invoke.texi (-mlwp): Add documentation.

2009-11-04 Harsha Jagasia <harsha.jagasia@amd.com> Dwarakanath Rajagopal <dwarak.rajagopal@amd.com> * doc/invoke.texi (-mlwp): Add documentation. * doc/extend.texi (x86 intrinsics): Add LWP intrinsics. * config.gcc (i[34567]86-*-*): Include lwpintrin.h. (x86_64-*-*): Ditto. * config/i386/lwpintrin.h: New file, provide x86 compiler intrinisics for LWP. * config/i386/cpuid.h (bit_LWP): Define LWP bit. * config/i386/x86intrin.h: Add LWP check and lwpintrin.h. * config/i386/i386-c.c (ix86_target_macros_internal): Check ISA_FLAG for LWP. * config/i386/i386.h (TARGET_LWP): New macro for LWP. * config/i386/i386.opt (-mlwp): New switch for LWP support. * config/i386/i386.c (OPTION_MASK_ISA_LWP_SET): New. (OPTION_MASK_ISA_LWP_UNSET): New. (ix86_handle_option): Handle -mlwp. (isa_opts): Handle -mlwp. (enum pta_flags): Add PTA_LWP. (override_options): Add LWP support. (IX86_BUILTIN_LLWPCB16): New for LWP intrinsic. (IX86_BUILTIN_LLWPCB32): Ditto. (IX86_BUILTIN_LLWPCB64): Ditto. (IX86_BUILTIN_SLWPCB16): Ditto. (IX86_BUILTIN_SLWPCB32): Ditto. (IX86_BUILTIN_SLWPCB64): Ditto. (IX86_BUILTIN_LWPVAL16): Ditto. (IX86_BUILTIN_LWPVAL32): Ditto. (IX86_BUILTIN_LWPVAL64): Ditto. (IX86_BUILTIN_LWPINS16): Ditto. (IX86_BUILTIN_LWPINS32): Ditto. (IX86_BUILTIN_LWPINS64): Ditto. (enum ix86_special_builtin_type): Add LWP intrinsic support. (builtin_description): Ditto. (ix86_init_mmx_sse_builtins): Ditto. (ix86_expand_special_args_builtin): Ditto. * config/i386/i386.md (UNSPEC_LLWP_INTRINSIC): Add new UNSPEC for LWP support. (UNSPEC_SLWP_INTRINSIC): Ditto. (UNSPECV_LWPVAL_INTRINSIC): Ditto. (UNSPECV_LWPINS_INTRINSIC): Ditto. (lwp_llwpcbhi1): New lwp pattern. (lwp_llwpcbsi1): Ditto. (lwp_llwpcbdi1): Ditto. (lwp_slwpcbhi1): Ditto. (lwp_slwpcbsi1): Ditto. (lwp_slwpcbdi1): Ditto. (lwp_lwpvalhi3): Ditto. (lwp_lwpvalsi3): Ditto. (lwp_lwpvaldi3): Ditto. (lwp_lwpinshi3): Ditto. (lwp_lwpinssi3): Ditto. (lwp_lwpinsdi3): Ditto. Co-Authored-By: Dwarakanath Rajagopal <dwarak.rajagopal@amd.com> From-SVN: r153917
2025-03-21 23:00:52 +08:00 · 2009-11-04 21:15:42 +00:00 · 2009-11-04 21:15:42 +00:00 · 3e901069e7
commit 3e901069e7
parent 6168891d1f
12 changed files with 457 additions and 8 deletions
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@ -1,3 +1,58 @@
+2009-11-04  Harsha Jagasia  <harsha.jagasia@amd.com>
+	    Dwarakanath Rajagopal  <dwarak.rajagopal@amd.com>
+
+	* doc/invoke.texi (-mlwp): Add documentation.
+	* doc/extend.texi (x86 intrinsics): Add LWP intrinsics.
+	* config.gcc (i[34567]86-*-*): Include lwpintrin.h.
+	(x86_64-*-*): Ditto.
+	* config/i386/lwpintrin.h: New file, provide x86 compiler
+	intrinisics for LWP.
+	* config/i386/cpuid.h (bit_LWP): Define LWP bit.
+	* config/i386/x86intrin.h: Add LWP check and lwpintrin.h.
+	* config/i386/i386-c.c (ix86_target_macros_internal): Check
+	ISA_FLAG for LWP. 
+	* config/i386/i386.h (TARGET_LWP): New macro for LWP.
+	* config/i386/i386.opt (-mlwp): New switch for LWP support.
+	* config/i386/i386.c (OPTION_MASK_ISA_LWP_SET): New.
+	(OPTION_MASK_ISA_LWP_UNSET): New.	
+	(ix86_handle_option): Handle -mlwp.
+	(isa_opts): Handle -mlwp.
+	(enum pta_flags): Add PTA_LWP.
+	(override_options): Add LWP support.
+	(IX86_BUILTIN_LLWPCB16): New for LWP intrinsic.
+	(IX86_BUILTIN_LLWPCB32): Ditto.
+	(IX86_BUILTIN_LLWPCB64): Ditto.
+	(IX86_BUILTIN_SLWPCB16): Ditto.
+	(IX86_BUILTIN_SLWPCB32): Ditto.
+	(IX86_BUILTIN_SLWPCB64): Ditto.
+	(IX86_BUILTIN_LWPVAL16): Ditto.
+	(IX86_BUILTIN_LWPVAL32): Ditto.
+	(IX86_BUILTIN_LWPVAL64): Ditto.
+	(IX86_BUILTIN_LWPINS16): Ditto.
+	(IX86_BUILTIN_LWPINS32): Ditto.
+	(IX86_BUILTIN_LWPINS64): Ditto.
+	(enum  ix86_special_builtin_type): Add LWP intrinsic support.
+	(builtin_description): Ditto.
+	(ix86_init_mmx_sse_builtins): Ditto.
+	(ix86_expand_special_args_builtin): Ditto.
+	* config/i386/i386.md (UNSPEC_LLWP_INTRINSIC): Add new UNSPEC for 
+	LWP support.
+	(UNSPEC_SLWP_INTRINSIC): Ditto.
+	(UNSPECV_LWPVAL_INTRINSIC): Ditto.
+	(UNSPECV_LWPINS_INTRINSIC): Ditto.
+	(lwp_llwpcbhi1): New lwp pattern.
+	(lwp_llwpcbsi1): Ditto.
+	(lwp_llwpcbdi1): Ditto.
+	(lwp_slwpcbhi1): Ditto.
+	(lwp_slwpcbsi1): Ditto.
+	(lwp_slwpcbdi1): Ditto.
+	(lwp_lwpvalhi3): Ditto.
+	(lwp_lwpvalsi3): Ditto.
+	(lwp_lwpvaldi3): Ditto.
+	(lwp_lwpinshi3): Ditto.
+	(lwp_lwpinssi3): Ditto.
+	(lwp_lwpinsdi3): Ditto.
+	
 2009-11-04  Andrew Pinski  <andrew_pinski@playstation.sony.com>
            Trevor Smigiel <Trevor_Smigiel@playstation.sony.com>

--- a/gcc/config.gcc
+++ b/gcc/config.gcc
@ -288,7 +288,7 @@ i[34567]86-*-*)
 		       pmmintrin.h tmmintrin.h ammintrin.h smmintrin.h
 		       nmmintrin.h bmmintrin.h fma4intrin.h wmmintrin.h
 		       immintrin.h x86intrin.h avxintrin.h xopintrin.h
-		       ia32intrin.h cross-stdarg.h"
+		       ia32intrin.h cross-stdarg.h lwpintrin.h"
 	;;
 x86_64-*-*)
 	cpu_type=i386
@ -298,7 +298,7 @@ x86_64-*-*)
 		       pmmintrin.h tmmintrin.h ammintrin.h smmintrin.h
 		       nmmintrin.h bmmintrin.h fma4intrin.h wmmintrin.h
 		       immintrin.h x86intrin.h avxintrin.h xopintrin.h
-		       ia32intrin.h cross-stdarg.h"
+		       ia32intrin.h cross-stdarg.h lwpintrin.h"
 	need_64bit_hwint=yes
 	;;
 ia64-*-*)
--- a/gcc/config/i386/cpuid.h
+++ b/gcc/config/i386/cpuid.h
@ -48,6 +48,7 @@
 /* %ecx */
 #define bit_FMA4        (1 << 16) 
 #define bit_LAHF_LM	(1 << 0)
+#define bit_LWP 	(1 << 15)
 #define bit_SSE4a	(1 << 6)
 #define bit_XOP         (1 << 11)

--- a/gcc/config/i386/i386-c.c
+++ b/gcc/config/i386/i386-c.c
@ -234,6 +234,8 @@ ix86_target_macros_internal (int isa_flag,
    def_or_undef (parse_in, "__FMA4__");
  if (isa_flag & OPTION_MASK_ISA_XOP)
    def_or_undef (parse_in, "__XOP__");
+  if (isa_flag & OPTION_MASK_ISA_LWP)
+    def_or_undef (parse_in, "__LWP__");
  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))
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@ -1966,6 +1966,8 @@ static int ix86_isa_flags_explicit;
   | OPTION_MASK_ISA_AVX_SET)
 #define OPTION_MASK_ISA_XOP_SET \
  (OPTION_MASK_ISA_XOP | OPTION_MASK_ISA_FMA4_SET)
+#define OPTION_MASK_ISA_LWP_SET \
+  OPTION_MASK_ISA_LWP

 /* AES and PCLMUL need SSE2 because they use xmm registers */
 #define OPTION_MASK_ISA_AES_SET \
@ -2020,6 +2022,7 @@ static int ix86_isa_flags_explicit;
 #define OPTION_MASK_ISA_FMA4_UNSET \
  (OPTION_MASK_ISA_FMA4 | OPTION_MASK_ISA_XOP_UNSET)
 #define OPTION_MASK_ISA_XOP_UNSET OPTION_MASK_ISA_XOP
+#define OPTION_MASK_ISA_LWP_UNSET OPTION_MASK_ISA_LWP

 #define OPTION_MASK_ISA_AES_UNSET OPTION_MASK_ISA_AES
 #define OPTION_MASK_ISA_PCLMUL_UNSET OPTION_MASK_ISA_PCLMUL
@ -2280,6 +2283,19 @@ ix86_handle_option (size_t code, const char *arg ATTRIBUTE_UNUSED, int value)
 	}
      return true;

+   case OPT_mlwp:
+      if (value)
+	{
+	  ix86_isa_flags |= OPTION_MASK_ISA_LWP_SET;
+	  ix86_isa_flags_explicit |= OPTION_MASK_ISA_LWP_SET;
+	}
+      else
+	{
+	  ix86_isa_flags &= ~OPTION_MASK_ISA_LWP_UNSET;
+	  ix86_isa_flags_explicit |= OPTION_MASK_ISA_LWP_UNSET;
+	}
+      return true;
+
    case OPT_mabm:
      if (value)
 	{
@ -2409,6 +2425,7 @@ ix86_target_string (int isa, int flags, const char *arch, const char *tune,
    { "-m64",		OPTION_MASK_ISA_64BIT },
    { "-mfma4",		OPTION_MASK_ISA_FMA4 },
    { "-mxop",		OPTION_MASK_ISA_XOP },
+    { "-mlwp",		OPTION_MASK_ISA_LWP },
    { "-msse4a",	OPTION_MASK_ISA_SSE4A },
    { "-msse4.2",	OPTION_MASK_ISA_SSE4_2 },
    { "-msse4.1",	OPTION_MASK_ISA_SSE4_1 },
@ -2640,7 +2657,8 @@ override_options (bool main_args_p)
      PTA_FMA = 1 << 19,
      PTA_MOVBE = 1 << 20,
      PTA_FMA4 = 1 << 21,
-      PTA_XOP = 1 << 22
+      PTA_XOP = 1 << 22,
+      PTA_LWP = 1 << 23
    };

  static struct pta
@ -2989,6 +3007,9 @@ override_options (bool main_args_p)
 	if (processor_alias_table[i].flags & PTA_XOP
 	    && !(ix86_isa_flags_explicit & OPTION_MASK_ISA_XOP))
 	  ix86_isa_flags |= OPTION_MASK_ISA_XOP;
+	if (processor_alias_table[i].flags & PTA_LWP
+	    && !(ix86_isa_flags_explicit & OPTION_MASK_ISA_LWP))
+	  ix86_isa_flags |= OPTION_MASK_ISA_LWP;
 	if (processor_alias_table[i].flags & PTA_ABM
 	    && !(ix86_isa_flags_explicit & OPTION_MASK_ISA_ABM))
 	  ix86_isa_flags |= OPTION_MASK_ISA_ABM;
@ -3672,6 +3693,7 @@ ix86_valid_target_attribute_inner_p (tree args, char *p_strings[])
    IX86_ATTR_ISA ("ssse3",	OPT_mssse3),
    IX86_ATTR_ISA ("fma4",	OPT_mfma4),
    IX86_ATTR_ISA ("xop",	OPT_mxop),
+    IX86_ATTR_ISA ("lwp",	OPT_mlwp),

    /* string options */
    IX86_ATTR_STR ("arch=",	IX86_FUNCTION_SPECIFIC_ARCH),
@ -20897,7 +20919,7 @@ enum ix86_builtins

  IX86_BUILTIN_CVTUDQ2PS,

-  /* FMA4 instructions.  */
+  /* FMA4 and XOP instructions.  */
  IX86_BUILTIN_VFMADDSS,
  IX86_BUILTIN_VFMADDSD,
  IX86_BUILTIN_VFMADDPS,
@ -21074,6 +21096,20 @@ enum ix86_builtins
  IX86_BUILTIN_VPCOMFALSEQ,
  IX86_BUILTIN_VPCOMTRUEQ,

+  /* LWP instructions.  */
+  IX86_BUILTIN_LLWPCB16,
+  IX86_BUILTIN_LLWPCB32,
+  IX86_BUILTIN_LLWPCB64,
+  IX86_BUILTIN_SLWPCB16,
+  IX86_BUILTIN_SLWPCB32,
+  IX86_BUILTIN_SLWPCB64,
+  IX86_BUILTIN_LWPVAL16,
+  IX86_BUILTIN_LWPVAL32,
+  IX86_BUILTIN_LWPVAL64,
+  IX86_BUILTIN_LWPINS16,
+  IX86_BUILTIN_LWPINS32,
+  IX86_BUILTIN_LWPINS64,
+
  IX86_BUILTIN_MAX
 };

@ -21287,7 +21323,13 @@ enum ix86_special_builtin_type
  VOID_FTYPE_PV8SF_V8SF_V8SF,
  VOID_FTYPE_PV4DF_V4DF_V4DF,
  VOID_FTYPE_PV4SF_V4SF_V4SF,
-  VOID_FTYPE_PV2DF_V2DF_V2DF
+  VOID_FTYPE_PV2DF_V2DF_V2DF,
+  VOID_FTYPE_USHORT_UINT_USHORT,
+  VOID_FTYPE_UINT_UINT_UINT,
+  VOID_FTYPE_UINT64_UINT_UINT,
+  UCHAR_FTYPE_USHORT_UINT_USHORT,
+  UCHAR_FTYPE_UINT_UINT_UINT,
+  UCHAR_FTYPE_UINT64_UINT_UINT
 };

 /* Builtin types */
@ -21534,6 +21576,22 @@ static const struct builtin_description bdesc_special_args[] =
  { OPTION_MASK_ISA_AVX, CODE_FOR_avx_maskstoreps, "__builtin_ia32_maskstoreps", IX86_BUILTIN_MASKSTOREPS, UNKNOWN, (int) VOID_FTYPE_PV4SF_V4SF_V4SF },
  { OPTION_MASK_ISA_AVX, CODE_FOR_avx_maskstorepd256, "__builtin_ia32_maskstorepd256", IX86_BUILTIN_MASKSTOREPD256, UNKNOWN, (int) VOID_FTYPE_PV4DF_V4DF_V4DF },
  { OPTION_MASK_ISA_AVX, CODE_FOR_avx_maskstoreps256, "__builtin_ia32_maskstoreps256", IX86_BUILTIN_MASKSTOREPS256, UNKNOWN, (int) VOID_FTYPE_PV8SF_V8SF_V8SF },
+
+  { OPTION_MASK_ISA_LWP, CODE_FOR_lwp_llwpcbhi1,   "__builtin_ia32_llwpcb16",   IX86_BUILTIN_LLWPCB16,    UNKNOWN,     (int) VOID_FTYPE_VOID },
+  { OPTION_MASK_ISA_LWP, CODE_FOR_lwp_llwpcbsi1,   "__builtin_ia32_llwpcb32",   IX86_BUILTIN_LLWPCB32,    UNKNOWN,     (int) VOID_FTYPE_VOID },
+  { OPTION_MASK_ISA_LWP, CODE_FOR_lwp_llwpcbdi1,   "__builtin_ia32_llwpcb64",   IX86_BUILTIN_LLWPCB64,    UNKNOWN,     (int) VOID_FTYPE_VOID },
+
+  { OPTION_MASK_ISA_LWP, CODE_FOR_lwp_slwpcbhi1,   "__builtin_ia32_slwpcb16",   IX86_BUILTIN_SLWPCB16,    UNKNOWN,     (int) VOID_FTYPE_VOID },
+  { OPTION_MASK_ISA_LWP, CODE_FOR_lwp_slwpcbsi1,   "__builtin_ia32_slwpcb32",   IX86_BUILTIN_SLWPCB32,    UNKNOWN,     (int) VOID_FTYPE_VOID },
+  { OPTION_MASK_ISA_LWP, CODE_FOR_lwp_slwpcbdi1,   "__builtin_ia32_slwpcb64",   IX86_BUILTIN_SLWPCB64,    UNKNOWN,     (int) VOID_FTYPE_VOID },
+
+  { OPTION_MASK_ISA_LWP, CODE_FOR_lwp_lwpvalhi3,   "__builtin_ia32_lwpval16", IX86_BUILTIN_LWPVAL16,  UNKNOWN,     (int) VOID_FTYPE_USHORT_UINT_USHORT },
+  { OPTION_MASK_ISA_LWP, CODE_FOR_lwp_lwpvalsi3,   "__builtin_ia32_lwpval32", IX86_BUILTIN_LWPVAL64,  UNKNOWN,     (int) VOID_FTYPE_UINT_UINT_UINT },
+  { OPTION_MASK_ISA_LWP, CODE_FOR_lwp_lwpvaldi3,   "__builtin_ia32_lwpval64", IX86_BUILTIN_LWPVAL64,  UNKNOWN,     (int) VOID_FTYPE_UINT64_UINT_UINT },
+  { OPTION_MASK_ISA_LWP, CODE_FOR_lwp_lwpinshi3,   "__builtin_ia32_lwpins16", IX86_BUILTIN_LWPINS16,  UNKNOWN,     (int) UCHAR_FTYPE_USHORT_UINT_USHORT },
+  { OPTION_MASK_ISA_LWP, CODE_FOR_lwp_lwpinssi3,   "__builtin_ia32_lwpins32", IX86_BUILTIN_LWPINS64,  UNKNOWN,     (int) UCHAR_FTYPE_UINT_UINT_UINT },
+  { OPTION_MASK_ISA_LWP, CODE_FOR_lwp_lwpinsdi3,   "__builtin_ia32_lwpins64", IX86_BUILTIN_LWPINS64,  UNKNOWN,     (int) UCHAR_FTYPE_UINT64_UINT_UINT },
+
 };

 /* Builtins with variable number of arguments.  */
@ -23192,6 +23250,50 @@ ix86_init_mmx_sse_builtins (void)
 				integer_type_node,
 				NULL_TREE);

+  /* LWP instructions.  */
+
+  tree void_ftype_ushort_unsigned_ushort
+    = build_function_type_list (void_type_node,
+				short_unsigned_type_node,
+				unsigned_type_node,
+				short_unsigned_type_node,
+				NULL_TREE);
+
+  tree void_ftype_unsigned_unsigned_unsigned
+    = build_function_type_list (void_type_node,
+				unsigned_type_node,
+				unsigned_type_node,
+				unsigned_type_node,
+				NULL_TREE);
+
+  tree void_ftype_uint64_unsigned_unsigned
+    = build_function_type_list (void_type_node,
+				long_long_unsigned_type_node,
+				unsigned_type_node,
+				unsigned_type_node,
+				NULL_TREE);
+
+  tree uchar_ftype_ushort_unsigned_ushort
+    = build_function_type_list (unsigned_char_type_node,
+				short_unsigned_type_node,
+				unsigned_type_node,
+				short_unsigned_type_node,
+				NULL_TREE);
+
+  tree uchar_ftype_unsigned_unsigned_unsigned
+    = build_function_type_list (unsigned_char_type_node,
+				unsigned_type_node,
+				unsigned_type_node,
+				unsigned_type_node,
+				NULL_TREE);
+
+  tree uchar_ftype_uint64_unsigned_unsigned
+    = build_function_type_list (unsigned_char_type_node,
+				long_long_unsigned_type_node,
+				unsigned_type_node,
+				unsigned_type_node,
+				NULL_TREE);
+
  tree ftype;

  /* Add all special builtins with variable number of operands.  */
@ -23305,6 +23407,25 @@ ix86_init_mmx_sse_builtins (void)
 	case VOID_FTYPE_PV2DF_V2DF_V2DF:
 	  type = void_ftype_pv2df_v2df_v2df;
 	  break;
+	case VOID_FTYPE_USHORT_UINT_USHORT:
+	  type = void_ftype_ushort_unsigned_ushort;
+	  break;
+	case VOID_FTYPE_UINT_UINT_UINT:
+	  type = void_ftype_unsigned_unsigned_unsigned;
+	  break;
+	case VOID_FTYPE_UINT64_UINT_UINT:
+	  type = void_ftype_uint64_unsigned_unsigned;
+	  break;
+	case UCHAR_FTYPE_USHORT_UINT_USHORT:
+	  type = uchar_ftype_ushort_unsigned_ushort;
+	  break;
+	case UCHAR_FTYPE_UINT_UINT_UINT:
+	  type = uchar_ftype_unsigned_unsigned_unsigned;
+	  break;
+	case UCHAR_FTYPE_UINT64_UINT_UINT:
+	  type = uchar_ftype_uint64_unsigned_unsigned;
+	  break;
+
 	default:
 	  gcc_unreachable ();
 	}
@ -25196,6 +25317,16 @@ ix86_expand_special_args_builtin (const struct builtin_description *d,
      /* Reserve memory operand for target.  */
      memory = ARRAY_SIZE (args);
      break;
+    case VOID_FTYPE_USHORT_UINT_USHORT:
+    case VOID_FTYPE_UINT_UINT_UINT:
+    case VOID_FTYPE_UINT64_UINT_UINT:
+    case UCHAR_FTYPE_USHORT_UINT_USHORT:
+    case UCHAR_FTYPE_UINT_UINT_UINT:
+    case UCHAR_FTYPE_UINT64_UINT_UINT:
+      nargs = 3;
+      klass = store;
+      memory = 0;
+      break;
    default:
      gcc_unreachable ();
    }
--- a/gcc/config/i386/i386.h
+++ b/gcc/config/i386/i386.h
@ -56,6 +56,7 @@ see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
 #define TARGET_SSE4A	OPTION_ISA_SSE4A
 #define TARGET_FMA4	OPTION_ISA_FMA4
 #define TARGET_XOP	OPTION_ISA_XOP
+#define TARGET_LWP	OPTION_ISA_LWP
 #define TARGET_ROUND	OPTION_ISA_ROUND
 #define TARGET_ABM	OPTION_ISA_ABM
 #define TARGET_POPCNT	OPTION_ISA_POPCNT
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@ -204,6 +204,10 @@
   (UNSPEC_XOP_TRUEFALSE	152)
   (UNSPEC_XOP_PERMUTE		153)
   (UNSPEC_FRCZ			154)
+   (UNSPEC_LLWP_INTRINSIC	155)
+   (UNSPEC_SLWP_INTRINSIC	156)
+   (UNSPECV_LWPVAL_INTRINSIC	157)
+   (UNSPECV_LWPINS_INTRINSIC	158)

   ; For AES support
   (UNSPEC_AESENC		159)
@ -353,7 +357,7 @@
   fmov,fop,fsgn,fmul,fdiv,fpspc,fcmov,fcmp,fxch,fistp,fisttp,frndint,
   sselog,sselog1,sseiadd,sseiadd1,sseishft,sseimul,
   sse,ssemov,sseadd,ssemul,ssecmp,ssecomi,ssecvt,ssecvt1,sseicvt,ssediv,sseins,
-   ssemuladd,sse4arg,
+   ssemuladd,sse4arg,lwp,
   mmx,mmxmov,mmxadd,mmxmul,mmxcmp,mmxcvt,mmxshft"
  (const_string "other"))

@ -21838,6 +21842,120 @@
  [(set_attr "type" "other")
   (set_attr "length" "3")])

+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+;;
+;; LWP instructions
+;;
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+
+(define_insn "lwp_llwpcbhi1"
+  [(unspec [(match_operand:HI 0 "register_operand" "r")]
+  	   UNSPEC_LLWP_INTRINSIC)]
+  "TARGET_LWP"
+  "llwpcb\t%0"
+  [(set_attr "type" "lwp")
+   (set_attr "mode" "HI")])
+
+(define_insn "lwp_llwpcbsi1"
+  [(unspec [(match_operand:SI 0 "register_operand" "r")]
+  	   UNSPEC_LLWP_INTRINSIC)]
+  "TARGET_LWP"
+  "llwpcb\t%0"
+  [(set_attr "type" "lwp")
+   (set_attr "mode" "SI")])
+
+(define_insn "lwp_llwpcbdi1"
+  [(unspec [(match_operand:DI 0 "register_operand" "r")]
+  	   UNSPEC_LLWP_INTRINSIC)]
+  "TARGET_LWP"
+  "llwpcb\t%0"
+  [(set_attr "type" "lwp")
+   (set_attr "mode" "DI")])
+
+(define_insn "lwp_slwpcbhi1"
+  [(unspec [(match_operand:HI 0 "register_operand" "r")]
+  	   UNSPEC_SLWP_INTRINSIC)]
+  "TARGET_LWP"
+  "slwpcb\t%0"
+  [(set_attr "type" "lwp")
+   (set_attr "mode" "HI")])
+
+(define_insn "lwp_slwpcbsi1"
+  [(unspec [(match_operand:SI 0 "register_operand" "r")]
+  	   UNSPEC_SLWP_INTRINSIC)]
+  "TARGET_LWP"
+  "slwpcb\t%0"
+  [(set_attr "type" "lwp")
+   (set_attr "mode" "SI")])
+
+(define_insn "lwp_slwpcbdi1"
+  [(unspec [(match_operand:DI 0 "register_operand" "r")]
+  	   UNSPEC_SLWP_INTRINSIC)]
+  "TARGET_LWP"
+  "slwpcb\t%0"
+  [(set_attr "type" "lwp")
+   (set_attr "mode" "DI")])
+
+(define_insn "lwp_lwpvalhi3"
+  [(unspec_volatile [(match_operand:HI 0 "register_operand" "r")
+  	   	     (match_operand:SI 1 "nonimmediate_operand" "rm")
+	   	     (match_operand:HI 2 "const_int_operand" "")]
+  	   	    UNSPECV_LWPVAL_INTRINSIC)]
+  "TARGET_LWP"
+  "lwpval\t{%2, %1, %0|%0, %1, %2}"
+  [(set_attr "type" "lwp")
+   (set_attr "mode" "HI")])
+
+(define_insn "lwp_lwpvalsi3"
+  [(unspec_volatile [(match_operand:SI 0 "register_operand" "r")
+    	    	     (match_operand:SI 1 "nonimmediate_operand" "rm")
+	    	     (match_operand:SI 2 "const_int_operand" "")]
+		    UNSPECV_LWPVAL_INTRINSIC)]
+  "TARGET_LWP"
+  "lwpval\t{%2, %1, %0|%0, %1, %2}"
+  [(set_attr "type" "lwp")
+   (set_attr "mode" "SI")])
+
+(define_insn "lwp_lwpvaldi3"
+  [(unspec_volatile [(match_operand:DI 0 "register_operand" "r")
+  		     (match_operand:SI 1 "nonimmediate_operand" "rm")
+		     (match_operand:SI 2 "const_int_operand" "")]
+		    UNSPECV_LWPVAL_INTRINSIC)]
+  "TARGET_LWP"
+  "lwpval\t{%2, %1, %0|%0, %1, %2}"
+  [(set_attr "type" "lwp")
+   (set_attr "mode" "DI")])
+
+(define_insn "lwp_lwpinshi3"
+  [(unspec_volatile [(match_operand:HI 0 "register_operand" "r")
+  		     (match_operand:SI 1 "nonimmediate_operand" "rm")
+		     (match_operand:HI 2 "const_int_operand" "")]
+		    UNSPECV_LWPINS_INTRINSIC)]
+  "TARGET_LWP"
+  "lwpins\t{%2, %1, %0|%0, %1, %2}"
+  [(set_attr "type" "lwp")
+   (set_attr "mode" "HI")])
+
+(define_insn "lwp_lwpinssi3"
+  [(unspec_volatile [(match_operand:SI 0 "register_operand" "r")
+  		     (match_operand:SI 1 "nonimmediate_operand" "rm")
+		     (match_operand:SI 2 "const_int_operand" "")]
+		    UNSPECV_LWPINS_INTRINSIC)]
+  "TARGET_LWP"
+  "lwpins\t{%2, %1, %0|%0, %1, %2}"
+  [(set_attr "type" "lwp")
+   (set_attr "mode" "SI")])
+
+(define_insn "lwp_lwpinsdi3"
+  [(unspec_volatile [(match_operand:DI 0 "register_operand" "r")
+  		     (match_operand:SI 1 "nonimmediate_operand" "rm")
+		     (match_operand:SI 2 "const_int_operand" "")]
+		    UNSPECV_LWPINS_INTRINSIC)]
+  "TARGET_LWP"
+  "lwpins\t{%2, %1, %0|%0, %1, %2}"
+  [(set_attr "type" "lwp")
+   (set_attr "mode" "DI")])
+
 (include "mmx.md")
 (include "sse.md")
 (include "sync.md")
--- a/gcc/config/i386/i386.opt
+++ b/gcc/config/i386/i386.opt
@ -318,6 +318,10 @@ mxop
 Target Report Mask(ISA_XOP) Var(ix86_isa_flags) VarExists Save
 Support XOP built-in functions and code generation 

+mlwp
+Target Report Mask(ISA_LWP) Var(ix86_isa_flags) VarExists Save
+Support LWP 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.
--- a/gcc/config/i386/lwpintrin.h
+++ b/gcc/config/i386/lwpintrin.h
@ -0,0 +1,109 @@
+/* Copyright (C) 2007, 2008, 2009 Free Software Foundation, Inc.
+
+   This file is part of GCC.
+
+   GCC is free software; you can redistribute it and/or modify
+   it under the terms of the GNU General Public License as published by
+   the Free Software Foundation; either version 3, or (at your option)
+   any later version.
+
+   GCC is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+
+   Under Section 7 of GPL version 3, you are granted additional
+   permissions described in the GCC Runtime Library Exception, version
+   3.1, as published by the Free Software Foundation.
+
+   You should have received a copy of the GNU General Public License and
+   a copy of the GCC Runtime Library Exception along with this program;
+   see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
+   <http://www.gnu.org/licenses/>.  */
+
+#ifndef _X86INTRIN_H_INCLUDED
+# error "Never use <lwpintrin.h> directly; include <x86intrin.h> instead."
+#endif
+
+#ifndef _LWPINTRIN_H_INCLUDED
+#define _LWPINTRIN_H_INCLUDED
+
+#ifndef __LWP__
+# error "LWP instruction set not enabled"
+#else
+
+extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+__llwpcb16 (void *pcbAddress)
+{
+  __builtin_ia32_llwpcb16 (pcbAddress);
+}
+
+extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+__llwpcb32 (void *pcbAddress)
+{
+  __builtin_ia32_llwpcb32 (pcbAddress);
+}
+
+extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+__llwpcb64 (void *pcbAddress)
+{
+  __builtin_ia32_llwpcb64 (pcbAddress);
+}
+
+extern __inline void * __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+__slwpcb16 (void)
+{
+  return __builtin_ia32_slwpcb16 ();
+}
+
+extern __inline void * __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+__slwpcb32 (void)
+{
+  return __builtin_ia32_slwpcb32 ();
+}
+
+extern __inline void * __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+__slwpcb64 (void)
+{
+  return __builtin_ia32_slwpcb64 ();
+}
+
+extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+__lwpval16 (unsigned short data2, unsigned int data1, unsigned short flags)
+{
+  __builtin_ia32_lwpval16 (data2, data1, flags);
+}
+/*
+extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+__lwpval32 (unsigned int data2, unsigned int data1, unsigned int flags)
+{
+  __builtin_ia32_lwpval32 (data2, data1, flags);
+}
+
+extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+__lwpval64 (unsigned __int64 data2, unsigned int data1, unsigned int flags)
+{
+  __builtin_ia32_lwpval64 (data2, data1, flags);
+}
+
+extern __inline unsigned char __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+__lwpins16 (unsigned short data2, unsigned int data1, unsigned short flags)
+{
+  return __builtin_ia32_lwpins16 (data2, data1, flags);
+}
+
+extern __inline unsigned char __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+__lwpins32 (unsigned int data2, unsigned int data1, unsigned int flags)
+{
+  return __builtin_ia32_lwpins32 (data2, data1, flags);
+}
+
+extern __inline unsigned char __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+__lwpins64 (unsigned __int64 data2, unsigned int data1, unsigned int flags)
+{
+  return __builtin_ia32_lwpins64 (data2, data1, flags);
+}
+*/
+#endif /* __LWP__ */
+
+#endif /* _LWPINTRIN_H_INCLUDED */
--- a/gcc/config/i386/x86intrin.h
+++ b/gcc/config/i386/x86intrin.h
@ -62,6 +62,10 @@
 #include <xopintrin.h>
 #endif

+#ifdef __LWP__
+#include <lwpintrin.h>
+#endif
+
 #if defined (__AES__) || defined (__PCLMUL__)
 #include <wmmintrin.h>
 #endif
--- a/gcc/doc/extend.texi
+++ b/gcc/doc/extend.texi
@ -3212,6 +3212,11 @@ Enable/disable the generation of the FMA4 instructions.
@cindex @code{target("xop")} attribute
 Enable/disable the generation of the XOP instructions.

+@item lwp
+@itemx no-lwp
+@cindex @code{target("lwp")} attribute
+Enable/disable the generation of the LWP instructions.
+
@item ssse3
@itemx no-ssse3
@cindex @code{target("ssse3")} attribute
@ -9101,6 +9106,23 @@ v8sf __builtin_ia32_fmsubaddps256 (v8sf, v8sf, v8sf)

@end smallexample

+The following built-in functions are available when @option{-mlwp} is used.
+
+@smallexample
+void __builtin_ia32_llwpcb16 (void *);
+void __builtin_ia32_llwpcb32 (void *);
+void __builtin_ia32_llwpcb64 (void *);
+void * __builtin_ia32_llwpcb16 (void);
+void * __builtin_ia32_llwpcb32 (void);
+void * __builtin_ia32_llwpcb64 (void);
+void __builtin_ia32_lwpval16 (unsigned short, unsigned int, unsigned short)
+void __builtin_ia32_lwpval32 (unsigned int, unsigned int, unsigned int)
+void __builtin_ia32_lwpval64 (unsigned __int64, unsigned int, unsigned int)
+unsigned char __builtin_ia32_lwpins16 (unsigned short, unsigned int, unsigned short)
+unsigned char __builtin_ia32_lwpins32 (unsigned int, unsigned int, unsigned int)
+unsigned char __builtin_ia32_lwpins64 (unsigned __int64, unsigned int, unsigned int)
+@end smallexample
+
 The following built-in functions are available when @option{-m3dnow} is used.
 All of them generate the machine instruction that is part of the name.

--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@ -594,7 +594,7 @@ Objective-C and Objective-C++ Dialects}.
 -mcld -mcx16 -msahf -mmovbe -mcrc32 -mrecip @gol
 -mmmx  -msse  -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4 -mavx @gol
 -maes -mpclmul @gol
-msse4a -m3dnow -mpopcnt -mabm -mfma4 -mxop @gol
+-msse4a -m3dnow -mpopcnt -mabm -mfma4 -mxop -mlwp @gol
 -mthreads  -mno-align-stringops  -minline-all-stringops @gol
 -minline-stringops-dynamically -mstringop-strategy=@var{alg} @gol
 -mpush-args  -maccumulate-outgoing-args  -m128bit-long-double @gol
@ -12007,6 +12007,8 @@ preferred alignment to @option{-mpreferred-stack-boundary=2}.
@itemx -mno-fma4
@itemx -mxop
@itemx -mno-xop
+@itemx -mlwp
+@itemx -mno-lwp
@itemx -m3dnow
@itemx -mno-3dnow
@itemx -mpopcnt
@ -12021,7 +12023,7 @@ preferred alignment to @option{-mpreferred-stack-boundary=2}.
@opindex mno-3dnow
 These switches enable or disable the use of instructions in the MMX,
 SSE, SSE2, SSE3, SSSE3, SSE4.1, AVX, AES, PCLMUL, SSE4A, FMA4, XOP,
-ABM or 3DNow!@: extended instruction sets.
+LWP, ABM or 3DNow!@: extended instruction sets.
 These extensions are also available as built-in functions: see
@ref{X86 Built-in Functions}, for details of the functions enabled and
 disabled by these switches.