gas/

2004-11-23 Jan Beulich <jbeulich@novell.com>

	* config/tc-i386.h (CpuMMX2): Declare. Artificial classifier to
	indicate the MMX extensions added by both SSE and 3DNow!A.
	(Cpu3dnowA): Declare.
	(CpuUnknownFlags): Update.
	* config/tc-i386.c (cpu_sub_arch_name): Declare.
	(cpu_arch): i586 and pentium do not imply MMX. i686 and pentiumpro do
	neither imply SSE nor MMX. k6 implies MMX. k6_2 additionally implies
	3DNow!. Athlon additionally implies 3DNow!A. Several new
	entries (those starting with a dot are for sub-arch specification).
	(set_cpu_arch): Handle sub-arch specifications.
	(parse_insn): Distinguish between instructions not supported because
	of insufficient CPU features and because of 64-bit mode.
	* doc/c-i386.texi: Describe enhanced .arch directive.

include/opcode/
2004-11-23 Jan Beulich <jbeulich@novell.com>

	* i386.h (i386_optab): paddq and psubq, even in their MMX form, are
	available only with SSE2. Change the MMX additions introduced by SSE
	and 3DNow!A to CpuMMX2 (rather than CpuMMX). Indicate the 3DNow!A
	instructions by their now designated identifier (since combining i686
	and 3DNow! does not really imply 3DNow!A).

6 files changed, 128 insertions, 57 deletions

diff --git a/gas/ChangeLog b/gas/ChangeLog
index 9b9d7d6..39bc794 100644
--- a/gas/ChangeLog
+++ b/gas/ChangeLog
@@ -1,3 +1,19 @@
+2004-11-23 Jan Beulich <jbeulich@novell.com>
+
+	* config/tc-i386.h (CpuMMX2): Declare. Artificial classifier to
+	indicate the MMX extensions added by both SSE and 3DNow!A.
+	(Cpu3dnowA): Declare.
+	(CpuUnknownFlags): Update.
+	* config/tc-i386.c (cpu_sub_arch_name): Declare.
+	(cpu_arch): i586 and pentium do not imply MMX. i686 and pentiumpro do
+	neither imply SSE nor MMX. k6 implies MMX. k6_2 additionally implies
+	3DNow!. Athlon additionally implies 3DNow!A. Several new
+	entries (those starting with a dot are for sub-arch specification).
+	(set_cpu_arch): Handle sub-arch specifications.
+	(parse_insn): Distinguish between instructions not supported because
+	of insufficient CPU features and because of 64-bit mode.
+	* doc/c-i386.texi: Describe enhanced .arch directive.
+
 2004-11-22  Bob Wilson  <bob.wilson@acm.org>
 
 	* config/tc-xtensa.c (xg_add_opcode_fix): Set fx_no_overflow.
diff --git a/gas/config/tc-i386.c b/gas/config/tc-i386.c
index aa2ec54..430a338 100644
--- a/gas/config/tc-i386.c
+++ b/gas/config/tc-i386.c
@@ -314,6 +314,7 @@ static int quiet_warnings = 0;
 
 /* CPU name.  */
 static const char *cpu_arch_name = NULL;
+static const char *cpu_sub_arch_name = NULL;
 
 /* CPU feature flags.  */
 static unsigned int cpu_arch_flags = CpuUnknownFlags | CpuNo64;
@@ -416,14 +417,24 @@ static const arch_entry cpu_arch[] = {
   {"i286",	Cpu086|Cpu186|Cpu286 },
   {"i386",	Cpu086|Cpu186|Cpu286|Cpu386 },
   {"i486",	Cpu086|Cpu186|Cpu286|Cpu386|Cpu486 },
-  {"i586",	Cpu086|Cpu186|Cpu286|Cpu386|Cpu486|Cpu586|CpuMMX },
-  {"i686",	Cpu086|Cpu186|Cpu286|Cpu386|Cpu486|Cpu586|Cpu686|CpuMMX|CpuSSE },
-  {"pentium",	Cpu086|Cpu186|Cpu286|Cpu386|Cpu486|Cpu586|CpuMMX },
-  {"pentiumpro",Cpu086|Cpu186|Cpu286|Cpu386|Cpu486|Cpu586|Cpu686|CpuMMX|CpuSSE },
-  {"pentium4",	Cpu086|Cpu186|Cpu286|Cpu386|Cpu486|Cpu586|Cpu686|CpuP4|CpuMMX|CpuSSE|CpuSSE2 },
-  {"k6",	Cpu086|Cpu186|Cpu286|Cpu386|Cpu486|Cpu586|CpuK6|CpuMMX|Cpu3dnow },
-  {"athlon",	Cpu086|Cpu186|Cpu286|Cpu386|Cpu486|Cpu586|Cpu686|CpuK6|CpuAthlon|CpuMMX|Cpu3dnow },
-  {"sledgehammer",Cpu086|Cpu186|Cpu286|Cpu386|Cpu486|Cpu586|Cpu686|CpuK6|CpuAthlon|CpuSledgehammer|CpuMMX|Cpu3dnow|CpuSSE|CpuSSE2 },
+  {"i586",	Cpu086|Cpu186|Cpu286|Cpu386|Cpu486|Cpu586 },
+  {"i686",	Cpu086|Cpu186|Cpu286|Cpu386|Cpu486|Cpu586|Cpu686 },
+  {"pentium",	Cpu086|Cpu186|Cpu286|Cpu386|Cpu486|Cpu586 },
+  {"pentiumpro",Cpu086|Cpu186|Cpu286|Cpu386|Cpu486|Cpu586|Cpu686 },
+  {"pentiumii",	Cpu086|Cpu186|Cpu286|Cpu386|Cpu486|Cpu586|Cpu686|CpuMMX },
+  {"pentiumiii",Cpu086|Cpu186|Cpu286|Cpu386|Cpu486|Cpu586|Cpu686|CpuMMX|CpuMMX2|CpuSSE },
+  {"pentium4",	Cpu086|Cpu186|Cpu286|Cpu386|Cpu486|Cpu586|Cpu686|CpuP4|CpuMMX|CpuMMX2|CpuSSE|CpuSSE2 },
+  {"prescott",	Cpu086|Cpu186|Cpu286|Cpu386|Cpu486|Cpu586|Cpu686|CpuP4|CpuMMX|CpuMMX2|CpuSSE|CpuSSE2|CpuPNI },
+  {"k6",	Cpu086|Cpu186|Cpu286|Cpu386|Cpu486|Cpu586|CpuK6|CpuMMX },
+  {"k6_2",	Cpu086|Cpu186|Cpu286|Cpu386|Cpu486|Cpu586|CpuK6|CpuMMX|Cpu3dnow },
+  {"athlon",	Cpu086|Cpu186|Cpu286|Cpu386|Cpu486|Cpu586|Cpu686|CpuK6|CpuAthlon|CpuMMX|CpuMMX2|Cpu3dnow|Cpu3dnowA },
+  {"sledgehammer",Cpu086|Cpu186|Cpu286|Cpu386|Cpu486|Cpu586|Cpu686|CpuK6|CpuAthlon|CpuSledgehammer|CpuMMX|CpuMMX2|Cpu3dnow|Cpu3dnowA|CpuSSE|CpuSSE2 },
+  {".mmx",	CpuMMX },
+  {".sse",	CpuMMX|CpuMMX2|CpuSSE },
+  {".sse2",	CpuMMX|CpuMMX2|CpuSSE|CpuSSE2 },
+  {".3dnow",	CpuMMX|Cpu3dnow },
+  {".3dnowa",	CpuMMX|CpuMMX2|Cpu3dnow|Cpu3dnowA },
+  {".padlock",	CpuPadLock },
   {NULL, 0 }
 };
 
@@ -836,10 +847,22 @@ set_cpu_arch (dummy)
 	{
 	  if (strcmp (string, cpu_arch[i].name) == 0)
 	    {
-	      cpu_arch_name = cpu_arch[i].name;
-	      cpu_arch_flags = (cpu_arch[i].flags
-				| (flag_code == CODE_64BIT ? Cpu64 : CpuNo64));
-	      break;
+	      if (*string != '.')
+		{
+		  cpu_arch_name = cpu_arch[i].name;
+		  cpu_sub_arch_name = NULL;
+		  cpu_arch_flags = (cpu_arch[i].flags
+				    | (flag_code == CODE_64BIT ? Cpu64 : CpuNo64));
+		  break;
+		}
+	      if ((cpu_arch_flags | cpu_arch[i].flags) != cpu_arch_flags)
+		{
+		  cpu_sub_arch_name = cpu_arch[i].name;
+		  cpu_arch_flags |= cpu_arch[i].flags;
+		}
+	      *input_line_pointer = e;
+	      demand_empty_rest_of_line ();
+	      return;
 	    }
 	}
       if (!cpu_arch[i].name)
@@ -1561,6 +1584,8 @@ parse_insn (line, mnemonic)
   char *l = line;
   char *token_start = l;
   char *mnem_p;
+  int supported;
+  const template *t;
 
   /* Non-zero if we found a prefix only acceptable with string insns.  */
   const char *expecting_string_instruction = NULL;
@@ -1709,11 +1734,29 @@ parse_insn (line, mnemonic)
     }
 
   /* Check if instruction is supported on specified architecture.  */
-  if ((current_templates->start->cpu_flags & ~(Cpu64 | CpuNo64))
-      & ~(cpu_arch_flags & ~(Cpu64 | CpuNo64)))
+  supported = 0;
+  for (t = current_templates->start; t < current_templates->end; ++t)
+    {
+      if (!((t->cpu_flags & ~(Cpu64 | CpuNo64))
+	    & ~(cpu_arch_flags & ~(Cpu64 | CpuNo64))))
+	  supported |= 1;
+      if (!(t->cpu_flags & (flag_code == CODE_64BIT ? CpuNo64 : Cpu64)))
+	  supported |= 2;
+    }
+  if (!(supported & 2))
+    {
+      as_bad (flag_code == CODE_64BIT
+	      ? _("`%s' is not supported in 64-bit mode")
+	      : _("`%s' is only supported in 64-bit mode"),
+	      current_templates->start->name);
+      return NULL;
+    }
+  if (!(supported & 1))
     {
-      as_warn (_("`%s' is not supported on `%s'"),
-	       current_templates->start->name, cpu_arch_name);
+      as_warn (_("`%s' is not supported on `%s%s'"),
+	       current_templates->start->name,
+	       cpu_arch_name,
+	       cpu_sub_arch_name ? cpu_sub_arch_name : "");
     }
   else if ((Cpu386 & ~cpu_arch_flags) && (flag_code != CODE_16BIT))
     {
diff --git a/gas/config/tc-i386.h b/gas/config/tc-i386.h
index 3b377cc..e56130c 100644
--- a/gas/config/tc-i386.h
+++ b/gas/config/tc-i386.h
@@ -174,18 +174,20 @@ typedef struct
 #define CpuAthlon	0x200	/* AMD Athlon or better required*/
 #define CpuSledgehammer 0x400	/* Sledgehammer or better required */
 #define CpuMMX		0x800	/* MMX support required */
-#define CpuSSE	       0x1000	/* Streaming SIMD extensions required */
-#define CpuSSE2	       0x2000	/* Streaming SIMD extensions 2 required */
-#define Cpu3dnow       0x4000	/* 3dnow! support required */
-#define CpuPNI	       0x8000	/* Prescott New Instructions required */
-#define CpuPadLock    0x10000	/* VIA PadLock required */
+#define CpuMMX2	       0x1000	/* extended MMX support (with SSE or 3DNow!Ext) required */
+#define CpuSSE	       0x2000	/* Streaming SIMD extensions required */
+#define CpuSSE2	       0x4000	/* Streaming SIMD extensions 2 required */
+#define Cpu3dnow       0x8000	/* 3dnow! support required */
+#define Cpu3dnowA     0x10000	/* 3dnow!Extensions support required */
+#define CpuPNI	      0x20000	/* Prescott New Instructions required */
+#define CpuPadLock    0x40000	/* VIA PadLock required */
 
   /* These flags are set by gas depending on the flag_code.  */
 #define Cpu64	     0x4000000   /* 64bit support required  */
 #define CpuNo64      0x8000000   /* Not supported in the 64bit mode  */
 
   /* The default value for unknown CPUs - enable all features to avoid problems.  */
-#define CpuUnknownFlags (Cpu086|Cpu186|Cpu286|Cpu386|Cpu486|Cpu586|Cpu686|CpuP4|CpuSledgehammer|CpuMMX|CpuSSE|CpuSSE2|CpuPNI|Cpu3dnow|CpuK6|CpuAthlon|CpuPadLock)
+#define CpuUnknownFlags (Cpu086|Cpu186|Cpu286|Cpu386|Cpu486|Cpu586|Cpu686|CpuP4|CpuSledgehammer|CpuMMX|CpuMMX2|CpuSSE|CpuSSE2|CpuPNI|Cpu3dnow|Cpu3dnowA|CpuK6|CpuAthlon|CpuPadLock)
 
   /* the bits in opcode_modifier are used to generate the final opcode from
      the base_opcode.  These bits also are used to detect alternate forms of
diff --git a/gas/doc/c-i386.texi b/gas/doc/c-i386.texi
index f9fc55b..c561bcb 100644
--- a/gas/doc/c-i386.texi
+++ b/gas/doc/c-i386.texi
@@ -691,15 +691,16 @@ register is @samp{%st(i)}.
 @cindex x86-64 arch directive
 
 @code{@value{AS}} may be told to assemble for a particular CPU
-architecture with the @code{.arch @var{cpu_type}} directive.  This
+(sub-)architecture with the @code{.arch @var{cpu_type}} directive.  This
 directive enables a warning when gas detects an instruction that is not
 supported on the CPU specified.  The choices for @var{cpu_type} are:
 
 @multitable @columnfractions .20 .20 .20 .20
 @item @samp{i8086} @tab @samp{i186} @tab @samp{i286} @tab @samp{i386}
 @item @samp{i486} @tab @samp{i586} @tab @samp{i686} @tab @samp{pentium}
-@item @samp{pentiumpro} @tab @samp{pentium4} @tab @samp{k6} @tab @samp{athlon}
-@item @samp{sledgehammer}
+@item @samp{pentiumpro} @tab @samp{pentiumii} @tab @samp{pentiumiii} @tab @samp{pentium4}
+@item @samp{k6} @tab @samp{athlon} @samp{sledgehammer}
+@item @samp{.mmx} @samp{.sse} @samp{.sse2} @samp{.3dnow}
 @end multitable
 
 Apart from the warning, there are only two other effects on
@@ -715,13 +716,14 @@ conditional jumps will be promoted when necessary to a two instruction
 sequence consisting of a conditional jump of the opposite sense around
 an unconditional jump to the target.
 
-Following the CPU architecture, you may specify @samp{jumps} or
-@samp{nojumps} to control automatic promotion of conditional jumps.
-@samp{jumps} is the default, and enables jump promotion;  All external
-jumps will be of the long variety, and file-local jumps will be promoted
-as necessary.  (@pxref{i386-Jumps})  @samp{nojumps} leaves external
-conditional jumps as byte offset jumps, and warns about file-local
-conditional jumps that @code{@value{AS}} promotes.
+Following the CPU architecture (but not a sub-architecture, which are those
+starting with a dot), you may specify @samp{jumps} or @samp{nojumps} to
+control automatic promotion of conditional jumps. @samp{jumps} is the
+default, and enables jump promotion;  All external jumps will be of the long
+variety, and file-local jumps will be promoted as necessary.
+(@pxref{i386-Jumps})  @samp{nojumps} leaves external conditional jumps as
+byte offset jumps, and warns about file-local conditional jumps that
+@code{@value{AS}} promotes.
 Unconditional jumps are treated as for @samp{jumps}.
 
 For example
diff --git a/include/opcode/ChangeLog b/include/opcode/ChangeLog
index 3429c73..14bd353 100644
--- a/include/opcode/ChangeLog
+++ b/include/opcode/ChangeLog
@@ -1,3 +1,11 @@
+2004-11-23 Jan Beulich <jbeulich@novell.com>
+
+	* i386.h (i386_optab): paddq and psubq, even in their MMX form, are
+	available only with SSE2. Change the MMX additions introduced by SSE
+	and 3DNow!A to CpuMMX2 (rather than CpuMMX). Indicate the 3DNow!A
+	instructions by their now designated identifier (since combining i686
+	and 3DNow! does not really imply 3DNow!A).
+
 2004-11-19  Alan Modra  <amodra@bigpond.net.au>
 
 	* msp430.h (struct rcodes_s, MSP430_RLC, msp430_rcodes,
diff --git a/include/opcode/i386.h b/include/opcode/i386.h
index fc2f5f0..1a88da4 100644
--- a/include/opcode/i386.h
+++ b/include/opcode/i386.h
@@ -1020,7 +1020,7 @@ static const template i386_optab[] =
 {"paddw",    2, 0x660ffd,X,CpuSSE2,NoSuf|IgnoreSize|Modrm,		{ RegXMM|LLongMem, RegXMM, 0 } },
 {"paddd",    2, 0x0ffe, X, CpuMMX, NoSuf|IgnoreSize|Modrm,		{ RegMMX|LongMem, RegMMX, 0 } },
 {"paddd",    2, 0x660ffe,X,CpuSSE2,NoSuf|IgnoreSize|Modrm,		{ RegXMM|LLongMem, RegXMM, 0 } },
-{"paddq",    2, 0x0fd4, X, CpuMMX, NoSuf|IgnoreSize|Modrm,		{ RegMMX|LLongMem, RegMMX, 0 } },
+{"paddq",    2, 0x0fd4, X, CpuSSE2,NoSuf|IgnoreSize|Modrm,		{ RegMMX|LLongMem, RegMMX, 0 } },
 {"paddq",    2, 0x660fd4,X,CpuSSE2,NoSuf|IgnoreSize|Modrm,		{ RegXMM|LLongMem, RegXMM, 0 } },
 {"paddsb",   2, 0x0fec, X, CpuMMX, NoSuf|IgnoreSize|Modrm,		{ RegMMX|LongMem, RegMMX, 0 } },
 {"paddsb",   2, 0x660fec,X,CpuSSE2,NoSuf|IgnoreSize|Modrm,		{ RegXMM|LLongMem, RegXMM, 0 } },
@@ -1151,7 +1151,7 @@ static const template i386_optab[] =
 {"divps",     2, 0x0f5e,    X, CpuSSE, NoSuf|IgnoreSize|Modrm,	{ RegXMM|LLongMem, RegXMM, 0 } },
 {"divss",     2, 0xf30f5e,  X, CpuSSE, NoSuf|IgnoreSize|Modrm,	{ RegXMM|WordMem, RegXMM, 0 } },
 {"ldmxcsr",   1, 0x0fae,    2, CpuSSE, NoSuf|IgnoreSize|Modrm, 	{ WordMem, 0, 0 } },
-{"maskmovq",  2, 0x0ff7,    X, CpuSSE, NoSuf|IgnoreSize|Modrm,	{ RegMMX|InvMem, RegMMX, 0 } },
+{"maskmovq",  2, 0x0ff7,    X, CpuMMX2,NoSuf|IgnoreSize|Modrm,	{ RegMMX|InvMem, RegMMX, 0 } },
 {"maxps",     2, 0x0f5f,    X, CpuSSE, NoSuf|IgnoreSize|Modrm,	{ RegXMM|LLongMem, RegXMM, 0 } },
 {"maxss",     2, 0xf30f5f,  X, CpuSSE, NoSuf|IgnoreSize|Modrm,	{ RegXMM|WordMem, RegXMM, 0 } },
 {"minps",     2, 0x0f5d,    X, CpuSSE, NoSuf|IgnoreSize|Modrm,	{ RegXMM|LLongMem, RegXMM, 0 } },
@@ -1166,7 +1166,7 @@ static const template i386_optab[] =
 {"movlps",    2, 0x0f13,    X, CpuSSE, NoSuf|IgnoreSize|Modrm,	{ RegXMM, LLongMem, 0 } },
 {"movmskps",  2, 0x0f50,    X, CpuSSE, lq_Suf|IgnoreSize|Modrm,	{ RegXMM|InvMem, Reg32|Reg64, 0 } },
 {"movntps",   2, 0x0f2b,    X, CpuSSE, NoSuf|IgnoreSize|Modrm, 	{ RegXMM, LLongMem, 0 } },
-{"movntq",    2, 0x0fe7,    X, CpuSSE, NoSuf|IgnoreSize|Modrm, 	{ RegMMX, LLongMem, 0 } },
+{"movntq",    2, 0x0fe7,    X, CpuMMX2,NoSuf|IgnoreSize|Modrm, 	{ RegMMX, LLongMem, 0 } },
 {"movntdq",   2, 0x660fe7,  X, CpuSSE2,NoSuf|IgnoreSize|Modrm, 	{ RegXMM, LLongMem, 0 } },
 {"movss",     2, 0xf30f10,  X, CpuSSE, NoSuf|IgnoreSize|Modrm,	{ RegXMM|WordMem, RegXMM, 0 } },
 {"movss",     2, 0xf30f11,  X, CpuSSE, NoSuf|IgnoreSize|Modrm,	{ RegXMM, RegXMM|WordMem, 0 } },
@@ -1175,38 +1175,38 @@ static const template i386_optab[] =
 {"mulps",     2, 0x0f59,    X, CpuSSE, NoSuf|IgnoreSize|Modrm,	{ RegXMM|LLongMem, RegXMM, 0 } },
 {"mulss",     2, 0xf30f59,  X, CpuSSE, NoSuf|IgnoreSize|Modrm,	{ RegXMM|WordMem, RegXMM, 0 } },
 {"orps",      2, 0x0f56,    X, CpuSSE, NoSuf|IgnoreSize|Modrm,	{ RegXMM|LLongMem, RegXMM, 0 } },
-{"pavgb",     2, 0x0fe0,    X, CpuSSE, NoSuf|IgnoreSize|Modrm,	{ RegMMX|LLongMem, RegMMX, 0 } },
+{"pavgb",     2, 0x0fe0,    X, CpuMMX2,NoSuf|IgnoreSize|Modrm,	{ RegMMX|LLongMem, RegMMX, 0 } },
 {"pavgb",     2, 0x660fe0,  X, CpuSSE2,NoSuf|IgnoreSize|Modrm,	{ RegXMM|LLongMem, RegXMM, 0 } },
-{"pavgw",     2, 0x0fe3,    X, CpuSSE, NoSuf|IgnoreSize|Modrm,	{ RegMMX|LLongMem, RegMMX, 0 } },
+{"pavgw",     2, 0x0fe3,    X, CpuMMX2,NoSuf|IgnoreSize|Modrm,	{ RegMMX|LLongMem, RegMMX, 0 } },
 {"pavgw",     2, 0x660fe3,  X, CpuSSE2,NoSuf|IgnoreSize|Modrm,	{ RegXMM|LLongMem, RegXMM, 0 } },
-{"pextrw",    3, 0x0fc5,    X, CpuSSE, lq_Suf|IgnoreSize|Modrm,	{ Imm8, RegMMX|InvMem, Reg32|Reg64 } },
+{"pextrw",    3, 0x0fc5,    X, CpuMMX2,lq_Suf|IgnoreSize|Modrm,	{ Imm8, RegMMX|InvMem, Reg32|Reg64 } },
 {"pextrw",    3, 0x660fc5,  X, CpuSSE2,lq_Suf|IgnoreSize|Modrm,	{ Imm8, RegXMM|InvMem, Reg32|Reg64 } },
-{"pinsrw",    3, 0x0fc4,    X, CpuSSE, lq_Suf|IgnoreSize|Modrm,	{ Imm8, Reg32|Reg64|ShortMem, RegMMX } },
+{"pinsrw",    3, 0x0fc4,    X, CpuMMX2,lq_Suf|IgnoreSize|Modrm,	{ Imm8, Reg32|Reg64|ShortMem, RegMMX } },
 {"pinsrw",    3, 0x660fc4,  X, CpuSSE2,lq_Suf|IgnoreSize|Modrm,	{ Imm8, Reg32|Reg64|ShortMem, RegXMM } },
-{"pmaxsw",    2, 0x0fee,    X, CpuSSE, NoSuf|IgnoreSize|Modrm,	{ RegMMX|LLongMem, RegMMX, 0 } },
+{"pmaxsw",    2, 0x0fee,    X, CpuMMX2,NoSuf|IgnoreSize|Modrm,	{ RegMMX|LLongMem, RegMMX, 0 } },
 {"pmaxsw",    2, 0x660fee,  X, CpuSSE2,NoSuf|IgnoreSize|Modrm,	{ RegXMM|LLongMem, RegXMM, 0 } },
-{"pmaxub",    2, 0x0fde,    X, CpuSSE, NoSuf|IgnoreSize|Modrm,	{ RegMMX|LLongMem, RegMMX, 0 } },
+{"pmaxub",    2, 0x0fde,    X, CpuMMX2,NoSuf|IgnoreSize|Modrm,	{ RegMMX|LLongMem, RegMMX, 0 } },
 {"pmaxub",    2, 0x660fde,  X, CpuSSE2,NoSuf|IgnoreSize|Modrm,	{ RegXMM|LLongMem, RegXMM, 0 } },
-{"pminsw",    2, 0x0fea,    X, CpuSSE, NoSuf|IgnoreSize|Modrm,	{ RegMMX|LLongMem, RegMMX, 0 } },
+{"pminsw",    2, 0x0fea,    X, CpuMMX2,NoSuf|IgnoreSize|Modrm,	{ RegMMX|LLongMem, RegMMX, 0 } },
 {"pminsw",    2, 0x660fea,  X, CpuSSE2,NoSuf|IgnoreSize|Modrm,	{ RegXMM|LLongMem, RegXMM, 0 } },
-{"pminub",    2, 0x0fda,    X, CpuSSE, NoSuf|IgnoreSize|Modrm,	{ RegMMX|LLongMem, RegMMX, 0 } },
+{"pminub",    2, 0x0fda,    X, CpuMMX2,NoSuf|IgnoreSize|Modrm,	{ RegMMX|LLongMem, RegMMX, 0 } },
 {"pminub",    2, 0x660fda,  X, CpuSSE2,NoSuf|IgnoreSize|Modrm,	{ RegXMM|LLongMem, RegXMM, 0 } },
-{"pmovmskb",  2, 0x0fd7,    X, CpuSSE, lq_Suf|IgnoreSize|Modrm,	{ RegMMX|InvMem, Reg32|Reg64, 0 } },
+{"pmovmskb",  2, 0x0fd7,    X, CpuMMX2,lq_Suf|IgnoreSize|Modrm,	{ RegMMX|InvMem, Reg32|Reg64, 0 } },
 {"pmovmskb",  2, 0x660fd7,  X, CpuSSE2,lq_Suf|IgnoreSize|Modrm,	{ RegXMM|InvMem, Reg32|Reg64, 0 } },
-{"pmulhuw",   2, 0x0fe4,    X, CpuSSE, NoSuf|IgnoreSize|Modrm,	{ RegMMX|LLongMem, RegMMX, 0 } },
+{"pmulhuw",   2, 0x0fe4,    X, CpuMMX2,NoSuf|IgnoreSize|Modrm,	{ RegMMX|LLongMem, RegMMX, 0 } },
 {"pmulhuw",   2, 0x660fe4,  X, CpuSSE2,NoSuf|IgnoreSize|Modrm,	{ RegXMM|LLongMem, RegXMM, 0 } },
-{"prefetchnta", 1, 0x0f18,  0, CpuSSE, NoSuf|IgnoreSize|Modrm, 	{ LLongMem, 0, 0 } },
-{"prefetcht0",  1, 0x0f18,  1, CpuSSE, NoSuf|IgnoreSize|Modrm, 	{ LLongMem, 0, 0 } },
-{"prefetcht1",  1, 0x0f18,  2, CpuSSE, NoSuf|IgnoreSize|Modrm, 	{ LLongMem, 0, 0 } },
-{"prefetcht2",  1, 0x0f18,  3, CpuSSE, NoSuf|IgnoreSize|Modrm, 	{ LLongMem, 0, 0 } },
-{"psadbw",    2, 0x0ff6,    X, CpuSSE, NoSuf|IgnoreSize|Modrm,	{ RegMMX|LLongMem, RegMMX, 0 } },
+{"prefetchnta", 1, 0x0f18,  0, CpuMMX2,NoSuf|IgnoreSize|Modrm, 	{ LLongMem, 0, 0 } },
+{"prefetcht0",  1, 0x0f18,  1, CpuMMX2,NoSuf|IgnoreSize|Modrm, 	{ LLongMem, 0, 0 } },
+{"prefetcht1",  1, 0x0f18,  2, CpuMMX2,NoSuf|IgnoreSize|Modrm, 	{ LLongMem, 0, 0 } },
+{"prefetcht2",  1, 0x0f18,  3, CpuMMX2,NoSuf|IgnoreSize|Modrm, 	{ LLongMem, 0, 0 } },
+{"psadbw",    2, 0x0ff6,    X, CpuMMX2,NoSuf|IgnoreSize|Modrm,	{ RegMMX|LLongMem, RegMMX, 0 } },
 {"psadbw",    2, 0x660ff6,  X, CpuSSE2,NoSuf|IgnoreSize|Modrm,	{ RegXMM|LLongMem, RegXMM, 0 } },
-{"pshufw",    3, 0x0f70,    X, CpuSSE, NoSuf|IgnoreSize|Modrm,	{ Imm8, RegMMX|LLongMem, RegMMX } },
+{"pshufw",    3, 0x0f70,    X, CpuMMX2,NoSuf|IgnoreSize|Modrm,	{ Imm8, RegMMX|LLongMem, RegMMX } },
 {"rcpps",     2, 0x0f53,    X, CpuSSE, NoSuf|IgnoreSize|Modrm,	{ RegXMM|LLongMem, RegXMM, 0 } },
 {"rcpss",     2, 0xf30f53,  X, CpuSSE, NoSuf|IgnoreSize|Modrm,	{ RegXMM|WordMem, RegXMM, 0 } },
 {"rsqrtps",   2, 0x0f52,    X, CpuSSE, NoSuf|IgnoreSize|Modrm,	{ RegXMM|LLongMem, RegXMM, 0 } },
 {"rsqrtss",   2, 0xf30f52,  X, CpuSSE, NoSuf|IgnoreSize|Modrm,	{ RegXMM|WordMem, RegXMM, 0 } },
-{"sfence",    0, 0x0fae, 0xf8, CpuSSE, NoSuf|IgnoreSize|ImmExt,	{ 0, 0, 0 } },
+{"sfence",    0, 0x0fae, 0xf8, CpuMMX2,NoSuf|IgnoreSize|ImmExt,	{ 0, 0, 0 } },
 {"shufps",    3, 0x0fc6,    X, CpuSSE, NoSuf|IgnoreSize|Modrm,	{ Imm8, RegXMM|LLongMem, RegXMM } },
 {"sqrtps",    2, 0x0f51,    X, CpuSSE, NoSuf|IgnoreSize|Modrm,	{ RegXMM|LLongMem, RegXMM, 0 } },
 {"sqrtss",    2, 0xf30f51,  X, CpuSSE, NoSuf|IgnoreSize|Modrm,	{ RegXMM|WordMem, RegXMM, 0 } },
@@ -1341,7 +1341,7 @@ static const template i386_optab[] =
 {"femms",    0, 0x0f0e,	   X, Cpu3dnow, NoSuf,			{ 0, 0, 0 } },
 {"pavgusb",  2, 0x0f0f, 0xbf, Cpu3dnow, NoSuf|IgnoreSize|Modrm|ImmExt,	{ RegMMX|LongMem, RegMMX, 0 } },
 {"pf2id",    2, 0x0f0f, 0x1d, Cpu3dnow, NoSuf|IgnoreSize|Modrm|ImmExt,	{ RegMMX|LongMem, RegMMX, 0 } },
-{"pf2iw",    2, 0x0f0f, 0x1c, Cpu3dnow|Cpu686,NoSuf|IgnoreSize|Modrm|ImmExt,	{ RegMMX|LongMem, RegMMX, 0 } },
+{"pf2iw",    2, 0x0f0f, 0x1c, Cpu3dnowA,NoSuf|IgnoreSize|Modrm|ImmExt,	{ RegMMX|LongMem, RegMMX, 0 } },
 {"pfacc",    2, 0x0f0f, 0xae, Cpu3dnow, NoSuf|IgnoreSize|Modrm|ImmExt,	{ RegMMX|LongMem, RegMMX, 0 } },
 {"pfadd",    2, 0x0f0f, 0x9e, Cpu3dnow, NoSuf|IgnoreSize|Modrm|ImmExt,	{ RegMMX|LongMem, RegMMX, 0 } },
 {"pfcmpeq",  2, 0x0f0f, 0xb0, Cpu3dnow, NoSuf|IgnoreSize|Modrm|ImmExt,	{ RegMMX|LongMem, RegMMX, 0 } },
@@ -1350,8 +1350,8 @@ static const template i386_optab[] =
 {"pfmax",    2, 0x0f0f, 0xa4, Cpu3dnow, NoSuf|IgnoreSize|Modrm|ImmExt,	{ RegMMX|LongMem, RegMMX, 0 } },
 {"pfmin",    2, 0x0f0f, 0x94, Cpu3dnow, NoSuf|IgnoreSize|Modrm|ImmExt,	{ RegMMX|LongMem, RegMMX, 0 } },
 {"pfmul",    2, 0x0f0f, 0xb4, Cpu3dnow, NoSuf|IgnoreSize|Modrm|ImmExt,	{ RegMMX|LongMem, RegMMX, 0 } },
-{"pfnacc",   2, 0x0f0f, 0x8a, Cpu3dnow|Cpu686,NoSuf|IgnoreSize|Modrm|ImmExt,	{ RegMMX|LongMem, RegMMX, 0 } },
-{"pfpnacc",  2, 0x0f0f, 0x8e, Cpu3dnow|Cpu686,NoSuf|IgnoreSize|Modrm|ImmExt,	{ RegMMX|LongMem, RegMMX, 0 } },
+{"pfnacc",   2, 0x0f0f, 0x8a, Cpu3dnowA,NoSuf|IgnoreSize|Modrm|ImmExt,	{ RegMMX|LongMem, RegMMX, 0 } },
+{"pfpnacc",  2, 0x0f0f, 0x8e, Cpu3dnowA,NoSuf|IgnoreSize|Modrm|ImmExt,	{ RegMMX|LongMem, RegMMX, 0 } },
 {"pfrcp",    2, 0x0f0f, 0x96, Cpu3dnow, NoSuf|IgnoreSize|Modrm|ImmExt,	{ RegMMX|LongMem, RegMMX, 0 } },
 {"pfrcpit1", 2, 0x0f0f, 0xa6, Cpu3dnow, NoSuf|IgnoreSize|Modrm|ImmExt,	{ RegMMX|LongMem, RegMMX, 0 } },
 {"pfrcpit2", 2, 0x0f0f, 0xb6, Cpu3dnow, NoSuf|IgnoreSize|Modrm|ImmExt,	{ RegMMX|LongMem, RegMMX, 0 } },
@@ -1360,9 +1360,9 @@ static const template i386_optab[] =
 {"pfsub",    2, 0x0f0f, 0x9a, Cpu3dnow, NoSuf|IgnoreSize|Modrm|ImmExt,	{ RegMMX|LongMem, RegMMX, 0 } },
 {"pfsubr",   2, 0x0f0f, 0xaa, Cpu3dnow, NoSuf|IgnoreSize|Modrm|ImmExt,	{ RegMMX|LongMem, RegMMX, 0 } },
 {"pi2fd",    2, 0x0f0f, 0x0d, Cpu3dnow, NoSuf|IgnoreSize|Modrm|ImmExt,	{ RegMMX|LongMem, RegMMX, 0 } },
-{"pi2fw",    2, 0x0f0f, 0x0c, Cpu3dnow|Cpu686,NoSuf|IgnoreSize|Modrm|ImmExt,	{ RegMMX|LongMem, RegMMX, 0 } },
+{"pi2fw",    2, 0x0f0f, 0x0c, Cpu3dnowA,NoSuf|IgnoreSize|Modrm|ImmExt,	{ RegMMX|LongMem, RegMMX, 0 } },
 {"pmulhrw",  2, 0x0f0f, 0xb7, Cpu3dnow, NoSuf|IgnoreSize|Modrm|ImmExt,	{ RegMMX|LongMem, RegMMX, 0 } },
-{"pswapd",   2, 0x0f0f, 0xbb, Cpu3dnow|Cpu686,NoSuf|IgnoreSize|Modrm|ImmExt,	{ RegMMX|LongMem, RegMMX, 0 } },
+{"pswapd",   2, 0x0f0f, 0xbb, Cpu3dnowA,NoSuf|IgnoreSize|Modrm|ImmExt,	{ RegMMX|LongMem, RegMMX, 0 } },
 
 /* AMD extensions. */
 {"syscall",  0, 0x0f05,    X, CpuK6,	NoSuf,			{ 0, 0, 0} },