |= OPTION_MASK_ISA_SSE5_UNSET;
-	}
-      return true;
-
     case OPT_mabm:
       if (value)
 	{
@@ -2374,12 +2358,11 @@ ix86_target_string (int isa, int flags, const char *arch, const char *tune,
     int mask;			/* isa mask options */
   };
 
-  /* This table is ordered so that options like -msse5 or -msse4.2 that imply
+  /* This table is ordered so that options like -msse4.2 that imply
      preceding options while match those first.  */
   static struct ix86_target_opts isa_opts[] =
   {
     { "-m64",		OPTION_MASK_ISA_64BIT },
-    { "-msse5",		OPTION_MASK_ISA_SSE5 },
     { "-msse4a",	OPTION_MASK_ISA_SSE4A },
     { "-msse4.2",	OPTION_MASK_ISA_SSE4_2 },
     { "-msse4.1",	OPTION_MASK_ISA_SSE4_1 },
@@ -2413,7 +2396,6 @@ ix86_target_string (int isa, int flags, const char *arch, const char *tune,
     { "-mms-bitfields",			MASK_MS_BITFIELD_LAYOUT },
     { "-mno-align-stringops",		MASK_NO_ALIGN_STRINGOPS },
     { "-mno-fancy-math-387",		MASK_NO_FANCY_MATH_387 },
-    { "-mno-fused-madd",		MASK_NO_FUSED_MADD },
     { "-mno-push-args",			MASK_NO_PUSH_ARGS },
     { "-mno-red-zone",			MASK_NO_RED_ZONE },
     { "-momit-leaf-frame-pointer",	MASK_OMIT_LEAF_FRAME_POINTER },
@@ -2606,12 +2588,11 @@ override_options (bool main_args_p)
       PTA_NO_SAHF = 1 << 13,
       PTA_SSE4_1 = 1 << 14,
       PTA_SSE4_2 = 1 << 15,
-      PTA_SSE5 = 1 << 16,
-      PTA_AES = 1 << 17,
-      PTA_PCLMUL = 1 << 18,
-      PTA_AVX = 1 << 19,
-      PTA_FMA = 1 << 20,
-      PTA_MOVBE = 1 << 21
+      PTA_AES = 1 << 16,
+      PTA_PCLMUL = 1 << 17,
+      PTA_AVX = 1 << 18,
+      PTA_FMA = 1 << 19,
+      PTA_MOVBE = 1 << 20
     };
 
   static struct pta
@@ -2954,9 +2935,6 @@ override_options (bool main_args_p)
 	if (processor_alias_table[i].flags & PTA_SSE4A
 	    && !(ix86_isa_flags_explicit & OPTION_MASK_ISA_SSE4A))
 	  ix86_isa_flags |= OPTION_MASK_ISA_SSE4A;
-	if (processor_alias_table[i].flags & PTA_SSE5
-	    && !(ix86_isa_flags_explicit & OPTION_MASK_ISA_SSE5))
-	  ix86_isa_flags |= OPTION_MASK_ISA_SSE5;
 	if (processor_alias_table[i].flags & PTA_ABM
 	    && !(ix86_isa_flags_explicit & OPTION_MASK_ISA_ABM))
 	  ix86_isa_flags |= OPTION_MASK_ISA_ABM;
@@ -3639,7 +3617,6 @@ ix86_valid_target_attribute_inner_p (tree args, char *p_strings[])
     IX86_ATTR_ISA ("sse4.1",	OPT_msse4_1),
     IX86_ATTR_ISA ("sse4.2",	OPT_msse4_2),
     IX86_ATTR_ISA ("sse4a",	OPT_msse4a),
-    IX86_ATTR_ISA ("sse5",	OPT_msse5),
     IX86_ATTR_ISA ("ssse3",	OPT_mssse3),
 
     /* string options */
@@ -3656,10 +3633,6 @@ ix86_valid_target_attribute_inner_p (tree args, char *p_strings[])
 		  OPT_mfancy_math_387,
 		  MASK_NO_FANCY_MATH_387),
 
-    IX86_ATTR_NO ("fused-madd",
-		  OPT_mfused_madd,
-		  MASK_NO_FUSED_MADD),
-
     IX86_ATTR_YES ("ieee-fp",
 		   OPT_mieee_fp,
 		   MASK_IEEE_FP),
@@ -3932,8 +3905,8 @@ ix86_can_inline_p (tree caller, tree callee)
       struct cl_target_option *caller_opts = TREE_TARGET_OPTION (caller_tree);
       struct cl_target_option *callee_opts = TREE_TARGET_OPTION (callee_tree);
 
-      /* Callee's isa options should a subset of the caller's, i.e. a SSE5 function
-	 can inline a SSE2 function but a SSE2 function can't inline a SSE5
+      /* Callee's isa options should a subset of the caller's, i.e. a SSE4 function
+	 can inline a SSE2 function but a SSE2 function can't inline a SSE4
 	 function.  */
       if ((caller_opts->ix86_isa_flags & callee_opts->ix86_isa_flags)
 	  != callee_opts->ix86_isa_flags)
@@ -7357,28 +7330,8 @@ standard_80387_constant_rtx (int idx)
 				       XFmode);
 }
 
-/* Return 1 if mode is a valid mode for sse.  */
-static int
-standard_sse_mode_p (enum machine_mode mode)
-{
-  switch (mode)
-    {
-    case V16QImode:
-    case V8HImode:
-    case V4SImode:
-    case V2DImode:
-    case V4SFmode:
-    case V2DFmode:
-      return 1;
-
-    default:
-      return 0;
-    }
-}
-
-/* Return 1 if X is all 0s.  For all 1s, return 2 if X is in 128bit
-   SSE modes and SSE2 is enabled,  return 3 if X is in 256bit AVX
-   modes and AVX is enabled.  */
+/* Return 1 if X is all 0s and 2 if x is all 1s
+   in supported SSE vector mode.  */
 
 int
 standard_sse_constant_p (rtx x)
@@ -7388,12 +7341,17 @@ standard_sse_constant_p (rtx x)
   if (x == const0_rtx || x == CONST0_RTX (GET_MODE (x)))
     return 1;
   if (vector_all_ones_operand (x, mode))
-    {
-      if (standard_sse_mode_p (mode))
-	return TARGET_SSE2 ? 2 : -2;
-      else if (VALID_AVX256_REG_MODE (mode))
-	return TARGET_AVX ? 3 : -3;
-    }
+    switch (mode)
+      {
+      case V16QImode:
+      case V8HImode:
+      case V4SImode:
+      case V2DImode:
+	if (TARGET_SSE2)
+	  return 2;
+      default:
+	break;
+      }
 
   return 0;
 }
@@ -7422,22 +7380,12 @@ standard_sse_constant_opcode (rtx insn, rtx x)
 	case MODE_OI:
 	  return "vpxor\t%x0, %x0, %x0";
 	default:
-	  gcc_unreachable ();
+	  break;
 	}
     case 2:
-      if (TARGET_AVX)
-	switch (get_attr_mode (insn))
-	  {
-	  case MODE_V4SF:
-	  case MODE_V2DF:
-	  case MODE_TI:
-	    return "vpcmpeqd\t%0, %0, %0";
-	    break;
-	  default:
-	    gcc_unreachable ();
-	}
-      else
-	return "pcmpeqd\t%0, %0";
+      return TARGET_AVX ? "vpcmpeqd\t%0, %0, %0" : "pcmpeqd\t%0, %0";
+    default:
+      break;
     }
   gcc_unreachable ();
 }
@@ -7819,8 +7767,8 @@ ix86_nsaved_sseregs (void)
    pointer.  Otherwise, frame pointer elimination is automatically
    handled and all other eliminations are valid.  */
 
-int
-ix86_can_eliminate (int from, int to)
+static bool
+ix86_can_eliminate (const int from, const int to)
 {
   if (stack_realign_fp)
     return ((from == ARG_POINTER_REGNUM
@@ -7828,7 +7776,7 @@ ix86_can_eliminate (int from, int to)
 	    || (from == FRAME_POINTER_REGNUM
 		&& to == STACK_POINTER_REGNUM));
   else
-    return to == STACK_POINTER_REGNUM ? !frame_pointer_needed : 1;
+    return to == STACK_POINTER_REGNUM ? !frame_pointer_needed : true;
 }
 
 /* Return the offset between two registers, one to be eliminated, and the other
@@ -11254,7 +11202,6 @@ get_some_local_dynamic_name (void)
    X -- don't print any sort of PIC '@' suffix for a symbol.
    & -- print some in-use local-dynamic symbol name.
    H -- print a memory address offset by 8; used for sse high-parts
-   Y -- print condition for SSE5 com* instruction.
    + -- print a branch hint as 'cs' or 'ds' prefix
    ; -- print a semicolon (after prefixes due to bug in older gas).
  */
@@ -11672,61 +11619,6 @@ print_operand (FILE *file, rtx x, int code)
 	    return;
 	  }
 
-	case 'Y':
-	  switch (GET_CODE (x))
-	    {
-	    case NE:
-	      fputs ("neq", file);
-	      break;
-	    case EQ:
-	      fputs ("eq", file);
-	      break;
-	    case GE:
-	    case GEU:
-	      fputs (INTEGRAL_MODE_P (GET_MODE (x)) ? "ge" : "unlt", file);
-	      break;
-	    case GT:
-	    case GTU:
-	      fputs (INTEGRAL_MODE_P (GET_MODE (x)) ? "gt" : "unle", file);
-	      break;
-	    case LE:
-	    case LEU:
-	      fputs ("le", file);
-	      break;
-	    case LT:
-	    case LTU:
-	      fputs ("lt", file);
-	      break;
-	    case UNORDERED:
-	      fputs ("unord", file);
-	      break;
-	    case ORDERED:
-	      fputs ("ord", file);
-	      break;
-	    case UNEQ:
-	      fputs ("ueq", file);
-	      break;
-	    case UNGE:
-	      fputs ("nlt", file);
-	      break;
-	    case UNGT:
-	      fputs ("nle", file);
-	      break;
-	    case UNLE:
-	      fputs ("ule", file);
-	      break;
-	    case UNLT:
-	      fputs ("ult", file);
-	      break;
-	    case LTGT:
-	      fputs ("une", file);
-	      break;
-	    default:
-	      output_operand_lossage ("operand is not a condition code, invalid operand code 'D'");
-	      return;
-	    }
-	  return;
-
 	case ';':
 #if TARGET_MACHO
 	  fputs (" ; ", file);
@@ -12908,7 +12800,7 @@ ix86_expand_vector_move (enum machine_mode mode, rtx operands[])
       && (CONSTANT_P (op1)
 	  || (GET_CODE (op1) == SUBREG
 	      && CONSTANT_P (SUBREG_REG (op1))))
-      && standard_sse_constant_p (op1) <= 0)
+      && !standard_sse_constant_p (op1))
     op1 = validize_mem (force_const_mem (mode, op1));
 
   /* We need to check memory alignment for SSE mode since attribute
@@ -14619,7 +14511,7 @@ ix86_fp_comparison_strategy (enum rtx_code code ATTRIBUTE_UNUSED)
   if (TARGET_CMOVE)
     return IX86_FPCMP_COMI;
 
-  if (TARGET_SAHF && (TARGET_USE_SAHF || optimize_insn_for_size_p ()))
+  if (TARGET_SAHF && (TARGET_USE_SAHF || optimize_function_for_size_p (cfun)))
     return IX86_FPCMP_SAHF;
 
   return IX86_FPCMP_ARITH;
@@ -14814,13 +14706,13 @@ ix86_expand_fp_compare (enum rtx_code code, rtx op0, rtx op1, rtx scratch)
 	  if (code == LT && TARGET_IEEE_FP)
 	    {
 	      emit_insn (gen_andqi_ext_0 (scratch, scratch, GEN_INT (0x45)));
-	      emit_insn (gen_cmpqi_ext_3 (scratch, GEN_INT (0x01)));
+	      emit_insn (gen_cmpqi_ext_3 (scratch, const1_rtx));
 	      intcmp_mode = CCmode;
 	      code = EQ;
 	    }
 	  else
 	    {
-	      emit_insn (gen_testqi_ext_ccno_0 (scratch, GEN_INT (0x01)));
+	      emit_insn (gen_testqi_ext_ccno_0 (scratch, const1_rtx));
 	      code = NE;
 	    }
 	  break;
@@ -14834,8 +14726,7 @@ ix86_expand_fp_compare (enum rtx_code code, rtx op0, rtx op1, rtx scratch)
 	  else
 	    {
 	      emit_insn (gen_andqi_ext_0 (scratch, scratch, GEN_INT (0x45)));
-	      emit_insn (gen_xorqi_cc_ext_1 (scratch, scratch,
-					     GEN_INT (0x01)));
+	      emit_insn (gen_xorqi_cc_ext_1 (scratch, scratch, const1_rtx));
 	      code = NE;
 	    }
 	  break;
@@ -14868,7 +14759,6 @@ ix86_expand_fp_compare (enum rtx_code code, rtx op0, rtx op1, rtx scratch)
 	    {
 	      emit_insn (gen_testqi_ext_ccno_0 (scratch, GEN_INT (0x40)));
 	      code = NE;
-	      break;
 	    }
 	  break;
 	case NE:
@@ -15938,14 +15828,6 @@ ix86_expand_sse_movcc (rtx dest, rtx cmp, rtx op_true, rtx op_false)
       x = gen_rtx_AND (mode, x, op_false);
       emit_insn (gen_rtx_SET (VOIDmode, dest, x));
     }
-  else if (TARGET_SSE5)
-    {
-      rtx pcmov = gen_rtx_SET (mode, dest,
-			       gen_rtx_IF_THEN_ELSE (mode, cmp,
-						     op_true,
-						     op_false));
-      emit_insn (pcmov);
-    }
   else
     {
       op_true = force_reg (mode, op_true);
@@ -16068,119 +15950,115 @@ ix86_expand_int_vcond (rtx operands[])
   cop0 = operands[4];
   cop1 = operands[5];
 
-  /* SSE5 supports all of the comparisons on all vector int types.  */
-  if (!TARGET_SSE5)
+  /* Canonicalize the comparison to EQ, GT, GTU.  */
+  switch (code)
+    {
+    case EQ:
+    case GT:
+    case GTU:
+      break;
+
+    case NE:
+    case LE:
+    case LEU:
+      code = reverse_condition (code);
+      negate = true;
+      break;
+
+    case GE:
+    case GEU:
+      code = reverse_condition (code);
+      negate = true;
+      /* FALLTHRU */
+
+    case LT:
+    case LTU:
+      code = swap_condition (code);
+      x = cop0, cop0 = cop1, cop1 = x;
+      break;
+
+    default:
+      gcc_unreachable ();
+    }
+
+  /* Only SSE4.1/SSE4.2 supports V2DImode.  */
+  if (mode == V2DImode)
     {
-      /* Canonicalize the comparison to EQ, GT, GTU.  */
       switch (code)
 	{
 	case EQ:
-	case GT:
-	case GTU:
-	  break;
-
-	case NE:
-	case LE:
-	case LEU:
-	  code = reverse_condition (code);
-	  negate = true;
+	  /* SSE4.1 supports EQ.  */
+	  if (!TARGET_SSE4_1)
+	    return false;
 	  break;
 
-	case GE:
-	case GEU:
-	  code = reverse_condition (code);
-	  negate = true;
-	  /* FALLTHRU */
-
-	case LT:
-	case LTU:
-	  code = swap_condition (code);
-	  x = cop0, cop0 = cop1, cop1 = x;
+	case GT:
+	case GTU:
+	  /* SSE4.2 supports GT/GTU.  */
+	  if (!TARGET_SSE4_2)
+	    return false;
 	  break;
 
 	default:
 	  gcc_unreachable ();
 	}
+    }
 
-      /* Only SSE4.1/SSE4.2 supports V2DImode.  */
-      if (mode == V2DImode)
-	{
-	  switch (code)
-	    {
-	    case EQ:
-	      /* SSE4.1 supports EQ.  */
-	      if (!TARGET_SSE4_1)
-		return false;
-	      break;
-
-	    case GT:
-	    case GTU:
-	      /* SSE4.2 supports GT/GTU.  */
-	      if (!TARGET_SSE4_2)
-		return false;
-	      break;
-
-	    default:
-	      gcc_unreachable ();
-	    }
-	}
+  /* Unsigned parallel compare is not supported by the hardware.  Play some
+     tricks to turn this into a signed comparison against 0.  */
+  if (code == GTU)
+    {
+      cop0 = force_reg (mode, cop0);
 
-      /* Unsigned parallel compare is not supported by the hardware.  Play some
-	 tricks to turn this into a signed comparison against 0.  */
-      if (code == GTU)
+      switch (mode)
 	{
-	  cop0 = force_reg (mode, cop0);
-
-	  switch (mode)
-	    {
-	    case V4SImode:
-	    case V2DImode:
-	      {
-		rtx t1, t2, mask;
-
-		/* Perform a parallel modulo subtraction.  */
-		t1 = gen_reg_rtx (mode);
-		emit_insn ((mode == V4SImode
-			    ? gen_subv4si3
-			    : gen_subv2di3) (t1, cop0, cop1));
-
-		/* Extract the original sign bit of op0.  */
-		mask = ix86_build_signbit_mask (GET_MODE_INNER (mode),
-						true, false);
-		t2 = gen_reg_rtx (mode);
-		emit_insn ((mode == V4SImode
-			    ? gen_andv4si3
-			    : gen_andv2di3) (t2, cop0, mask));
-
-		/* XOR it back into the result of the subtraction.  This results
-		   in the sign bit set iff we saw unsigned underflow.  */
-		x = gen_reg_rtx (mode);
-		emit_insn ((mode == V4SImode
-			    ? gen_xorv4si3
-			    : gen_xorv2di3) (x, t1, t2));
-
-		code = GT;
-	      }
-	      break;
-
-	    case V16QImode:
-	    case V8HImode:
-	      /* Perform a parallel unsigned saturating subtraction.  */
-	      x = gen_reg_rtx (mode);
-	      emit_insn (gen_rtx_SET (VOIDmode, x,
-				      gen_rtx_US_MINUS (mode, cop0, cop1)));
+	case V4SImode:
+	case V2DImode:
+	  {
+	    rtx t1, t2, mask;
+
+	    /* Perform a parallel modulo subtraction.  */
+	    t1 = gen_reg_rtx (mode);
+	    emit_insn ((mode == V4SImode
+			? gen_subv4si3
+			: gen_subv2di3) (t1, cop0, cop1));
+
+	    /* Extract the original sign bit of op0.  */
+	    mask = ix86_build_signbit_mask (GET_MODE_INNER (mode),
+					    true, false);
+	    t2 = gen_reg_rtx (mode);
+	    emit_insn ((mode == V4SImode
+			? gen_andv4si3
+			: gen_andv2di3) (t2, cop0, mask));
+
+	    /* XOR it back into the result of the subtraction.  This results
+	       in the sign bit set iff we saw unsigned underflow.  */
+	    x = gen_reg_rtx (mode);
+	    emit_insn ((mode == V4SImode
+			? gen_xorv4si3
+			: gen_xorv2di3) (x, t1, t2));
+
+	    code = GT;
+	  }
+	  break;
 
-	      code = EQ;
-	      negate = !negate;
-	      break;
+	case V16QImode:
+	case V8HImode:
+	  /* Perform a parallel unsigned saturating subtraction.  */
+	  x = gen_reg_rtx (mode);
+	  emit_insn (gen_rtx_SET (VOIDmode, x,
+				  gen_rtx_US_MINUS (mode, cop0, cop1)));
 
-	    default:
-	      gcc_unreachable ();
-	    }
+	  code = EQ;
+	  negate = !negate;
+	  break;
 
-	  cop0 = x;
-	  cop1 = CONST0_RTX (mode);
+	default:
+	  gcc_unreachable ();
 	}
+
+      cop0 = x;
+      cop1 = CONST0_RTX (mode);
     }
 
   x = ix86_expand_sse_cmp (operands[0], code, cop0, cop1,
@@ -16286,190 +16164,6 @@ ix86_expand_sse4_unpack (rtx operands[2], bool unsigned_p, bool high_p)
   emit_insn (unpack (dest, src));
 }
 
-/* This function performs the same task as ix86_expand_sse_unpack,
-   but with sse5 instructions.  */
-
-void
-ix86_expand_sse5_unpack (rtx operands[2], bool unsigned_p, bool high_p)
-{
-  enum machine_mode imode = GET_MODE (operands[1]);
-  int pperm_bytes[16];
-  int i;
-  int h = (high_p) ? 8 : 0;
-  int h2;
-  int sign_extend;
-  rtvec v = rtvec_alloc (16);
-  rtvec vs;
-  rtx x, p;
-  rtx op0 = operands[0], op1 = operands[1];
-
-  switch (imode)
-    {
-    case V16QImode:
-      vs = rtvec_alloc (8);
-      h2 = (high_p) ? 8 : 0;
-      for (i = 0; i < 8; i++)
-	{
-	  pperm_bytes[2*i+0] = PPERM_SRC | PPERM_SRC2 | i | h;
-	  pperm_bytes[2*i+1] = ((unsigned_p)
-				? PPERM_ZERO
-				: PPERM_SIGN | PPERM_SRC2 | i | h);
-	}
-
-      for (i = 0; i < 16; i++)
-	RTVEC_ELT (v, i) = GEN_INT (pperm_bytes[i]);
-
-      for (i = 0; i < 8; i++)
-	RTVEC_ELT (vs, i) = GEN_INT (i + h2);
-
-      p = gen_rtx_PARALLEL (VOIDmode, vs);
-      x = force_reg (V16QImode, gen_rtx_CONST_VECTOR (V16QImode, v));
-      if (unsigned_p)
-	emit_insn (gen_sse5_pperm_zero_v16qi_v8hi (op0, op1, p, x));
-      else
-	emit_insn (gen_sse5_pperm_sign_v16qi_v8hi (op0, op1, p, x));
-      break;
-
-    case V8HImode:
-      vs = rtvec_alloc (4);
-      h2 = (high_p) ? 4 : 0;
-      for (i = 0; i < 4; i++)
-	{
-	  sign_extend = ((unsigned_p)
-			 ? PPERM_ZERO
-			 : PPERM_SIGN | PPERM_SRC2 | ((2*i) + 1 + h));
-	  pperm_bytes[4*i+0] = PPERM_SRC | PPERM_SRC2 | ((2*i) + 0 + h);
-	  pperm_bytes[4*i+1] = PPERM_SRC | PPERM_SRC2 | ((2*i) + 1 + h);
-	  pperm_bytes[4*i+2] = sign_extend;
-	  pperm_bytes[4*i+3] = sign_extend;
-	}
-
-      for (i = 0; i < 16; i++)
-	RTVEC_ELT (v, i) = GEN_INT (pperm_bytes[i]);
-
-      for (i = 0; i < 4; i++)
-	RTVEC_ELT (vs, i) = GEN_INT (i + h2);
-
-      p = gen_rtx_PARALLEL (VOIDmode, vs);
-      x = force_reg (V16QImode, gen_rtx_CONST_VECTOR (V16QImode, v));
-      if (unsigned_p)
-	emit_insn (gen_sse5_pperm_zero_v8hi_v4si (op0, op1, p, x));
-      else
-	emit_insn (gen_sse5_pperm_sign_v8hi_v4si (op0, op1, p, x));
-      break;
-
-    case V4SImode:
-      vs = rtvec_alloc (2);
-      h2 = (high_p) ? 2 : 0;
-      for (i = 0; i < 2; i++)
-	{
-	  sign_extend = ((unsigned_p)
-			 ? PPERM_ZERO
-			 : PPERM_SIGN | PPERM_SRC2 | ((4*i) + 3 + h));
-	  pperm_bytes[8*i+0] = PPERM_SRC | PPERM_SRC2 | ((4*i) + 0 + h);
-	  pperm_bytes[8*i+1] = PPERM_SRC | PPERM_SRC2 | ((4*i) + 1 + h);
-	  pperm_bytes[8*i+2] = PPERM_SRC | PPERM_SRC2 | ((4*i) + 2 + h);
-	  pperm_bytes[8*i+3] = PPERM_SRC | PPERM_SRC2 | ((4*i) + 3 + h);
-	  pperm_bytes[8*i+4] = sign_extend;
-	  pperm_bytes[8*i+5] = sign_extend;
-	  pperm_bytes[8*i+6] = sign_extend;
-	  pperm_bytes[8*i+7] = sign_extend;
-	}
-
-      for (i = 0; i < 16; i++)
-	RTVEC_ELT (v, i) = GEN_INT (pperm_bytes[i]);
-
-      for (i = 0; i < 2; i++)
-	RTVEC_ELT (vs, i) = GEN_INT (i + h2);
-
-      p = gen_rtx_PARALLEL (VOIDmode, vs);
-      x = force_reg (V16QImode, gen_rtx_CONST_VECTOR (V16QImode, v));
-      if (unsigned_p)
-	emit_insn (gen_sse5_pperm_zero_v4si_v2di (op0, op1, p, x));
-      else
-	emit_insn (gen_sse5_pperm_sign_v4si_v2di (op0, op1, p, x));
-      break;
-
-    default:
-      gcc_unreachable ();
-    }
-
-  return;
-}
-
-/* Pack the high bits from OPERANDS[1] and low bits from OPERANDS[2] into the
-   next narrower integer vector type */
-void
-ix86_expand_sse5_pack (rtx operands[3])
-{
-  enum machine_mode imode = GET_MODE (operands[0]);
-  int pperm_bytes[16];
-  int i;
-  rtvec v = rtvec_alloc (16);
-  rtx x;
-  rtx op0 = operands[0];
-  rtx op1 = operands[1];
-  rtx op2 = operands[2];
-
-  switch (imode)
-    {
-    case V16QImode:
-      for (i = 0; i < 8; i++)
-	{
-	  pperm_bytes[i+0] = PPERM_SRC | PPERM_SRC1 | (i*2);
-	  pperm_bytes[i+8] = PPERM_SRC | PPERM_SRC2 | (i*2);
-	}
-
-      for (i = 0; i < 16; i++)
-	RTVEC_ELT (v, i) = GEN_INT (pperm_bytes[i]);
-
-      x = force_reg (V16QImode, gen_rtx_CONST_VECTOR (V16QImode, v));
-      emit_insn (gen_sse5_pperm_pack_v8hi_v16qi (op0, op1, op2, x));
-      break;
-
-    case V8HImode:
-      for (i = 0; i < 4; i++)
-	{
-	  pperm_bytes[(2*i)+0] = PPERM_SRC | PPERM_SRC1 | ((i*4) + 0);
-	  pperm_bytes[(2*i)+1] = PPERM_SRC | PPERM_SRC1 | ((i*4) + 1);
-	  pperm_bytes[(2*i)+8] = PPERM_SRC | PPERM_SRC2 | ((i*4) + 0);
-	  pperm_bytes[(2*i)+9] = PPERM_SRC | PPERM_SRC2 | ((i*4) + 1);
-	}
-
-      for (i = 0; i < 16; i++)
-	RTVEC_ELT (v, i) = GEN_INT (pperm_bytes[i]);
-
-      x = force_reg (V16QImode, gen_rtx_CONST_VECTOR (V16QImode, v));
-      emit_insn (gen_sse5_pperm_pack_v4si_v8hi (op0, op1, op2, x));
-      break;
-
-    case V4SImode:
-      for (i = 0; i < 2; i++)
-	{
-	  pperm_bytes[(4*i)+0]  = PPERM_SRC | PPERM_SRC1 | ((i*8) + 0);
-	  pperm_bytes[(4*i)+1]  = PPERM_SRC | PPERM_SRC1 | ((i*8) + 1);
-	  pperm_bytes[(4*i)+2]  = PPERM_SRC | PPERM_SRC1 | ((i*8) + 2);
-	  pperm_bytes[(4*i)+3]  = PPERM_SRC | PPERM_SRC1 | ((i*8) + 3);
-	  pperm_bytes[(4*i)+8]  = PPERM_SRC | PPERM_SRC2 | ((i*8) + 0);
-	  pperm_bytes[(4*i)+9]  = PPERM_SRC | PPERM_SRC2 | ((i*8) + 1);
-	  pperm_bytes[(4*i)+10] = PPERM_SRC | PPERM_SRC2 | ((i*8) + 2);
-	  pperm_bytes[(4*i)+11] = PPERM_SRC | PPERM_SRC2 | ((i*8) + 3);
-	}
-
-      for (i = 0; i < 16; i++)
-	RTVEC_ELT (v, i) = GEN_INT (pperm_bytes[i]);
-
-      x = force_reg (V16QImode, gen_rtx_CONST_VECTOR (V16QImode, v));
-      emit_insn (gen_sse5_pperm_pack_v2di_v4si (op0, op1, op2, x));
-      break;
-
-    default:
-      gcc_unreachable ();
-    }
-
-  return;
-}
-
 /* Expand conditional increment or decrement using adb/sbb instructions.
    The default case using setcc followed by the conditional move can be
    done by generic code.  */
@@ -16766,10 +16460,20 @@ ix86_split_long_move (rtx operands[])
   /* When emitting push, take care for source operands on the stack.  */
   if (push && MEM_P (operands[1])
       && reg_overlap_mentioned_p (stack_pointer_rtx, operands[1]))
-    for (i = 0; i < nparts - 1; i++)
-      part[1][i] = change_address (part[1][i],
-				   GET_MODE (part[1][i]),
-				   XEXP (part[1][i + 1], 0));
+    {
+      rtx src_base = XEXP (part[1][nparts - 1], 0);
+
+      /* Compensate for the stack decrement by 4.  */
+      if (!TARGET_64BIT && nparts == 3
+	  && mode == XFmode && TARGET_128BIT_LONG_DOUBLE)
+	src_base = plus_constant (src_base, 4);
+
+      /* src_base refers to the stack pointer and is
+	 automatically decreased by emitted push.  */
+      for (i = 0; i < nparts; i++)
+	part[1][i] = change_address (part[1][i],
+				     GET_MODE (part[1][i]), src_base);
+    }
 
   /* We need to do copy in the right order in case an address register
      of the source overlaps the destination.  */
@@ -16839,7 +16543,8 @@ ix86_split_long_move (rtx operands[])
 	  if (nparts == 3)
 	    {
 	      if (TARGET_128BIT_LONG_DOUBLE && mode == XFmode)
-                emit_insn (gen_addsi3 (stack_pointer_rtx, stack_pointer_rtx, GEN_INT (-4)));
+                emit_insn (gen_addsi3 (stack_pointer_rtx,
+				       stack_pointer_rtx, GEN_INT (-4)));
 	      emit_move_insn (part[0][2], part[1][2]);
 	    }
 	  else if (nparts == 4)
@@ -17028,14 +16733,15 @@ ix86_split_ashl (rtx *operands, rtx scratch, enum machine_mode mode)
 
 	  emit_insn ((mode == DImode
 		      ? gen_lshrsi3
-		      : gen_lshrdi3) (high[0], high[0], GEN_INT (mode == DImode ? 5 : 6)));
+		      : gen_lshrdi3) (high[0], high[0],
+				      GEN_INT (mode == DImode ? 5 : 6)));
 	  emit_insn ((mode == DImode
 		      ? gen_andsi3
-		      : gen_anddi3) (high[0], high[0], GEN_INT (1)));
+		      : gen_anddi3) (high[0], high[0], const1_rtx));
 	  emit_move_insn (low[0], high[0]);
 	  emit_insn ((mode == DImode
 		      ? gen_xorsi3
-		      : gen_xordi3) (low[0], low[0], GEN_INT (1)));
+		      : gen_xordi3) (low[0], low[0], const1_rtx));
 	}
 
       emit_insn ((mode == DImode
@@ -20912,217 +20618,6 @@ enum ix86_builtins
 
   IX86_BUILTIN_CVTUDQ2PS,
 
-  /* SSE5 instructions */
-  IX86_BUILTIN_FMADDSS,
-  IX86_BUILTIN_FMADDSD,
-  IX86_BUILTIN_FMADDPS,
-  IX86_BUILTIN_FMADDPD,
-  IX86_BUILTIN_FMSUBSS,
-  IX86_BUILTIN_FMSUBSD,
-  IX86_BUILTIN_FMSUBPS,
-  IX86_BUILTIN_FMSUBPD,
-  IX86_BUILTIN_FNMADDSS,
-  IX86_BUILTIN_FNMADDSD,
-  IX86_BUILTIN_FNMADDPS,
-  IX86_BUILTIN_FNMADDPD,
-  IX86_BUILTIN_FNMSUBSS,
-  IX86_BUILTIN_FNMSUBSD,
-  IX86_BUILTIN_FNMSUBPS,
-  IX86_BUILTIN_FNMSUBPD,
-  IX86_BUILTIN_PCMOV,
-  IX86_BUILTIN_PCMOV_V2DI,
-  IX86_BUILTIN_PCMOV_V4SI,
-  IX86_BUILTIN_PCMOV_V8HI,
-  IX86_BUILTIN_PCMOV_V16QI,
-  IX86_BUILTIN_PCMOV_V4SF,
-  IX86_BUILTIN_PCMOV_V2DF,
-  IX86_BUILTIN_PPERM,
-  IX86_BUILTIN_PERMPS,
-  IX86_BUILTIN_PERMPD,
-  IX86_BUILTIN_PMACSSWW,
-  IX86_BUILTIN_PMACSWW,
-  IX86_BUILTIN_PMACSSWD,
-  IX86_BUILTIN_PMACSWD,
-  IX86_BUILTIN_PMACSSDD,
-  IX86_BUILTIN_PMACSDD,
-  IX86_BUILTIN_PMACSSDQL,
-  IX86_BUILTIN_PMACSSDQH,
-  IX86_BUILTIN_PMACSDQL,
-  IX86_BUILTIN_PMACSDQH,
-  IX86_BUILTIN_PMADCSSWD,
-  IX86_BUILTIN_PMADCSWD,
-  IX86_BUILTIN_PHADDBW,
-  IX86_BUILTIN_PHADDBD,
-  IX86_BUILTIN_PHADDBQ,
-  IX86_BUILTIN_PHADDWD,
-  IX86_BUILTIN_PHADDWQ,
-  IX86_BUILTIN_PHADDDQ,
-  IX86_BUILTIN_PHADDUBW,
-  IX86_BUILTIN_PHADDUBD,
-  IX86_BUILTIN_PHADDUBQ,
-  IX86_BUILTIN_PHADDUWD,
-  IX86_BUILTIN_PHADDUWQ,
-  IX86_BUILTIN_PHADDUDQ,
-  IX86_BUILTIN_PHSUBBW,
-  IX86_BUILTIN_PHSUBWD,
-  IX86_BUILTIN_PHSUBDQ,
-  IX86_BUILTIN_PROTB,
-  IX86_BUILTIN_PROTW,
-  IX86_BUILTIN_PROTD,
-  IX86_BUILTIN_PROTQ,
-  IX86_BUILTIN_PROTB_IMM,
-  IX86_BUILTIN_PROTW_IMM,
-  IX86_BUILTIN_PROTD_IMM,
-  IX86_BUILTIN_PROTQ_IMM,
-  IX86_BUILTIN_PSHLB,
-  IX86_BUILTIN_PSHLW,
-  IX86_BUILTIN_PSHLD,
-  IX86_BUILTIN_PSHLQ,
-  IX86_BUILTIN_PSHAB,
-  IX86_BUILTIN_PSHAW,
-  IX86_BUILTIN_PSHAD,
-  IX86_BUILTIN_PSHAQ,
-  IX86_BUILTIN_FRCZSS,
-  IX86_BUILTIN_FRCZSD,
-  IX86_BUILTIN_FRCZPS,
-  IX86_BUILTIN_FRCZPD,
-  IX86_BUILTIN_CVTPH2PS,
-  IX86_BUILTIN_CVTPS2PH,
-
-  IX86_BUILTIN_COMEQSS,
-  IX86_BUILTIN_COMNESS,
-  IX86_BUILTIN_COMLTSS,
-  IX86_BUILTIN_COMLESS,
-  IX86_BUILTIN_COMGTSS,
-  IX86_BUILTIN_COMGESS,
-  IX86_BUILTIN_COMUEQSS,
-  IX86_BUILTIN_COMUNESS,
-  IX86_BUILTIN_COMULTSS,
-  IX86_BUILTIN_COMULESS,
-  IX86_BUILTIN_COMUGTSS,
-  IX86_BUILTIN_COMUGESS,
-  IX86_BUILTIN_COMORDSS,
-  IX86_BUILTIN_COMUNORDSS,
-  IX86_BUILTIN_COMFALSESS,
-  IX86_BUILTIN_COMTRUESS,
-
-  IX86_BUILTIN_COMEQSD,
-  IX86_BUILTIN_COMNESD,
-  IX86_BUILTIN_COMLTSD,
-  IX86_BUILTIN_COMLESD,
-  IX86_BUILTIN_COMGTSD,
-  IX86_BUILTIN_COMGESD,
-  IX86_BUILTIN_COMUEQSD,
-  IX86_BUILTIN_COMUNESD,
-  IX86_BUILTIN_COMULTSD,
-  IX86_BUILTIN_COMULESD,
-  IX86_BUILTIN_COMUGTSD,
-  IX86_BUILTIN_COMUGESD,
-  IX86_BUILTIN_COMORDSD,
-  IX86_BUILTIN_COMUNORDSD,
-  IX86_BUILTIN_COMFALSESD,
-  IX86_BUILTIN_COMTRUESD,
-
-  IX86_BUILTIN_COMEQPS,
-  IX86_BUILTIN_COMNEPS,
-  IX86_BUILTIN_COMLTPS,
-  IX86_BUILTIN_COMLEPS,
-  IX86_BUILTIN_COMGTPS,
-  IX86_BUILTIN_COMGEPS,
-  IX86_BUILTIN_COMUEQPS,
-  IX86_BUILTIN_COMUNEPS,
-  IX86_BUILTIN_COMULTPS,
-  IX86_BUILTIN_COMULEPS,
-  IX86_BUILTIN_COMUGTPS,
-  IX86_BUILTIN_COMUGEPS,
-  IX86_BUILTIN_COMORDPS,
-  IX86_BUILTIN_COMUNORDPS,
-  IX86_BUILTIN_COMFALSEPS,
-  IX86_BUILTIN_COMTRUEPS,
-
-  IX86_BUILTIN_COMEQPD,
-  IX86_BUILTIN_COMNEPD,
-  IX86_BUILTIN_COMLTPD,
-  IX86_BUILTIN_COMLEPD,
-  IX86_BUILTIN_COMGTPD,
-  IX86_BUILTIN_COMGEPD,
-  IX86_BUILTIN_COMUEQPD,
-  IX86_BUILTIN_COMUNEPD,
-  IX86_BUILTIN_COMULTPD,
-  IX86_BUILTIN_COMULEPD,
-  IX86_BUILTIN_COMUGTPD,
-  IX86_BUILTIN_COMUGEPD,
-  IX86_BUILTIN_COMORDPD,
-  IX86_BUILTIN_COMUNORDPD,
-  IX86_BUILTIN_COMFALSEPD,
-  IX86_BUILTIN_COMTRUEPD,
-
-  IX86_BUILTIN_PCOMEQUB,
-  IX86_BUILTIN_PCOMNEUB,
-  IX86_BUILTIN_PCOMLTUB,
-  IX86_BUILTIN_PCOMLEUB,
-  IX86_BUILTIN_PCOMGTUB,
-  IX86_BUILTIN_PCOMGEUB,
-  IX86_BUILTIN_PCOMFALSEUB,
-  IX86_BUILTIN_PCOMTRUEUB,
-  IX86_BUILTIN_PCOMEQUW,
-  IX86_BUILTIN_PCOMNEUW,
-  IX86_BUILTIN_PCOMLTUW,
-  IX86_BUILTIN_PCOMLEUW,
-  IX86_BUILTIN_PCOMGTUW,
-  IX86_BUILTIN_PCOMGEUW,
-  IX86_BUILTIN_PCOMFALSEUW,
-  IX86_BUILTIN_PCOMTRUEUW,
-  IX86_BUILTIN_PCOMEQUD,
-  IX86_BUILTIN_PCOMNEUD,
-  IX86_BUILTIN_PCOMLTUD,
-  IX86_BUILTIN_PCOMLEUD,
-  IX86_BUILTIN_PCOMGTUD,
-  IX86_BUILTIN_PCOMGEUD,
-  IX86_BUILTIN_PCOMFALSEUD,
-  IX86_BUILTIN_PCOMTRUEUD,
-  IX86_BUILTIN_PCOMEQUQ,
-  IX86_BUILTIN_PCOMNEUQ,
-  IX86_BUILTIN_PCOMLTUQ,
-  IX86_BUILTIN_PCOMLEUQ,
-  IX86_BUILTIN_PCOMGTUQ,
-  IX86_BUILTIN_PCOMGEUQ,
-  IX86_BUILTIN_PCOMFALSEUQ,
-  IX86_BUILTIN_PCOMTRUEUQ,
-
-  IX86_BUILTIN_PCOMEQB,
-  IX86_BUILTIN_PCOMNEB,
-  IX86_BUILTIN_PCOMLTB,
-  IX86_BUILTIN_PCOMLEB,
-  IX86_BUILTIN_PCOMGTB,
-  IX86_BUILTIN_PCOMGEB,
-  IX86_BUILTIN_PCOMFALSEB,
-  IX86_BUILTIN_PCOMTRUEB,
-  IX86_BUILTIN_PCOMEQW,
-  IX86_BUILTIN_PCOMNEW,
-  IX86_BUILTIN_PCOMLTW,
-  IX86_BUILTIN_PCOMLEW,
-  IX86_BUILTIN_PCOMGTW,
-  IX86_BUILTIN_PCOMGEW,
-  IX86_BUILTIN_PCOMFALSEW,
-  IX86_BUILTIN_PCOMTRUEW,
-  IX86_BUILTIN_PCOMEQD,
-  IX86_BUILTIN_PCOMNED,
-  IX86_BUILTIN_PCOMLTD,
-  IX86_BUILTIN_PCOMLED,
-  IX86_BUILTIN_PCOMGTD,
-  IX86_BUILTIN_PCOMGED,
-  IX86_BUILTIN_PCOMFALSED,
-  IX86_BUILTIN_PCOMTRUED,
-  IX86_BUILTIN_PCOMEQQ,
-  IX86_BUILTIN_PCOMNEQ,
-  IX86_BUILTIN_PCOMLTQ,
-  IX86_BUILTIN_PCOMLEQ,
-  IX86_BUILTIN_PCOMGTQ,
-  IX86_BUILTIN_PCOMGEQ,
-  IX86_BUILTIN_PCOMFALSEQ,
-  IX86_BUILTIN_PCOMTRUEQ,
-
   IX86_BUILTIN_MAX
 };
 
@@ -22046,7 +21541,7 @@ static const struct builtin_description bdesc_args[] =
   { OPTION_MASK_ISA_SSE4_1, CODE_FOR_sse4_1_mulv2siv2di3, "__builtin_ia32_pmuldq128", IX86_BUILTIN_PMULDQ128, UNKNOWN, (int) V2DI_FTYPE_V4SI_V4SI },
   { OPTION_MASK_ISA_SSE4_1, CODE_FOR_mulv4si3, "__builtin_ia32_pmulld128", IX86_BUILTIN_PMULLD128, UNKNOWN, (int) V4SI_FTYPE_V4SI_V4SI },
 
-  /* SSE4.1 and SSE5 */
+  /* SSE4.1 */
   { OPTION_MASK_ISA_ROUND, CODE_FOR_sse4_1_roundpd, "__builtin_ia32_roundpd", IX86_BUILTIN_ROUNDPD, UNKNOWN, (int) V2DF_FTYPE_V2DF_INT },
   { OPTION_MASK_ISA_ROUND, CODE_FOR_sse4_1_roundps, "__builtin_ia32_roundps", IX86_BUILTIN_ROUNDPS, UNKNOWN, (int) V4SF_FTYPE_V4SF_INT },
   { OPTION_MASK_ISA_ROUND, CODE_FOR_sse4_1_roundsd, "__builtin_ia32_roundsd", IX86_BUILTIN_ROUNDSD, UNKNOWN, (int) V2DF_FTYPE_V2DF_V2DF_INT },
@@ -22196,294 +21691,6 @@ static const struct builtin_description bdesc_args[] =
   { OPTION_MASK_ISA_AVX, CODE_FOR_avx_movmskps256, "__builtin_ia32_movmskps256", IX86_BUILTIN_MOVMSKPS256, UNKNOWN, (int) INT_FTYPE_V8SF },
 };
 
-/* SSE5 */
-enum multi_arg_type {
-  MULTI_ARG_UNKNOWN,
-  MULTI_ARG_3_SF,
-  MULTI_ARG_3_DF,
-  MULTI_ARG_3_DI,
-  MULTI_ARG_3_SI,
-  MULTI_ARG_3_SI_DI,
-  MULTI_ARG_3_HI,
-  MULTI_ARG_3_HI_SI,
-  MULTI_ARG_3_QI,
-  MULTI_ARG_3_PERMPS,
-  MULTI_ARG_3_PERMPD,
-  MULTI_ARG_2_SF,
-  MULTI_ARG_2_DF,
-  MULTI_ARG_2_DI,
-  MULTI_ARG_2_SI,
-  MULTI_ARG_2_HI,
-  MULTI_ARG_2_QI,
-  MULTI_ARG_2_DI_IMM,
-  MULTI_ARG_2_SI_IMM,
-  MULTI_ARG_2_HI_IMM,
-  MULTI_ARG_2_QI_IMM,
-  MULTI_ARG_2_SF_CMP,
-  MULTI_ARG_2_DF_CMP,
-  MULTI_ARG_2_DI_CMP,
-  MULTI_ARG_2_SI_CMP,
-  MULTI_ARG_2_HI_CMP,
-  MULTI_ARG_2_QI_CMP,
-  MULTI_ARG_2_DI_TF,
-  MULTI_ARG_2_SI_TF,
-  MULTI_ARG_2_HI_TF,
-  MULTI_ARG_2_QI_TF,
-  MULTI_ARG_2_SF_TF,
-  MULTI_ARG_2_DF_TF,
-  MULTI_ARG_1_SF,
-  MULTI_ARG_1_DF,
-  MULTI_ARG_1_DI,
-  MULTI_ARG_1_SI,
-  MULTI_ARG_1_HI,
-  MULTI_ARG_1_QI,
-  MULTI_ARG_1_SI_DI,
-  MULTI_ARG_1_HI_DI,
-  MULTI_ARG_1_HI_SI,
-  MULTI_ARG_1_QI_DI,
-  MULTI_ARG_1_QI_SI,
-  MULTI_ARG_1_QI_HI,
-  MULTI_ARG_1_PH2PS,
-  MULTI_ARG_1_PS2PH
-};
-
-static const struct builtin_description bdesc_multi_arg[] =
-{
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5i_vmfmaddv4sf4,     "__builtin_ia32_fmaddss",    IX86_BUILTIN_FMADDSS,    UNKNOWN,      (int)MULTI_ARG_3_SF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5i_vmfmaddv2df4,     "__builtin_ia32_fmaddsd",    IX86_BUILTIN_FMADDSD,    UNKNOWN,      (int)MULTI_ARG_3_DF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5i_fmaddv4sf4,       "__builtin_ia32_fmaddps",    IX86_BUILTIN_FMADDPS,    UNKNOWN,      (int)MULTI_ARG_3_SF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5i_fmaddv2df4,       "__builtin_ia32_fmaddpd",    IX86_BUILTIN_FMADDPD,    UNKNOWN,      (int)MULTI_ARG_3_DF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5i_vmfmsubv4sf4,     "__builtin_ia32_fmsubss",    IX86_BUILTIN_FMSUBSS,    UNKNOWN,      (int)MULTI_ARG_3_SF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5i_vmfmsubv2df4,     "__builtin_ia32_fmsubsd",    IX86_BUILTIN_FMSUBSD,    UNKNOWN,      (int)MULTI_ARG_3_DF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5i_fmsubv4sf4,       "__builtin_ia32_fmsubps",    IX86_BUILTIN_FMSUBPS,    UNKNOWN,      (int)MULTI_ARG_3_SF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5i_fmsubv2df4,       "__builtin_ia32_fmsubpd",    IX86_BUILTIN_FMSUBPD,    UNKNOWN,      (int)MULTI_ARG_3_DF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5i_vmfnmaddv4sf4,    "__builtin_ia32_fnmaddss",   IX86_BUILTIN_FNMADDSS,   UNKNOWN,      (int)MULTI_ARG_3_SF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5i_vmfnmaddv2df4,    "__builtin_ia32_fnmaddsd",   IX86_BUILTIN_FNMADDSD,   UNKNOWN,      (int)MULTI_ARG_3_DF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5i_fnmaddv4sf4,      "__builtin_ia32_fnmaddps",   IX86_BUILTIN_FNMADDPS,   UNKNOWN,      (int)MULTI_ARG_3_SF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5i_fnmaddv2df4,      "__builtin_ia32_fnmaddpd",   IX86_BUILTIN_FNMADDPD,   UNKNOWN,      (int)MULTI_ARG_3_DF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5i_vmfnmsubv4sf4,    "__builtin_ia32_fnmsubss",   IX86_BUILTIN_FNMSUBSS,   UNKNOWN,      (int)MULTI_ARG_3_SF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5i_vmfnmsubv2df4,    "__builtin_ia32_fnmsubsd",   IX86_BUILTIN_FNMSUBSD,   UNKNOWN,      (int)MULTI_ARG_3_DF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5i_fnmsubv4sf4,      "__builtin_ia32_fnmsubps",   IX86_BUILTIN_FNMSUBPS,   UNKNOWN,      (int)MULTI_ARG_3_SF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5i_fnmsubv2df4,      "__builtin_ia32_fnmsubpd",   IX86_BUILTIN_FNMSUBPD,   UNKNOWN,      (int)MULTI_ARG_3_DF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pcmov_v2di,        "__builtin_ia32_pcmov",      IX86_BUILTIN_PCMOV,	 UNKNOWN,      (int)MULTI_ARG_3_DI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pcmov_v2di,        "__builtin_ia32_pcmov_v2di", IX86_BUILTIN_PCMOV_V2DI, UNKNOWN,      (int)MULTI_ARG_3_DI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pcmov_v4si,        "__builtin_ia32_pcmov_v4si", IX86_BUILTIN_PCMOV_V4SI, UNKNOWN,      (int)MULTI_ARG_3_SI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pcmov_v8hi,        "__builtin_ia32_pcmov_v8hi", IX86_BUILTIN_PCMOV_V8HI, UNKNOWN,      (int)MULTI_ARG_3_HI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pcmov_v16qi,       "__builtin_ia32_pcmov_v16qi",IX86_BUILTIN_PCMOV_V16QI,UNKNOWN,      (int)MULTI_ARG_3_QI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pcmov_v2df,        "__builtin_ia32_pcmov_v2df", IX86_BUILTIN_PCMOV_V2DF, UNKNOWN,      (int)MULTI_ARG_3_DF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pcmov_v4sf,        "__builtin_ia32_pcmov_v4sf", IX86_BUILTIN_PCMOV_V4SF, UNKNOWN,      (int)MULTI_ARG_3_SF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pperm,             "__builtin_ia32_pperm",      IX86_BUILTIN_PPERM,      UNKNOWN,      (int)MULTI_ARG_3_QI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_permv4sf,          "__builtin_ia32_permps",     IX86_BUILTIN_PERMPS,     UNKNOWN,      (int)MULTI_ARG_3_PERMPS },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_permv2df,          "__builtin_ia32_permpd",     IX86_BUILTIN_PERMPD,     UNKNOWN,      (int)MULTI_ARG_3_PERMPD },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pmacssww,          "__builtin_ia32_pmacssww",   IX86_BUILTIN_PMACSSWW,   UNKNOWN,      (int)MULTI_ARG_3_HI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pmacsww,           "__builtin_ia32_pmacsww",    IX86_BUILTIN_PMACSWW,    UNKNOWN,      (int)MULTI_ARG_3_HI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pmacsswd,          "__builtin_ia32_pmacsswd",   IX86_BUILTIN_PMACSSWD,   UNKNOWN,      (int)MULTI_ARG_3_HI_SI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pmacswd,           "__builtin_ia32_pmacswd",    IX86_BUILTIN_PMACSWD,    UNKNOWN,      (int)MULTI_ARG_3_HI_SI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pmacssdd,          "__builtin_ia32_pmacssdd",   IX86_BUILTIN_PMACSSDD,   UNKNOWN,      (int)MULTI_ARG_3_SI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pmacsdd,           "__builtin_ia32_pmacsdd",    IX86_BUILTIN_PMACSDD,    UNKNOWN,      (int)MULTI_ARG_3_SI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pmacssdql,         "__builtin_ia32_pmacssdql",  IX86_BUILTIN_PMACSSDQL,  UNKNOWN,      (int)MULTI_ARG_3_SI_DI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pmacssdqh,         "__builtin_ia32_pmacssdqh",  IX86_BUILTIN_PMACSSDQH,  UNKNOWN,      (int)MULTI_ARG_3_SI_DI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pmacsdql,          "__builtin_ia32_pmacsdql",   IX86_BUILTIN_PMACSDQL,   UNKNOWN,      (int)MULTI_ARG_3_SI_DI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pmacsdqh,          "__builtin_ia32_pmacsdqh",   IX86_BUILTIN_PMACSDQH,   UNKNOWN,      (int)MULTI_ARG_3_SI_DI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pmadcsswd,         "__builtin_ia32_pmadcsswd",  IX86_BUILTIN_PMADCSSWD,  UNKNOWN,      (int)MULTI_ARG_3_HI_SI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pmadcswd,          "__builtin_ia32_pmadcswd",   IX86_BUILTIN_PMADCSWD,   UNKNOWN,      (int)MULTI_ARG_3_HI_SI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vrotlv2di3,        "__builtin_ia32_protq",      IX86_BUILTIN_PROTQ,      UNKNOWN,      (int)MULTI_ARG_2_DI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vrotlv4si3,        "__builtin_ia32_protd",      IX86_BUILTIN_PROTD,      UNKNOWN,      (int)MULTI_ARG_2_SI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vrotlv8hi3,        "__builtin_ia32_protw",      IX86_BUILTIN_PROTW,      UNKNOWN,      (int)MULTI_ARG_2_HI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vrotlv16qi3,       "__builtin_ia32_protb",      IX86_BUILTIN_PROTB,      UNKNOWN,      (int)MULTI_ARG_2_QI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_rotlv2di3,         "__builtin_ia32_protqi",     IX86_BUILTIN_PROTQ_IMM,  UNKNOWN,      (int)MULTI_ARG_2_DI_IMM },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_rotlv4si3,         "__builtin_ia32_protdi",     IX86_BUILTIN_PROTD_IMM,  UNKNOWN,      (int)MULTI_ARG_2_SI_IMM },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_rotlv8hi3,         "__builtin_ia32_protwi",     IX86_BUILTIN_PROTW_IMM,  UNKNOWN,      (int)MULTI_ARG_2_HI_IMM },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_rotlv16qi3,        "__builtin_ia32_protbi",     IX86_BUILTIN_PROTB_IMM,  UNKNOWN,      (int)MULTI_ARG_2_QI_IMM },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_ashlv2di3,         "__builtin_ia32_pshaq",      IX86_BUILTIN_PSHAQ,      UNKNOWN,      (int)MULTI_ARG_2_DI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_ashlv4si3,         "__builtin_ia32_pshad",      IX86_BUILTIN_PSHAD,      UNKNOWN,      (int)MULTI_ARG_2_SI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_ashlv8hi3,         "__builtin_ia32_pshaw",      IX86_BUILTIN_PSHAW,      UNKNOWN,      (int)MULTI_ARG_2_HI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_ashlv16qi3,        "__builtin_ia32_pshab",      IX86_BUILTIN_PSHAB,      UNKNOWN,      (int)MULTI_ARG_2_QI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_lshlv2di3,         "__builtin_ia32_pshlq",      IX86_BUILTIN_PSHLQ,      UNKNOWN,      (int)MULTI_ARG_2_DI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_lshlv4si3,         "__builtin_ia32_pshld",      IX86_BUILTIN_PSHLD,      UNKNOWN,      (int)MULTI_ARG_2_SI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_lshlv8hi3,         "__builtin_ia32_pshlw",      IX86_BUILTIN_PSHLW,      UNKNOWN,      (int)MULTI_ARG_2_HI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_lshlv16qi3,        "__builtin_ia32_pshlb",      IX86_BUILTIN_PSHLB,      UNKNOWN,      (int)MULTI_ARG_2_QI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vmfrczv4sf2,       "__builtin_ia32_frczss",     IX86_BUILTIN_FRCZSS,     UNKNOWN,      (int)MULTI_ARG_2_SF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vmfrczv2df2,       "__builtin_ia32_frczsd",     IX86_BUILTIN_FRCZSD,     UNKNOWN,      (int)MULTI_ARG_2_DF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_frczv4sf2,         "__builtin_ia32_frczps",     IX86_BUILTIN_FRCZPS,     UNKNOWN,      (int)MULTI_ARG_1_SF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_frczv2df2,         "__builtin_ia32_frczpd",     IX86_BUILTIN_FRCZPD,     UNKNOWN,      (int)MULTI_ARG_1_DF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_cvtph2ps,          "__builtin_ia32_cvtph2ps",   IX86_BUILTIN_CVTPH2PS,   UNKNOWN,      (int)MULTI_ARG_1_PH2PS },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_cvtps2ph,          "__builtin_ia32_cvtps2ph",   IX86_BUILTIN_CVTPS2PH,   UNKNOWN,      (int)MULTI_ARG_1_PS2PH },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_phaddbw,           "__builtin_ia32_phaddbw",    IX86_BUILTIN_PHADDBW,    UNKNOWN,      (int)MULTI_ARG_1_QI_HI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_phaddbd,           "__builtin_ia32_phaddbd",    IX86_BUILTIN_PHADDBD,    UNKNOWN,      (int)MULTI_ARG_1_QI_SI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_phaddbq,           "__builtin_ia32_phaddbq",    IX86_BUILTIN_PHADDBQ,    UNKNOWN,      (int)MULTI_ARG_1_QI_DI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_phaddwd,           "__builtin_ia32_phaddwd",    IX86_BUILTIN_PHADDWD,    UNKNOWN,      (int)MULTI_ARG_1_HI_SI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_phaddwq,           "__builtin_ia32_phaddwq",    IX86_BUILTIN_PHADDWQ,    UNKNOWN,      (int)MULTI_ARG_1_HI_DI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_phadddq,           "__builtin_ia32_phadddq",    IX86_BUILTIN_PHADDDQ,    UNKNOWN,      (int)MULTI_ARG_1_SI_DI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_phaddubw,          "__builtin_ia32_phaddubw",   IX86_BUILTIN_PHADDUBW,   UNKNOWN,      (int)MULTI_ARG_1_QI_HI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_phaddubd,          "__builtin_ia32_phaddubd",   IX86_BUILTIN_PHADDUBD,   UNKNOWN,      (int)MULTI_ARG_1_QI_SI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_phaddubq,          "__builtin_ia32_phaddubq",   IX86_BUILTIN_PHADDUBQ,   UNKNOWN,      (int)MULTI_ARG_1_QI_DI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_phadduwd,          "__builtin_ia32_phadduwd",   IX86_BUILTIN_PHADDUWD,   UNKNOWN,      (int)MULTI_ARG_1_HI_SI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_phadduwq,          "__builtin_ia32_phadduwq",   IX86_BUILTIN_PHADDUWQ,   UNKNOWN,      (int)MULTI_ARG_1_HI_DI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_phaddudq,          "__builtin_ia32_phaddudq",   IX86_BUILTIN_PHADDUDQ,   UNKNOWN,      (int)MULTI_ARG_1_SI_DI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_phsubbw,           "__builtin_ia32_phsubbw",    IX86_BUILTIN_PHSUBBW,    UNKNOWN,      (int)MULTI_ARG_1_QI_HI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_phsubwd,           "__builtin_ia32_phsubwd",    IX86_BUILTIN_PHSUBWD,    UNKNOWN,      (int)MULTI_ARG_1_HI_SI },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_phsubdq,           "__builtin_ia32_phsubdq",    IX86_BUILTIN_PHSUBDQ,    UNKNOWN,      (int)MULTI_ARG_1_SI_DI },
-
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vmmaskcmpv4sf3,    "__builtin_ia32_comeqss",    IX86_BUILTIN_COMEQSS,    EQ,           (int)MULTI_ARG_2_SF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vmmaskcmpv4sf3,    "__builtin_ia32_comness",    IX86_BUILTIN_COMNESS,    NE,           (int)MULTI_ARG_2_SF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vmmaskcmpv4sf3,    "__builtin_ia32_comneqss",   IX86_BUILTIN_COMNESS,    NE,           (int)MULTI_ARG_2_SF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vmmaskcmpv4sf3,    "__builtin_ia32_comltss",    IX86_BUILTIN_COMLTSS,    LT,           (int)MULTI_ARG_2_SF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vmmaskcmpv4sf3,    "__builtin_ia32_comless",    IX86_BUILTIN_COMLESS,    LE,           (int)MULTI_ARG_2_SF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vmmaskcmpv4sf3,    "__builtin_ia32_comgtss",    IX86_BUILTIN_COMGTSS,    GT,           (int)MULTI_ARG_2_SF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vmmaskcmpv4sf3,    "__builtin_ia32_comgess",    IX86_BUILTIN_COMGESS,    GE,           (int)MULTI_ARG_2_SF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vmmaskcmpv4sf3,    "__builtin_ia32_comueqss",   IX86_BUILTIN_COMUEQSS,   UNEQ,         (int)MULTI_ARG_2_SF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vmmaskcmpv4sf3,    "__builtin_ia32_comuness",   IX86_BUILTIN_COMUNESS,   LTGT,         (int)MULTI_ARG_2_SF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vmmaskcmpv4sf3,    "__builtin_ia32_comuneqss",  IX86_BUILTIN_COMUNESS,   LTGT,         (int)MULTI_ARG_2_SF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vmmaskcmpv4sf3,    "__builtin_ia32_comunltss",  IX86_BUILTIN_COMULTSS,   UNLT,         (int)MULTI_ARG_2_SF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vmmaskcmpv4sf3,    "__builtin_ia32_comunless",  IX86_BUILTIN_COMULESS,   UNLE,         (int)MULTI_ARG_2_SF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vmmaskcmpv4sf3,    "__builtin_ia32_comungtss",  IX86_BUILTIN_COMUGTSS,   UNGT,         (int)MULTI_ARG_2_SF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vmmaskcmpv4sf3,    "__builtin_ia32_comungess",  IX86_BUILTIN_COMUGESS,   UNGE,         (int)MULTI_ARG_2_SF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vmmaskcmpv4sf3,    "__builtin_ia32_comordss",   IX86_BUILTIN_COMORDSS,   ORDERED,      (int)MULTI_ARG_2_SF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vmmaskcmpv4sf3,    "__builtin_ia32_comunordss", IX86_BUILTIN_COMUNORDSS, UNORDERED,    (int)MULTI_ARG_2_SF_CMP },
-
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vmmaskcmpv2df3,    "__builtin_ia32_comeqsd",    IX86_BUILTIN_COMEQSD,    EQ,           (int)MULTI_ARG_2_DF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vmmaskcmpv2df3,    "__builtin_ia32_comnesd",    IX86_BUILTIN_COMNESD,    NE,           (int)MULTI_ARG_2_DF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vmmaskcmpv2df3,    "__builtin_ia32_comneqsd",   IX86_BUILTIN_COMNESD,    NE,           (int)MULTI_ARG_2_DF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vmmaskcmpv2df3,    "__builtin_ia32_comltsd",    IX86_BUILTIN_COMLTSD,    LT,           (int)MULTI_ARG_2_DF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vmmaskcmpv2df3,    "__builtin_ia32_comlesd",    IX86_BUILTIN_COMLESD,    LE,           (int)MULTI_ARG_2_DF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vmmaskcmpv2df3,    "__builtin_ia32_comgtsd",    IX86_BUILTIN_COMGTSD,    GT,           (int)MULTI_ARG_2_DF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vmmaskcmpv2df3,    "__builtin_ia32_comgesd",    IX86_BUILTIN_COMGESD,    GE,           (int)MULTI_ARG_2_DF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vmmaskcmpv2df3,    "__builtin_ia32_comueqsd",   IX86_BUILTIN_COMUEQSD,   UNEQ,         (int)MULTI_ARG_2_DF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vmmaskcmpv2df3,    "__builtin_ia32_comunesd",   IX86_BUILTIN_COMUNESD,   LTGT,         (int)MULTI_ARG_2_DF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vmmaskcmpv2df3,    "__builtin_ia32_comuneqsd",  IX86_BUILTIN_COMUNESD,   LTGT,         (int)MULTI_ARG_2_DF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vmmaskcmpv2df3,    "__builtin_ia32_comunltsd",  IX86_BUILTIN_COMULTSD,   UNLT,         (int)MULTI_ARG_2_DF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vmmaskcmpv2df3,    "__builtin_ia32_comunlesd",  IX86_BUILTIN_COMULESD,   UNLE,         (int)MULTI_ARG_2_DF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vmmaskcmpv2df3,    "__builtin_ia32_comungtsd",  IX86_BUILTIN_COMUGTSD,   UNGT,         (int)MULTI_ARG_2_DF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vmmaskcmpv2df3,    "__builtin_ia32_comungesd",  IX86_BUILTIN_COMUGESD,   UNGE,         (int)MULTI_ARG_2_DF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vmmaskcmpv2df3,    "__builtin_ia32_comordsd",   IX86_BUILTIN_COMORDSD,   ORDERED,      (int)MULTI_ARG_2_DF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_vmmaskcmpv2df3,    "__builtin_ia32_comunordsd", IX86_BUILTIN_COMUNORDSD, UNORDERED,    (int)MULTI_ARG_2_DF_CMP },
-
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv4sf3,      "__builtin_ia32_comeqps",    IX86_BUILTIN_COMEQPS,    EQ,           (int)MULTI_ARG_2_SF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv4sf3,      "__builtin_ia32_comneps",    IX86_BUILTIN_COMNEPS,    NE,           (int)MULTI_ARG_2_SF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv4sf3,      "__builtin_ia32_comneqps",   IX86_BUILTIN_COMNEPS,    NE,           (int)MULTI_ARG_2_SF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv4sf3,      "__builtin_ia32_comltps",    IX86_BUILTIN_COMLTPS,    LT,           (int)MULTI_ARG_2_SF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv4sf3,      "__builtin_ia32_comleps",    IX86_BUILTIN_COMLEPS,    LE,           (int)MULTI_ARG_2_SF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv4sf3,      "__builtin_ia32_comgtps",    IX86_BUILTIN_COMGTPS,    GT,           (int)MULTI_ARG_2_SF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv4sf3,      "__builtin_ia32_comgeps",    IX86_BUILTIN_COMGEPS,    GE,           (int)MULTI_ARG_2_SF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv4sf3,      "__builtin_ia32_comueqps",   IX86_BUILTIN_COMUEQPS,   UNEQ,         (int)MULTI_ARG_2_SF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv4sf3,      "__builtin_ia32_comuneps",   IX86_BUILTIN_COMUNEPS,   LTGT,         (int)MULTI_ARG_2_SF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv4sf3,      "__builtin_ia32_comuneqps",  IX86_BUILTIN_COMUNEPS,   LTGT,         (int)MULTI_ARG_2_SF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv4sf3,      "__builtin_ia32_comunltps",  IX86_BUILTIN_COMULTPS,   UNLT,         (int)MULTI_ARG_2_SF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv4sf3,      "__builtin_ia32_comunleps",  IX86_BUILTIN_COMULEPS,   UNLE,         (int)MULTI_ARG_2_SF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv4sf3,      "__builtin_ia32_comungtps",  IX86_BUILTIN_COMUGTPS,   UNGT,         (int)MULTI_ARG_2_SF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv4sf3,      "__builtin_ia32_comungeps",  IX86_BUILTIN_COMUGEPS,   UNGE,         (int)MULTI_ARG_2_SF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv4sf3,      "__builtin_ia32_comordps",   IX86_BUILTIN_COMORDPS,   ORDERED,      (int)MULTI_ARG_2_SF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv4sf3,      "__builtin_ia32_comunordps", IX86_BUILTIN_COMUNORDPS, UNORDERED,    (int)MULTI_ARG_2_SF_CMP },
-
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv2df3,      "__builtin_ia32_comeqpd",    IX86_BUILTIN_COMEQPD,    EQ,           (int)MULTI_ARG_2_DF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv2df3,      "__builtin_ia32_comnepd",    IX86_BUILTIN_COMNEPD,    NE,           (int)MULTI_ARG_2_DF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv2df3,      "__builtin_ia32_comneqpd",   IX86_BUILTIN_COMNEPD,    NE,           (int)MULTI_ARG_2_DF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv2df3,      "__builtin_ia32_comltpd",    IX86_BUILTIN_COMLTPD,    LT,           (int)MULTI_ARG_2_DF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv2df3,      "__builtin_ia32_comlepd",    IX86_BUILTIN_COMLEPD,    LE,           (int)MULTI_ARG_2_DF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv2df3,      "__builtin_ia32_comgtpd",    IX86_BUILTIN_COMGTPD,    GT,           (int)MULTI_ARG_2_DF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv2df3,      "__builtin_ia32_comgepd",    IX86_BUILTIN_COMGEPD,    GE,           (int)MULTI_ARG_2_DF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv2df3,      "__builtin_ia32_comueqpd",   IX86_BUILTIN_COMUEQPD,   UNEQ,         (int)MULTI_ARG_2_DF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv2df3,      "__builtin_ia32_comunepd",   IX86_BUILTIN_COMUNEPD,   LTGT,         (int)MULTI_ARG_2_DF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv2df3,      "__builtin_ia32_comuneqpd",  IX86_BUILTIN_COMUNEPD,   LTGT,         (int)MULTI_ARG_2_DF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv2df3,      "__builtin_ia32_comunltpd",  IX86_BUILTIN_COMULTPD,   UNLT,         (int)MULTI_ARG_2_DF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv2df3,      "__builtin_ia32_comunlepd",  IX86_BUILTIN_COMULEPD,   UNLE,         (int)MULTI_ARG_2_DF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv2df3,      "__builtin_ia32_comungtpd",  IX86_BUILTIN_COMUGTPD,   UNGT,         (int)MULTI_ARG_2_DF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv2df3,      "__builtin_ia32_comungepd",  IX86_BUILTIN_COMUGEPD,   UNGE,         (int)MULTI_ARG_2_DF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv2df3,      "__builtin_ia32_comordpd",   IX86_BUILTIN_COMORDPD,   ORDERED,      (int)MULTI_ARG_2_DF_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv2df3,      "__builtin_ia32_comunordpd", IX86_BUILTIN_COMUNORDPD, UNORDERED,    (int)MULTI_ARG_2_DF_CMP },
-
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv16qi3,     "__builtin_ia32_pcomeqb",    IX86_BUILTIN_PCOMEQB,    EQ,           (int)MULTI_ARG_2_QI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv16qi3,     "__builtin_ia32_pcomneb",    IX86_BUILTIN_PCOMNEB,    NE,           (int)MULTI_ARG_2_QI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv16qi3,     "__builtin_ia32_pcomneqb",   IX86_BUILTIN_PCOMNEB,    NE,           (int)MULTI_ARG_2_QI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv16qi3,     "__builtin_ia32_pcomltb",    IX86_BUILTIN_PCOMLTB,    LT,           (int)MULTI_ARG_2_QI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv16qi3,     "__builtin_ia32_pcomleb",    IX86_BUILTIN_PCOMLEB,    LE,           (int)MULTI_ARG_2_QI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv16qi3,     "__builtin_ia32_pcomgtb",    IX86_BUILTIN_PCOMGTB,    GT,           (int)MULTI_ARG_2_QI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv16qi3,     "__builtin_ia32_pcomgeb",    IX86_BUILTIN_PCOMGEB,    GE,           (int)MULTI_ARG_2_QI_CMP },
-
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv8hi3,      "__builtin_ia32_pcomeqw",    IX86_BUILTIN_PCOMEQW,    EQ,           (int)MULTI_ARG_2_HI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv8hi3,      "__builtin_ia32_pcomnew",    IX86_BUILTIN_PCOMNEW,    NE,           (int)MULTI_ARG_2_HI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv8hi3,      "__builtin_ia32_pcomneqw",   IX86_BUILTIN_PCOMNEW,    NE,           (int)MULTI_ARG_2_HI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv8hi3,      "__builtin_ia32_pcomltw",    IX86_BUILTIN_PCOMLTW,    LT,           (int)MULTI_ARG_2_HI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv8hi3,      "__builtin_ia32_pcomlew",    IX86_BUILTIN_PCOMLEW,    LE,           (int)MULTI_ARG_2_HI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv8hi3,      "__builtin_ia32_pcomgtw",    IX86_BUILTIN_PCOMGTW,    GT,           (int)MULTI_ARG_2_HI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv8hi3,      "__builtin_ia32_pcomgew",    IX86_BUILTIN_PCOMGEW,    GE,           (int)MULTI_ARG_2_HI_CMP },
-
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv4si3,      "__builtin_ia32_pcomeqd",    IX86_BUILTIN_PCOMEQD,    EQ,           (int)MULTI_ARG_2_SI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv4si3,      "__builtin_ia32_pcomned",    IX86_BUILTIN_PCOMNED,    NE,           (int)MULTI_ARG_2_SI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv4si3,      "__builtin_ia32_pcomneqd",   IX86_BUILTIN_PCOMNED,    NE,           (int)MULTI_ARG_2_SI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv4si3,      "__builtin_ia32_pcomltd",    IX86_BUILTIN_PCOMLTD,    LT,           (int)MULTI_ARG_2_SI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv4si3,      "__builtin_ia32_pcomled",    IX86_BUILTIN_PCOMLED,    LE,           (int)MULTI_ARG_2_SI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv4si3,      "__builtin_ia32_pcomgtd",    IX86_BUILTIN_PCOMGTD,    GT,           (int)MULTI_ARG_2_SI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv4si3,      "__builtin_ia32_pcomged",    IX86_BUILTIN_PCOMGED,    GE,           (int)MULTI_ARG_2_SI_CMP },
-
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv2di3,      "__builtin_ia32_pcomeqq",    IX86_BUILTIN_PCOMEQQ,    EQ,           (int)MULTI_ARG_2_DI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv2di3,      "__builtin_ia32_pcomneq",    IX86_BUILTIN_PCOMNEQ,    NE,           (int)MULTI_ARG_2_DI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv2di3,      "__builtin_ia32_pcomneqq",   IX86_BUILTIN_PCOMNEQ,    NE,           (int)MULTI_ARG_2_DI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv2di3,      "__builtin_ia32_pcomltq",    IX86_BUILTIN_PCOMLTQ,    LT,           (int)MULTI_ARG_2_DI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv2di3,      "__builtin_ia32_pcomleq",    IX86_BUILTIN_PCOMLEQ,    LE,           (int)MULTI_ARG_2_DI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv2di3,      "__builtin_ia32_pcomgtq",    IX86_BUILTIN_PCOMGTQ,    GT,           (int)MULTI_ARG_2_DI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmpv2di3,      "__builtin_ia32_pcomgeq",    IX86_BUILTIN_PCOMGEQ,    GE,           (int)MULTI_ARG_2_DI_CMP },
-
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmp_uns2v16qi3,"__builtin_ia32_pcomequb",   IX86_BUILTIN_PCOMEQUB,   EQ,           (int)MULTI_ARG_2_QI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmp_uns2v16qi3,"__builtin_ia32_pcomneub",   IX86_BUILTIN_PCOMNEUB,   NE,           (int)MULTI_ARG_2_QI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmp_uns2v16qi3,"__builtin_ia32_pcomnequb",  IX86_BUILTIN_PCOMNEUB,   NE,           (int)MULTI_ARG_2_QI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmp_unsv16qi3, "__builtin_ia32_pcomltub",   IX86_BUILTIN_PCOMLTUB,   LTU,          (int)MULTI_ARG_2_QI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmp_unsv16qi3, "__builtin_ia32_pcomleub",   IX86_BUILTIN_PCOMLEUB,   LEU,          (int)MULTI_ARG_2_QI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmp_unsv16qi3, "__builtin_ia32_pcomgtub",   IX86_BUILTIN_PCOMGTUB,   GTU,          (int)MULTI_ARG_2_QI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmp_unsv16qi3, "__builtin_ia32_pcomgeub",   IX86_BUILTIN_PCOMGEUB,   GEU,          (int)MULTI_ARG_2_QI_CMP },
-
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmp_uns2v8hi3, "__builtin_ia32_pcomequw",   IX86_BUILTIN_PCOMEQUW,   EQ,           (int)MULTI_ARG_2_HI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmp_uns2v8hi3, "__builtin_ia32_pcomneuw",   IX86_BUILTIN_PCOMNEUW,   NE,           (int)MULTI_ARG_2_HI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmp_uns2v8hi3, "__builtin_ia32_pcomnequw",  IX86_BUILTIN_PCOMNEUW,   NE,           (int)MULTI_ARG_2_HI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmp_unsv8hi3,  "__builtin_ia32_pcomltuw",   IX86_BUILTIN_PCOMLTUW,   LTU,          (int)MULTI_ARG_2_HI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmp_unsv8hi3,  "__builtin_ia32_pcomleuw",   IX86_BUILTIN_PCOMLEUW,   LEU,          (int)MULTI_ARG_2_HI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmp_unsv8hi3,  "__builtin_ia32_pcomgtuw",   IX86_BUILTIN_PCOMGTUW,   GTU,          (int)MULTI_ARG_2_HI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmp_unsv8hi3,  "__builtin_ia32_pcomgeuw",   IX86_BUILTIN_PCOMGEUW,   GEU,          (int)MULTI_ARG_2_HI_CMP },
-
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmp_uns2v4si3, "__builtin_ia32_pcomequd",   IX86_BUILTIN_PCOMEQUD,   EQ,           (int)MULTI_ARG_2_SI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmp_uns2v4si3, "__builtin_ia32_pcomneud",   IX86_BUILTIN_PCOMNEUD,   NE,           (int)MULTI_ARG_2_SI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmp_uns2v4si3, "__builtin_ia32_pcomnequd",  IX86_BUILTIN_PCOMNEUD,   NE,           (int)MULTI_ARG_2_SI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmp_unsv4si3,  "__builtin_ia32_pcomltud",   IX86_BUILTIN_PCOMLTUD,   LTU,          (int)MULTI_ARG_2_SI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmp_unsv4si3,  "__builtin_ia32_pcomleud",   IX86_BUILTIN_PCOMLEUD,   LEU,          (int)MULTI_ARG_2_SI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmp_unsv4si3,  "__builtin_ia32_pcomgtud",   IX86_BUILTIN_PCOMGTUD,   GTU,          (int)MULTI_ARG_2_SI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmp_unsv4si3,  "__builtin_ia32_pcomgeud",   IX86_BUILTIN_PCOMGEUD,   GEU,          (int)MULTI_ARG_2_SI_CMP },
-
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmp_uns2v2di3, "__builtin_ia32_pcomequq",   IX86_BUILTIN_PCOMEQUQ,   EQ,           (int)MULTI_ARG_2_DI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmp_uns2v2di3, "__builtin_ia32_pcomneuq",   IX86_BUILTIN_PCOMNEUQ,   NE,           (int)MULTI_ARG_2_DI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmp_uns2v2di3, "__builtin_ia32_pcomnequq",  IX86_BUILTIN_PCOMNEUQ,   NE,           (int)MULTI_ARG_2_DI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmp_unsv2di3,  "__builtin_ia32_pcomltuq",   IX86_BUILTIN_PCOMLTUQ,   LTU,          (int)MULTI_ARG_2_DI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmp_unsv2di3,  "__builtin_ia32_pcomleuq",   IX86_BUILTIN_PCOMLEUQ,   LEU,          (int)MULTI_ARG_2_DI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmp_unsv2di3,  "__builtin_ia32_pcomgtuq",   IX86_BUILTIN_PCOMGTUQ,   GTU,          (int)MULTI_ARG_2_DI_CMP },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_maskcmp_unsv2di3,  "__builtin_ia32_pcomgeuq",   IX86_BUILTIN_PCOMGEUQ,   GEU,          (int)MULTI_ARG_2_DI_CMP },
-
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_com_tfv4sf3,       "__builtin_ia32_comfalsess", IX86_BUILTIN_COMFALSESS, (enum rtx_code) COM_FALSE_S,  (int)MULTI_ARG_2_SF_TF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_com_tfv4sf3,       "__builtin_ia32_comtruess",  IX86_BUILTIN_COMTRUESS,  (enum rtx_code) COM_TRUE_S,   (int)MULTI_ARG_2_SF_TF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_com_tfv4sf3,       "__builtin_ia32_comfalseps", IX86_BUILTIN_COMFALSEPS, (enum rtx_code) COM_FALSE_P,  (int)MULTI_ARG_2_SF_TF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_com_tfv4sf3,       "__builtin_ia32_comtrueps",  IX86_BUILTIN_COMTRUEPS,  (enum rtx_code) COM_TRUE_P,   (int)MULTI_ARG_2_SF_TF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_com_tfv2df3,       "__builtin_ia32_comfalsesd", IX86_BUILTIN_COMFALSESD, (enum rtx_code) COM_FALSE_S,  (int)MULTI_ARG_2_DF_TF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_com_tfv2df3,       "__builtin_ia32_comtruesd",  IX86_BUILTIN_COMTRUESD,  (enum rtx_code) COM_TRUE_S,   (int)MULTI_ARG_2_DF_TF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_com_tfv2df3,       "__builtin_ia32_comfalsepd", IX86_BUILTIN_COMFALSEPD, (enum rtx_code) COM_FALSE_P,  (int)MULTI_ARG_2_DF_TF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_com_tfv2df3,       "__builtin_ia32_comtruepd",  IX86_BUILTIN_COMTRUEPD,  (enum rtx_code) COM_TRUE_P,   (int)MULTI_ARG_2_DF_TF },
-
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pcom_tfv16qi3,     "__builtin_ia32_pcomfalseb", IX86_BUILTIN_PCOMFALSEB, (enum rtx_code) PCOM_FALSE,   (int)MULTI_ARG_2_QI_TF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pcom_tfv8hi3,      "__builtin_ia32_pcomfalsew", IX86_BUILTIN_PCOMFALSEW, (enum rtx_code) PCOM_FALSE,   (int)MULTI_ARG_2_HI_TF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pcom_tfv4si3,      "__builtin_ia32_pcomfalsed", IX86_BUILTIN_PCOMFALSED, (enum rtx_code) PCOM_FALSE,   (int)MULTI_ARG_2_SI_TF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pcom_tfv2di3,      "__builtin_ia32_pcomfalseq", IX86_BUILTIN_PCOMFALSEQ, (enum rtx_code) PCOM_FALSE,   (int)MULTI_ARG_2_DI_TF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pcom_tfv16qi3,     "__builtin_ia32_pcomfalseub",IX86_BUILTIN_PCOMFALSEUB,(enum rtx_code) PCOM_FALSE,   (int)MULTI_ARG_2_QI_TF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pcom_tfv8hi3,      "__builtin_ia32_pcomfalseuw",IX86_BUILTIN_PCOMFALSEUW,(enum rtx_code) PCOM_FALSE,   (int)MULTI_ARG_2_HI_TF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pcom_tfv4si3,      "__builtin_ia32_pcomfalseud",IX86_BUILTIN_PCOMFALSEUD,(enum rtx_code) PCOM_FALSE,   (int)MULTI_ARG_2_SI_TF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pcom_tfv2di3,      "__builtin_ia32_pcomfalseuq",IX86_BUILTIN_PCOMFALSEUQ,(enum rtx_code) PCOM_FALSE,   (int)MULTI_ARG_2_DI_TF },
-
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pcom_tfv16qi3,     "__builtin_ia32_pcomtrueb",  IX86_BUILTIN_PCOMTRUEB,  (enum rtx_code) PCOM_TRUE,    (int)MULTI_ARG_2_QI_TF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pcom_tfv8hi3,      "__builtin_ia32_pcomtruew",  IX86_BUILTIN_PCOMTRUEW,  (enum rtx_code) PCOM_TRUE,    (int)MULTI_ARG_2_HI_TF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pcom_tfv4si3,      "__builtin_ia32_pcomtrued",  IX86_BUILTIN_PCOMTRUED,  (enum rtx_code) PCOM_TRUE,    (int)MULTI_ARG_2_SI_TF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pcom_tfv2di3,      "__builtin_ia32_pcomtrueq",  IX86_BUILTIN_PCOMTRUEQ,  (enum rtx_code) PCOM_TRUE,    (int)MULTI_ARG_2_DI_TF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pcom_tfv16qi3,     "__builtin_ia32_pcomtrueub", IX86_BUILTIN_PCOMTRUEUB, (enum rtx_code) PCOM_TRUE,    (int)MULTI_ARG_2_QI_TF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pcom_tfv8hi3,      "__builtin_ia32_pcomtrueuw", IX86_BUILTIN_PCOMTRUEUW, (enum rtx_code) PCOM_TRUE,    (int)MULTI_ARG_2_HI_TF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pcom_tfv4si3,      "__builtin_ia32_pcomtrueud", IX86_BUILTIN_PCOMTRUEUD, (enum rtx_code) PCOM_TRUE,    (int)MULTI_ARG_2_SI_TF },
-  { OPTION_MASK_ISA_SSE5, CODE_FOR_sse5_pcom_tfv2di3,      "__builtin_ia32_pcomtrueuq", IX86_BUILTIN_PCOMTRUEUQ, (enum rtx_code) PCOM_TRUE,    (int)MULTI_ARG_2_DI_TF },
-};
 
 /* Set up all the MMX/SSE builtins, even builtins for instructions that are not
    in the current target ISA to allow the user to compile particular modules
@@ -22863,88 +22070,6 @@ ix86_init_mmx_sse_builtins (void)
 				integer_type_node,
 				NULL_TREE);
 
-  /* SSE5 instructions */
-  tree v2di_ftype_v2di_v2di_v2di
-    = build_function_type_list (V2DI_type_node,
-				V2DI_type_node,
-				V2DI_type_node,
-				V2DI_type_node,
-				NULL_TREE);
-
-  tree v4si_ftype_v4si_v4si_v4si
-    = build_function_type_list (V4SI_type_node,
-				V4SI_type_node,
-				V4SI_type_node,
-				V4SI_type_node,
-				NULL_TREE);
-
-  tree v4si_ftype_v4si_v4si_v2di
-    = build_function_type_list (V4SI_type_node,
-				V4SI_type_node,
-				V4SI_type_node,
-				V2DI_type_node,
-				NULL_TREE);
-
-  tree v8hi_ftype_v8hi_v8hi_v8hi
-    = build_function_type_list (V8HI_type_node,
-				V8HI_type_node,
-				V8HI_type_node,
-				V8HI_type_node,
-				NULL_TREE);
-
-  tree v8hi_ftype_v8hi_v8hi_v4si
-    = build_function_type_list (V8HI_type_node,
-				V8HI_type_node,
-				V8HI_type_node,
-				V4SI_type_node,
-				NULL_TREE);
-
-  tree v2df_ftype_v2df_v2df_v16qi
-    = build_function_type_list (V2DF_type_node,
-				V2DF_type_node,
-				V2DF_type_node,
-				V16QI_type_node,
-				NULL_TREE);
-
-  tree v4sf_ftype_v4sf_v4sf_v16qi
-    = build_function_type_list (V4SF_type_node,
-				V4SF_type_node,
-				V4SF_type_node,
-				V16QI_type_node,
-				NULL_TREE);
-
-  tree v2di_ftype_v2di_si
-    = build_function_type_list (V2DI_type_node,
-				V2DI_type_node,
-				integer_type_node,
-				NULL_TREE);
-
-  tree v4si_ftype_v4si_si
-    = build_function_type_list (V4SI_type_node,
-				V4SI_type_node,
-				integer_type_node,
-				NULL_TREE);
-
-  tree v8hi_ftype_v8hi_si
-    = build_function_type_list (V8HI_type_node,
-				V8HI_type_node,
-				integer_type_node,
-				NULL_TREE);
-
-  tree v16qi_ftype_v16qi_si
-    = build_function_type_list (V16QI_type_node,
-				V16QI_type_node,
-				integer_type_node,
-				NULL_TREE);
-  tree v4sf_ftype_v4hi
-    = build_function_type_list (V4SF_type_node,
-				V4HI_type_node,
-				NULL_TREE);
-
-  tree v4hi_ftype_v4sf
-    = build_function_type_list (V4HI_type_node,
-				V4SF_type_node,
-				NULL_TREE);
 
   tree v2di_ftype_v2di
     = build_function_type_list (V2DI_type_node, V2DI_type_node, NULL_TREE);
@@ -23999,71 +23124,6 @@ ix86_init_mmx_sse_builtins (void)
 				    intQI_type_node,
 				    integer_type_node, NULL_TREE);
   def_builtin_const (OPTION_MASK_ISA_SSE4_1, "__builtin_ia32_vec_set_v16qi", ftype, IX86_BUILTIN_VEC_SET_V16QI);
-
-  /* Add SSE5 multi-arg argument instructions */
-  for (i = 0, d = bdesc_multi_arg; i < ARRAY_SIZE (bdesc_multi_arg); i++, d++)
-    {
-      tree mtype = NULL_TREE;
-
-      if (d->name == 0)
-	continue;
-
-      switch ((enum multi_arg_type)d->flag)
-	{
-	case MULTI_ARG_3_SF:     mtype = v4sf_ftype_v4sf_v4sf_v4sf; 	break;
-	case MULTI_ARG_3_DF:     mtype = v2df_ftype_v2df_v2df_v2df; 	break;
-	case MULTI_ARG_3_DI:     mtype = v2di_ftype_v2di_v2di_v2di; 	break;
-	case MULTI_ARG_3_SI:     mtype = v4si_ftype_v4si_v4si_v4si; 	break;
-	case MULTI_ARG_3_SI_DI:  mtype = v4si_ftype_v4si_v4si_v2di; 	break;
-	case MULTI_ARG_3_HI:     mtype = v8hi_ftype_v8hi_v8hi_v8hi; 	break;
-	case MULTI_ARG_3_HI_SI:  mtype = v8hi_ftype_v8hi_v8hi_v4si; 	break;
-	case MULTI_ARG_3_QI:     mtype = v16qi_ftype_v16qi_v16qi_v16qi; break;
-	case MULTI_ARG_3_PERMPS: mtype = v4sf_ftype_v4sf_v4sf_v16qi; 	break;
-	case MULTI_ARG_3_PERMPD: mtype = v2df_ftype_v2df_v2df_v16qi; 	break;
-	case MULTI_ARG_2_SF:     mtype = v4sf_ftype_v4sf_v4sf;      	break;
-	case MULTI_ARG_2_DF:     mtype = v2df_ftype_v2df_v2df;      	break;
-	case MULTI_ARG_2_DI:     mtype = v2di_ftype_v2di_v2di;      	break;
-	case MULTI_ARG_2_SI:     mtype = v4si_ftype_v4si_v4si;      	break;
-	case MULTI_ARG_2_HI:     mtype = v8hi_ftype_v8hi_v8hi;      	break;
-	case MULTI_ARG_2_QI:     mtype = v16qi_ftype_v16qi_v16qi;      	break;
-	case MULTI_ARG_2_DI_IMM: mtype = v2di_ftype_v2di_si;        	break;
-	case MULTI_ARG_2_SI_IMM: mtype = v4si_ftype_v4si_si;        	break;
-	case MULTI_ARG_2_HI_IMM: mtype = v8hi_ftype_v8hi_si;        	break;
-	case MULTI_ARG_2_QI_IMM: mtype = v16qi_ftype_v16qi_si;        	break;
-	case MULTI_ARG_2_SF_CMP: mtype = v4sf_ftype_v4sf_v4sf;      	break;
-	case MULTI_ARG_2_DF_CMP: mtype = v2df_ftype_v2df_v2df;      	break;
-	case MULTI_ARG_2_DI_CMP: mtype = v2di_ftype_v2di_v2di;      	break;
-	case MULTI_ARG_2_SI_CMP: mtype = v4si_ftype_v4si_v4si;      	break;
-	case MULTI_ARG_2_HI_CMP: mtype = v8hi_ftype_v8hi_v8hi;      	break;
-	case MULTI_ARG_2_QI_CMP: mtype = v16qi_ftype_v16qi_v16qi;      	break;
-	case MULTI_ARG_2_SF_TF:  mtype = v4sf_ftype_v4sf_v4sf;      	break;
-	case MULTI_ARG_2_DF_TF:  mtype = v2df_ftype_v2df_v2df;      	break;
-	case MULTI_ARG_2_DI_TF:  mtype = v2di_ftype_v2di_v2di;      	break;
-	case MULTI_ARG_2_SI_TF:  mtype = v4si_ftype_v4si_v4si;      	break;
-	case MULTI_ARG_2_HI_TF:  mtype = v8hi_ftype_v8hi_v8hi;      	break;
-	case MULTI_ARG_2_QI_TF:  mtype = v16qi_ftype_v16qi_v16qi;      	break;
-	case MULTI_ARG_1_SF:     mtype = v4sf_ftype_v4sf;           	break;
-	case MULTI_ARG_1_DF:     mtype = v2df_ftype_v2df;           	break;
-	case MULTI_ARG_1_DI:     mtype = v2di_ftype_v2di;           	break;
-	case MULTI_ARG_1_SI:     mtype = v4si_ftype_v4si;           	break;
-	case MULTI_ARG_1_HI:     mtype = v8hi_ftype_v8hi;           	break;
-	case MULTI_ARG_1_QI:     mtype = v16qi_ftype_v16qi;           	break;
-	case MULTI_ARG_1_SI_DI:  mtype = v2di_ftype_v4si;           	break;
-	case MULTI_ARG_1_HI_DI:  mtype = v2di_ftype_v8hi;           	break;
-	case MULTI_ARG_1_HI_SI:  mtype = v4si_ftype_v8hi;           	break;
-	case MULTI_ARG_1_QI_DI:  mtype = v2di_ftype_v16qi;           	break;
-	case MULTI_ARG_1_QI_SI:  mtype = v4si_ftype_v16qi;           	break;
-	case MULTI_ARG_1_QI_HI:  mtype = v8hi_ftype_v16qi;           	break;
-	case MULTI_ARG_1_PH2PS:  mtype = v4sf_ftype_v4hi;		break;
-	case MULTI_ARG_1_PS2PH:  mtype = v4hi_ftype_v4sf;		break;
-	case MULTI_ARG_UNKNOWN:
-	default:
-	  gcc_unreachable ();
-	}
-
-      if (mtype)
-	def_builtin_const (d->mask, d->name, mtype, d->code);
-    }
 }
 
 /* Internal method for ix86_init_builtins.  */
@@ -24236,182 +23296,6 @@ ix86_expand_binop_builtin (enum insn_code icode, tree exp, rtx target)
   return target;
 }
 
-/* Subroutine of ix86_expand_builtin to take care of 2-4 argument insns.  */
-
-static rtx
-ix86_expand_multi_arg_builtin (enum insn_code icode, tree exp, rtx target,
-			       enum multi_arg_type m_type,
-			       enum rtx_code sub_code)
-{
-  rtx pat;
-  int i;
-  int nargs;
-  bool comparison_p = false;
-  bool tf_p = false;
-  bool last_arg_constant = false;
-  int num_memory = 0;
-  struct {
-    rtx op;
-    enum machine_mode mode;
-  } args[4];
-
-  enum machine_mode tmode = insn_data[icode].operand[0].mode;
-
-  switch (m_type)
-    {
-    case MULTI_ARG_3_SF:
-    case MULTI_ARG_3_DF:
-    case MULTI_ARG_3_DI:
-    case MULTI_ARG_3_SI:
-    case MULTI_ARG_3_SI_DI:
-    case MULTI_ARG_3_HI:
-    case MULTI_ARG_3_HI_SI:
-    case MULTI_ARG_3_QI:
-    case MULTI_ARG_3_PERMPS:
-    case MULTI_ARG_3_PERMPD:
-      nargs = 3;
-      break;
-
-    case MULTI_ARG_2_SF:
-    case MULTI_ARG_2_DF:
-    case MULTI_ARG_2_DI:
-    case MULTI_ARG_2_SI:
-    case MULTI_ARG_2_HI:
-    case MULTI_ARG_2_QI:
-      nargs = 2;
-      break;
-
-    case MULTI_ARG_2_DI_IMM:
-    case MULTI_ARG_2_SI_IMM:
-    case MULTI_ARG_2_HI_IMM:
-    case MULTI_ARG_2_QI_IMM:
-      nargs = 2;
-      last_arg_constant = true;
-      break;
-
-    case MULTI_ARG_1_SF:
-    case MULTI_ARG_1_DF:
-    case MULTI_ARG_1_DI:
-    case MULTI_ARG_1_SI:
-    case MULTI_ARG_1_HI:
-    case MULTI_ARG_1_QI:
-    case MULTI_ARG_1_SI_DI:
-    case MULTI_ARG_1_HI_DI:
-    case MULTI_ARG_1_HI_SI:
-    case MULTI_ARG_1_QI_DI:
-    case MULTI_ARG_1_QI_SI:
-    case MULTI_ARG_1_QI_HI:
-    case MULTI_ARG_1_PH2PS:
-    case MULTI_ARG_1_PS2PH:
-      nargs = 1;
-      break;
-
-    case MULTI_ARG_2_SF_CMP:
-    case MULTI_ARG_2_DF_CMP:
-    case MULTI_ARG_2_DI_CMP:
-    case MULTI_ARG_2_SI_CMP:
-    case MULTI_ARG_2_HI_CMP:
-    case MULTI_ARG_2_QI_CMP:
-      nargs = 2;
-      comparison_p = true;
-      break;
-
-    case MULTI_ARG_2_SF_TF:
-    case MULTI_ARG_2_DF_TF:
-    case MULTI_ARG_2_DI_TF:
-    case MULTI_ARG_2_SI_TF:
-    case MULTI_ARG_2_HI_TF:
-    case MULTI_ARG_2_QI_TF:
-      nargs = 2;
-      tf_p = true;
-      break;
-
-    case MULTI_ARG_UNKNOWN:
-    default:
-      gcc_unreachable ();
-    }
-
-  if (optimize || !target
-      || GET_MODE (target) != tmode
-      || ! (*insn_data[icode].operand[0].predicate) (target, tmode))
-    target = gen_reg_rtx (tmode);
-
-  gcc_assert (nargs <= 4);
-
-  for (i = 0; i < nargs; i++)
-    {
-      tree arg = CALL_EXPR_ARG (exp, i);
-      rtx op = expand_normal (arg);
-      int adjust = (comparison_p) ? 1 : 0;
-      enum machine_mode mode = insn_data[icode].operand[i+adjust+1].mode;
-
-      if (last_arg_constant && i == nargs-1)
-	{
-	  if (!CONST_INT_P (op))
-	    {
-	      error ("last argument must be an immediate");
-	      return gen_reg_rtx (tmode);
-	    }
-	}
-      else
-	{
-	  if (VECTOR_MODE_P (mode))
-	    op = safe_vector_operand (op, mode);
-
-	  /* If we aren't optimizing, only allow one memory operand to be
-	     generated.  */
-	  if (memory_operand (op, mode))
-	    num_memory++;
-
-	  gcc_assert (GET_MODE (op) == mode || GET_MODE (op) == VOIDmode);
-
-	  if (optimize
-	      || ! (*insn_data[icode].operand[i+adjust+1].predicate) (op, mode)
-	      || num_memory > 1)
-	    op = force_reg (mode, op);
-	}
-
-      args[i].op = op;
-      args[i].mode = mode;
-    }
-
-  switch (nargs)
-    {
-    case 1:
-      pat = GEN_FCN (icode) (target, args[0].op);
-      break;
-
-    case 2:
-      if (tf_p)
-	pat = GEN_FCN (icode) (target, args[0].op, args[1].op,
-			       GEN_INT ((int)sub_code));
-      else if (! comparison_p)
-	pat = GEN_FCN (icode) (target, args[0].op, args[1].op);
-      else
-	{
-	  rtx cmp_op = gen_rtx_fmt_ee (sub_code, GET_MODE (target),
-				       args[0].op,
-				       args[1].op);
-
-	  pat = GEN_FCN (icode) (target, cmp_op, args[0].op, args[1].op);
-	}
-      break;
-
-    case 3:
-      pat = GEN_FCN (icode) (target, args[0].op, args[1].op, args[2].op);
-      break;
-
-    default:
-      gcc_unreachable ();
-    }
-
-  if (! pat)
-    return 0;
-
-  emit_insn (pat);
-  return target;
-}
-
 /* Subroutine of ix86_expand_args_builtin to take care of scalar unop
    insns with vec_merge.  */
 
@@ -25681,12 +24565,6 @@ ix86_expand_builtin (tree exp, rtx target, rtx subtarget ATTRIBUTE_UNUSED,
     if (d->code == fcode)
       return ix86_expand_sse_pcmpistr (d, exp, target);
 
-  for (i = 0, d = bdesc_multi_arg; i < ARRAY_SIZE (bdesc_multi_arg); i++, d++)
-    if (d->code == fcode)
-      return ix86_expand_multi_arg_builtin (d->icode, exp, target,
-					    (enum multi_arg_type)d->flag,
-					    d->comparison);
-
   gcc_unreachable ();
 }
 
@@ -28105,7 +26983,7 @@ ix86_expand_vector_init_one_nonzero (bool mmx_ok, enum machine_mode mode,
 	  if (mode != V4SFmode && TARGET_SSE2)
 	    {
 	      emit_insn (gen_sse2_pshufd_1 (new_target, new_target,
-					    GEN_INT (1),
+					    const1_rtx,
 					    GEN_INT (one_var == 1 ? 0 : 1),
 					    GEN_INT (one_var == 2 ? 0 : 1),
 					    GEN_INT (one_var == 3 ? 0 : 1)));
@@ -28125,7 +27003,7 @@ ix86_expand_vector_init_one_nonzero (bool mmx_ok, enum machine_mode mode,
 	    tmp = new_target;
 
 	  emit_insn (gen_sse_shufps_v4sf (tmp, tmp, tmp,
-				       GEN_INT (1),
+				       const1_rtx,
 				       GEN_INT (one_var == 1 ? 0 : 1),
 				       GEN_INT (one_var == 2 ? 0+4 : 1+4),
 				       GEN_INT (one_var == 3 ? 0+4 : 1+4)));
@@ -28788,8 +27666,8 @@ ix86_expand_vector_set (bool mmx_ok, rtx target, rtx val, int elt)
 	  ix86_expand_vector_set (false, target, val, 0);
 	  /* target = A X C D  */
 	  emit_insn (gen_sse_shufps_v4sf (target, target, tmp,
-				       GEN_INT (1), GEN_INT (0),
-				       GEN_INT (2+4), GEN_INT (3+4)));
+					  const1_rtx, const0_rtx,
+					  GEN_INT (2+4), GEN_INT (3+4)));
 	  return;
 
 	case 2:
@@ -28799,8 +27677,8 @@ ix86_expand_vector_set (bool mmx_ok, rtx target, rtx val, int elt)
 	  ix86_expand_vector_set (false, tmp, val, 0);
 	  /* target = A B X D */
 	  emit_insn (gen_sse_shufps_v4sf (target, target, tmp,
-				       GEN_INT (0), GEN_INT (1),
-				       GEN_INT (0+4), GEN_INT (3+4)));
+					  const0_rtx, const1_rtx,
+					  GEN_INT (0+4), GEN_INT (3+4)));
 	  return;
 
 	case 3:
@@ -28810,8 +27688,8 @@ ix86_expand_vector_set (bool mmx_ok, rtx target, rtx val, int elt)
 	  ix86_expand_vector_set (false, tmp, val, 0);
 	  /* target = A B X D */
 	  emit_insn (gen_sse_shufps_v4sf (target, target, tmp,
-				       GEN_INT (0), GEN_INT (1),
-				       GEN_INT (2+4), GEN_INT (0+4)));
+					  const0_rtx, const1_rtx,
+					  GEN_INT (2+4), GEN_INT (0+4)));
 	  return;
 
 	default:
@@ -29104,8 +27982,8 @@ ix86_expand_reduc_v4sf (rtx (*fn) (rtx, rtx, rtx), rtx dest, rtx in)
   emit_insn (fn (tmp2, tmp1, in));
 
   emit_insn (gen_sse_shufps_v4sf (tmp3, tmp2, tmp2,
-			       GEN_INT (1), GEN_INT (1),
-			       GEN_INT (1+4), GEN_INT (1+4)));
+				  const1_rtx, const1_rtx,
+				  GEN_INT (1+4), GEN_INT (1+4)));
   emit_insn (fn (dest, tmp2, tmp3));
 }
 
@@ -30068,200 +28946,6 @@ ix86_expand_round (rtx operand0, rtx operand1)
 
   emit_move_insn (operand0, res);
 }
-
-
-/* Validate whether a SSE5 instruction is valid or not.
-   OPERANDS is the array of operands.
-   NUM is the number of operands.
-   USES_OC0 is true if the instruction uses OC0 and provides 4 variants.
-   NUM_MEMORY is the maximum number of memory operands to accept.  
-   when COMMUTATIVE is set, operand 1 and 2 can be swapped.  */
-
-bool
-ix86_sse5_valid_op_p (rtx operands[], rtx insn ATTRIBUTE_UNUSED, int num,
-		      bool uses_oc0, int num_memory, bool commutative)
-{
-  int mem_mask;
-  int mem_count;
-  int i;
-
-  /* Count the number of memory arguments */
-  mem_mask = 0;
-  mem_count = 0;
-  for (i = 0; i < num; i++)
-    {
-      enum machine_mode mode = GET_MODE (operands[i]);
-      if (register_operand (operands[i], mode))
-	;
-
-      else if (memory_operand (operands[i], mode))
-	{
-	  mem_mask |= (1 << i);
-	  mem_count++;
-	}
-
-      else
-	{
-	  rtx pattern = PATTERN (insn);
-
-	  /* allow 0 for pcmov */
-	  if (GET_CODE (pattern) != SET
-	      || GET_CODE (SET_SRC (pattern)) != IF_THEN_ELSE
-	      || i < 2
-	      || operands[i] != CONST0_RTX (mode))
-	    return false;
-	}
-    }
-
-  /* Special case pmacsdq{l,h} where we allow the 3rd argument to be
-     a memory operation.  */
-  if (num_memory < 0)
-    {
-      num_memory = -num_memory;
-      if ((mem_mask & (1 << (num-1))) != 0)
-	{
-	  mem_mask &= ~(1 << (num-1));
-	  mem_count--;
-	}
-    }
-
-  /* If there were no memory operations, allow the insn */
-  if (mem_mask == 0)
-    return true;
-
-  /* Do not allow the destination register to be a memory operand.  */
-  else if (mem_mask & (1 << 0))
-    return false;
-
-  /* If there are too many memory operations, disallow the instruction.  While
-     the hardware only allows 1 memory reference, before register allocation
-     for some insns, we allow two memory operations sometimes in order to allow
-     code like the following to be optimized:
-
-	float fmadd (float *a, float *b, float *c) { return (*a * *b) + *c; }
-
-    or similar cases that are vectorized into using the fmaddss
-    instruction.  */
-  else if (mem_count > num_memory)
-    return false;
-
-  /* Don't allow more than one memory operation if not optimizing.  */
-  else if (mem_count > 1 && !optimize)
-    return false;
-
-  else if (num == 4 && mem_count == 1)
-    {
-      /* formats (destination is the first argument), example fmaddss:
-	 xmm1, xmm1, xmm2, xmm3/mem
-	 xmm1, xmm1, xmm2/mem, xmm3
-	 xmm1, xmm2, xmm3/mem, xmm1
-	 xmm1, xmm2/mem, xmm3, xmm1 */
-      if (uses_oc0)
-	return ((mem_mask == (1 << 1))
-		|| (mem_mask == (1 << 2))
-		|| (mem_mask == (1 << 3)));
-
-      /* format, example pmacsdd:
-	 xmm1, xmm2, xmm3/mem, xmm1 */
-      if (commutative)
-	return (mem_mask == (1 << 2) || mem_mask == (1 << 1));
-      else
-	return (mem_mask == (1 << 2));
-    }
-
-  else if (num == 4 && num_memory == 2)
-    {
-      /* If there are two memory operations, we can load one of the memory ops
-	 into the destination register.  This is for optimizing the
-	 multiply/add ops, which the combiner has optimized both the multiply
-	 and the add insns to have a memory operation.  We have to be careful
-	 that the destination doesn't overlap with the inputs.  */
-      rtx op0 = operands[0];
-
-      if (reg_mentioned_p (op0, operands[1])
-	  || reg_mentioned_p (op0, operands[2])
-	  || reg_mentioned_p (op0, operands[3]))
-	return false;
-
-      /* formats (destination is the first argument), example fmaddss:
-	 xmm1, xmm1, xmm2, xmm3/mem
-	 xmm1, xmm1, xmm2/mem, xmm3
-	 xmm1, xmm2, xmm3/mem, xmm1
-	 xmm1, xmm2/mem, xmm3, xmm1
-
-         For the oc0 case, we will load either operands[1] or operands[3] into
-         operands[0], so any combination of 2 memory operands is ok.  */
-      if (uses_oc0)
-	return true;
-
-      /* format, example pmacsdd:
-	 xmm1, xmm2, xmm3/mem, xmm1
-
-         For the integer multiply/add instructions be more restrictive and
-         require operands[2] and operands[3] to be the memory operands.  */
-      if (commutative)
-	return (mem_mask == ((1 << 1) | (1 << 3)) || ((1 << 2) | (1 << 3)));
-      else
-	return (mem_mask == ((1 << 2) | (1 << 3)));
-    }
-
-  else if (num == 3 && num_memory == 1)
-    {
-      /* formats, example protb:
-	 xmm1, xmm2, xmm3/mem
-	 xmm1, xmm2/mem, xmm3 */
-      if (uses_oc0)
-	return ((mem_mask == (1 << 1)) || (mem_mask == (1 << 2)));
-
-      /* format, example comeq:
-	 xmm1, xmm2, xmm3/mem */
-      else
-	return (mem_mask == (1 << 2));
-    }
-
-  else
-    gcc_unreachable ();
-
-  return false;
-}
-
-
-/* Fixup an SSE5 instruction that has 2 memory input references into a form the
-   hardware will allow by using the destination register to load one of the
-   memory operations.  Presently this is used by the multiply/add routines to
-   allow 2 memory references.  */
-
-void
-ix86_expand_sse5_multiple_memory (rtx operands[],
-				  int num,
-				  enum machine_mode mode)
-{
-  rtx op0 = operands[0];
-  if (num != 4
-      || memory_operand (op0, mode)
-      || reg_mentioned_p (op0, operands[1])
-      || reg_mentioned_p (op0, operands[2])
-      || reg_mentioned_p (op0, operands[3]))
-    gcc_unreachable ();
-
-  /* For 2 memory operands, pick either operands[1] or operands[3] to move into
-     the destination register.  */
-  if (memory_operand (operands[1], mode))
-    {
-      emit_move_insn (op0, operands[1]);
-      operands[1] = op0;
-    }
-  else if (memory_operand (operands[3], mode))
-    {
-      emit_move_insn (op0, operands[3]);
-      operands[3] = op0;
-    }
-  else
-    gcc_unreachable ();
-
-  return;
-}
-
 
 /* Table of valid machine attributes.  */
 static const struct attribute_spec ix86_attribute_table[] =
@@ -30491,6 +29175,9 @@ ix86_enum_va_list (int idx, const char **pname, tree *ptree)
 #undef TARGET_ASM_CLOSE_PAREN
 #define TARGET_ASM_CLOSE_PAREN ""
 
+#undef TARGET_ASM_BYTE_OP
+#define TARGET_ASM_BYTE_OP ASM_BYTE
+
 #undef TARGET_ASM_ALIGNED_HI_OP
 #define TARGET_ASM_ALIGNED_HI_OP ASM_SHORT
 #undef TARGET_ASM_ALIGNED_SI_OP
@@ -30676,6 +29363,9 @@ ix86_enum_va_list (int idx, const char **pname, tree *ptree)
 #undef TARGET_FRAME_POINTER_REQUIRED
 #define TARGET_FRAME_POINTER_REQUIRED ix86_frame_pointer_required
 
+#undef TARGET_CAN_ELIMINATE
+#define TARGET_CAN_ELIMINATE ix86_can_eliminate
+
 struct gcc_target targetm = TARGET_INITIALIZER;
 
 #include "gt-i386.h"
diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h
index 15ac4d38247..e898a651fc9 100644
--- a/gcc/config/i386/i386.h
+++ b/gcc/config/i386/i386.h
@@ -54,7 +54,6 @@ see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
 #define TARGET_AVX	OPTION_ISA_AVX
 #define TARGET_FMA	OPTION_ISA_FMA
 #define TARGET_SSE4A	OPTION_ISA_SSE4A
-#define TARGET_SSE5	OPTION_ISA_SSE5
 #define TARGET_ROUND	OPTION_ISA_ROUND
 #define TARGET_ABM	OPTION_ISA_ABM
 #define TARGET_POPCNT	OPTION_ISA_POPCNT
@@ -66,8 +65,8 @@ see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
 #define TARGET_CMPXCHG16B OPTION_ISA_CX16
 
 
-/* SSE5 and SSE4.1 define the same round instructions */
-#define	OPTION_MASK_ISA_ROUND	(OPTION_MASK_ISA_SSE4_1 | OPTION_MASK_ISA_SSE5)
+/* SSE4.1 define round instructions */
+#define	OPTION_MASK_ISA_ROUND	(OPTION_MASK_ISA_SSE4_1)
 #define	OPTION_ISA_ROUND	((ix86_isa_flags & OPTION_MASK_ISA_ROUND) != 0)
 
 #include "config/vxworks-dummy.h"
@@ -542,6 +541,10 @@ extern const char *host_detect_local_cpu (int argc, const char **argv);
 %<mcpu=* \
 %{mintel-syntax:-masm=intel \
 %n`-mintel-syntax' is deprecated. Use `-masm=intel' instead.\n} \
+%{msse5:-mavx \
+%n'-msse5' was removed.\n} \
+%{mfused-madd:-mavx \
+%n'-mfused-madd' was removed.\n} \
 %{mno-intel-syntax:-masm=att \
 %n`-mno-intel-syntax' is deprecated. Use `-masm=att' instead.\n}"
 
@@ -1684,11 +1687,6 @@ typedef struct ix86_args {
  { FRAME_POINTER_REGNUM, STACK_POINTER_REGNUM},		\
  { FRAME_POINTER_REGNUM, HARD_FRAME_POINTER_REGNUM}}	\
 
-/* Given FROM and TO register numbers, say whether this elimination is
-   allowed.   */
-
-#define CAN_ELIMINATE(FROM, TO) ix86_can_eliminate ((FROM), (TO))
-
 /* Define the offset between two registers, one to be eliminated, and the other
    its replacement, at the start of a routine.  */
 
diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index f50bcc19320..26bbc9a5234 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -57,7 +57,6 @@
 ;; X -- don't print any sort of PIC '@' suffix for a symbol.
 ;; & -- print some in-use local-dynamic symbol name.
 ;; H -- print a memory address offset by 8; used for sse high-parts
-;; Y -- print condition for SSE5 com* instruction.
 ;; + -- print a branch hint as 'cs' or 'ds' prefix
 ;; ; -- print a semicolon (after prefixes due to bug in older gas).
 
@@ -196,15 +195,6 @@
    (UNSPEC_PCMPESTR		144)
    (UNSPEC_PCMPISTR		145)
 
-   ;; For SSE5
-   (UNSPEC_SSE5_INTRINSIC	150)
-   (UNSPEC_SSE5_UNSIGNED_CMP	151)
-   (UNSPEC_SSE5_TRUEFALSE	152)
-   (UNSPEC_SSE5_PERMUTE		153)
-   (UNSPEC_FRCZ			154)
-   (UNSPEC_CVTPH2PS		155)
-   (UNSPEC_CVTPS2PH		156)
-
    ; For AES support
    (UNSPEC_AESENC		159)
    (UNSPEC_AESENCLAST		160)
@@ -259,20 +249,6 @@
    (COM_TRUE_P			5)
   ])
 
-;; Constants used in the SSE5 pperm instruction
-(define_constants
-  [(PPERM_SRC			0x00)	/* copy source */
-   (PPERM_INVERT		0x20)	/* invert source */
-   (PPERM_REVERSE		0x40)	/* bit reverse source */
-   (PPERM_REV_INV		0x60)	/* bit reverse & invert src */
-   (PPERM_ZERO			0x80)	/* all 0's */
-   (PPERM_ONES			0xa0)	/* all 1's */
-   (PPERM_SIGN			0xc0)	/* propagate sign bit */
-   (PPERM_INV_SIGN		0xe0)	/* invert & propagate sign */
-   (PPERM_SRC1			0x00)	/* use first source byte */
-   (PPERM_SRC2			0x10)	/* use second source byte */
-   ])
-
 ;; Registers by name.
 (define_constants
   [(AX_REG			 0)
@@ -465,7 +441,7 @@
 	]
 	(const_int 0)))
 
-;; There are also additional prefixes in 3DNOW, SSSE3 or SSE5.
+;; There are also additional prefixes in 3DNOW, SSSE3.
 ;; ssemuladd,sse4arg default to 0f24/0f25 and DREX byte,
 ;; sseiadd1,ssecvt1 to 0f7a with no DREX byte.
 ;; 3DNOW has 0f0f prefix, SSSE3 and SSE4_{1,2} 0f38/0f3a.
@@ -1555,7 +1531,7 @@
 #ifdef HAVE_AS_IX86_SAHF
   return "sahf";
 #else
-  return ".byte\t0x9e";
+  return ASM_BYTE "0x9e";
 #endif
 }
   [(set_attr "length" "1")
@@ -8879,8 +8855,6 @@
     || (SSE_FLOAT_MODE_P (<MODE>mode) && TARGET_SSE_MATH)"
   "")
 
-;; SSE5 scalar multiply/add instructions are defined in sse.md.
-
 
 ;; Divide instructions
 
@@ -14826,23 +14800,11 @@
 	(match_operator:MODEF 1 "sse_comparison_operator"
 	  [(match_operand:MODEF 2 "register_operand" "0")
 	   (match_operand:MODEF 3 "nonimmediate_operand" "xm")]))]
-  "SSE_FLOAT_MODE_P (<MODE>mode) && !TARGET_SSE5"
+  "SSE_FLOAT_MODE_P (<MODE>mode)"
   "cmp%D1s<ssemodefsuffix>\t{%3, %0|%0, %3}"
   [(set_attr "type" "ssecmp")
    (set_attr "length_immediate" "1")
    (set_attr "mode" "<MODE>")])
-
-(define_insn "*sse5_setcc<mode>"
-  [(set (match_operand:MODEF 0 "register_operand" "=x")
-	(match_operator:MODEF 1 "sse5_comparison_float_operator"
-	  [(match_operand:MODEF 2 "register_operand" "x")
-	   (match_operand:MODEF 3 "nonimmediate_operand" "xm")]))]
-  "TARGET_SSE5"
-  "com%Y1s<ssemodefsuffix>\t{%3, %2, %0|%0, %2, %3}"
-  [(set_attr "type" "sse4arg")
-   (set_attr "length_immediate" "1")
-   (set_attr "mode" "<MODE>")])
-
 
 ;; Basic conditional jump instructions.
 ;; We ignore the overflow flag for signed branch instructions.
@@ -15476,22 +15438,25 @@
 	 (match_operand:SI 1 "" ""))
    (set (reg:SI SP_REG) (plus:SI (reg:SI SP_REG)
 			    (match_operand:SI 2 "immediate_operand" "i")))]
-  "!TARGET_64BIT"
+  "!SIBLING_CALL_P (insn) && !TARGET_64BIT"
 {
   if (constant_call_address_operand (operands[0], Pmode))
-    {
-      if (SIBLING_CALL_P (insn))
-	return "jmp\t%P0";
-      else
-	return "call\t%P0";
-    }
-  if (SIBLING_CALL_P (insn))
-    return "jmp\t%A0";
-  else
-    return "call\t%A0";
+    return "call\t%P0";
+  return "call\t%A0";
 }
   [(set_attr "type" "call")])
 
+(define_insn "*sibcall_pop_1"
+  [(call (mem:QI (match_operand:SI 0 "sibcall_insn_operand" "s,U"))
+	 (match_operand:SI 1 "" ""))
+   (set (reg:SI SP_REG) (plus:SI (reg:SI SP_REG)
+			    (match_operand:SI 2 "immediate_operand" "i,i")))]
+  "SIBLING_CALL_P (insn) && !TARGET_64BIT"
+  "@
+   jmp\t%P0
+   jmp\t%A0"
+  [(set_attr "type" "call")])
+
 (define_expand "call"
   [(call (match_operand:QI 0 "" "")
 	 (match_operand 1 "" ""))
@@ -16473,7 +16438,7 @@
    (unspec:DI [(match_operand:DI 1 "tls_symbolic_operand" "")]
 	      UNSPEC_TLS_GD)]
   "TARGET_64BIT"
-  { return ".byte\t0x66\n\tlea{q}\t{%a1@TLSGD(%%rip), %%rdi|rdi, %a1@TLSGD[rip]}\n" ASM_SHORT "0x6666\n\trex64\n\tcall\t%P2"; }
+  { return ASM_BYTE "0x66\n\tlea{q}\t{%a1@TLSGD(%%rip), %%rdi|rdi, %a1@TLSGD[rip]}\n" ASM_SHORT "0x6666\n\trex64\n\tcall\t%P2"; }
   [(set_attr "type" "multi")
    (set_attr "length" "16")])
 
@@ -20640,20 +20605,6 @@
   [(set_attr "type" "fcmov")
    (set_attr "mode" "XF")])
 
-;; All moves in SSE5 pcmov instructions are 128 bits and hence we restrict
-;; the scalar versions to have only XMM registers as operands.
-
-;; SSE5 conditional move
-(define_insn "*sse5_pcmov_<mode>"
-  [(set (match_operand:MODEF 0 "register_operand" "=x,x")
-	(if_then_else:MODEF
-	  (match_operand:MODEF 1 "register_operand" "x,0")
-	  (match_operand:MODEF 2 "register_operand" "0,x")
-	  (match_operand:MODEF 3 "register_operand" "x,x")))]
-  "TARGET_SSE5 && ix86_sse5_valid_op_p (operands, insn, 4, true, 1, false)"
-  "pcmov\t{%1, %3, %2, %0|%0, %2, %3, %1}"
-  [(set_attr "type" "sse4arg")])
-
 ;; These versions of the min/max patterns are intentionally ignorant of
 ;; their behavior wrt -0.0 and NaN (via the commutative operand mark).
 ;; Since both the tree-level MAX_EXPR and the rtl-level SMAX operator
@@ -22092,22 +22043,26 @@
 	      (match_operand:SI 2 "" "")))
    (set (reg:SI SP_REG) (plus:SI (reg:SI SP_REG)
 			    (match_operand:SI 3 "immediate_operand" "i")))]
-  "!TARGET_64BIT"
+  "!SIBLING_CALL_P (insn) && !TARGET_64BIT"
 {
   if (constant_call_address_operand (operands[1], Pmode))
-    {
-      if (SIBLING_CALL_P (insn))
-	return "jmp\t%P1";
-      else
-	return "call\t%P1";
-    }
-  if (SIBLING_CALL_P (insn))
-    return "jmp\t%A1";
-  else
-    return "call\t%A1";
+    return "call\t%P1";
+  return "call\t%A1";
 }
   [(set_attr "type" "callv")])
 
+(define_insn "*sibcall_value_pop_1"
+  [(set (match_operand 0 "" "")
+	(call (mem:QI (match_operand:SI 1 "sibcall_insn_operand" "s,U"))
+	      (match_operand:SI 2 "" "")))
+   (set (reg:SI SP_REG) (plus:SI (reg:SI SP_REG)
+			    (match_operand:SI 3 "immediate_operand" "i,i")))]
+  "SIBLING_CALL_P (insn) && !TARGET_64BIT"
+  "@
+   jmp\t%P1
+   jmp\t%A1"
+  [(set_attr "type" "callv")])
+
 (define_insn "*call_value_0"
   [(set (match_operand 0 "" "")
 	(call (mem:QI (match_operand:SI 1 "constant_call_address_operand" ""))
diff --git a/gcc/config/i386/i386.opt b/gcc/config/i386/i386.opt
index 9ec93d8c2a8..f23763b8cf6 100644
--- a/gcc/config/i386/i386.opt
+++ b/gcc/config/i386/i386.opt
@@ -244,15 +244,6 @@ mcld
 Target Report Mask(CLD) Save
 Generate cld instruction in the function prologue.
 
-mno-fused-madd
-Target RejectNegative Report Mask(NO_FUSED_MADD) Undocumented Save
-
-mfused-madd
-Target Report InverseMask(NO_FUSED_MADD, FUSED_MADD) Save
-Enable automatic generation of fused floating point multiply-add instructions
-if the ISA supports such instructions.  The -mfused-madd option is on by
-default.
-
 ;; ISA support
 
 m32
@@ -319,10 +310,6 @@ msse4a
 Target Report Mask(ISA_SSE4A) Var(ix86_isa_flags) VarExists Save
 Support MMX, SSE, SSE2, SSE3 and SSE4A built-in functions and code generation
 
-msse5
-Target Report Mask(ISA_SSE5) Var(ix86_isa_flags) VarExists Save
-Support SSE5 built-in functions and code generation
-
 mabm
 Target Report Mask(ISA_ABM) Var(ix86_isa_flags) VarExists Save
 Support code generation of Advanced Bit Manipulation (ABM) instructions.
diff --git a/gcc/config/i386/i386elf.h b/gcc/config/i386/i386elf.h
index ba53749acc9..44cf6818f7c 100644
--- a/gcc/config/i386/i386elf.h
+++ b/gcc/config/i386/i386elf.h
@@ -63,7 +63,7 @@ along with GCC; see the file COPYING3.  If not see
       const unsigned char *limit = _ascii_bytes + (LENGTH);		\
       unsigned bytes_in_chunk = 0;					\
       for (; _ascii_bytes < limit; _ascii_bytes++)			\
-        {								\
+	{								\
 	  const unsigned char *p;					\
 	  if (bytes_in_chunk >= 64)					\
 	    {								\
@@ -85,7 +85,7 @@ along with GCC; see the file COPYING3.  If not see
 	  else								\
 	    {								\
 	      if (bytes_in_chunk == 0)					\
-		fprintf ((FILE), "\t.byte\t");				\
+		fputs (ASM_BYTE, (FILE));				\
 	      else							\
 		fputc (',', (FILE));					\
 	      fprintf ((FILE), "0x%02x", *_ascii_bytes);		\
@@ -93,7 +93,7 @@ along with GCC; see the file COPYING3.  If not see
 	    }								\
 	}								\
       if (bytes_in_chunk > 0)						\
-        fprintf ((FILE), "\n");						\
+	fputc ('\n', (FILE));						\
     }									\
   while (0)
 
diff --git a/gcc/config/i386/mmintrin-common.h b/gcc/config/i386/mmintrin-common.h
index 0054168cc00..25fd6aa6392 100644
--- a/gcc/config/i386/mmintrin-common.h
+++ b/gcc/config/i386/mmintrin-common.h
@@ -21,14 +21,13 @@
    see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
    <http://www.gnu.org/licenses/>.  */
 
-/* Common definition of the ROUND and PTEST intrinsics that are shared
-   between SSE4.1 and SSE5.  */
+/* Common definition of the ROUND and PTEST intrinsics, SSE4.1.  */
 
 #ifndef _MMINTRIN_COMMON_H_INCLUDED
 #define _MMINTRIN_COMMON_H_INCLUDED
 
-#if !defined(__SSE5__) && !defined(__SSE4_1__)
-# error "SSE5 or SSE4.1 instruction set not enabled"
+#if !defined(__SSE4_1__)
+# error "SSE4.1 instruction set not enabled"
 #else
 
 /* Rounding mode macros. */
@@ -150,6 +149,6 @@ _mm_round_ss (__m128 __D, __m128 __V, const int __M)
 #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)
 
-#endif /* __SSE5__/__SSE4_1__ */
+#endif /* __SSE4_1__ */
 
 #endif /* _MMINTRIN_COMMON_H_INCLUDED */
diff --git a/gcc/config/i386/msformat-c.c b/gcc/config/i386/msformat-c.c
index d7eb42d9c3c..020cdb3c897 100644
--- a/gcc/config/i386/msformat-c.c
+++ b/gcc/config/i386/msformat-c.c
@@ -36,12 +36,12 @@ along with GCC; see the file COPYING3.  If not see
 
 static format_length_info ms_printf_length_specs[] =
 {
-  { "h", FMT_LEN_h, STD_C89, NULL, FMT_LEN_none, STD_C89 },
-  { "l", FMT_LEN_l, STD_C89, NULL, FMT_LEN_none, STD_C89 },
-  { "I32", FMT_LEN_l, STD_EXT, NULL, FMT_LEN_none, STD_C89 },
-  { "I64", FMT_LEN_ll, STD_EXT, NULL, FMT_LEN_none, STD_C89 },
-  { "I", FMT_LEN_L, STD_EXT, NULL, FMT_LEN_none, STD_C89 },
-  { NULL, FMT_LEN_none, STD_C89, NULL, FMT_LEN_none, STD_C89 }
+  { "h", FMT_LEN_h, STD_C89, NULL, FMT_LEN_none, STD_C89, 0 },
+  { "l", FMT_LEN_l, STD_C89, NULL, FMT_LEN_none, STD_C89, 0 },
+  { "I32", FMT_LEN_l, STD_EXT, NULL, FMT_LEN_none, STD_C89, 1 },
+  { "I64", FMT_LEN_ll, STD_EXT, NULL, FMT_LEN_none, STD_C89, 1 },
+  { "I", FMT_LEN_L, STD_EXT, NULL, FMT_LEN_none, STD_C89, 0 },
+  { NULL, FMT_LEN_none, STD_C89, NULL, FMT_LEN_none, STD_C89, 0 }
 };
 
 static const format_flag_spec ms_printf_flag_specs[] =
diff --git a/gcc/config/i386/netware.c b/gcc/config/i386/netware.c
index 7f040d4b0e0..fa9ffbbeac1 100644
--- a/gcc/config/i386/netware.c
+++ b/gcc/config/i386/netware.c
@@ -30,6 +30,7 @@ along with GCC; see the file COPYING3.  If not see
 #include "flags.h"
 #include "tm_p.h"
 #include "toplev.h"
+#include "langhooks.h"
 #include "ggc.h"
 
 /* Return string which is the function name, identified by ID, modified
@@ -179,16 +180,15 @@ i386_nlm_encode_section_info (tree decl, rtx rtl, int first)
 {
   default_encode_section_info (decl, rtl, first);
 
-  if (first
-      && TREE_CODE (decl) == FUNCTION_DECL
+  if (TREE_CODE (decl) == FUNCTION_DECL
       /* Do not change the identifier if a verbatim asmspec
 	 or if stdcall suffix already added.  */
       && *IDENTIFIER_POINTER (DECL_ASSEMBLER_NAME (decl)) != '*'
-      && !strchr (IDENTIFIER_POINTER (DECL_ASSEMBLER_NAME (decl)), '@'))
+      && !strchr (IDENTIFIER_POINTER (DECL_ASSEMBLER_NAME (decl)), '@')
+      /* FIXME:  Imported stdcall names are not modified by the Ada frontend.
+	 Check and decorate the RTL name now.  */
+      && strcmp (lang_hooks.name, "GNU Ada") == 0)
     {
-      /* FIXME: In Ada, and perhaps other language frontends,
-	 imported stdcall names may not yet have been modified.
-	 Check and do it know.  */
       rtx symbol = XEXP (rtl, 0);
       tree new_id;
       tree old_id = DECL_ASSEMBLER_NAME (decl);
@@ -196,14 +196,7 @@ i386_nlm_encode_section_info (tree decl, rtx rtl, int first)
       gcc_assert (GET_CODE (symbol) == SYMBOL_REF);
 
       if ((new_id = i386_nlm_maybe_mangle_decl_assembler_name (decl, old_id)))
-	{
-	  /* These attributes must be present on first declaration,
-	     change_decl_assembler_name will warn if they are added
-	     later and the decl has been referenced, but duplicate_decls
-	     should catch the mismatch first.  */
-	  change_decl_assembler_name (decl, new_id);
-	  XSTR (symbol, 0) = IDENTIFIER_POINTER (DECL_ASSEMBLER_NAME (decl));
-	}
+	XSTR (symbol, 0) = IDENTIFIER_POINTER (new_id);
     }
 }
 
@@ -233,24 +226,3 @@ i386_nlm_strip_name_encoding (const char *str)
     }
   return name;
 }
-
-/* Sometimes certain combinations of command options do not make
-   sense on a particular target machine.  You can define a macro
-   `OVERRIDE_OPTIONS' to take account of this.  This macro, if
-   defined, is executed once just after all the command options have
-   been parsed.
-
-   Don't use this macro to turn on various extra optimizations for
-   `-O'.  That is what `OPTIMIZATION_OPTIONS' is for.  */
-
-void
-netware_override_options (void)
-{
-  override_options ();
-
-  if (flag_pic)
-    {
-      error ("-fPIC and -fpic are not supported for this target");
-      flag_pic = 0;
-    }
-}
diff --git a/gcc/config/i386/netware.h b/gcc/config/i386/netware.h
index 4f1ef5588af..6b423e36fc1 100644
--- a/gcc/config/i386/netware.h
+++ b/gcc/config/i386/netware.h
@@ -72,17 +72,16 @@ along with GCC; see the file COPYING3.  If not see
 #define TARGET_SUBTARGET_DEFAULT (MASK_80387 | MASK_IEEE_FP | \
 	MASK_FLOAT_RETURNS | MASK_ALIGN_DOUBLE | MASK_MS_BITFIELD_LAYOUT)
 
-/* Sometimes certain combinations of command options do not make
-   sense on a particular target machine.  You can define a macro
-   `OVERRIDE_OPTIONS' to take account of this.  This macro, if
-   defined, is executed once just after all the command options have
-   been parsed.
-
-   Don't use this macro to turn on various extra optimizations for
-   `-O'.  That is what `OPTIMIZATION_OPTIONS' is for.  */
-#undef  OVERRIDE_OPTIONS
-extern void netware_override_options (void);
-#define OVERRIDE_OPTIONS netware_override_options ()
+/* Don't allow flag_pic to propagate since invalid relocations will
+   result otherwise.  */
+#define SUBTARGET_OVERRIDE_OPTIONS					\
+do {									\
+  if (flag_pic)								\
+    {									\
+      error ("-fPIC and -fpic are not supported for this target");	\
+      flag_pic = 0;							\
+    }									\
+} while (0)
 
 #undef MATH_LIBRARY
 #define MATH_LIBRARY ""
@@ -99,6 +98,9 @@ extern void netware_override_options (void);
 #undef KEEP_AGGREGATE_RETURN_POINTER
 #define KEEP_AGGREGATE_RETURN_POINTER 1
 
+#undef ASM_COMMENT_START
+#define ASM_COMMENT_START "#"
+
 #undef DBX_REGISTER_NUMBER
 #define DBX_REGISTER_NUMBER(n) (svr4_dbx_register_map[n])
 
diff --git a/gcc/config/i386/nwld.h b/gcc/config/i386/nwld.h
index be41e96e19a..3a0afc8b63d 100644
--- a/gcc/config/i386/nwld.h
+++ b/gcc/config/i386/nwld.h
@@ -55,6 +55,13 @@ void nwld_named_section_asm_out_destructor (rtx, int);
 #define TARGET_ASM_CONSTRUCTOR nwld_named_section_asm_out_constructor
 #define TARGET_ASM_DESTRUCTOR  nwld_named_section_asm_out_destructor
 
+#define SUBSUBTARGET_OVERRIDE_OPTIONS					\
+do {									\
+  /* XXX This can be enabled once gas output meets nwld's needs. */	\
+  /* if (!flag_unwind_tables && !flag_exceptions) */			\
+    flag_dwarf2_cfi_asm = 0;						\
+} while (0)
+
 #undef  EH_FRAME_SECTION_NAME
 #define EH_FRAME_SECTION_NAME ".eh_frame"TARGET_SUB_SECTION_SEPARATOR
 
diff --git a/gcc/config/i386/predicates.md b/gcc/config/i386/predicates.md
index 2a4b61d8615..f9a4744d1de 100644
--- a/gcc/config/i386/predicates.md
+++ b/gcc/config/i386/predicates.md
@@ -988,12 +988,6 @@
 (define_predicate "avx_comparison_float_operator"
   (match_code "ne,eq,ge,gt,le,lt,unordered,ordered,uneq,unge,ungt,unle,unlt,ltgt"))
 
-;; Return 1 if OP is a comparison operator that can be issued by sse predicate
-;; generation instructions
-(define_predicate "sse5_comparison_float_operator"
-  (and (match_test "TARGET_SSE5")
-       (match_code "ne,eq,ge,gt,le,lt,unordered,ordered,uneq,unge,ungt,unle,unlt,ltgt")))
-
 (define_predicate "ix86_comparison_int_operator"
   (match_code "ne,eq,ge,gt,le,lt"))
 
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index 43ec67a9c10..2ddbbf551de 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -64,21 +64,21 @@
 (define_mode_iterator SSEMODE4S [V4SF V4SI])
 (define_mode_iterator SSEMODE2D [V2DF V2DI])
 
+;; Modes handled by integer vcond pattern
+(define_mode_iterator SSEMODE124C8 [V16QI V8HI V4SI
+				    (V2DI "TARGET_SSE4_2")])
+
 ;; Mapping from float mode to required SSE level
 (define_mode_attr sse [(SF "sse") (DF "sse2") (V4SF "sse") (V2DF "sse2")])
 
 ;; Mapping from integer vector mode to mnemonic suffix
 (define_mode_attr ssevecsize [(V16QI "b") (V8HI "w") (V4SI "d") (V2DI "q")])
 
-;; Mapping of the sse5 suffix
+;; Mapping of the avx suffix
 (define_mode_attr ssemodesuffixf4 [(SF "ss") (DF "sd")
 				   (V4SF "ps") (V2DF "pd")])
-(define_mode_attr ssemodesuffixf2s [(SF "ss") (DF "sd")
-				    (V4SF "ss") (V2DF "sd")])
-(define_mode_attr ssemodesuffixf2c [(V4SF "s") (V2DF "d")])
 
-;; Mapping of the max integer size for sse5 rotate immediate constraint
-(define_mode_attr sserotatemax [(V16QI "7") (V8HI "15") (V4SI "31") (V2DI "63")])
+(define_mode_attr ssemodesuffixf2c [(V4SF "s") (V2DF "d")])
 
 ;; Mapping of vector modes back to the scalar modes
 (define_mode_attr ssescalarmode [(V4SF "SF") (V2DF "DF")
@@ -1449,8 +1449,7 @@
 	(match_operator:SSEMODEF4 3 "sse_comparison_operator"
 		[(match_operand:SSEMODEF4 1 "register_operand" "0")
 		 (match_operand:SSEMODEF4 2 "nonimmediate_operand" "xm")]))]
-  "(SSE_FLOAT_MODE_P (<MODE>mode) || SSE_VEC_FLOAT_MODE_P (<MODE>mode))
-   && !TARGET_SSE5"
+  "(SSE_FLOAT_MODE_P (<MODE>mode) || SSE_VEC_FLOAT_MODE_P (<MODE>mode))"
   "cmp%D3<ssemodesuffixf4>\t{%2, %0|%0, %2}"
   [(set_attr "type" "ssecmp")
    (set_attr "length_immediate" "1")
@@ -1464,7 +1463,7 @@
 		 (match_operand:SSEMODEF2P 2 "nonimmediate_operand" "xm")])
 	 (match_dup 1)
 	 (const_int 1)))]
-  "SSE_VEC_FLOAT_MODE_P (<MODE>mode) && !TARGET_SSE5"
+  "SSE_VEC_FLOAT_MODE_P (<MODE>mode)"
   "cmp%D3s<ssemodesuffixf2c>\t{%2, %0|%0, %2}"
   [(set_attr "type" "ssecmp")
    (set_attr "length_immediate" "1")
@@ -1520,10 +1519,9 @@
           (match_operand:SSEMODEF2P 2 "general_operand" "")))]
   "SSE_VEC_FLOAT_MODE_P (<MODE>mode)"
 {
-  if (ix86_expand_fp_vcond (operands))
-    DONE;
-  else
-    FAIL;
+  bool ok = ix86_expand_fp_vcond (operands);
+  gcc_assert (ok);
+  DONE;
 })
 
 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
@@ -1663,563 +1661,6 @@
 
 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 ;;
-;; SSE5 floating point multiply/accumulate instructions This includes the
-;; scalar version of the instructions as well as the vector
-;;
-;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
-
-;; In order to match (*a * *b) + *c, particularly when vectorizing, allow
-;; combine to generate a multiply/add with two memory references.  We then
-;; split this insn, into loading up the destination register with one of the
-;; memory operations.  If we don't manage to split the insn, reload will
-;; generate the appropriate moves.  The reason this is needed, is that combine
-;; has already folded one of the memory references into both the multiply and
-;; add insns, and it can't generate a new pseudo.  I.e.:
-;;	(set (reg1) (mem (addr1)))
-;;	(set (reg2) (mult (reg1) (mem (addr2))))
-;;	(set (reg3) (plus (reg2) (mem (addr3))))
-
-(define_insn "sse5_fmadd<mode>4"
-  [(set (match_operand:SSEMODEF4 0 "register_operand" "=x,x,x,x")
-	(plus:SSEMODEF4
-	 (mult:SSEMODEF4
-	  (match_operand:SSEMODEF4 1 "nonimmediate_operand" "%0,0,x,xm")
-	  (match_operand:SSEMODEF4 2 "nonimmediate_operand" "x,xm,xm,x"))
-	 (match_operand:SSEMODEF4 3 "nonimmediate_operand" "xm,x,0,0")))]
-  "TARGET_SSE5 && TARGET_FUSED_MADD
-   && ix86_sse5_valid_op_p (operands, insn, 4, true, 2, true)"
-  "fmadd<ssemodesuffixf4>\t{%3, %2, %1, %0|%0, %1, %2, %3}"
-  [(set_attr "type" "ssemuladd")
-   (set_attr "mode" "<MODE>")])
-
-;; Split fmadd with two memory operands into a load and the fmadd.
-(define_split
-  [(set (match_operand:SSEMODEF4 0 "register_operand" "")
-	(plus:SSEMODEF4
-	 (mult:SSEMODEF4
-	  (match_operand:SSEMODEF4 1 "nonimmediate_operand" "")
-	  (match_operand:SSEMODEF4 2 "nonimmediate_operand" ""))
-	 (match_operand:SSEMODEF4 3 "nonimmediate_operand" "")))]
-  "TARGET_SSE5
-   && !ix86_sse5_valid_op_p (operands, insn, 4, true, 1, true)
-   && ix86_sse5_valid_op_p (operands, insn, 4, true, 2, true)
-   && !reg_mentioned_p (operands[0], operands[1])
-   && !reg_mentioned_p (operands[0], operands[2])
-   && !reg_mentioned_p (operands[0], operands[3])"
-  [(const_int 0)]
-{
-  ix86_expand_sse5_multiple_memory (operands, 4, <MODE>mode);
-  emit_insn (gen_sse5_fmadd<mode>4 (operands[0], operands[1],
-				    operands[2], operands[3]));
-  DONE;
-})
-
-;; For the scalar operations, use operand1 for the upper words that aren't
-;; modified, so restrict the forms that are generated.
-;; Scalar version of fmadd
-(define_insn "sse5_vmfmadd<mode>4"
-  [(set (match_operand:SSEMODEF2P 0 "register_operand" "=x,x")
-	(vec_merge:SSEMODEF2P
-	 (plus:SSEMODEF2P
-	  (mult:SSEMODEF2P
-	   (match_operand:SSEMODEF2P 1 "nonimmediate_operand" "0,0")
-	   (match_operand:SSEMODEF2P 2 "nonimmediate_operand" "x,xm"))
-	  (match_operand:SSEMODEF2P 3 "nonimmediate_operand" "xm,x"))
-	 (match_dup 1)
-	 (const_int 1)))]
-  "TARGET_SSE5 && TARGET_FUSED_MADD
-   && ix86_sse5_valid_op_p (operands, insn, 4, true, 1, true)"
-  "fmadd<ssemodesuffixf2s>\t{%3, %2, %1, %0|%0, %1, %2, %3}"
-  [(set_attr "type" "ssemuladd")
-   (set_attr "mode" "<MODE>")])
-
-;; Floating multiply and subtract
-;; Allow two memory operands the same as fmadd
-(define_insn "sse5_fmsub<mode>4"
-  [(set (match_operand:SSEMODEF4 0 "register_operand" "=x,x,x,x")
-	(minus:SSEMODEF4
-	 (mult:SSEMODEF4
-	  (match_operand:SSEMODEF4 1 "nonimmediate_operand" "%0,0,x,xm")
-	  (match_operand:SSEMODEF4 2 "nonimmediate_operand" "x,xm,xm,x"))
-	 (match_operand:SSEMODEF4 3 "nonimmediate_operand" "xm,x,0,0")))]
-  "TARGET_SSE5 && TARGET_FUSED_MADD
-   && ix86_sse5_valid_op_p (operands, insn, 4, true, 2, true)"
-  "fmsub<ssemodesuffixf4>\t{%3, %2, %1, %0|%0, %1, %2, %3}"
-  [(set_attr "type" "ssemuladd")
-   (set_attr "mode" "<MODE>")])
-
-;; Split fmsub with two memory operands into a load and the fmsub.
-(define_split
-  [(set (match_operand:SSEMODEF4 0 "register_operand" "")
-	(minus:SSEMODEF4
-	 (mult:SSEMODEF4
-	  (match_operand:SSEMODEF4 1 "nonimmediate_operand" "")
-	  (match_operand:SSEMODEF4 2 "nonimmediate_operand" ""))
-	 (match_operand:SSEMODEF4 3 "nonimmediate_operand" "")))]
-  "TARGET_SSE5
-   && !ix86_sse5_valid_op_p (operands, insn, 4, true, 1, true)
-   && ix86_sse5_valid_op_p (operands, insn, 4, true, 2, true)
-   && !reg_mentioned_p (operands[0], operands[1])
-   && !reg_mentioned_p (operands[0], operands[2])
-   && !reg_mentioned_p (operands[0], operands[3])"
-  [(const_int 0)]
-{
-  ix86_expand_sse5_multiple_memory (operands, 4, <MODE>mode);
-  emit_insn (gen_sse5_fmsub<mode>4 (operands[0], operands[1],
-				    operands[2], operands[3]));
-  DONE;
-})
-
-;; For the scalar operations, use operand1 for the upper words that aren't
-;; modified, so restrict the forms that are generated.
-;; Scalar version of fmsub
-(define_insn "sse5_vmfmsub<mode>4"
-  [(set (match_operand:SSEMODEF2P 0 "register_operand" "=x,x")
-	(vec_merge:SSEMODEF2P
-	 (minus:SSEMODEF2P
-	  (mult:SSEMODEF2P
-	   (match_operand:SSEMODEF2P 1 "nonimmediate_operand" "0,0")
-	   (match_operand:SSEMODEF2P 2 "nonimmediate_operand" "x,xm"))
-	  (match_operand:SSEMODEF2P 3 "nonimmediate_operand" "xm,x"))
-	 (match_dup 1)
-	 (const_int 1)))]
-  "TARGET_SSE5 && TARGET_FUSED_MADD
-   && ix86_sse5_valid_op_p (operands, insn, 4, true, 1, false)"
-  "fmsub<ssemodesuffixf2s>\t{%3, %2, %1, %0|%0, %1, %2, %3}"
-  [(set_attr "type" "ssemuladd")
-   (set_attr "mode" "<MODE>")])
-
-;; Floating point negative multiply and add
-;; Rewrite (- (a * b) + c) into the canonical form: c - (a * b)
-;; Note operands are out of order to simplify call to ix86_sse5_valid_p
-;; Allow two memory operands to help in optimizing.
-(define_insn "sse5_fnmadd<mode>4"
-  [(set (match_operand:SSEMODEF4 0 "register_operand" "=x,x,x,x")
-	(minus:SSEMODEF4
-	 (match_operand:SSEMODEF4 3 "nonimmediate_operand" "xm,x,0,0")
-	 (mult:SSEMODEF4
-	  (match_operand:SSEMODEF4 1 "nonimmediate_operand" "%0,0,x,xm")
-	  (match_operand:SSEMODEF4 2 "nonimmediate_operand" "x,xm,xm,x"))))]
-  "TARGET_SSE5 && TARGET_FUSED_MADD
-   && ix86_sse5_valid_op_p (operands, insn, 4, true, 2, true)"
-  "fnmadd<ssemodesuffixf4>\t{%3, %2, %1, %0|%0, %1, %2, %3}"
-  [(set_attr "type" "ssemuladd")
-   (set_attr "mode" "<MODE>")])
-
-;; Split fnmadd with two memory operands into a load and the fnmadd.
-(define_split
-  [(set (match_operand:SSEMODEF4 0 "register_operand" "")
-	(minus:SSEMODEF4
-	 (match_operand:SSEMODEF4 3 "nonimmediate_operand" "")
-	 (mult:SSEMODEF4
-	  (match_operand:SSEMODEF4 1 "nonimmediate_operand" "")
-	  (match_operand:SSEMODEF4 2 "nonimmediate_operand" ""))))]
-  "TARGET_SSE5
-   && !ix86_sse5_valid_op_p (operands, insn, 4, true, 1, true)
-   && ix86_sse5_valid_op_p (operands, insn, 4, true, 2, true)
-   && !reg_mentioned_p (operands[0], operands[1])
-   && !reg_mentioned_p (operands[0], operands[2])
-   && !reg_mentioned_p (operands[0], operands[3])"
-  [(const_int 0)]
-{
-  ix86_expand_sse5_multiple_memory (operands, 4, <MODE>mode);
-  emit_insn (gen_sse5_fnmadd<mode>4 (operands[0], operands[1],
-				     operands[2], operands[3]));
-  DONE;
-})
-
-;; For the scalar operations, use operand1 for the upper words that aren't
-;; modified, so restrict the forms that are generated.
-;; Scalar version of fnmadd
-(define_insn "sse5_vmfnmadd<mode>4"
-  [(set (match_operand:SSEMODEF2P 0 "register_operand" "=x,x")
-	(vec_merge:SSEMODEF2P
-	 (minus:SSEMODEF2P
-	  (match_operand:SSEMODEF2P 3 "nonimmediate_operand" "xm,x")
-	  (mult:SSEMODEF2P
-	   (match_operand:SSEMODEF2P 1 "nonimmediate_operand" "0,0")
-	   (match_operand:SSEMODEF2P 2 "nonimmediate_operand" "x,xm")))
-	 (match_dup 1)
-	 (const_int 1)))]
-  "TARGET_SSE5 && TARGET_FUSED_MADD
-   && ix86_sse5_valid_op_p (operands, insn, 4, true, 1, true)"
-  "fnmadd<ssemodesuffixf2s>\t{%3, %2, %1, %0|%0, %1, %2, %3}"
-  [(set_attr "type" "ssemuladd")
-   (set_attr "mode" "<MODE>")])
-
-;; Floating point negative multiply and subtract
-;; Rewrite (- (a * b) - c) into the canonical form: ((-a) * b) - c
-;; Allow 2 memory operands to help with optimization
-(define_insn "sse5_fnmsub<mode>4"
-  [(set (match_operand:SSEMODEF4 0 "register_operand" "=x,x")
-	(minus:SSEMODEF4
-	 (mult:SSEMODEF4
-	  (neg:SSEMODEF4
-	   (match_operand:SSEMODEF4 1 "nonimmediate_operand" "0,0"))
-	  (match_operand:SSEMODEF4 2 "nonimmediate_operand" "x,xm"))
-	 (match_operand:SSEMODEF4 3 "nonimmediate_operand" "xm,x")))]
-  "TARGET_SSE5 && TARGET_FUSED_MADD
-   && ix86_sse5_valid_op_p (operands, insn, 4, true, 2, false)"
-  "fnmsub<ssemodesuffixf4>\t{%3, %2, %1, %0|%0, %1, %2, %3}"
-  [(set_attr "type" "ssemuladd")
-   (set_attr "mode" "<MODE>")])
-
-;; Split fnmsub with two memory operands into a load and the fmsub.
-(define_split
-  [(set (match_operand:SSEMODEF4 0 "register_operand" "")
-	(minus:SSEMODEF4
-	 (mult:SSEMODEF4
-	  (neg:SSEMODEF4
-	   (match_operand:SSEMODEF4 1 "nonimmediate_operand" ""))
-	  (match_operand:SSEMODEF4 2 "nonimmediate_operand" ""))
-	 (match_operand:SSEMODEF4 3 "nonimmediate_operand" "")))]
-  "TARGET_SSE5
-   && !ix86_sse5_valid_op_p (operands, insn, 4, true, 1, false)
-   && ix86_sse5_valid_op_p (operands, insn, 4, true, 2, false)
-   && !reg_mentioned_p (operands[0], operands[1])
-   && !reg_mentioned_p (operands[0], operands[2])
-   && !reg_mentioned_p (operands[0], operands[3])"
-  [(const_int 0)]
-{
-  ix86_expand_sse5_multiple_memory (operands, 4, <MODE>mode);
-  emit_insn (gen_sse5_fnmsub<mode>4 (operands[0], operands[1],
-				     operands[2], operands[3]));
-  DONE;
-})
-
-;; For the scalar operations, use operand1 for the upper words that aren't
-;; modified, so restrict the forms that are generated.
-;; Scalar version of fnmsub
-(define_insn "sse5_vmfnmsub<mode>4"
-  [(set (match_operand:SSEMODEF2P 0 "register_operand" "=x,x")
-	(vec_merge:SSEMODEF2P
-	 (minus:SSEMODEF2P
-	  (mult:SSEMODEF2P
-	   (neg:SSEMODEF2P
-	    (match_operand:SSEMODEF2P 1 "nonimmediate_operand" "0,0"))
-	   (match_operand:SSEMODEF2P 2 "nonimmediate_operand" "x,xm"))
-	  (match_operand:SSEMODEF2P 3 "nonimmediate_operand" "xm,x"))
-	 (match_dup 1)
-	 (const_int 1)))]
-  "TARGET_SSE5 && TARGET_FUSED_MADD
-   && ix86_sse5_valid_op_p (operands, insn, 4, true, 2, false)"
-  "fnmsub<ssemodesuffixf2s>\t{%3, %2, %1, %0|%0, %1, %2, %3}"
-  [(set_attr "type" "ssemuladd")
-   (set_attr "mode" "<MODE>")])
-
-;; The same instructions using an UNSPEC to allow the intrinsic to be used
-;; even if the user used -mno-fused-madd
-;; Parallel instructions.  During instruction generation, just default
-;; to registers, and let combine later build the appropriate instruction.
-(define_expand "sse5i_fmadd<mode>4"
-  [(set (match_operand:SSEMODEF2P 0 "register_operand" "")
-	(unspec:SSEMODEF2P
-	 [(plus:SSEMODEF2P
-	   (mult:SSEMODEF2P
-	    (match_operand:SSEMODEF2P 1 "register_operand" "")
-	    (match_operand:SSEMODEF2P 2 "register_operand" ""))
-	   (match_operand:SSEMODEF2P 3 "register_operand" ""))]
-	 UNSPEC_SSE5_INTRINSIC))]
-  "TARGET_SSE5"
-{
-  /* If we have -mfused-madd, emit the normal insn rather than the UNSPEC */
-  if (TARGET_FUSED_MADD)
-    {
-      emit_insn (gen_sse5_fmadd<mode>4 (operands[0], operands[1],
-					operands[2], operands[3]));
-      DONE;
-    }
-})
-
-(define_insn "*sse5i_fmadd<mode>4"
-  [(set (match_operand:SSEMODEF2P 0 "register_operand" "=x,x,x,x")
-	(unspec:SSEMODEF2P
-	 [(plus:SSEMODEF2P
-	   (mult:SSEMODEF2P
-	    (match_operand:SSEMODEF2P 1 "nonimmediate_operand" "%0,0,x,xm")
-	    (match_operand:SSEMODEF2P 2 "nonimmediate_operand" "x,xm,xm,x"))
-	   (match_operand:SSEMODEF2P 3 "nonimmediate_operand" "xm,x,0,0"))]
-	 UNSPEC_SSE5_INTRINSIC))]
-  "TARGET_SSE5 && ix86_sse5_valid_op_p (operands, insn, 4, true, 1, true)"
-  "fmadd<ssemodesuffixf4>\t{%3, %2, %1, %0|%0, %1, %2, %3}"
-  [(set_attr "type" "ssemuladd")
-   (set_attr "mode" "<MODE>")])
-
-(define_expand "sse5i_fmsub<mode>4"
-  [(set (match_operand:SSEMODEF2P 0 "register_operand" "")
-	(unspec:SSEMODEF2P
-	 [(minus:SSEMODEF2P
-	   (mult:SSEMODEF2P
-	    (match_operand:SSEMODEF2P 1 "register_operand" "")
-	    (match_operand:SSEMODEF2P 2 "register_operand" ""))
-	   (match_operand:SSEMODEF2P 3 "register_operand" ""))]
-	 UNSPEC_SSE5_INTRINSIC))]
-  "TARGET_SSE5"
-{
-  /* If we have -mfused-madd, emit the normal insn rather than the UNSPEC */
-  if (TARGET_FUSED_MADD)
-    {
-      emit_insn (gen_sse5_fmsub<mode>4 (operands[0], operands[1],
-					operands[2], operands[3]));
-      DONE;
-    }
-})
-
-(define_insn "*sse5i_fmsub<mode>4"
-  [(set (match_operand:SSEMODEF2P 0 "register_operand" "=x,x,x,x")
-	(unspec:SSEMODEF2P
-	 [(minus:SSEMODEF2P
-	   (mult:SSEMODEF2P
-	    (match_operand:SSEMODEF2P 1 "nonimmediate_operand" "%0,0,x,xm")
-	    (match_operand:SSEMODEF2P 2 "nonimmediate_operand" "x,xm,xm,x"))
-	   (match_operand:SSEMODEF2P 3 "nonimmediate_operand" "xm,x,0,0"))]
-	 UNSPEC_SSE5_INTRINSIC))]
-  "TARGET_SSE5 && ix86_sse5_valid_op_p (operands, insn, 4, true, 1, true)"
-  "fmsub<ssemodesuffixf4>\t{%3, %2, %1, %0|%0, %1, %2, %3}"
-  [(set_attr "type" "ssemuladd")
-   (set_attr "mode" "<MODE>")])
-
-;; Rewrite (- (a * b) + c) into the canonical form: c - (a * b)
-;; Note operands are out of order to simplify call to ix86_sse5_valid_p
-(define_expand "sse5i_fnmadd<mode>4"
-  [(set (match_operand:SSEMODEF2P 0 "register_operand" "")
-	(unspec:SSEMODEF2P
-	 [(minus:SSEMODEF2P
-	   (match_operand:SSEMODEF2P 3 "register_operand" "")
-	   (mult:SSEMODEF2P
-	    (match_operand:SSEMODEF2P 1 "register_operand" "")
-	    (match_operand:SSEMODEF2P 2 "register_operand" "")))]
-	 UNSPEC_SSE5_INTRINSIC))]
-  "TARGET_SSE5"
-{
-  /* If we have -mfused-madd, emit the normal insn rather than the UNSPEC */
-  if (TARGET_FUSED_MADD)
-    {
-      emit_insn (gen_sse5_fnmadd<mode>4 (operands[0], operands[1],
-					 operands[2], operands[3]));
-      DONE;
-    }
-})
-
-(define_insn "*sse5i_fnmadd<mode>4"
-  [(set (match_operand:SSEMODEF2P 0 "register_operand" "=x,x,x,x")
-	(unspec:SSEMODEF2P
-	 [(minus:SSEMODEF2P
-	   (match_operand:SSEMODEF2P 3 "nonimmediate_operand" "xm,x,0,0")
-	   (mult:SSEMODEF2P
-	    (match_operand:SSEMODEF2P 1 "nonimmediate_operand" "%0,0,x,xm")
-	    (match_operand:SSEMODEF2P 2 "nonimmediate_operand" "x,xm,xm,x")))]
-	 UNSPEC_SSE5_INTRINSIC))]
-  "TARGET_SSE5 && ix86_sse5_valid_op_p (operands, insn, 4, true, 1, true)"
-  "fnmadd<ssemodesuffixf4>\t{%3, %2, %1, %0|%0, %1, %2, %3}"
-  [(set_attr "type" "ssemuladd")
-   (set_attr "mode" "<MODE>")])
-
-;; Rewrite (- (a * b) - c) into the canonical form: ((-a) * b) - c
-(define_expand "sse5i_fnmsub<mode>4"
-  [(set (match_operand:SSEMODEF2P 0 "register_operand" "")
-	(unspec:SSEMODEF2P
-	 [(minus:SSEMODEF2P
-	   (mult:SSEMODEF2P
-	    (neg:SSEMODEF2P
-	     (match_operand:SSEMODEF2P 1 "register_operand" ""))
-	    (match_operand:SSEMODEF2P 2 "register_operand" ""))
-	   (match_operand:SSEMODEF2P 3 "register_operand" ""))]
-	 UNSPEC_SSE5_INTRINSIC))]
-  "TARGET_SSE5"
-{
-  /* If we have -mfused-madd, emit the normal insn rather than the UNSPEC */
-  if (TARGET_FUSED_MADD)
-    {
-      emit_insn (gen_sse5_fnmsub<mode>4 (operands[0], operands[1],
-					 operands[2], operands[3]));
-      DONE;
-    }
-})
-
-(define_insn "*sse5i_fnmsub<mode>4"
-  [(set (match_operand:SSEMODEF2P 0 "register_operand" "=x,x,x,x")
-	(unspec:SSEMODEF2P
-	 [(minus:SSEMODEF2P
-	   (mult:SSEMODEF2P
-	    (neg:SSEMODEF2P
-	     (match_operand:SSEMODEF2P 1 "nonimmediate_operand" "0,0,x,xm"))
-	    (match_operand:SSEMODEF2P 2 "nonimmediate_operand" "x,xm,xm,x"))
-	   (match_operand:SSEMODEF2P 3 "nonimmediate_operand" "xm,x,0,0"))]
-	 UNSPEC_SSE5_INTRINSIC))]
-  "TARGET_SSE5 && ix86_sse5_valid_op_p (operands, insn, 4, true, 1, false)"
-  "fnmsub<ssemodesuffixf4>\t{%3, %2, %1, %0|%0, %1, %2, %3}"
-  [(set_attr "type" "ssemuladd")
-   (set_attr "mode" "<MODE>")])
-
-;; Scalar instructions
-(define_expand "sse5i_vmfmadd<mode>4"
-  [(set (match_operand:SSEMODEF2P 0 "register_operand" "")
-	(unspec:SSEMODEF2P
-	 [(vec_merge:SSEMODEF2P
-	   (plus:SSEMODEF2P
-	    (mult:SSEMODEF2P
-	     (match_operand:SSEMODEF2P 1 "register_operand" "")
-	     (match_operand:SSEMODEF2P 2 "register_operand" ""))
-	    (match_operand:SSEMODEF2P 3 "register_operand" ""))
-	   (match_dup 1)
-	   (const_int 0))]
-	 UNSPEC_SSE5_INTRINSIC))]
-  "TARGET_SSE5"
-{
-  /* If we have -mfused-madd, emit the normal insn rather than the UNSPEC */
-  if (TARGET_FUSED_MADD)
-    {
-      emit_insn (gen_sse5_vmfmadd<mode>4 (operands[0], operands[1],
-					  operands[2], operands[3]));
-      DONE;
-    }
-})
-
-;; For the scalar operations, use operand1 for the upper words that aren't
-;; modified, so restrict the forms that are accepted.
-(define_insn "*sse5i_vmfmadd<mode>4"
-  [(set (match_operand:SSEMODEF2P 0 "register_operand" "=x,x")
-	(unspec:SSEMODEF2P
-	 [(vec_merge:SSEMODEF2P
-	   (plus:SSEMODEF2P
-	    (mult:SSEMODEF2P
-	     (match_operand:SSEMODEF2P 1 "register_operand" "0,0")
-	     (match_operand:SSEMODEF2P 2 "nonimmediate_operand" "x,xm"))
-	    (match_operand:SSEMODEF2P 3 "nonimmediate_operand" "xm,x"))
-	   (match_dup 0)
-	   (const_int 0))]
-	 UNSPEC_SSE5_INTRINSIC))]
-  "TARGET_SSE5 && ix86_sse5_valid_op_p (operands, insn, 4, true, 1, false)"
-  "fmadd<ssemodesuffixf2s>\t{%3, %2, %1, %0|%0, %1, %2, %3}"
-  [(set_attr "type" "ssemuladd")
-   (set_attr "mode" "<ssescalarmode>")])
-
-(define_expand "sse5i_vmfmsub<mode>4"
-  [(set (match_operand:SSEMODEF2P 0 "register_operand" "")
-	(unspec:SSEMODEF2P
-	 [(vec_merge:SSEMODEF2P
-	   (minus:SSEMODEF2P
-	    (mult:SSEMODEF2P
-	     (match_operand:SSEMODEF2P 1 "register_operand" "")
-	     (match_operand:SSEMODEF2P 2 "register_operand" ""))
-	    (match_operand:SSEMODEF2P 3 "register_operand" ""))
-	   (match_dup 0)
-	   (const_int 1))]
-	 UNSPEC_SSE5_INTRINSIC))]
-  "TARGET_SSE5"
-{
-  /* If we have -mfused-madd, emit the normal insn rather than the UNSPEC */
-  if (TARGET_FUSED_MADD)
-    {
-      emit_insn (gen_sse5_vmfmsub<mode>4 (operands[0], operands[1],
-					  operands[2], operands[3]));
-      DONE;
-    }
-})
-
-(define_insn "*sse5i_vmfmsub<mode>4"
-  [(set (match_operand:SSEMODEF2P 0 "register_operand" "=x,x")
-	(unspec:SSEMODEF2P
-	 [(vec_merge:SSEMODEF2P
-	   (minus:SSEMODEF2P
-	    (mult:SSEMODEF2P
-	     (match_operand:SSEMODEF2P 1 "register_operand" "0,0")
-	     (match_operand:SSEMODEF2P 2 "nonimmediate_operand" "x,xm"))
-	    (match_operand:SSEMODEF2P 3 "nonimmediate_operand" "xm,x"))
-	   (match_dup 1)
-	   (const_int 1))]
-	 UNSPEC_SSE5_INTRINSIC))]
-  "TARGET_SSE5 && ix86_sse5_valid_op_p (operands, insn, 4, true, 1, false)"
-  "fmsub<ssemodesuffixf2s>\t{%3, %2, %1, %0|%0, %1, %2, %3}"
-  [(set_attr "type" "ssemuladd")
-   (set_attr "mode" "<ssescalarmode>")])
-
-;; Note operands are out of order to simplify call to ix86_sse5_valid_p
-(define_expand "sse5i_vmfnmadd<mode>4"
-  [(set (match_operand:SSEMODEF2P 0 "register_operand" "")
-	(unspec:SSEMODEF2P
-	 [(vec_merge:SSEMODEF2P
-	   (minus:SSEMODEF2P
-	    (match_operand:SSEMODEF2P 3 "register_operand" "")
-	    (mult:SSEMODEF2P
-	     (match_operand:SSEMODEF2P 1 "register_operand" "")
-	     (match_operand:SSEMODEF2P 2 "register_operand" "")))
-	   (match_dup 1)
-	   (const_int 1))]
-	 UNSPEC_SSE5_INTRINSIC))]
-  "TARGET_SSE5"
-{
-  /* If we have -mfused-madd, emit the normal insn rather than the UNSPEC */
-  if (TARGET_FUSED_MADD)
-    {
-      emit_insn (gen_sse5_vmfnmadd<mode>4 (operands[0], operands[1],
-					   operands[2], operands[3]));
-      DONE;
-    }
-})
-
-(define_insn "*sse5i_vmfnmadd<mode>4"
-  [(set (match_operand:SSEMODEF2P 0 "register_operand" "=x,x")
-	(unspec:SSEMODEF2P
-	 [(vec_merge:SSEMODEF2P
-	   (minus:SSEMODEF2P
-	    (match_operand:SSEMODEF2P 3 "nonimmediate_operand" "xm,x")
-	    (mult:SSEMODEF2P
-	     (match_operand:SSEMODEF2P 1 "nonimmediate_operand" "%0,0")
-	     (match_operand:SSEMODEF2P 2 "nonimmediate_operand" "x,xm")))
-	   (match_dup 1)
-	   (const_int 1))]
-	 UNSPEC_SSE5_INTRINSIC))]
-  "TARGET_SSE5 && ix86_sse5_valid_op_p (operands, insn, 4, true, 1, true)"
-  "fnmadd<ssemodesuffixf2s>\t{%3, %2, %1, %0|%0, %1, %2, %3}"
-  [(set_attr "type" "ssemuladd")
-   (set_attr "mode" "<ssescalarmode>")])
-
-(define_expand "sse5i_vmfnmsub<mode>4"
-  [(set (match_operand:SSEMODEF2P 0 "register_operand" "")
-	(unspec:SSEMODEF2P
-	 [(vec_merge:SSEMODEF2P
-	   (minus:SSEMODEF2P
-	    (mult:SSEMODEF2P
-	     (neg:SSEMODEF2P
-	      (match_operand:SSEMODEF2P 1 "register_operand" ""))
-	     (match_operand:SSEMODEF2P 2 "register_operand" ""))
-	    (match_operand:SSEMODEF2P 3 "register_operand" ""))
-	   (match_dup 1)
-	   (const_int 1))]
-	 UNSPEC_SSE5_INTRINSIC))]
-  "TARGET_SSE5"
-{
-  /* If we have -mfused-madd, emit the normal insn rather than the UNSPEC */
-  if (TARGET_FUSED_MADD)
-    {
-      emit_insn (gen_sse5_vmfnmsub<mode>4 (operands[0], operands[1],
-					   operands[2], operands[3]));
-      DONE;
-    }
-})
-
-(define_insn "*sse5i_vmfnmsub<mode>4"
-  [(set (match_operand:SSEMODEF2P 0 "register_operand" "=x,x")
-	(unspec:SSEMODEF2P
-	 [(vec_merge:SSEMODEF2P
-	   (minus:SSEMODEF2P
-	    (mult:SSEMODEF2P
-	     (neg:SSEMODEF2P
-	      (match_operand:SSEMODEF2P 1 "register_operand" "0,0"))
-	     (match_operand:SSEMODEF2P 2 "nonimmediate_operand" "x,xm"))
-	    (match_operand:SSEMODEF2P 3 "nonimmediate_operand" "xm,x"))
-	   (match_dup 1)
-	   (const_int 1))]
-	 UNSPEC_SSE5_INTRINSIC))]
-  "TARGET_SSE5 && ix86_sse5_valid_op_p (operands, insn, 4, true, 1, false)"
-  "fnmsub<ssemodesuffixf2s>\t{%3, %2, %1, %0|%0, %1, %2, %3}"
-  [(set_attr "type" "ssemuladd")
-   (set_attr "mode" "<ssescalarmode>")])
-
-;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
-;;
 ;; Parallel single-precision floating point conversion operations
 ;;
 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
@@ -4871,40 +4312,9 @@
   "&& 1"
   [(const_int 0)]
 {
-  rtx t[12], op0, op[3];
+  rtx t[12];
   int i;
 
-  if (TARGET_SSE5)
-    {
-      /* On SSE5, we can take advantage of the pperm instruction to pack and
-	 unpack the bytes.  Unpack data such that we've got a source byte in
-	 each low byte of each word.  We don't care what goes into the high
-	 byte, so put 0 there.  */
-      for (i = 0; i < 6; ++i)
-        t[i] = gen_reg_rtx (V8HImode);
-
-      for (i = 0; i < 2; i++)
-        {
-          op[0] = t[i];
-          op[1] = operands[i+1];
-          ix86_expand_sse5_unpack (op, true, true);		/* high bytes */
-
-          op[0] = t[i+2];
-          ix86_expand_sse5_unpack (op, true, false);		/* low bytes */
-        }
-
-      /* Multiply words.  */
-      emit_insn (gen_mulv8hi3 (t[4], t[0], t[1]));		/* high bytes */
-      emit_insn (gen_mulv8hi3 (t[5], t[2], t[3]));		/* low  bytes */
-
-      /* Pack the low byte of each word back into a single xmm */
-      op[0] = operands[0];
-      op[1] = t[5];
-      op[2] = t[4];
-      ix86_expand_sse5_pack (op);
-      DONE;
-    }
-
   for (i = 0; i < 12; ++i)
     t[i] = gen_reg_rtx (V16QImode);
 
@@ -4935,8 +4345,7 @@
   emit_insn (gen_sse2_punpckhbw (t[10], t[9], t[8]));	/* ........ACEGIKMO */
   emit_insn (gen_sse2_punpcklbw (t[11], t[9], t[8]));	/* ........BDFHJLNP */
 
-  op0 = operands[0];
-  emit_insn (gen_sse2_punpcklbw (op0, t[11], t[10]));	/* ABCDEFGHIJKLMNOP */
+  emit_insn (gen_sse2_punpcklbw (operands[0], t[11], t[10]));	/* ABCDEFGHIJKLMNOP */
   DONE;
 })
 
@@ -5269,7 +4678,7 @@
 		   (match_operand:V4SI 2 "register_operand" "")))]
   "TARGET_SSE2"
 {
-  if (TARGET_SSE4_1 || TARGET_SSE5)
+  if (TARGET_SSE4_1)
     ix86_fixup_binary_operands_no_copy (MULT, V4SImode, operands);
 })
 
@@ -5294,36 +4703,11 @@
    (set_attr "prefix_extra" "1")
    (set_attr "mode" "TI")])
 
-;; We don't have a straight 32-bit parallel multiply on SSE5, so fake it with a
-;; multiply/add.  In general, we expect the define_split to occur before
-;; register allocation, so we have to handle the corner case where the target
-;; is the same as one of the inputs.
-(define_insn_and_split "*sse5_mulv4si3"
-  [(set (match_operand:V4SI 0 "register_operand" "=&x")
-	(mult:V4SI (match_operand:V4SI 1 "register_operand" "%x")
-		   (match_operand:V4SI 2 "nonimmediate_operand" "xm")))]
-  "TARGET_SSE5"
-  "#"
-  "&& (reload_completed
-       || (!reg_mentioned_p (operands[0], operands[1])
-	   && !reg_mentioned_p (operands[0], operands[2])))"
-  [(set (match_dup 0)
-	(match_dup 3))
-   (set (match_dup 0)
-	(plus:V4SI (mult:V4SI (match_dup 1)
-			      (match_dup 2))
-		   (match_dup 0)))]
-{
-  operands[3] = CONST0_RTX (V4SImode);
-}
-  [(set_attr "type" "ssemuladd")
-   (set_attr "mode" "TI")])
-
 (define_insn_and_split "*sse2_mulv4si3"
   [(set (match_operand:V4SI 0 "register_operand" "")
 	(mult:V4SI (match_operand:V4SI 1 "register_operand" "")
 		   (match_operand:V4SI 2 "register_operand" "")))]
-  "TARGET_SSE2 && !TARGET_SSE4_1 && !TARGET_SSE5
+  "TARGET_SSE2 && !TARGET_SSE4_1
    && can_create_pseudo_p ()"
   "#"
   "&& 1"
@@ -5385,42 +4769,6 @@
   rtx t1, t2, t3, t4, t5, t6, thirtytwo;
   rtx op0, op1, op2;
 
-  if (TARGET_SSE5)
-    {
-      /* op1: A,B,C,D, op2: E,F,G,H */
-      op0 = operands[0];
-      op1 = gen_lowpart (V4SImode, operands[1]);
-      op2 = gen_lowpart (V4SImode, operands[2]);
-      t1 = gen_reg_rtx (V4SImode);
-      t2 = gen_reg_rtx (V4SImode);
-      t3 = gen_reg_rtx (V4SImode);
-      t4 = gen_reg_rtx (V2DImode);
-      t5 = gen_reg_rtx (V2DImode);
-
-      /* t1: B,A,D,C */
-      emit_insn (gen_sse2_pshufd_1 (t1, op1,
-				    GEN_INT (1),
-				    GEN_INT (0),
-				    GEN_INT (3),
-				    GEN_INT (2)));
-
-      /* t2: 0 */
-      emit_move_insn (t2, CONST0_RTX (V4SImode));
-
-      /* t3: (B*E),(A*F),(D*G),(C*H) */
-      emit_insn (gen_sse5_pmacsdd (t3, t1, op2, t2));
-
-      /* t4: (B*E)+(A*F), (D*G)+(C*H) */
-      emit_insn (gen_sse5_phadddq (t4, t3));
-
-      /* t5: ((B*E)+(A*F))<<32, ((D*G)+(C*H))<<32 */
-      emit_insn (gen_ashlv2di3 (t5, t4, GEN_INT (32)));
-
-      /* op0: (((B*E)+(A*F))<<32)+(B*F), (((D*G)+(C*H))<<32)+(D*H) */
-      emit_insn (gen_sse5_pmacsdql (op0, op1, op2, t5));
-      DONE;
-    }
-
   op0 = operands[0];
   op1 = operands[1];
   op2 = operands[2];
@@ -5536,57 +4884,6 @@
   DONE;
 })
 
-(define_expand "vec_widen_smult_hi_v4si"
-  [(match_operand:V2DI 0 "register_operand" "")
-   (match_operand:V4SI 1 "register_operand" "")
-   (match_operand:V4SI 2 "register_operand" "")]
-  "TARGET_SSE5"
-{
-  rtx t1, t2;
-
-  t1 = gen_reg_rtx (V4SImode);
-  t2 = gen_reg_rtx (V4SImode);
-
-  emit_insn (gen_sse2_pshufd_1 (t1, operands[1],
-				GEN_INT (0),
-				GEN_INT (2),
-				GEN_INT (1),
-				GEN_INT (3)));
-  emit_insn (gen_sse2_pshufd_1 (t2, operands[2],
-				GEN_INT (0),
-				GEN_INT (2),
-				GEN_INT (1),
-				GEN_INT (3)));
-  emit_insn (gen_sse5_mulv2div2di3_high (operands[0], t1, t2));
-  DONE;
-})
-
-(define_expand "vec_widen_smult_lo_v4si"
-  [(match_operand:V2DI 0 "register_operand" "")
-   (match_operand:V4SI 1 "register_operand" "")
-   (match_operand:V4SI 2 "register_operand" "")]
-  "TARGET_SSE5"
-{
-  rtx t1, t2;
-
-  t1 = gen_reg_rtx (V4SImode);
-  t2 = gen_reg_rtx (V4SImode);
-
-  emit_insn (gen_sse2_pshufd_1 (t1, operands[1],
-				GEN_INT (0),
-				GEN_INT (2),
-				GEN_INT (1),
-				GEN_INT (3)));
-  emit_insn (gen_sse2_pshufd_1 (t2, operands[2],
-				GEN_INT (0),
-				GEN_INT (2),
-				GEN_INT (1),
-				GEN_INT (3)));
-  emit_insn (gen_sse5_mulv2div2di3_low (operands[0], t1, t2));
-  DONE;
-  DONE;
-})
-
 (define_expand "vec_widen_umult_hi_v4si"
   [(match_operand:V2DI 0 "register_operand" "")
    (match_operand:V4SI 1 "register_operand" "")
@@ -5984,7 +5281,7 @@
 	(eq:SSEMODE124
 	  (match_operand:SSEMODE124 1 "nonimmediate_operand" "")
 	  (match_operand:SSEMODE124 2 "nonimmediate_operand" "")))]
-  "TARGET_SSE2 && !TARGET_SSE5"
+  "TARGET_SSE2"
   "ix86_fixup_binary_operands_no_copy (EQ, <MODE>mode, operands);")
 
 (define_insn "*avx_eq<mode>3"
@@ -6007,7 +5304,7 @@
 	(eq:SSEMODE124
 	  (match_operand:SSEMODE124 1 "nonimmediate_operand" "%0")
 	  (match_operand:SSEMODE124 2 "nonimmediate_operand" "xm")))]
-  "TARGET_SSE2 && !TARGET_SSE5
+  "TARGET_SSE2
    && ix86_binary_operator_ok (EQ, <MODE>mode, operands)"
   "pcmpeq<ssevecsize>\t{%2, %0|%0, %2}"
   [(set_attr "type" "ssecmp")
@@ -6053,7 +5350,7 @@
 	(gt:SSEMODE124
 	  (match_operand:SSEMODE124 1 "register_operand" "0")
 	  (match_operand:SSEMODE124 2 "nonimmediate_operand" "xm")))]
-  "TARGET_SSE2 && !TARGET_SSE5"
+  "TARGET_SSE2"
   "pcmpgt<ssevecsize>\t{%2, %0|%0, %2}"
   [(set_attr "type" "ssecmp")
    (set_attr "prefix_data16" "1")
@@ -6071,35 +5368,33 @@
    (set_attr "mode" "TI")])
 
 (define_expand "vcond<mode>"
-  [(set (match_operand:SSEMODEI 0 "register_operand" "")
-        (if_then_else:SSEMODEI
+  [(set (match_operand:SSEMODE124C8 0 "register_operand" "")
+        (if_then_else:SSEMODE124C8
           (match_operator 3 ""
-            [(match_operand:SSEMODEI 4 "nonimmediate_operand" "")
-             (match_operand:SSEMODEI 5 "nonimmediate_operand" "")])
-          (match_operand:SSEMODEI 1 "general_operand" "")
-          (match_operand:SSEMODEI 2 "general_operand" "")))]
+            [(match_operand:SSEMODE124C8 4 "nonimmediate_operand" "")
+             (match_operand:SSEMODE124C8 5 "nonimmediate_operand" "")])
+          (match_operand:SSEMODE124C8 1 "general_operand" "")
+          (match_operand:SSEMODE124C8 2 "general_operand" "")))]
   "TARGET_SSE2"
 {
-  if (ix86_expand_int_vcond (operands))
-    DONE;
-  else
-    FAIL;
+  bool ok = ix86_expand_int_vcond (operands);
+  gcc_assert (ok);
+  DONE;
 })
 
 (define_expand "vcondu<mode>"
-  [(set (match_operand:SSEMODEI 0 "register_operand" "")
-        (if_then_else:SSEMODEI
+  [(set (match_operand:SSEMODE124C8 0 "register_operand" "")
+        (if_then_else:SSEMODE124C8
           (match_operator 3 ""
-            [(match_operand:SSEMODEI 4 "nonimmediate_operand" "")
-             (match_operand:SSEMODEI 5 "nonimmediate_operand" "")])
-          (match_operand:SSEMODEI 1 "general_operand" "")
-          (match_operand:SSEMODEI 2 "general_operand" "")))]
+            [(match_operand:SSEMODE124C8 4 "nonimmediate_operand" "")
+             (match_operand:SSEMODE124C8 5 "nonimmediate_operand" "")])
+          (match_operand:SSEMODE124C8 1 "general_operand" "")
+          (match_operand:SSEMODE124C8 2 "general_operand" "")))]
   "TARGET_SSE2"
 {
-  if (ix86_expand_int_vcond (operands))
-    DONE;
-  else
-    FAIL;
+  bool ok = ix86_expand_int_vcond (operands);
+  gcc_assert (ok);
+  DONE;
 })
 
 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
@@ -6274,12 +5569,6 @@
 {
   rtx op1, op2, h1, l1, h2, l2, h3, l3;
 
-  if (TARGET_SSE5)
-    {
-      ix86_expand_sse5_pack (operands);
-      DONE;	
-    }	
- 
   op1 = gen_lowpart (V16QImode, operands[1]);
   op2 = gen_lowpart (V16QImode, operands[2]);
   h1 = gen_reg_rtx (V16QImode);
@@ -6315,12 +5604,6 @@
 {
   rtx op1, op2, h1, l1, h2, l2;
 
-  if (TARGET_SSE5)
-    {
-      ix86_expand_sse5_pack (operands);
-      DONE;	
-    }	
- 
   op1 = gen_lowpart (V8HImode, operands[1]);
   op2 = gen_lowpart (V8HImode, operands[2]);
   h1 = gen_reg_rtx (V8HImode);
@@ -6350,12 +5633,6 @@
 {
   rtx op1, op2, h1, l1;
 
-  if (TARGET_SSE5)
-    {
-      ix86_expand_sse5_pack (operands);
-      DONE;	
-    }	
- 
   op1 = gen_lowpart (V4SImode, operands[1]);
   op2 = gen_lowpart (V4SImode, operands[2]);
   h1 = gen_reg_rtx (V4SImode);
@@ -7567,8 +6844,6 @@
 {
   if (TARGET_SSE4_1)
     ix86_expand_sse4_unpack (operands, true, true);
-  else if (TARGET_SSE5)
-    ix86_expand_sse5_unpack (operands, true, true);
   else
     ix86_expand_sse_unpack (operands, true, true);
   DONE;
@@ -7581,8 +6856,6 @@
 {
   if (TARGET_SSE4_1)
     ix86_expand_sse4_unpack (operands, false, true);
-  else if (TARGET_SSE5)
-    ix86_expand_sse5_unpack (operands, false, true);
   else
     ix86_expand_sse_unpack (operands, false, true);
   DONE;
@@ -7595,8 +6868,6 @@
 {
   if (TARGET_SSE4_1)
     ix86_expand_sse4_unpack (operands, true, false);
-  else if (TARGET_SSE5)
-    ix86_expand_sse5_unpack (operands, true, false);
   else
     ix86_expand_sse_unpack (operands, true, false);
   DONE;
@@ -7609,8 +6880,6 @@
 {
   if (TARGET_SSE4_1)
     ix86_expand_sse4_unpack (operands, false, false);
-  else if (TARGET_SSE5)
-    ix86_expand_sse5_unpack (operands, false, false);
   else
     ix86_expand_sse_unpack (operands, false, false);
   DONE;
@@ -7623,8 +6892,6 @@
 {
   if (TARGET_SSE4_1)
     ix86_expand_sse4_unpack (operands, true, true);
-  else if (TARGET_SSE5)
-    ix86_expand_sse5_unpack (operands, true, true);
   else
     ix86_expand_sse_unpack (operands, true, true);
   DONE;
@@ -7637,8 +6904,6 @@
 {
   if (TARGET_SSE4_1)
     ix86_expand_sse4_unpack (operands, false, true);
-  else if (TARGET_SSE5)
-    ix86_expand_sse5_unpack (operands, false, true);
   else
     ix86_expand_sse_unpack (operands, false, true);
   DONE;
@@ -7651,8 +6916,6 @@
 {
   if (TARGET_SSE4_1)
     ix86_expand_sse4_unpack (operands, true, false);
-  else if (TARGET_SSE5)
-    ix86_expand_sse5_unpack (operands, true, false);
   else
     ix86_expand_sse_unpack (operands, true, false);
   DONE;
@@ -7665,8 +6928,6 @@
 {
   if (TARGET_SSE4_1)
     ix86_expand_sse4_unpack (operands, false, false);
-  else if (TARGET_SSE5)
-    ix86_expand_sse5_unpack (operands, false, false);
   else
     ix86_expand_sse_unpack (operands, false, false);
   DONE;
@@ -7679,8 +6940,6 @@
 {
   if (TARGET_SSE4_1)
     ix86_expand_sse4_unpack (operands, true, true);
-  else if (TARGET_SSE5)
-    ix86_expand_sse5_unpack (operands, true, true);
   else
     ix86_expand_sse_unpack (operands, true, true);
   DONE;
@@ -7693,8 +6952,6 @@
 {
   if (TARGET_SSE4_1)
     ix86_expand_sse4_unpack (operands, false, true);
-  else if (TARGET_SSE5)
-    ix86_expand_sse5_unpack (operands, false, true);
   else
     ix86_expand_sse_unpack (operands, false, true);
   DONE;
@@ -7707,8 +6964,6 @@
 {
   if (TARGET_SSE4_1)
     ix86_expand_sse4_unpack (operands, true, false);
-  else if (TARGET_SSE5)
-    ix86_expand_sse5_unpack (operands, true, false);
   else
     ix86_expand_sse_unpack (operands, true, false);
   DONE;
@@ -7721,8 +6976,6 @@
 {
   if (TARGET_SSE4_1)
     ix86_expand_sse4_unpack (operands, false, false);
-  else if (TARGET_SSE5)
-    ix86_expand_sse5_unpack (operands, false, false);
   else
     ix86_expand_sse_unpack (operands, false, false);
   DONE;
@@ -10175,1646 +9428,6 @@
    (set_attr "prefix" "maybe_vex")
    (set_attr "mode" "TI")])
 
-;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
-;;
-;; SSE5 instructions
-;;
-;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
-
-;; SSE5 parallel integer multiply/add instructions.
-;; Note the instruction does not allow the value being added to be a memory
-;; operation.  However by pretending via the nonimmediate_operand predicate
-;; that it does and splitting it later allows the following to be recognized:
-;;	a[i] = b[i] * c[i] + d[i];
-(define_insn "sse5_pmacsww"
-  [(set (match_operand:V8HI 0 "register_operand" "=x,x,x")
-        (plus:V8HI
-	 (mult:V8HI
-	  (match_operand:V8HI 1 "nonimmediate_operand" "%x,x,xm")
-	  (match_operand:V8HI 2 "nonimmediate_operand" "x,xm,x"))
-	 (match_operand:V8HI 3 "register_operand" "0,0,0")))]
-  "TARGET_SSE5 && ix86_sse5_valid_op_p (operands, insn, 4, false, 2, true)"
-  "@
-   pmacsww\t{%3, %2, %1, %0|%0, %1, %2, %3}
-   pmacsww\t{%3, %2, %1, %0|%0, %1, %2, %3}
-   pmacsww\t{%3, %1, %2, %0|%0, %2, %1, %3}"
-  [(set_attr "type" "ssemuladd")
-   (set_attr "mode" "TI")])
-
-;; Split pmacsww with two memory operands into a load and the pmacsww.
-(define_split
-  [(set (match_operand:V8HI 0 "register_operand" "")
-	(plus:V8HI
-	 (mult:V8HI (match_operand:V8HI 1 "nonimmediate_operand" "")
-		    (match_operand:V8HI 2 "nonimmediate_operand" ""))
-	 (match_operand:V8HI 3 "nonimmediate_operand" "")))]
-  "TARGET_SSE5
-   && !ix86_sse5_valid_op_p (operands, insn, 4, false, 1, true)
-   && ix86_sse5_valid_op_p (operands, insn, 4, false, 2, true)
-   && !reg_mentioned_p (operands[0], operands[1])
-   && !reg_mentioned_p (operands[0], operands[2])
-   && !reg_mentioned_p (operands[0], operands[3])"
-  [(const_int 0)]
-{
-  ix86_expand_sse5_multiple_memory (operands, 4, V8HImode);
-  emit_insn (gen_sse5_pmacsww (operands[0], operands[1], operands[2],
-			       operands[3]));
-  DONE;
-})
-
-(define_insn "sse5_pmacssww"
-  [(set (match_operand:V8HI 0 "register_operand" "=x,x,x")
-        (ss_plus:V8HI
-	 (mult:V8HI (match_operand:V8HI 1 "nonimmediate_operand" "%x,x,m")
-		    (match_operand:V8HI 2 "nonimmediate_operand" "x,m,x"))
-	 (match_operand:V8HI 3 "register_operand" "0,0,0")))]
-  "TARGET_SSE5 && ix86_sse5_valid_op_p (operands, insn, 4, false, 1, true)"
-  "@
-   pmacssww\t{%3, %2, %1, %0|%0, %1, %2, %3}
-   pmacssww\t{%3, %2, %1, %0|%0, %1, %2, %3}
-   pmacssww\t{%3, %1, %2, %0|%0, %2, %1, %3}"
-  [(set_attr "type" "ssemuladd")
-   (set_attr "mode" "TI")])
-
-;; Note the instruction does not allow the value being added to be a memory
-;; operation.  However by pretending via the nonimmediate_operand predicate
-;; that it does and splitting it later allows the following to be recognized:
-;;	a[i] = b[i] * c[i] + d[i];
-(define_insn "sse5_pmacsdd"
-  [(set (match_operand:V4SI 0 "register_operand" "=x,x,x")
-        (plus:V4SI
-	 (mult:V4SI
-	  (match_operand:V4SI 1 "nonimmediate_operand" "%x,x,m")
-	  (match_operand:V4SI 2 "nonimmediate_operand" "x,m,x"))
-	 (match_operand:V4SI 3 "register_operand" "0,0,0")))]
-  "TARGET_SSE5 && ix86_sse5_valid_op_p (operands, insn, 4, false, 2, true)"
-  "@
-   pmacsdd\t{%3, %2, %1, %0|%0, %1, %2, %3}
-   pmacsdd\t{%3, %2, %1, %0|%0, %1, %2, %3}
-   pmacsdd\t{%3, %1, %2, %0|%0, %2, %1, %3}"
-  [(set_attr "type" "ssemuladd")
-   (set_attr "mode" "TI")])
-
-;; Split pmacsdd with two memory operands into a load and the pmacsdd.
-(define_split
-  [(set (match_operand:V4SI 0 "register_operand" "")
-	(plus:V4SI
-	 (mult:V4SI (match_operand:V4SI 1 "nonimmediate_operand" "")
-		    (match_operand:V4SI 2 "nonimmediate_operand" ""))
-	 (match_operand:V4SI 3 "nonimmediate_operand" "")))]
-  "TARGET_SSE5
-   && !ix86_sse5_valid_op_p (operands, insn, 4, false, 1, true)
-   && ix86_sse5_valid_op_p (operands, insn, 4, false, 2, true)
-   && !reg_mentioned_p (operands[0], operands[1])
-   && !reg_mentioned_p (operands[0], operands[2])
-   && !reg_mentioned_p (operands[0], operands[3])"
-  [(const_int 0)]
-{
-  ix86_expand_sse5_multiple_memory (operands, 4, V4SImode);
-  emit_insn (gen_sse5_pmacsdd (operands[0], operands[1], operands[2],
-			       operands[3]));
-  DONE;
-})
-
-(define_insn "sse5_pmacssdd"
-  [(set (match_operand:V4SI 0 "register_operand" "=x,x,x")
-        (ss_plus:V4SI
-	 (mult:V4SI (match_operand:V4SI 1 "nonimmediate_operand" "%x,x,m")
-		    (match_operand:V4SI 2 "nonimmediate_operand" "x,m,x"))
-	 (match_operand:V4SI 3 "register_operand" "0,0,0")))]
-  "TARGET_SSE5 && ix86_sse5_valid_op_p (operands, insn, 4, false, 1, true)"
-  "@
-   pmacssdd\t{%3, %2, %1, %0|%0, %1, %2, %3}
-   pmacssdd\t{%3, %2, %1, %0|%0, %1, %2, %3}
-   pmacssdd\t{%3, %1, %2, %0|%0, %2, %1, %3}"
-  [(set_attr "type" "ssemuladd")
-   (set_attr "mode" "TI")])
-
-(define_insn "sse5_pmacssdql"
-  [(set (match_operand:V2DI 0 "register_operand" "=x,x,x")
-	(ss_plus:V2DI
-	 (mult:V2DI
-	  (sign_extend:V2DI
-	   (vec_select:V2SI
-	    (match_operand:V4SI 1 "nonimmediate_operand" "%x,x,m")
-	    (parallel [(const_int 1)
-		       (const_int 3)])))
-	   (vec_select:V2SI
-	    (match_operand:V4SI 2 "nonimmediate_operand" "x,m,x")
-	    (parallel [(const_int 1)
-		       (const_int 3)])))
-	 (match_operand:V2DI 3 "register_operand" "0,0,0")))]
-  "TARGET_SSE5 && ix86_sse5_valid_op_p (operands, insn, 4, false, 1, true)"
-  "@
-   pmacssdql\t{%3, %2, %1, %0|%0, %1, %2, %3}
-   pmacssdql\t{%3, %2, %1, %0|%0, %1, %2, %3}
-   pmacssdql\t{%3, %1, %2, %0|%0, %2, %1, %3}"
-  [(set_attr "type" "ssemuladd")
-   (set_attr "mode" "TI")])
-
-(define_insn "sse5_pmacssdqh"
-  [(set (match_operand:V2DI 0 "register_operand" "=x,x,x")
-	(ss_plus:V2DI
-	 (mult:V2DI
-	  (sign_extend:V2DI
-	   (vec_select:V2SI
-	    (match_operand:V4SI 1 "nonimmediate_operand" "%x,x,m")
-	    (parallel [(const_int 0)
-		       (const_int 2)])))
-	  (sign_extend:V2DI
-	   (vec_select:V2SI
-	    (match_operand:V4SI 2 "nonimmediate_operand" "x,m,x")
-	    (parallel [(const_int 0)
-		       (const_int 2)]))))
-	 (match_operand:V2DI 3 "register_operand" "0,0,0")))]
-  "TARGET_SSE5 && ix86_sse5_valid_op_p (operands, insn, 4, false, 1, true)"
-  "@
-   pmacssdqh\t{%3, %2, %1, %0|%0, %1, %2, %3}
-   pmacssdqh\t{%3, %2, %1, %0|%0, %1, %2, %3}
-   pmacssdqh\t{%3, %1, %2, %0|%0, %2, %1, %3}"
-  [(set_attr "type" "ssemuladd")
-   (set_attr "mode" "TI")])
-
-(define_insn "sse5_pmacsdql"
-  [(set (match_operand:V2DI 0 "register_operand" "=x,x,x")
-	(plus:V2DI
-	 (mult:V2DI
-	  (sign_extend:V2DI
-	   (vec_select:V2SI
-	    (match_operand:V4SI 1 "nonimmediate_operand" "%x,x,m")
-	    (parallel [(const_int 1)
-		       (const_int 3)])))
-	  (sign_extend:V2DI
-	   (vec_select:V2SI
-	    (match_operand:V4SI 2 "nonimmediate_operand" "x,m,x")
-	    (parallel [(const_int 1)
-		       (const_int 3)]))))
-	 (match_operand:V2DI 3 "register_operand" "0,0,0")))]
-  "TARGET_SSE5 && ix86_sse5_valid_op_p (operands, insn, 4, false, 1, true)"
-  "@
-   pmacsdql\t{%3, %2, %1, %0|%0, %1, %2, %3}
-   pmacsdql\t{%3, %2, %1, %0|%0, %1, %2, %3}
-   pmacsdql\t{%3, %1, %2, %0|%0, %2, %1, %3}"
-  [(set_attr "type" "ssemuladd")
-   (set_attr "mode" "TI")])
-
-(define_insn_and_split "*sse5_pmacsdql_mem"
-  [(set (match_operand:V2DI 0 "register_operand" "=&x,&x,&x")
-	(plus:V2DI
-	 (mult:V2DI
-	  (sign_extend:V2DI
-	   (vec_select:V2SI
-	    (match_operand:V4SI 1 "nonimmediate_operand" "%x,x,m")
-	    (parallel [(const_int 1)
-		       (const_int 3)])))
-	  (sign_extend:V2DI
-	   (vec_select:V2SI
-	    (match_operand:V4SI 2 "nonimmediate_operand" "x,m,x")
-	    (parallel [(const_int 1)
-		       (const_int 3)]))))
-	 (match_operand:V2DI 3 "memory_operand" "m,m,m")))]
-  "TARGET_SSE5 && ix86_sse5_valid_op_p (operands, insn, 4, false, -1, true)"
-  "#"
-  "&& (reload_completed
-       || (!reg_mentioned_p (operands[0], operands[1])
-	   && !reg_mentioned_p (operands[0], operands[2])))"
-  [(set (match_dup 0)
-	(match_dup 3))
-   (set (match_dup 0)
-	(plus:V2DI
-	 (mult:V2DI
-	  (sign_extend:V2DI
-	   (vec_select:V2SI
-	    (match_dup 1)
-	    (parallel [(const_int 1)
-		       (const_int 3)])))
-	  (sign_extend:V2DI
-	   (vec_select:V2SI
-	    (match_dup 2)
-	    (parallel [(const_int 1)
-		       (const_int 3)]))))
-	 (match_dup 0)))])
-
-;; We don't have a straight 32-bit parallel multiply and extend on SSE5, so
-;; fake it with a multiply/add.  In general, we expect the define_split to
-;; occur before register allocation, so we have to handle the corner case where
-;; the target is the same as operands 1/2
-(define_insn_and_split "sse5_mulv2div2di3_low"
-  [(set (match_operand:V2DI 0 "register_operand" "=&x")
-	(mult:V2DI
-	  (sign_extend:V2DI
-	    (vec_select:V2SI
-	      (match_operand:V4SI 1 "nonimmediate_operand" "%x")
-	      (parallel [(const_int 1)
-			 (const_int 3)])))
-	  (sign_extend:V2DI
-	    (vec_select:V2SI
-	      (match_operand:V4SI 2 "nonimmediate_operand" "xm")
-	      (parallel [(const_int 1)
-			 (const_int 3)])))))]
-  "TARGET_SSE5"
-  "#"
-  "&& (reload_completed
-       || (!reg_mentioned_p (operands[0], operands[1])
-	   && !reg_mentioned_p (operands[0], operands[2])))"
-  [(set (match_dup 0)
-	(match_dup 3))
-   (set (match_dup 0)
-	(plus:V2DI
-	 (mult:V2DI
-	  (sign_extend:V2DI
-	   (vec_select:V2SI
-	    (match_dup 1)
-	    (parallel [(const_int 1)
-		       (const_int 3)])))
-	  (sign_extend:V2DI
-	   (vec_select:V2SI
-	    (match_dup 2)
-	    (parallel [(const_int 1)
-		       (const_int 3)]))))
-	 (match_dup 0)))]
-{
-  operands[3] = CONST0_RTX (V2DImode);
-}
-  [(set_attr "type" "ssemuladd")
-   (set_attr "mode" "TI")])
-
-(define_insn "sse5_pmacsdqh"
-  [(set (match_operand:V2DI 0 "register_operand" "=x,x,x")
-	(plus:V2DI
-	 (mult:V2DI
-	  (sign_extend:V2DI
-	   (vec_select:V2SI
-	    (match_operand:V4SI 1 "nonimmediate_operand" "%x,x,m")
-	    (parallel [(const_int 0)
-		       (const_int 2)])))
-	  (sign_extend:V2DI
-	   (vec_select:V2SI
-	    (match_operand:V4SI 2 "nonimmediate_operand" "x,m,x")
-	    (parallel [(const_int 0)
-		       (const_int 2)]))))
-	 (match_operand:V2DI 3 "register_operand" "0,0,0")))]
-  "TARGET_SSE5 && ix86_sse5_valid_op_p (operands, insn, 4, false, 1, true)"
-  "@
-   pmacsdqh\t{%3, %2, %1, %0|%0, %1, %2, %3}
-   pmacsdqh\t{%3, %2, %1, %0|%0, %1, %2, %3}
-   pmacsdqh\t{%3, %1, %2, %0|%0, %2, %1, %3}"
-  [(set_attr "type" "ssemuladd")
-   (set_attr "mode" "TI")])
-
-(define_insn_and_split "*sse5_pmacsdqh_mem"
-  [(set (match_operand:V2DI 0 "register_operand" "=&x,&x,&x")
-	(plus:V2DI
-	 (mult:V2DI
-	  (sign_extend:V2DI
-	   (vec_select:V2SI
-	    (match_operand:V4SI 1 "nonimmediate_operand" "%x,x,m")
-	    (parallel [(const_int 0)
-		       (const_int 2)])))
-	  (sign_extend:V2DI
-	   (vec_select:V2SI
-	    (match_operand:V4SI 2 "nonimmediate_operand" "x,m,x")
-	    (parallel [(const_int 0)
-		       (const_int 2)]))))
-	 (match_operand:V2DI 3 "memory_operand" "m,m,m")))]
-  "TARGET_SSE5 && ix86_sse5_valid_op_p (operands, insn, 4, false, -1, true)"
-  "#"
-  "&& (reload_completed
-       || (!reg_mentioned_p (operands[0], operands[1])
-	   && !reg_mentioned_p (operands[0], operands[2])))"
-  [(set (match_dup 0)
-	(match_dup 3))
-   (set (match_dup 0)
-	(plus:V2DI
-	 (mult:V2DI
-	  (sign_extend:V2DI
-	   (vec_select:V2SI
-	    (match_dup 1)
-	    (parallel [(const_int 0)
-		       (const_int 2)])))
-	  (sign_extend:V2DI
-	   (vec_select:V2SI
-	    (match_dup 2)
-	    (parallel [(const_int 0)
-		       (const_int 2)]))))
-	 (match_dup 0)))])
-
-;; We don't have a straight 32-bit parallel multiply and extend on SSE5, so
-;; fake it with a multiply/add.  In general, we expect the define_split to
-;; occur before register allocation, so we have to handle the corner case where
-;; the target is the same as either operands[1] or operands[2]
-(define_insn_and_split "sse5_mulv2div2di3_high"
-  [(set (match_operand:V2DI 0 "register_operand" "=&x")
-	(mult:V2DI
-	  (sign_extend:V2DI
-	    (vec_select:V2SI
-	      (match_operand:V4SI 1 "nonimmediate_operand" "%x")
-	      (parallel [(const_int 0)
-			 (const_int 2)])))
-	  (sign_extend:V2DI
-	    (vec_select:V2SI
-	      (match_operand:V4SI 2 "nonimmediate_operand" "xm")
-	      (parallel [(const_int 0)
-			 (const_int 2)])))))]
-  "TARGET_SSE5"
-  "#"
-  "&& (reload_completed
-       || (!reg_mentioned_p (operands[0], operands[1])
-	   && !reg_mentioned_p (operands[0], operands[2])))"
-  [(set (match_dup 0)
-	(match_dup 3))
-   (set (match_dup 0)
-	(plus:V2DI
-	 (mult:V2DI
-	  (sign_extend:V2DI
-	   (vec_select:V2SI
-	    (match_dup 1)
-	    (parallel [(const_int 0)
-		       (const_int 2)])))
-	  (sign_extend:V2DI
-	   (vec_select:V2SI
-	    (match_dup 2)
-	    (parallel [(const_int 0)
-		       (const_int 2)]))))
-	 (match_dup 0)))]
-{
-  operands[3] = CONST0_RTX (V2DImode);
-}
-  [(set_attr "type" "ssemuladd")
-   (set_attr "mode" "TI")])
-
-;; SSE5 parallel integer multiply/add instructions for the intrinisics
-(define_insn "sse5_pmacsswd"
-  [(set (match_operand:V4SI 0 "register_operand" "=x,x,x")
-	(ss_plus:V4SI
-	 (mult:V4SI
-	  (sign_extend:V4SI
-	   (vec_select:V4HI
-	    (match_operand:V8HI 1 "nonimmediate_operand" "%x,x,m")
-	    (parallel [(const_int 1)
-		       (const_int 3)
-		       (const_int 5)
-		       (const_int 7)])))
-	  (sign_extend:V4SI
-	   (vec_select:V4HI
-	    (match_operand:V8HI 2 "nonimmediate_operand" "x,m,x")
-	    (parallel [(const_int 1)
-		       (const_int 3)
-		       (const_int 5)
-		       (const_int 7)]))))
-	 (match_operand:V4SI 3 "register_operand" "0,0,0")))]
-  "TARGET_SSE5 && ix86_sse5_valid_op_p (operands, insn, 4, false, 1, true)"
-  "@
-   pmacsswd\t{%3, %2, %1, %0|%0, %1, %2, %3}
-   pmacsswd\t{%3, %2, %1, %0|%0, %1, %2, %3}
-   pmacsswd\t{%3, %1, %2, %0|%0, %2, %1, %3}"
-  [(set_attr "type" "ssemuladd")
-   (set_attr "mode" "TI")])
-
-(define_insn "sse5_pmacswd"
-  [(set (match_operand:V4SI 0 "register_operand" "=x,x,x")
-	(plus:V4SI
-	 (mult:V4SI
-	  (sign_extend:V4SI
-	   (vec_select:V4HI
-	    (match_operand:V8HI 1 "nonimmediate_operand" "%x,x,m")
-	    (parallel [(const_int 1)
-		       (const_int 3)
-		       (const_int 5)
-		       (const_int 7)])))
-	  (sign_extend:V4SI
-	   (vec_select:V4HI
-	    (match_operand:V8HI 2 "nonimmediate_operand" "x,m,x")
-	    (parallel [(const_int 1)
-		       (const_int 3)
-		       (const_int 5)
-		       (const_int 7)]))))
-	 (match_operand:V4SI 3 "register_operand" "0,0,0")))]
-  "TARGET_SSE5 && ix86_sse5_valid_op_p (operands, insn, 4, false, 1, true)"
-  "@
-   pmacswd\t{%3, %2, %1, %0|%0, %1, %2, %3}
-   pmacswd\t{%3, %2, %1, %0|%0, %1, %2, %3}
-   pmacswd\t{%3, %1, %2, %0|%0, %2, %1, %3}"
-  [(set_attr "type" "ssemuladd")
-   (set_attr "mode" "TI")])
-
-(define_insn "sse5_pmadcsswd"
-  [(set (match_operand:V4SI 0 "register_operand" "=x,x,x")
-	(ss_plus:V4SI
-	 (plus:V4SI
-	  (mult:V4SI
-	   (sign_extend:V4SI
-	    (vec_select:V4HI
-	     (match_operand:V8HI 1 "nonimmediate_operand" "%x,x,m")
-	     (parallel [(const_int 0)
-			(const_int 2)
-			(const_int 4)
-			(const_int 6)])))
-	   (sign_extend:V4SI
-	    (vec_select:V4HI
-	     (match_operand:V8HI 2 "nonimmediate_operand" "x,m,x")
-	     (parallel [(const_int 0)
-			(const_int 2)
-			(const_int 4)
-			(const_int 6)]))))
-	  (mult:V4SI
-	   (sign_extend:V4SI
-	    (vec_select:V4HI
-	     (match_dup 1)
-	     (parallel [(const_int 1)
-			(const_int 3)
-			(const_int 5)
-			(const_int 7)])))
-	   (sign_extend:V4SI
-	    (vec_select:V4HI
-	     (match_dup 2)
-	     (parallel [(const_int 1)
-			(const_int 3)
-			(const_int 5)
-			(const_int 7)])))))
-	 (match_operand:V4SI 3 "register_operand" "0,0,0")))]
-  "TARGET_SSE5 && ix86_sse5_valid_op_p (operands, insn, 4, false, 1, true)"
-  "@
-   pmadcsswd\t{%3, %2, %1, %0|%0, %1, %2, %3}
-   pmadcsswd\t{%3, %2, %1, %0|%0, %1, %2, %3}
-   pmadcsswd\t{%3, %1, %2, %0|%0, %2, %1, %3}"
-  [(set_attr "type" "ssemuladd")
-   (set_attr "mode" "TI")])
-
-(define_insn "sse5_pmadcswd"
-  [(set (match_operand:V4SI 0 "register_operand" "=x,x,x")
-	(plus:V4SI
-	 (plus:V4SI
-	  (mult:V4SI
-	   (sign_extend:V4SI
-	    (vec_select:V4HI
-	     (match_operand:V8HI 1 "nonimmediate_operand" "%x,x,m")
-	     (parallel [(const_int 0)
-			(const_int 2)
-			(const_int 4)
-			(const_int 6)])))
-	   (sign_extend:V4SI
-	    (vec_select:V4HI
-	     (match_operand:V8HI 2 "nonimmediate_operand" "x,m,x")
-	     (parallel [(const_int 0)
-			(const_int 2)
-			(const_int 4)
-			(const_int 6)]))))
-	  (mult:V4SI
-	   (sign_extend:V4SI
-	    (vec_select:V4HI
-	     (match_dup 1)
-	     (parallel [(const_int 1)
-			(const_int 3)
-			(const_int 5)
-			(const_int 7)])))
-	   (sign_extend:V4SI
-	    (vec_select:V4HI
-	     (match_dup 2)
-	     (parallel [(const_int 1)
-			(const_int 3)
-			(const_int 5)
-			(const_int 7)])))))
-	 (match_operand:V4SI 3 "register_operand" "0,0,0")))]
-  "TARGET_SSE5 && ix86_sse5_valid_op_p (operands, insn, 4, false, 1, true)"
-  "@
-   pmadcswd\t{%3, %2, %1, %0|%0, %1, %2, %3}
-   pmadcswd\t{%3, %2, %1, %0|%0, %1, %2, %3}
-   pmadcswd\t{%3, %1, %2, %0|%0, %2, %1, %3}"
-  [(set_attr "type" "ssemuladd")
-   (set_attr "mode" "TI")])
-
-;; SSE5 parallel XMM conditional moves
-(define_insn "sse5_pcmov_<mode>"
-  [(set (match_operand:SSEMODE 0 "register_operand" "=x,x,x,x")
-	(if_then_else:SSEMODE
-	  (match_operand:SSEMODE 3 "nonimmediate_operand" "0,0,xm,x")
-	  (match_operand:SSEMODE 1 "vector_move_operand" "x,xm,0,0")
-	  (match_operand:SSEMODE 2 "vector_move_operand" "xm,x,x,xm")))]
-  "TARGET_SSE5 && ix86_sse5_valid_op_p (operands, insn, 4, true, 1, false)"
-  "@
-   pcmov\t{%3, %2, %1, %0|%0, %1, %2, %3}
-   pcmov\t{%3, %2, %1, %0|%0, %1, %2, %3}
-   pcmov\t{%3, %2, %1, %0|%0, %1, %2, %3}
-   pcmov\t{%3, %2, %1, %0|%0, %1, %2, %3}"
-  [(set_attr "type" "sse4arg")])
-
-;; SSE5 horizontal add/subtract instructions
-(define_insn "sse5_phaddbw"
-  [(set (match_operand:V8HI 0 "register_operand" "=x")
-	(plus:V8HI
-	 (sign_extend:V8HI
-	  (vec_select:V8QI
-	   (match_operand:V16QI 1 "nonimmediate_operand" "xm")
-	   (parallel [(const_int 0)
-		      (const_int 2)
-		      (const_int 4)
-		      (const_int 6)
-		      (const_int 8)
-		      (const_int 10)
-		      (const_int 12)
-		      (const_int 14)])))
-	 (sign_extend:V8HI
-	  (vec_select:V8QI
-	   (match_dup 1)
-	   (parallel [(const_int 1)
-		      (const_int 3)
-		      (const_int 5)
-		      (const_int 7)
-		      (const_int 9)
-		      (const_int 11)
-		      (const_int 13)
-		      (const_int 15)])))))]
-  "TARGET_SSE5"
-  "phaddbw\t{%1, %0|%0, %1}"
-  [(set_attr "type" "sseiadd1")])
-
-(define_insn "sse5_phaddbd"
-  [(set (match_operand:V4SI 0 "register_operand" "=x")
-	(plus:V4SI
-	 (plus:V4SI
-	  (sign_extend:V4SI
-	   (vec_select:V4QI
-	    (match_operand:V16QI 1 "nonimmediate_operand" "xm")
-	    (parallel [(const_int 0)
-		       (const_int 4)
-		       (const_int 8)
-		       (const_int 12)])))
-	  (sign_extend:V4SI
-	   (vec_select:V4QI
-	    (match_dup 1)
-	    (parallel [(const_int 1)
-		       (const_int 5)
-		       (const_int 9)
-		       (const_int 13)]))))
-	 (plus:V4SI
-	  (sign_extend:V4SI
-	   (vec_select:V4QI
-	    (match_dup 1)
-	    (parallel [(const_int 2)
-		       (const_int 6)
-		       (const_int 10)
-		       (const_int 14)])))
-	  (sign_extend:V4SI
-	   (vec_select:V4QI
-	    (match_dup 1)
-	    (parallel [(const_int 3)
-		       (const_int 7)
-		       (const_int 11)
-		       (const_int 15)]))))))]
-  "TARGET_SSE5"
-  "phaddbd\t{%1, %0|%0, %1}"
-  [(set_attr "type" "sseiadd1")])
-
-(define_insn "sse5_phaddbq"
-  [(set (match_operand:V2DI 0 "register_operand" "=x")
-	(plus:V2DI
-	 (plus:V2DI
-	  (plus:V2DI
-	   (sign_extend:V2DI
-	    (vec_select:V2QI
-	     (match_operand:V16QI 1 "nonimmediate_operand" "xm")
-	     (parallel [(const_int 0)
-			(const_int 4)])))
-	   (sign_extend:V2DI
-	    (vec_select:V2QI
-	     (match_dup 1)
-	     (parallel [(const_int 1)
-			(const_int 5)]))))
-	  (plus:V2DI
-	   (sign_extend:V2DI
-	    (vec_select:V2QI
-	     (match_dup 1)
-	     (parallel [(const_int 2)
-			(const_int 6)])))
-	   (sign_extend:V2DI
-	    (vec_select:V2QI
-	     (match_dup 1)
-	     (parallel [(const_int 3)
-			(const_int 7)])))))
-	 (plus:V2DI
-	  (plus:V2DI
-	   (sign_extend:V2DI
-	    (vec_select:V2QI
-	     (match_dup 1)
-	     (parallel [(const_int 8)
-			(const_int 12)])))
-	   (sign_extend:V2DI
-	    (vec_select:V2QI
-	     (match_dup 1)
-	     (parallel [(const_int 9)
-			(const_int 13)]))))
-	  (plus:V2DI
-	   (sign_extend:V2DI
-	    (vec_select:V2QI
-	     (match_dup 1)
-	     (parallel [(const_int 10)
-			(const_int 14)])))
-	   (sign_extend:V2DI
-	    (vec_select:V2QI
-	     (match_dup 1)
-	     (parallel [(const_int 11)
-			(const_int 15)])))))))]
-  "TARGET_SSE5"
-  "phaddbq\t{%1, %0|%0, %1}"
-  [(set_attr "type" "sseiadd1")])
-
-(define_insn "sse5_phaddwd"
-  [(set (match_operand:V4SI 0 "register_operand" "=x")
-	(plus:V4SI
-	 (sign_extend:V4SI
-	  (vec_select:V4HI
-	   (match_operand:V8HI 1 "nonimmediate_operand" "xm")
-	   (parallel [(const_int 0)
-		      (const_int 2)
-		      (const_int 4)
-		      (const_int 6)])))
-	 (sign_extend:V4SI
-	  (vec_select:V4HI
-	   (match_dup 1)
-	   (parallel [(const_int 1)
-		      (const_int 3)
-		      (const_int 5)
-		      (const_int 7)])))))]
-  "TARGET_SSE5"
-  "phaddwd\t{%1, %0|%0, %1}"
-  [(set_attr "type" "sseiadd1")])
-
-(define_insn "sse5_phaddwq"
-  [(set (match_operand:V2DI 0 "register_operand" "=x")
-	(plus:V2DI
-	 (plus:V2DI
-	  (sign_extend:V2DI
-	   (vec_select:V2HI
-	    (match_operand:V8HI 1 "nonimmediate_operand" "xm")
-	    (parallel [(const_int 0)
-		       (const_int 4)])))
-	  (sign_extend:V2DI
-	   (vec_select:V2HI
-	    (match_dup 1)
-	    (parallel [(const_int 1)
-		       (const_int 5)]))))
-	 (plus:V2DI
-	  (sign_extend:V2DI
-	   (vec_select:V2HI
-	    (match_dup 1)
-	    (parallel [(const_int 2)
-		       (const_int 6)])))
-	  (sign_extend:V2DI
-	   (vec_select:V2HI
-	    (match_dup 1)
-	    (parallel [(const_int 3)
-		       (const_int 7)]))))))]
-  "TARGET_SSE5"
-  "phaddwq\t{%1, %0|%0, %1}"
-  [(set_attr "type" "sseiadd1")])
-
-(define_insn "sse5_phadddq"
-  [(set (match_operand:V2DI 0 "register_operand" "=x")
-	(plus:V2DI
-	 (sign_extend:V2DI
-	  (vec_select:V2SI
-	   (match_operand:V4SI 1 "nonimmediate_operand" "xm")
-	   (parallel [(const_int 0)
-		      (const_int 2)])))
-	 (sign_extend:V2DI
-	  (vec_select:V2SI
-	   (match_dup 1)
-	   (parallel [(const_int 1)
-		      (const_int 3)])))))]
-  "TARGET_SSE5"
-  "phadddq\t{%1, %0|%0, %1}"
-  [(set_attr "type" "sseiadd1")])
-
-(define_insn "sse5_phaddubw"
-  [(set (match_operand:V8HI 0 "register_operand" "=x")
-	(plus:V8HI
-	 (zero_extend:V8HI
-	  (vec_select:V8QI
-	   (match_operand:V16QI 1 "nonimmediate_operand" "xm")
-	   (parallel [(const_int 0)
-		      (const_int 2)
-		      (const_int 4)
-		      (const_int 6)
-		      (const_int 8)
-		      (const_int 10)
-		      (const_int 12)
-		      (const_int 14)])))
-	 (zero_extend:V8HI
-	  (vec_select:V8QI
-	   (match_dup 1)
-	   (parallel [(const_int 1)
-		      (const_int 3)
-		      (const_int 5)
-		      (const_int 7)
-		      (const_int 9)
-		      (const_int 11)
-		      (const_int 13)
-		      (const_int 15)])))))]
-  "TARGET_SSE5"
-  "phaddubw\t{%1, %0|%0, %1}"
-  [(set_attr "type" "sseiadd1")])
-
-(define_insn "sse5_phaddubd"
-  [(set (match_operand:V4SI 0 "register_operand" "=x")
-	(plus:V4SI
-	 (plus:V4SI
-	  (zero_extend:V4SI
-	   (vec_select:V4QI
-	    (match_operand:V16QI 1 "nonimmediate_operand" "xm")
-	    (parallel [(const_int 0)
-		       (const_int 4)
-		       (const_int 8)
-		       (const_int 12)])))
-	  (zero_extend:V4SI
-	   (vec_select:V4QI
-	    (match_dup 1)
-	    (parallel [(const_int 1)
-		       (const_int 5)
-		       (const_int 9)
-		       (const_int 13)]))))
-	 (plus:V4SI
-	  (zero_extend:V4SI
-	   (vec_select:V4QI
-	    (match_dup 1)
-	    (parallel [(const_int 2)
-		       (const_int 6)
-		       (const_int 10)
-		       (const_int 14)])))
-	  (zero_extend:V4SI
-	   (vec_select:V4QI
-	    (match_dup 1)
-	    (parallel [(const_int 3)
-		       (const_int 7)
-		       (const_int 11)
-		       (const_int 15)]))))))]
-  "TARGET_SSE5"
-  "phaddubd\t{%1, %0|%0, %1}"
-  [(set_attr "type" "sseiadd1")])
-
-(define_insn "sse5_phaddubq"
-  [(set (match_operand:V2DI 0 "register_operand" "=x")
-	(plus:V2DI
-	 (plus:V2DI
-	  (plus:V2DI
-	   (zero_extend:V2DI
-	    (vec_select:V2QI
-	     (match_operand:V16QI 1 "nonimmediate_operand" "xm")
-	     (parallel [(const_int 0)
-			(const_int 4)])))
-	   (sign_extend:V2DI
-	    (vec_select:V2QI
-	     (match_dup 1)
-	     (parallel [(const_int 1)
-			(const_int 5)]))))
-	  (plus:V2DI
-	   (zero_extend:V2DI
-	    (vec_select:V2QI
-	     (match_dup 1)
-	     (parallel [(const_int 2)
-			(const_int 6)])))
-	   (zero_extend:V2DI
-	    (vec_select:V2QI
-	     (match_dup 1)
-	     (parallel [(const_int 3)
-			(const_int 7)])))))
-	 (plus:V2DI
-	  (plus:V2DI
-	   (zero_extend:V2DI
-	    (vec_select:V2QI
-	     (match_dup 1)
-	     (parallel [(const_int 8)
-			(const_int 12)])))
-	   (sign_extend:V2DI
-	    (vec_select:V2QI
-	     (match_dup 1)
-	     (parallel [(const_int 9)
-			(const_int 13)]))))
-	  (plus:V2DI
-	   (zero_extend:V2DI
-	    (vec_select:V2QI
-	     (match_dup 1)
-	     (parallel [(const_int 10)
-			(const_int 14)])))
-	   (zero_extend:V2DI
-	    (vec_select:V2QI
-	     (match_dup 1)
-	     (parallel [(const_int 11)
-			(const_int 15)])))))))]
-  "TARGET_SSE5"
-  "phaddubq\t{%1, %0|%0, %1}"
-  [(set_attr "type" "sseiadd1")])
-
-(define_insn "sse5_phadduwd"
-  [(set (match_operand:V4SI 0 "register_operand" "=x")
-	(plus:V4SI
-	 (zero_extend:V4SI
-	  (vec_select:V4HI
-	   (match_operand:V8HI 1 "nonimmediate_operand" "xm")
-	   (parallel [(const_int 0)
-		      (const_int 2)
-		      (const_int 4)
-		      (const_int 6)])))
-	 (zero_extend:V4SI
-	  (vec_select:V4HI
-	   (match_dup 1)
-	   (parallel [(const_int 1)
-		      (const_int 3)
-		      (const_int 5)
-		      (const_int 7)])))))]
-  "TARGET_SSE5"
-  "phadduwd\t{%1, %0|%0, %1}"
-  [(set_attr "type" "sseiadd1")])
-
-(define_insn "sse5_phadduwq"
-  [(set (match_operand:V2DI 0 "register_operand" "=x")
-	(plus:V2DI
-	 (plus:V2DI
-	  (zero_extend:V2DI
-	   (vec_select:V2HI
-	    (match_operand:V8HI 1 "nonimmediate_operand" "xm")
-	    (parallel [(const_int 0)
-		       (const_int 4)])))
-	  (zero_extend:V2DI
-	   (vec_select:V2HI
-	    (match_dup 1)
-	    (parallel [(const_int 1)
-		       (const_int 5)]))))
-	 (plus:V2DI
-	  (zero_extend:V2DI
-	   (vec_select:V2HI
-	    (match_dup 1)
-	    (parallel [(const_int 2)
-		       (const_int 6)])))
-	  (zero_extend:V2DI
-	   (vec_select:V2HI
-	    (match_dup 1)
-	    (parallel [(const_int 3)
-		       (const_int 7)]))))))]
-  "TARGET_SSE5"
-  "phadduwq\t{%1, %0|%0, %1}"
-  [(set_attr "type" "sseiadd1")])
-
-(define_insn "sse5_phaddudq"
-  [(set (match_operand:V2DI 0 "register_operand" "=x")
-	(plus:V2DI
-	 (zero_extend:V2DI
-	  (vec_select:V2SI
-	   (match_operand:V4SI 1 "nonimmediate_operand" "xm")
-	   (parallel [(const_int 0)
-		      (const_int 2)])))
-	 (zero_extend:V2DI
-	  (vec_select:V2SI
-	   (match_dup 1)
-	   (parallel [(const_int 1)
-		      (const_int 3)])))))]
-  "TARGET_SSE5"
-  "phaddudq\t{%1, %0|%0, %1}"
-  [(set_attr "type" "sseiadd1")])
-
-(define_insn "sse5_phsubbw"
-  [(set (match_operand:V8HI 0 "register_operand" "=x")
-	(minus:V8HI
-	 (sign_extend:V8HI
-	  (vec_select:V8QI
-	   (match_operand:V16QI 1 "nonimmediate_operand" "xm")
-	   (parallel [(const_int 0)
-		      (const_int 2)
-		      (const_int 4)
-		      (const_int 6)
-		      (const_int 8)
-		      (const_int 10)
-		      (const_int 12)
-		      (const_int 14)])))
-	 (sign_extend:V8HI
-	  (vec_select:V8QI
-	   (match_dup 1)
-	   (parallel [(const_int 1)
-		      (const_int 3)
-		      (const_int 5)
-		      (const_int 7)
-		      (const_int 9)
-		      (const_int 11)
-		      (const_int 13)
-		      (const_int 15)])))))]
-  "TARGET_SSE5"
-  "phsubbw\t{%1, %0|%0, %1}"
-  [(set_attr "type" "sseiadd1")])
-
-(define_insn "sse5_phsubwd"
-  [(set (match_operand:V4SI 0 "register_operand" "=x")
-	(minus:V4SI
-	 (sign_extend:V4SI
-	  (vec_select:V4HI
-	   (match_operand:V8HI 1 "nonimmediate_operand" "xm")
-	   (parallel [(const_int 0)
-		      (const_int 2)
-		      (const_int 4)
-		      (const_int 6)])))
-	 (sign_extend:V4SI
-	  (vec_select:V4HI
-	   (match_dup 1)
-	   (parallel [(const_int 1)
-		      (const_int 3)
-		      (const_int 5)
-		      (const_int 7)])))))]
-  "TARGET_SSE5"
-  "phsubwd\t{%1, %0|%0, %1}"
-  [(set_attr "type" "sseiadd1")])
-
-(define_insn "sse5_phsubdq"
-  [(set (match_operand:V2DI 0 "register_operand" "=x")
-	(minus:V2DI
-	 (sign_extend:V2DI
-	  (vec_select:V2SI
-	   (match_operand:V4SI 1 "nonimmediate_operand" "xm")
-	   (parallel [(const_int 0)
-		      (const_int 2)])))
-	 (sign_extend:V2DI
-	  (vec_select:V2SI
-	   (match_dup 1)
-	   (parallel [(const_int 1)
-		      (const_int 3)])))))]
-  "TARGET_SSE5"
-  "phsubdq\t{%1, %0|%0, %1}"
-  [(set_attr "type" "sseiadd1")])
-
-;; SSE5 permute instructions
-(define_insn "sse5_pperm"
-  [(set (match_operand:V16QI 0 "register_operand" "=x,x,x,x")
-	(unspec:V16QI
-	  [(match_operand:V16QI 1 "nonimmediate_operand" "0,0,x,xm")
-	   (match_operand:V16QI 2 "nonimmediate_operand" "x,xm,xm,x")
-	   (match_operand:V16QI 3 "nonimmediate_operand" "xm,x,0,0")]
-	  UNSPEC_SSE5_PERMUTE))]
-  "TARGET_SSE5 && ix86_sse5_valid_op_p (operands, insn, 4, true, 1, false)"
-  "pperm\t{%3, %2, %1, %0|%0, %1, %2, %3}"
-  [(set_attr "type" "sse4arg")
-   (set_attr "mode" "TI")])
-
-;; The following are for the various unpack insns which doesn't need the first
-;; source operand, so we can just use the output operand for the first operand.
-;; This allows either of the other two operands to be a memory operand.  We
-;; can't just use the first operand as an argument to the normal pperm because
-;; then an output only argument, suddenly becomes an input operand.
-(define_insn "sse5_pperm_zero_v16qi_v8hi"
-  [(set (match_operand:V8HI 0 "register_operand" "=x,x")
-	(zero_extend:V8HI
-	 (vec_select:V8QI
-	  (match_operand:V16QI 1 "nonimmediate_operand" "xm,x")
-	  (match_operand 2 "" ""))))	;; parallel with const_int's
-   (use (match_operand:V16QI 3 "nonimmediate_operand" "x,xm"))]
-  "TARGET_SSE5
-   && (register_operand (operands[1], V16QImode)
-       || register_operand (operands[2], V16QImode))"
-  "pperm\t{%3, %1, %0, %0|%0, %0, %1, %3}"
-  [(set_attr "type" "sseadd")
-   (set_attr "prefix_data16" "0")
-   (set_attr "prefix_extra" "2")
-   (set_attr "mode" "TI")])
-
-(define_insn "sse5_pperm_sign_v16qi_v8hi"
-  [(set (match_operand:V8HI 0 "register_operand" "=x,x")
-	(sign_extend:V8HI
-	 (vec_select:V8QI
-	  (match_operand:V16QI 1 "nonimmediate_operand" "xm,x")
-	  (match_operand 2 "" ""))))	;; parallel with const_int's
-   (use (match_operand:V16QI 3 "nonimmediate_operand" "x,xm"))]
-  "TARGET_SSE5
-   && (register_operand (operands[1], V16QImode)
-       || register_operand (operands[2], V16QImode))"
-  "pperm\t{%3, %1, %0, %0|%0, %0, %1, %3}"
-  [(set_attr "type" "sseadd")
-   (set_attr "prefix_data16" "0")
-   (set_attr "prefix_extra" "2")
-   (set_attr "mode" "TI")])
-
-(define_insn "sse5_pperm_zero_v8hi_v4si"
-  [(set (match_operand:V4SI 0 "register_operand" "=x,x")
-	(zero_extend:V4SI
-	 (vec_select:V4HI
-	  (match_operand:V8HI 1 "nonimmediate_operand" "xm,x")
-	  (match_operand 2 "" ""))))	;; parallel with const_int's
-   (use (match_operand:V16QI 3 "nonimmediate_operand" "x,xm"))]
-  "TARGET_SSE5
-   && (register_operand (operands[1], V8HImode)
-       || register_operand (operands[2], V16QImode))"
-  "pperm\t{%3, %1, %0, %0|%0, %0, %1, %3}"
-  [(set_attr "type" "sseadd")
-   (set_attr "prefix_data16" "0")
-   (set_attr "prefix_extra" "2")
-   (set_attr "mode" "TI")])
-
-(define_insn "sse5_pperm_sign_v8hi_v4si"
-  [(set (match_operand:V4SI 0 "register_operand" "=x,x")
-	(sign_extend:V4SI
-	 (vec_select:V4HI
-	  (match_operand:V8HI 1 "nonimmediate_operand" "xm,x")
-	  (match_operand 2 "" ""))))	;; parallel with const_int's
-   (use (match_operand:V16QI 3 "nonimmediate_operand" "x,xm"))]
-  "TARGET_SSE5
-   && (register_operand (operands[1], V8HImode)
-       || register_operand (operands[2], V16QImode))"
-  "pperm\t{%3, %1, %0, %0|%0, %0, %1, %3}"
-  [(set_attr "type" "sseadd")
-   (set_attr "prefix_data16" "0")
-   (set_attr "prefix_extra" "2")
-   (set_attr "mode" "TI")])
-
-(define_insn "sse5_pperm_zero_v4si_v2di"
-  [(set (match_operand:V2DI 0 "register_operand" "=x,x")
-	(zero_extend:V2DI
-	 (vec_select:V2SI
-	  (match_operand:V4SI 1 "nonimmediate_operand" "xm,x")
-	  (match_operand 2 "" ""))))	;; parallel with const_int's
-   (use (match_operand:V16QI 3 "nonimmediate_operand" "x,xm"))]
-  "TARGET_SSE5
-   && (register_operand (operands[1], V4SImode)
-       || register_operand (operands[2], V16QImode))"
-  "pperm\t{%3, %1, %0, %0|%0, %0, %1, %3}"
-  [(set_attr "type" "sseadd")
-   (set_attr "prefix_data16" "0")
-   (set_attr "prefix_extra" "2")
-   (set_attr "mode" "TI")])
-
-(define_insn "sse5_pperm_sign_v4si_v2di"
-  [(set (match_operand:V2DI 0 "register_operand" "=x,x")
-	(sign_extend:V2DI
-	 (vec_select:V2SI
-	  (match_operand:V4SI 1 "nonimmediate_operand" "xm,x")
-	  (match_operand 2 "" ""))))	;; parallel with const_int's
-   (use (match_operand:V16QI 3 "nonimmediate_operand" "x,xm"))]
-  "TARGET_SSE5
-   && (register_operand (operands[1], V4SImode)
-       || register_operand (operands[2], V16QImode))"
-  "pperm\t{%3, %1, %0, %0|%0, %0, %1, %3}"
-  [(set_attr "type" "sseadd")
-   (set_attr "prefix_data16" "0")
-   (set_attr "prefix_extra" "2")
-   (set_attr "mode" "TI")])
-
-;; SSE5 pack instructions that combine two vectors into a smaller vector
-(define_insn "sse5_pperm_pack_v2di_v4si"
-  [(set (match_operand:V4SI 0 "register_operand" "=x,x,x,x")
-	(vec_concat:V4SI
-	 (truncate:V2SI
-	  (match_operand:V2DI 1 "nonimmediate_operand" "0,0,x,xm"))
-	 (truncate:V2SI
-	  (match_operand:V2DI 2 "nonimmediate_operand" "x,xm,xm,x"))))
-   (use (match_operand:V16QI 3 "nonimmediate_operand" "xm,x,0,0"))]
-  "TARGET_SSE5 && ix86_sse5_valid_op_p (operands, insn, 4, true, 1, false)"
-  "pperm\t{%3, %2, %1, %0|%0, %1, %2, %3}"
-  [(set_attr "type" "sse4arg")
-   (set_attr "mode" "TI")])
-
-(define_insn "sse5_pperm_pack_v4si_v8hi"
-  [(set (match_operand:V8HI 0 "register_operand" "=x,x,x,x")
-	(vec_concat:V8HI
-	 (truncate:V4HI
-	  (match_operand:V4SI 1 "nonimmediate_operand" "0,0,x,xm"))
-	 (truncate:V4HI
-	  (match_operand:V4SI 2 "nonimmediate_operand" "x,xm,xm,x"))))
-   (use (match_operand:V16QI 3 "nonimmediate_operand" "xm,x,0,0"))]
-  "TARGET_SSE5 && ix86_sse5_valid_op_p (operands, insn, 4, true, 1, false)"
-  "pperm\t{%3, %2, %1, %0|%0, %1, %2, %3}"
-  [(set_attr "type" "sse4arg")
-   (set_attr "mode" "TI")])
-
-(define_insn "sse5_pperm_pack_v8hi_v16qi"
-  [(set (match_operand:V16QI 0 "register_operand" "=x,x,x,x")
-	(vec_concat:V16QI
-	 (truncate:V8QI
-	  (match_operand:V8HI 1 "nonimmediate_operand" "0,0,x,xm"))
-	 (truncate:V8QI
-	  (match_operand:V8HI 2 "nonimmediate_operand" "x,xm,xm,x"))))
-   (use (match_operand:V16QI 3 "nonimmediate_operand" "xm,x,0,0"))]
-  "TARGET_SSE5 && ix86_sse5_valid_op_p (operands, insn, 4, true, 1, false)"
-  "pperm\t{%3, %2, %1, %0|%0, %1, %2, %3}"
-  [(set_attr "type" "sse4arg")
-   (set_attr "mode" "TI")])
-
-;; Floating point permutation (permps, permpd)
-(define_insn "sse5_perm<mode>"
-  [(set (match_operand:SSEMODEF2P 0 "register_operand" "=x,x,x,x")
-	(unspec:SSEMODEF2P
-	 [(match_operand:SSEMODEF2P 1 "nonimmediate_operand" "0,0,x,xm")
-	  (match_operand:SSEMODEF2P 2 "nonimmediate_operand" "x,xm,xm,x")
-	  (match_operand:V16QI 3 "nonimmediate_operand" "xm,x,0,0")]
-	 UNSPEC_SSE5_PERMUTE))]
-  "TARGET_SSE5 && ix86_sse5_valid_op_p (operands, insn, 4, true, 1, false)"
-  "perm<ssemodesuffixf4>\t{%3, %2, %1, %0|%0, %1, %2, %3}"
-  [(set_attr "type" "sse4arg")
-   (set_attr "mode" "<MODE>")])
-
-;; SSE5 packed rotate instructions
-(define_expand "rotl<mode>3"
-  [(set (match_operand:SSEMODE1248 0 "register_operand" "")
-	(rotate:SSEMODE1248
-	 (match_operand:SSEMODE1248 1 "nonimmediate_operand" "")
-	 (match_operand:SI 2 "general_operand")))]
-  "TARGET_SSE5"
-{
-  /* If we were given a scalar, convert it to parallel */
-  if (! const_0_to_<sserotatemax>_operand (operands[2], SImode))
-    {
-      rtvec vs = rtvec_alloc (<ssescalarnum>);
-      rtx par = gen_rtx_PARALLEL (<MODE>mode, vs);
-      rtx reg = gen_reg_rtx (<MODE>mode);
-      rtx op2 = operands[2];
-      int i;
-
-      if (GET_MODE (op2) != <ssescalarmode>mode)
-        {
-	  op2 = gen_reg_rtx (<ssescalarmode>mode);
-	  convert_move (op2, operands[2], false);
-	}
-
-      for (i = 0; i < <ssescalarnum>; i++)
-	RTVEC_ELT (vs, i) = op2;
-
-      emit_insn (gen_vec_init<mode> (reg, par));
-      emit_insn (gen_sse5_vrotl<mode>3 (operands[0], operands[1], reg));
-      DONE;
-    }
-})
-
-(define_expand "rotr<mode>3"
-  [(set (match_operand:SSEMODE1248 0 "register_operand" "")
-	(rotatert:SSEMODE1248
-	 (match_operand:SSEMODE1248 1 "nonimmediate_operand" "")
-	 (match_operand:SI 2 "general_operand")))]
-  "TARGET_SSE5"
-{
-  /* If we were given a scalar, convert it to parallel */
-  if (! const_0_to_<sserotatemax>_operand (operands[2], SImode))
-    {
-      rtvec vs = rtvec_alloc (<ssescalarnum>);
-      rtx par = gen_rtx_PARALLEL (<MODE>mode, vs);
-      rtx neg = gen_reg_rtx (<MODE>mode);
-      rtx reg = gen_reg_rtx (<MODE>mode);
-      rtx op2 = operands[2];
-      int i;
-
-      if (GET_MODE (op2) != <ssescalarmode>mode)
-        {
-	  op2 = gen_reg_rtx (<ssescalarmode>mode);
-	  convert_move (op2, operands[2], false);
-	}
-
-      for (i = 0; i < <ssescalarnum>; i++)
-	RTVEC_ELT (vs, i) = op2;
-
-      emit_insn (gen_vec_init<mode> (reg, par));
-      emit_insn (gen_neg<mode>2 (neg, reg));
-      emit_insn (gen_sse5_vrotl<mode>3 (operands[0], operands[1], neg));
-      DONE;
-    }
-})
-
-(define_insn "sse5_rotl<mode>3"
-  [(set (match_operand:SSEMODE1248 0 "register_operand" "=x")
-	(rotate:SSEMODE1248
-	 (match_operand:SSEMODE1248 1 "nonimmediate_operand" "xm")
-	 (match_operand:SI 2 "const_0_to_<sserotatemax>_operand" "n")))]
-  "TARGET_SSE5"
-  "prot<ssevecsize>\t{%2, %1, %0|%0, %1, %2}"
-  [(set_attr "type" "sseishft")
-   (set_attr "length_immediate" "1")
-   (set_attr "mode" "TI")])
-
-(define_insn "sse5_rotr<mode>3"
-  [(set (match_operand:SSEMODE1248 0 "register_operand" "=x")
-	(rotatert:SSEMODE1248
-	 (match_operand:SSEMODE1248 1 "nonimmediate_operand" "xm")
-	 (match_operand:SI 2 "const_0_to_<sserotatemax>_operand" "n")))]
-  "TARGET_SSE5"
-{
-  operands[3] = GEN_INT ((<ssescalarnum> * 8) - INTVAL (operands[2]));
-  return \"prot<ssevecsize>\t{%3, %1, %0|%0, %1, %3}\";
-}
-  [(set_attr "type" "sseishft")
-   (set_attr "length_immediate" "1")
-   (set_attr "mode" "TI")])
-
-(define_expand "vrotr<mode>3"
-  [(match_operand:SSEMODE1248 0 "register_operand" "")
-   (match_operand:SSEMODE1248 1 "register_operand" "")
-   (match_operand:SSEMODE1248 2 "register_operand" "")]
-  "TARGET_SSE5"
-{
-  rtx reg = gen_reg_rtx (<MODE>mode);
-  emit_insn (gen_neg<mode>2 (reg, operands[2]));
-  emit_insn (gen_sse5_vrotl<mode>3 (operands[0], operands[1], reg));
-  DONE;
-})
-
-(define_expand "vrotl<mode>3"
-  [(match_operand:SSEMODE1248 0 "register_operand" "")
-   (match_operand:SSEMODE1248 1 "register_operand" "")
-   (match_operand:SSEMODE1248 2 "register_operand" "")]
-  "TARGET_SSE5"
-{
-  emit_insn (gen_sse5_vrotl<mode>3 (operands[0], operands[1], operands[2]));
-  DONE;
-})
-
-(define_insn "sse5_vrotl<mode>3"
-  [(set (match_operand:SSEMODE1248 0 "register_operand" "=x,x")
-	(if_then_else:SSEMODE1248
-	 (ge:SSEMODE1248
-	  (match_operand:SSEMODE1248 2 "nonimmediate_operand" "xm,x")
-	  (const_int 0))
-	 (rotate:SSEMODE1248
-	  (match_operand:SSEMODE1248 1 "nonimmediate_operand" "x,xm")
-	  (match_dup 2))
-	 (rotatert:SSEMODE1248
-	  (match_dup 1)
-	  (neg:SSEMODE1248 (match_dup 2)))))]
-  "TARGET_SSE5 && ix86_sse5_valid_op_p (operands, insn, 3, true, 1, false)"
-  "prot<ssevecsize>\t{%2, %1, %0|%0, %1, %2}"
-  [(set_attr "type" "sseishft")
-   (set_attr "prefix_data16" "0")
-   (set_attr "prefix_extra" "2")
-   (set_attr "mode" "TI")])
-
-;; SSE5 packed shift instructions.
-;; FIXME: add V2DI back in
-(define_expand "vlshr<mode>3"
-  [(match_operand:SSEMODE124 0 "register_operand" "")
-   (match_operand:SSEMODE124 1 "register_operand" "")
-   (match_operand:SSEMODE124 2 "register_operand" "")]
-  "TARGET_SSE5"
-{
-  rtx neg = gen_reg_rtx (<MODE>mode);
-  emit_insn (gen_neg<mode>2 (neg, operands[2]));
-  emit_insn (gen_sse5_lshl<mode>3 (operands[0], operands[1], neg));
-  DONE;
-})
-
-(define_expand "vashr<mode>3"
-  [(match_operand:SSEMODE124 0 "register_operand" "")
-   (match_operand:SSEMODE124 1 "register_operand" "")
-   (match_operand:SSEMODE124 2 "register_operand" "")]
-  "TARGET_SSE5"
-{
-  rtx neg = gen_reg_rtx (<MODE>mode);
-  emit_insn (gen_neg<mode>2 (neg, operands[2]));
-  emit_insn (gen_sse5_ashl<mode>3 (operands[0], operands[1], neg));
-  DONE;
-})
-
-(define_expand "vashl<mode>3"
-  [(match_operand:SSEMODE124 0 "register_operand" "")
-   (match_operand:SSEMODE124 1 "register_operand" "")
-   (match_operand:SSEMODE124 2 "register_operand" "")]
-  "TARGET_SSE5"
-{
-  emit_insn (gen_sse5_ashl<mode>3 (operands[0], operands[1], operands[2]));
-  DONE;
-})
-
-(define_insn "sse5_ashl<mode>3"
-  [(set (match_operand:SSEMODE1248 0 "register_operand" "=x,x")
-	(if_then_else:SSEMODE1248
-	 (ge:SSEMODE1248
-	  (match_operand:SSEMODE1248 2 "nonimmediate_operand" "xm,x")
-	  (const_int 0))
-	 (ashift:SSEMODE1248
-	  (match_operand:SSEMODE1248 1 "nonimmediate_operand" "x,xm")
-	  (match_dup 2))
-	 (ashiftrt:SSEMODE1248
-	  (match_dup 1)
-	  (neg:SSEMODE1248 (match_dup 2)))))]
-  "TARGET_SSE5 && ix86_sse5_valid_op_p (operands, insn, 3, true, 1, false)"
-  "psha<ssevecsize>\t{%2, %1, %0|%0, %1, %2}"
-  [(set_attr "type" "sseishft")
-   (set_attr "prefix_data16" "0")
-   (set_attr "prefix_extra" "2")
-   (set_attr "mode" "TI")])
-
-(define_insn "sse5_lshl<mode>3"
-  [(set (match_operand:SSEMODE1248 0 "register_operand" "=x,x")
-	(if_then_else:SSEMODE1248
-	 (ge:SSEMODE1248
-	  (match_operand:SSEMODE1248 2 "nonimmediate_operand" "xm,x")
-	  (const_int 0))
-	 (ashift:SSEMODE1248
-	  (match_operand:SSEMODE1248 1 "nonimmediate_operand" "x,xm")
-	  (match_dup 2))
-	 (lshiftrt:SSEMODE1248
-	  (match_dup 1)
-	  (neg:SSEMODE1248 (match_dup 2)))))]
-  "TARGET_SSE5 && ix86_sse5_valid_op_p (operands, insn, 3, true, 1, false)"
-  "pshl<ssevecsize>\t{%2, %1, %0|%0, %1, %2}"
-  [(set_attr "type" "sseishft")
-   (set_attr "prefix_data16" "0")
-   (set_attr "prefix_extra" "2")
-   (set_attr "mode" "TI")])
-
-;; SSE2 doesn't have some shift varients, so define versions for SSE5
-(define_expand "ashlv16qi3"
-  [(match_operand:V16QI 0 "register_operand" "")
-   (match_operand:V16QI 1 "register_operand" "")
-   (match_operand:SI 2 "nonmemory_operand" "")]
-  "TARGET_SSE5"
-{
-  rtvec vs = rtvec_alloc (16);
-  rtx par = gen_rtx_PARALLEL (V16QImode, vs);
-  rtx reg = gen_reg_rtx (V16QImode);
-  int i;
-  for (i = 0; i < 16; i++)
-    RTVEC_ELT (vs, i) = operands[2];
-
-  emit_insn (gen_vec_initv16qi (reg, par));
-  emit_insn (gen_sse5_ashlv16qi3 (operands[0], operands[1], reg));
-  DONE;
-})
-
-(define_expand "lshlv16qi3"
-  [(match_operand:V16QI 0 "register_operand" "")
-   (match_operand:V16QI 1 "register_operand" "")
-   (match_operand:SI 2 "nonmemory_operand" "")]
-  "TARGET_SSE5"
-{
-  rtvec vs = rtvec_alloc (16);
-  rtx par = gen_rtx_PARALLEL (V16QImode, vs);
-  rtx reg = gen_reg_rtx (V16QImode);
-  int i;
-  for (i = 0; i < 16; i++)
-    RTVEC_ELT (vs, i) = operands[2];
-
-  emit_insn (gen_vec_initv16qi (reg, par));
-  emit_insn (gen_sse5_lshlv16qi3 (operands[0], operands[1], reg));
-  DONE;
-})
-
-(define_expand "ashrv16qi3"
-  [(match_operand:V16QI 0 "register_operand" "")
-   (match_operand:V16QI 1 "register_operand" "")
-   (match_operand:SI 2 "nonmemory_operand" "")]
-  "TARGET_SSE5"
-{
-  rtvec vs = rtvec_alloc (16);
-  rtx par = gen_rtx_PARALLEL (V16QImode, vs);
-  rtx reg = gen_reg_rtx (V16QImode);
-  int i;
-  rtx ele = ((CONST_INT_P (operands[2]))
-	     ? GEN_INT (- INTVAL (operands[2]))
-	     : operands[2]);
-
-  for (i = 0; i < 16; i++)
-    RTVEC_ELT (vs, i) = ele;
-
-  emit_insn (gen_vec_initv16qi (reg, par));
-
-  if (!CONST_INT_P (operands[2]))
-    {
-      rtx neg = gen_reg_rtx (V16QImode);
-      emit_insn (gen_negv16qi2 (neg, reg));
-      emit_insn (gen_sse5_ashlv16qi3 (operands[0], operands[1], neg));
-    }
-  else
-    emit_insn (gen_sse5_ashlv16qi3 (operands[0], operands[1], reg));
-
-  DONE;
-})
-
-(define_expand "ashrv2di3"
-  [(match_operand:V2DI 0 "register_operand" "")
-   (match_operand:V2DI 1 "register_operand" "")
-   (match_operand:DI 2 "nonmemory_operand" "")]
-  "TARGET_SSE5"
-{
-  rtvec vs = rtvec_alloc (2);
-  rtx par = gen_rtx_PARALLEL (V2DImode, vs);
-  rtx reg = gen_reg_rtx (V2DImode);
-  rtx ele;
-
-  if (CONST_INT_P (operands[2]))
-    ele = GEN_INT (- INTVAL (operands[2]));
-  else if (GET_MODE (operands[2]) != DImode)
-    {
-      rtx move = gen_reg_rtx (DImode);
-      ele = gen_reg_rtx (DImode);
-      convert_move (move, operands[2], false);
-      emit_insn (gen_negdi2 (ele, move));
-    }
-  else
-    {
-      ele = gen_reg_rtx (DImode);
-      emit_insn (gen_negdi2 (ele, operands[2]));
-    }
-
-  RTVEC_ELT (vs, 0) = ele;
-  RTVEC_ELT (vs, 1) = ele;
-  emit_insn (gen_vec_initv2di (reg, par));
-  emit_insn (gen_sse5_ashlv2di3 (operands[0], operands[1], reg));
-  DONE;
-})
-
-;; SSE5 FRCZ support
-;; parallel insns
-(define_insn "sse5_frcz<mode>2"
-  [(set (match_operand:SSEMODEF2P 0 "register_operand" "=x")
-	(unspec:SSEMODEF2P
-	 [(match_operand:SSEMODEF2P 1 "nonimmediate_operand" "xm")]
-	 UNSPEC_FRCZ))]
-  "TARGET_SSE5"
-  "frcz<ssemodesuffixf4>\t{%1, %0|%0, %1}"
-  [(set_attr "type" "ssecvt1")
-   (set_attr "mode" "<MODE>")])
-
-;; scalar insns
-(define_insn "sse5_vmfrcz<mode>2"
-  [(set (match_operand:SSEMODEF2P 0 "register_operand" "=x")
-	(vec_merge:SSEMODEF2P
-	  (unspec:SSEMODEF2P
-	   [(match_operand:SSEMODEF2P 2 "nonimmediate_operand" "xm")]
-	   UNSPEC_FRCZ)
-	  (match_operand:SSEMODEF2P 1 "register_operand" "0")
-	  (const_int 1)))]
-  "TARGET_SSE5"
-  "frcz<ssemodesuffixf2s>\t{%2, %0|%0, %2}"
-  [(set_attr "type" "ssecvt1")
-   (set_attr "mode" "<MODE>")])
-
-(define_insn "sse5_cvtph2ps"
-  [(set (match_operand:V4SF 0 "register_operand" "=x")
-	(unspec:V4SF [(match_operand:V4HI 1 "nonimmediate_operand" "xm")]
-		     UNSPEC_CVTPH2PS))]
-  "TARGET_SSE5"
-  "cvtph2ps\t{%1, %0|%0, %1}"
-  [(set_attr "type" "ssecvt")
-   (set_attr "mode" "V4SF")])
-
-(define_insn "sse5_cvtps2ph"
-  [(set (match_operand:V4HI 0 "nonimmediate_operand" "=xm")
-	(unspec:V4HI [(match_operand:V4SF 1 "register_operand" "x")]
-		     UNSPEC_CVTPS2PH))]
-  "TARGET_SSE5"
-  "cvtps2ph\t{%1, %0|%0, %1}"
-  [(set_attr "type" "ssecvt")
-   (set_attr "mode" "V4SF")])
-
-;; Scalar versions of the com instructions that use vector types that are
-;; called from the intrinsics.  Unlike the the other s{s,d} instructions, the
-;; com instructions fill in 0's in the upper bits instead of leaving them
-;; unmodified, so we use const_vector of 0 instead of match_dup.
-(define_expand "sse5_vmmaskcmp<mode>3"
-  [(set (match_operand:SSEMODEF2P 0 "register_operand" "")
-	(vec_merge:SSEMODEF2P
-	 (match_operator:SSEMODEF2P 1 "sse5_comparison_float_operator"
-	  [(match_operand:SSEMODEF2P 2 "register_operand" "")
-	   (match_operand:SSEMODEF2P 3 "nonimmediate_operand" "")])
-	 (match_dup 4)
-	 (const_int 1)))]
-  "TARGET_SSE5"
-{
-  operands[4] = CONST0_RTX (<MODE>mode);
-})
-
-(define_insn "*sse5_vmmaskcmp<mode>3"
-  [(set (match_operand:SSEMODEF2P 0 "register_operand" "=x")
-	(vec_merge:SSEMODEF2P
-	 (match_operator:SSEMODEF2P 1 "sse5_comparison_float_operator"
-	  [(match_operand:SSEMODEF2P 2 "register_operand" "x")
-	   (match_operand:SSEMODEF2P 3 "nonimmediate_operand" "xm")])
-	  (match_operand:SSEMODEF2P 4 "")
-	  (const_int 1)))]
-  "TARGET_SSE5"
-  "com%Y1<ssemodesuffixf2s>\t{%3, %2, %0|%0, %2, %3}"
-  [(set_attr "type" "sse4arg")
-   (set_attr "prefix_data16" "0")
-   (set_attr "prefix_rep" "0")
-   (set_attr "prefix_extra" "2")
-   (set_attr "length_immediate" "1")
-   (set_attr "mode" "<ssescalarmode>")])
-
-;; We don't have a comparison operator that always returns true/false, so
-;; handle comfalse and comtrue specially.
-(define_insn "sse5_com_tf<mode>3"
-  [(set (match_operand:SSEMODEF2P 0 "register_operand" "=x")
-	(unspec:SSEMODEF2P
-	 [(match_operand:SSEMODEF2P 1 "register_operand" "x")
-	  (match_operand:SSEMODEF2P 2 "nonimmediate_operand" "xm")
-	  (match_operand:SI 3 "const_int_operand" "n")]
-	 UNSPEC_SSE5_TRUEFALSE))]
-  "TARGET_SSE5"
-{
-  const char *ret = NULL;
-
-  switch (INTVAL (operands[3]))
-    {
-    case COM_FALSE_S:
-      ret = \"comfalses<ssemodesuffixf2c>\t{%2, %1, %0|%0, %1, %2}\";
-      break;
-
-    case COM_FALSE_P:
-      ret = \"comfalsep<ssemodesuffixf2c>\t{%2, %1, %0|%0, %1, %2}\";
-      break;
-
-    case COM_TRUE_S:
-      ret = \"comfalses<ssemodesuffixf2c>\t{%2, %1, %0|%0, %1, %2}\";
-      break;
-
-    case COM_TRUE_P:
-      ret = \"comfalsep<ssemodesuffixf2c>\t{%2, %1, %0|%0, %1, %2}\";
-      break;
-
-    default:
-      gcc_unreachable ();
-    }
-
-  return ret;
-}
-  [(set_attr "type" "ssecmp")
-   (set_attr "prefix_data16" "0")
-   (set_attr "prefix_rep" "0")
-   (set_attr "prefix_extra" "2")
-   (set_attr "length_immediate" "1")
-   (set_attr "mode" "<MODE>")])
-
-(define_insn "sse5_maskcmp<mode>3"
-  [(set (match_operand:SSEMODEF2P 0 "register_operand" "=x")
-	(match_operator:SSEMODEF2P 1 "sse5_comparison_float_operator"
-	 [(match_operand:SSEMODEF2P 2 "register_operand" "x")
-	  (match_operand:SSEMODEF2P 3 "nonimmediate_operand" "xm")]))]
-  "TARGET_SSE5"
-  "com%Y1<ssemodesuffixf4>\t{%3, %2, %0|%0, %2, %3}"
-  [(set_attr "type" "ssecmp")
-   (set_attr "prefix_data16" "0")
-   (set_attr "prefix_rep" "0")
-   (set_attr "prefix_extra" "2")
-   (set_attr "length_immediate" "1")
-   (set_attr "mode" "<MODE>")])
-
-(define_insn "sse5_maskcmp<mode>3"
-  [(set (match_operand:SSEMODE1248 0 "register_operand" "=x")
-	(match_operator:SSEMODE1248 1 "ix86_comparison_int_operator"
-	 [(match_operand:SSEMODE1248 2 "register_operand" "x")
-	  (match_operand:SSEMODE1248 3 "nonimmediate_operand" "xm")]))]
-  "TARGET_SSE5"
-  "pcom%Y1<ssevecsize>\t{%3, %2, %0|%0, %2, %3}"
-  [(set_attr "type" "sse4arg")
-   (set_attr "prefix_data16" "0")
-   (set_attr "prefix_rep" "0")
-   (set_attr "prefix_extra" "2")
-   (set_attr "length_immediate" "1")
-   (set_attr "mode" "TI")])
-
-(define_insn "sse5_maskcmp_uns<mode>3"
-  [(set (match_operand:SSEMODE1248 0 "register_operand" "=x")
-	(match_operator:SSEMODE1248 1 "ix86_comparison_uns_operator"
-	 [(match_operand:SSEMODE1248 2 "register_operand" "x")
-	  (match_operand:SSEMODE1248 3 "nonimmediate_operand" "xm")]))]
-  "TARGET_SSE5"
-  "pcom%Y1u<ssevecsize>\t{%3, %2, %0|%0, %2, %3}"
-  [(set_attr "type" "ssecmp")
-   (set_attr "prefix_data16" "0")
-   (set_attr "prefix_rep" "0")
-   (set_attr "prefix_extra" "2")
-   (set_attr "length_immediate" "1")
-   (set_attr "mode" "TI")])
-
-;; Version of pcom*u* that is called from the intrinsics that allows pcomequ*
-;; and pcomneu* not to be converted to the signed ones in case somebody needs
-;; the exact instruction generated for the intrinsic.
-(define_insn "sse5_maskcmp_uns2<mode>3"
-  [(set (match_operand:SSEMODE1248 0 "register_operand" "=x")
-	(unspec:SSEMODE1248
-	 [(match_operator:SSEMODE1248 1 "ix86_comparison_uns_operator"
-	  [(match_operand:SSEMODE1248 2 "register_operand" "x")
-	   (match_operand:SSEMODE1248 3 "nonimmediate_operand" "xm")])]
-	 UNSPEC_SSE5_UNSIGNED_CMP))]
-  "TARGET_SSE5"
-  "pcom%Y1u<ssevecsize>\t{%3, %2, %0|%0, %2, %3}"
-  [(set_attr "type" "ssecmp")
-   (set_attr "prefix_data16" "0")
-   (set_attr "prefix_extra" "2")
-   (set_attr "length_immediate" "1")
-   (set_attr "mode" "TI")])
-
-;; Pcomtrue and pcomfalse support.  These are useless instructions, but are
-;; being added here to be complete.
-(define_insn "sse5_pcom_tf<mode>3"
-  [(set (match_operand:SSEMODE1248 0 "register_operand" "=x")
-	(unspec:SSEMODE1248
-	  [(match_operand:SSEMODE1248 1 "register_operand" "x")
-	   (match_operand:SSEMODE1248 2 "nonimmediate_operand" "xm")
-	   (match_operand:SI 3 "const_int_operand" "n")]
-	  UNSPEC_SSE5_TRUEFALSE))]
-  "TARGET_SSE5"
-{
-  return ((INTVAL (operands[3]) != 0)
-	  ? "pcomtrue<ssevecsize>\t{%2, %1, %0|%0, %1, %2}"
-	  : "pcomfalse<ssevecsize>\t{%2, %1, %0|%0, %1, %2}");
-}
-  [(set_attr "type" "ssecmp")
-   (set_attr "prefix_data16" "0")
-   (set_attr "prefix_extra" "2")
-   (set_attr "length_immediate" "1")
-   (set_attr "mode" "TI")])
-
 (define_insn "*avx_aesenc"
   [(set (match_operand:V2DI 0 "register_operand" "=x")
 	(unspec:V2DI [(match_operand:V2DI 1 "register_operand" "x")
diff --git a/gcc/config/i386/sysv4.h b/gcc/config/i386/sysv4.h
index bedac7a58b6..63c0cbc85a7 100644
--- a/gcc/config/i386/sysv4.h
+++ b/gcc/config/i386/sysv4.h
@@ -55,7 +55,7 @@ along with GCC; see the file COPYING3.  If not see
       const unsigned char *limit = _ascii_bytes + (LENGTH);		\
       unsigned bytes_in_chunk = 0;					\
       for (; _ascii_bytes < limit; _ascii_bytes++)			\
-        {								\
+	{								\
 	  const unsigned char *p;					\
 	  if (bytes_in_chunk >= 64)					\
 	    {								\
@@ -77,7 +77,7 @@ along with GCC; see the file COPYING3.  If not see
 	  else								\
 	    {								\
 	      if (bytes_in_chunk == 0)					\
-		fprintf ((FILE), "\t.byte\t");				\
+		fputs (ASM_BYTE, (FILE));				\
 	      else							\
 		fputc (',', (FILE));					\
 	      fprintf ((FILE), "0x%02x", *_ascii_bytes);		\
@@ -85,7 +85,7 @@ along with GCC; see the file COPYING3.  If not see
 	    }								\
 	}								\
       if (bytes_in_chunk > 0)						\
-        fprintf ((FILE), "\n");						\
+	fputc ('\n', (FILE));						\
     }									\
   while (0)
 
@@ -103,10 +103,10 @@ along with GCC; see the file COPYING3.  If not see
   do {									\
     if ((SIZE) == 4 && ((ENCODING) & 0x70) == DW_EH_PE_datarel)		\
       {									\
-        fputs (ASM_LONG, FILE);						\
-        assemble_name (FILE, XSTR (ADDR, 0));				\
-	fputs (((ENCODING) & DW_EH_PE_indirect ? "@GOT" : "@GOTOFF"), FILE); \
-        goto DONE;							\
+	fputs (ASM_LONG, (FILE));					\
+	assemble_name (FILE, XSTR (ADDR, 0));				\
+	fputs (((ENCODING) & DW_EH_PE_indirect ? "@GOT" : "@GOTOFF"), (FILE)); \
+	goto DONE;							\
       }									\
   } while (0)