[PATCH 0/7] x86: templatize various ALU insn templates

[PATCH 0/7] x86: templatize various ALU insn templates

[Jan Beulich]

With the multitude of new APX templates, it finally becomes desirable to
further remove redundancy by also templatizing basic arithmetic insns.

Unlike indicated previously, I think at least part of this would better
go ahead of the APX NF patch. This is because some of what needs adding
explicitly there is being added implicitly here (patches 3 and 4 at
least), in order to avoid losing templates we already had (prematurely
added by the APX NDD patch, imo).

Note that patches 4 and 5 also drop certain templates again which imo
were added by mistake in the course of the NDD work. See the descriptions
of those patches.

1: templatize INC/DEC
2: templatize unary ALU insns
3: templatize binary ALU insns
4: templatize shift/rotate insns
5: templatize shift-double insns
6: templatize ADX insns
7: templatize RAO-INT insns

Jan

[PATCH 1/7] x86: templatize INC/DEC

[Jan Beulich]

With the multitude of new APX templates, it finally becomes desirable to
further remove redundancy by also templatizing basic arithmetic insns.
Start with the simplest case, accompanied by a necessary adjustment to
i386-gen (such that template uses can also be at the start of a line).

While there also drop a bogus (meaningless / unreachable) "break" as
well as a unused variable (which I'm surprised compilers didn't warn
about).

--- a/opcodes/i386-gen.c
+++ b/opcodes/i386-gen.c
@@ -1538,10 +1538,10 @@ opcode_hash_eq (const void *p, const voi
   return strcmp (name, entry->name) == 0;
 }
 
-static void
+static bool
 parse_template (char *buf, int lineno)
 {
-  char sep, *end, *name;
+  char sep, *end, *ptr;
   struct template *tmpl;
   struct template_instance *last_inst = NULL;
 
@@ -1568,8 +1568,16 @@ parse_template (char *buf, int lineno)
 	prev->next = tmpl->next;
       else
 	templates = tmpl->next;
-      return;
+      return true;
     }
+
+  /* Check whether this actually is a reference to an existing template:
+     If there's '>' ahead of ':', it can't be a new template definition
+     (and template undefs have are dealt with above).  */
+  ptr = strchr (buf, '>');
+  if (ptr != NULL && ptr < end)
+    return false;
+
   *end++ = '\0';
   remove_trailing_whitespaces (buf);
 
@@ -1644,6 +1652,8 @@ parse_template (char *buf, int lineno)
 
   tmpl->next = templates;
   templates = tmpl;
+
+  return true;
 }
 
 static unsigned int
@@ -1900,10 +1910,12 @@ process_i386_opcodes (FILE *table)
 	  /* Ignore comments.  */
 	case '\0':
 	  continue;
-	  break;
+
 	case '<':
-	  parse_template (p, lineno);
-	  continue;
+	  if (parse_template (p, lineno))
+	    continue;
+	  break;
+
 	default:
 	  if (!marker)
 	    continue;
--- a/opcodes/i386-opc.tbl
+++ b/opcodes/i386-opc.tbl
@@ -316,10 +316,6 @@ add, 0x4, 0, W|No_sSuf, { Imm8|Imm16|Imm
 add, 0x80/0, APX_F, W|Modrm|CheckOperandSize|No_sSuf|DstVVVV|EVexMap4|NF, { Imm8|Imm16|Imm32|Imm32S, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64}
 add, 0x80/0, 0, W|Modrm|No_sSuf|HLEPrefixLock, { Imm8|Imm16|Imm32|Imm32S, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
 
-inc, 0x40, No64, No_bSuf|No_sSuf|No_qSuf, { Reg16|Reg32 }
-inc, 0xfe/0, APX_F, W|Modrm|No_sSuf|CheckOperandSize|DstVVVV|EVexMap4|NF, {Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64}
-inc, 0xfe/0, 0, W|Modrm|No_sSuf|HLEPrefixLock, { Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-
 sub, 0x28, APX_F, D|W|CheckOperandSize|Modrm|No_sSuf|DstVVVV|EVexMap4|NF|Optimize, { Reg8|Reg16|Reg32|Reg64, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64, }
 sub, 0x28, 0, D|W|CheckOperandSize|Modrm|No_sSuf|HLEPrefixLock|Optimize, { Reg8|Reg16|Reg32|Reg64, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
 sub, 0x83/5, APX_F, Modrm|No_bSuf|No_sSuf|DstVVVV|EVexMap4|NF, { Imm8S, Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg16|Reg32|Reg64 }
@@ -328,10 +324,6 @@ sub, 0x2c, 0, W|No_sSuf, { Imm8|Imm16|Im
 sub, 0x80/5, APX_F, W|Modrm|CheckOperandSize|No_sSuf|DstVVVV|EVexMap4|NF, { Imm8|Imm16|Imm32|Imm32S, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
 sub, 0x80/5, 0, W|Modrm|No_sSuf|HLEPrefixLock, { Imm8|Imm16|Imm32|Imm32S, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
 
-dec, 0x48, No64, No_bSuf|No_sSuf|No_qSuf, { Reg16|Reg32 }
-dec, 0xfe/1, APX_F, W|Modrm|CheckOperandSize|No_sSuf|DstVVVV|EVexMap4|NF, { Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-dec, 0xfe/1, 0, W|Modrm|No_sSuf|HLEPrefixLock, { Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-
 sbb, 0x18, APX_F, D|W|CheckOperandSize|Modrm|No_sSuf|DstVVVV|EVexMap4, { Reg8|Reg16|Reg32|Reg64, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
 sbb, 0x18, 0, D|W|CheckOperandSize|Modrm|No_sSuf|HLEPrefixLock, { Reg8|Reg16|Reg32|Reg64, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
 sbb, 0x83/3, APX_F, Modrm|CheckOperandSize|No_bSuf|No_sSuf|DstVVVV|EVexMap4, { Imm8S, Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg16|Reg32|Reg64 }
@@ -385,6 +377,14 @@ adc, 0x14, 0, W|No_sSuf, { Imm8|Imm16|Im
 adc, 0x80/2, APX_F, W|Modrm|CheckOperandSize|No_sSuf|DstVVVV|EVexMap4, { Imm8|Imm16|Imm32|Imm32S, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
 adc, 0x80/2, 0, W|Modrm|No_sSuf|HLEPrefixLock, { Imm8|Imm16|Imm32|Imm32S, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
 
+<incdec:opc, inc:0, dec:1>
+
+<incdec>, 0x40 | (<incdec:opc> << 3), No64, No_bSuf|No_sSuf|No_qSuf, { Reg16|Reg32 }
+<incdec>, 0xfe/<incdec:opc>, APX_F, W|Modrm|No_sSuf|CheckOperandSize|DstVVVV|EVexMap4|NF, {Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64}
+<incdec>, 0xfe/<incdec:opc>, 0, W|Modrm|No_sSuf|HLEPrefixLock, { Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
+
+<incdec>
+
 neg, 0xf6/3, APX_F, W|Modrm|CheckOperandSize|No_sSuf|DstVVVV|EVexMap4|NF, { Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
 neg, 0xf6/3, 0, W|Modrm|No_sSuf|HLEPrefixLock, { Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
 

[PATCH 2/7] x86: templatize unary ALU insns

[Jan Beulich]

With the multitude of new APX templates, it finally becomes desirable to
further remove redundancy by also templatizing basic arithmetic insns.
Continue with a few simple unary (single source) cases.

--- a/opcodes/i386-opc.tbl
+++ b/opcodes/i386-opc.tbl
@@ -385,11 +385,12 @@ adc, 0x80/2, 0, W|Modrm|No_sSuf|HLEPrefi
 
 <incdec>
 
-neg, 0xf6/3, APX_F, W|Modrm|CheckOperandSize|No_sSuf|DstVVVV|EVexMap4|NF, { Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-neg, 0xf6/3, 0, W|Modrm|No_sSuf|HLEPrefixLock, { Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
+<alu1:opc:nf, not:2:, neg:3:NF>
 
-not, 0xf6/2, APX_F, W|Modrm|CheckOperandSize|No_sSuf|DstVVVV|EVexMap4, { Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-not, 0xf6/2, 0, W|Modrm|No_sSuf|HLEPrefixLock, { Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
+<alu1>, 0xf6/<alu1:opc>, APX_F, W|Modrm|CheckOperandSize|No_sSuf|DstVVVV|EVexMap4|<alu1:nf>, { Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
+<alu1>, 0xf6/<alu1:opc>, 0, W|Modrm|No_sSuf|HLEPrefixLock, { Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
+
+<alu1>
 
 aaa, 0x37, No64, NoSuf, {}
 aas, 0x3f, No64, NoSuf, {}
@@ -420,8 +421,9 @@ cqto, 0x99, x64, Size64|NoSuf, {}
 // expanding 64-bit multiplies, and *cannot* be selected to accomplish
 // 'imul %ebx, %eax' (opcode 0x0faf must be used in this case)
 // These multiplies can only be selected with single operand forms.
-mul, 0xf6/4, 0, W|Modrm|No_sSuf, { Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-imul, 0xf6/5, 0, W|Modrm|No_sSuf, { Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
+<mul:opc, mul:4, imul:5>
+
+<mul>, 0xf6/<mul:opc>, 0, W|Modrm|No_sSuf, { Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
 imul, 0xaf, APX_F, C|Modrm|CheckOperandSize|No_bSuf|No_sSuf|DstVVVV|EVexMap4|NF, { Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg16|Reg32|Reg64, Reg16|Reg32|Reg64 }
 imul, 0xfaf, i386, Modrm|CheckOperandSize|No_bSuf|No_sSuf, { Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg16|Reg32|Reg64 }
 imul, 0x6b, i186, Modrm|CheckOperandSize|No_bSuf|No_sSuf, { Imm8S, Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg16|Reg32|Reg64 }
@@ -432,10 +434,14 @@ imul, 0x69, i186, Modrm|CheckOperandSize
 imul, 0x6b, i186, Modrm|No_bSuf|No_sSuf|RegKludge, { Imm8S, Reg16|Reg32|Reg64 }
 imul, 0x69, i186, Modrm|No_bSuf|No_sSuf|RegKludge, { Imm16|Imm32|Imm32S, Reg16|Reg32|Reg64 }
 
-div, 0xf6/6, 0, W|Modrm|No_sSuf, { Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-div, 0xf6/6, 0, W|CheckOperandSize|Modrm|No_sSuf, { Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Acc|Byte|Word|Dword|Qword }
-idiv, 0xf6/7, 0, W|Modrm|No_sSuf, { Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-idiv, 0xf6/7, 0, W|CheckOperandSize|Modrm|No_sSuf, { Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Acc|Byte|Word|Dword|Qword }
+<mul>
+
+<div:opc, div:6, idiv:7>
+
+<div>, 0xf6/<div:opc>, 0, W|Modrm|No_sSuf, { Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
+<div>, 0xf6/<div:opc>, 0, W|CheckOperandSize|Modrm|No_sSuf, { Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Acc|Byte|Word|Dword|Qword }
+
+<div>
 
 rol, 0xd0/0, APX_F, W|Modrm|No_sSuf|CheckOperandSize|DstVVVV|EVexMap4|NF, { Imm1, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
 rol, 0xd0/0, 0, W|Modrm|No_sSuf, { Imm1, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }

[PATCH 3/7] x86: templatize binary ALU insns

[Jan Beulich]

With the multitude of new APX templates, it finally becomes desirable to
further remove redundancy by also templatizing basic arithmetic insns.
Continue with a the more complex binary (two source) cases.

Note how this adds a missing CheckOperandSize to one of the APX sub
forms.

Furthermore since SBB already had a non-NDD APX form, one ends up
being added for the other 6 mnemonics, too.

--- a/opcodes/i386-opc.tbl
+++ b/opcodes/i386-opc.tbl
@@ -308,30 +308,29 @@ std, 0xfd, 0, NoSuf, {}
 sti, 0xfb, 0, NoSuf, {}
 
 // Arithmetic.
-add, 0x0, APX_F, D|C|W|CheckOperandSize|Modrm|No_sSuf|DstVVVV|EVexMap4|NF, { Reg8|Reg16|Reg32|Reg64, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-add, 0x0, 0, D|W|CheckOperandSize|Modrm|No_sSuf|HLEPrefixLock, { Reg8|Reg16|Reg32|Reg64, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-add, 0x83/0, APX_F, Modrm|CheckOperandSize|No_bSuf|No_sSuf|DstVVVV|EVexMap4|NF, { Imm8S, Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg16|Reg32|Reg64 }
-add, 0x83/0, 0, Modrm|No_bSuf|No_sSuf|HLEPrefixLock, { Imm8S, Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-add, 0x4, 0, W|No_sSuf, { Imm8|Imm16|Imm32|Imm32S, Acc|Byte|Word|Dword|Qword }
-add, 0x80/0, APX_F, W|Modrm|CheckOperandSize|No_sSuf|DstVVVV|EVexMap4|NF, { Imm8|Imm16|Imm32|Imm32S, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64}
-add, 0x80/0, 0, W|Modrm|No_sSuf|HLEPrefixLock, { Imm8|Imm16|Imm32|Imm32S, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-
-sub, 0x28, APX_F, D|W|CheckOperandSize|Modrm|No_sSuf|DstVVVV|EVexMap4|NF|Optimize, { Reg8|Reg16|Reg32|Reg64, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64, }
-sub, 0x28, 0, D|W|CheckOperandSize|Modrm|No_sSuf|HLEPrefixLock|Optimize, { Reg8|Reg16|Reg32|Reg64, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-sub, 0x83/5, APX_F, Modrm|No_bSuf|No_sSuf|DstVVVV|EVexMap4|NF, { Imm8S, Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg16|Reg32|Reg64 }
-sub, 0x83/5, 0, Modrm|No_bSuf|No_sSuf|HLEPrefixLock, { Imm8S, Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-sub, 0x2c, 0, W|No_sSuf, { Imm8|Imm16|Imm32|Imm32S, Acc|Byte|Word|Dword|Qword }
-sub, 0x80/5, APX_F, W|Modrm|CheckOperandSize|No_sSuf|DstVVVV|EVexMap4|NF, { Imm8|Imm16|Imm32|Imm32S, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-sub, 0x80/5, 0, W|Modrm|No_sSuf|HLEPrefixLock, { Imm8|Imm16|Imm32|Imm32S, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-
-sbb, 0x18, APX_F, D|W|CheckOperandSize|Modrm|No_sSuf|DstVVVV|EVexMap4, { Reg8|Reg16|Reg32|Reg64, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-sbb, 0x18, 0, D|W|CheckOperandSize|Modrm|No_sSuf|HLEPrefixLock, { Reg8|Reg16|Reg32|Reg64, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-sbb, 0x83/3, APX_F, Modrm|CheckOperandSize|No_bSuf|No_sSuf|DstVVVV|EVexMap4, { Imm8S, Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg16|Reg32|Reg64 }
-sbb, 0x83/3, 0, Modrm|No_bSuf|No_sSuf|HLEPrefixLock, { Imm8S, Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-sbb, 0x1c, 0, W|No_sSuf, { Imm8|Imm16|Imm32|Imm32S, Acc|Byte|Word|Dword|Qword }
-sbb, 0x80/3, APX_F, W|Modrm|CheckOperandSize|No_sSuf|DstVVVV|EVexMap4, { Imm8|Imm16|Imm32|Imm32S, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-sbb, 0x80/3, 0, W|Modrm|No_sSuf|HLEPrefixLock, { Imm8|Imm16|Imm32|Imm32S, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-sbb, 0x80/3, APX_F, W|Modrm|EVexMap4|No_sSuf, { Imm8|Imm16|Imm32|Imm32S, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
+
+<alu2:opc:c:optz:optt:opti:nf, +
+    add:0:C::::NF, +
+    or:1:C::Optimize::NF, +
+    adc:2:C::::, +
+    sbb:3:::::, +
+    and:4:C::Optimize:Optimize:NF, +
+    sub:5::Optimize:::NF, +
+    xor:6:C:Optimize:::NF>
+
+<alu2>, <alu2:opc> << 3, APX_F, D|<alu2:c>|W|CheckOperandSize|Modrm|No_sSuf|DstVVVV|EVexMap4|<alu2:nf>|<alu2:optz>, { Reg8|Reg16|Reg32|Reg64, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
+<alu2>, <alu2:opc> << 3, 0, D|W|CheckOperandSize|Modrm|No_sSuf|HLEPrefixLock|<alu2:optz>|<alu2:optt>, { Reg8|Reg16|Reg32|Reg64, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
+<alu2>, 0x83/<alu2:opc>, APX_F, Modrm|CheckOperandSize|No_bSuf|No_sSuf|DstVVVV|EVexMap4|<alu2:nf>, { Imm8S, Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg16|Reg32|Reg64 }
+<alu2>, 0x83/<alu2:opc>, 0, Modrm|No_bSuf|No_sSuf|HLEPrefixLock|<alu2:opti>, { Imm8S, Reg16|Reg32|Reg64|Unspecified|BaseIndex }
+<alu2>, 0x04 | (<alu2:opc> << 3), 0, W|No_sSuf|<alu2:opti>, { Imm8|Imm16|Imm32|Imm32S, Acc|Byte|Word|Dword|Qword }
+<alu2>, 0x80/<alu2:opc>, APX_F, W|Modrm|CheckOperandSize|No_sSuf|DstVVVV|EVexMap4|<alu2:nf>, { Imm8|Imm16|Imm32|Imm32S, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
+<alu2>, 0x80/<alu2:opc>, 0, W|Modrm|No_sSuf|HLEPrefixLock|<alu2:opti>, { Imm8|Imm16|Imm32|Imm32S, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
+<alu2>, 0x80/<alu2:opc>, APX_F, W|Modrm|EVexMap4|No_sSuf, { Imm8|Imm16|Imm32|Imm32S, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
+
+<alu2>
+
+// clr with 1 operand is really xor with 2 operands.
+clr, 0x30, 0, W|Modrm|No_sSuf|RegKludge|Optimize, { Reg8|Reg16|Reg32|Reg64 }
 
 cmp, 0x38, 0, D|W|CheckOperandSize|Modrm|No_sSuf, { Reg8|Reg16|Reg32|Reg64, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
 cmp, 0x83/7, 0, Modrm|No_bSuf|No_sSuf, { Imm8S, Reg16|Reg32|Reg64|Unspecified|BaseIndex }
@@ -342,41 +341,6 @@ test, 0x84, 0, D|W|C|CheckOperandSize|Mo
 test, 0xa8, 0, W|No_sSuf|Optimize, { Imm8|Imm16|Imm32|Imm32S, Acc|Byte|Word|Dword|Qword }
 test, 0xf6/0, 0, W|Modrm|No_sSuf|Optimize, { Imm8|Imm16|Imm32|Imm32S, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
 
-and, 0x20, APX_F, D|C|W|CheckOperandSize|Modrm|No_sSuf|DstVVVV|EVexMap4|NF, { Reg8|Reg16|Reg32|Reg64, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-and, 0x20, 0, D|W|CheckOperandSize|Modrm|No_sSuf|HLEPrefixLock|Optimize, { Reg8|Reg16|Reg32|Reg64, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-and, 0x83/4, APX_F, Modrm|CheckOperandSize|No_bSuf|No_sSuf|DstVVVV|EVexMap4|NF, { Imm8S, Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg16|Reg32|Reg64 }
-and, 0x83/4, 0, Modrm|No_bSuf|No_sSuf|HLEPrefixLock|Optimize, { Imm8S, Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-and, 0x24, 0, W|No_sSuf|Optimize, { Imm8|Imm16|Imm32|Imm32S, Acc|Byte|Word|Dword|Qword }
-and, 0x80/4, APX_F, W|Modrm|CheckOperandSize|No_sSuf|DstVVVV|EVexMap4|NF, { Imm8|Imm16|Imm32|Imm32S, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-and, 0x80/4, 0, W|Modrm|No_sSuf|HLEPrefixLock|Optimize, { Imm8|Imm16|Imm32|Imm32S, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-
-or, 0x8, APX_F, D|C|W|CheckOperandSize|Modrm|No_sSuf|DstVVVV|EVexMap4|NF, { Reg8|Reg16|Reg32|Reg64, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-or, 0x8, 0, D|W|CheckOperandSize|Modrm|No_sSuf|HLEPrefixLock|Optimize, { Reg8|Reg16|Reg32|Reg64, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-or, 0x83/1, APX_F, Modrm|CheckOperandSize|No_bSuf|No_sSuf|DstVVVV|EVexMap4|NF, { Imm8S, Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg16|Reg32|Reg64 }
-or, 0x83/1, 0, Modrm|No_bSuf|No_sSuf|HLEPrefixLock, { Imm8S, Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-or, 0xc, 0, W|No_sSuf, { Imm8|Imm16|Imm32|Imm32S, Acc|Byte|Word|Dword|Qword }
-or, 0x80/1, APX_F, W|Modrm|CheckOperandSize|No_sSuf|DstVVVV|EVexMap4|NF, { Imm8|Imm16|Imm32|Imm32S, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-or, 0x80/1, 0, W|Modrm|No_sSuf|HLEPrefixLock, { Imm8|Imm16|Imm32|Imm32S, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-
-xor, 0x30, APX_F, D|C|W|CheckOperandSize|Modrm|No_sSuf|DstVVVV|EVexMap4|NF|Optimize, { Reg8|Reg16|Reg32|Reg64, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-xor, 0x30, 0, D|W|CheckOperandSize|Modrm|No_sSuf|HLEPrefixLock|Optimize, { Reg8|Reg16|Reg32|Reg64, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-xor, 0x83/6, APX_F, Modrm|CheckOperandSize|No_bSuf|No_sSuf|DstVVVV|EVexMap4|NF, { Imm8S, Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg16|Reg32|Reg64 }
-xor, 0x83/6, 0, Modrm|No_bSuf|No_sSuf|HLEPrefixLock, { Imm8S, Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-xor, 0x34, 0, W|No_sSuf, { Imm8|Imm16|Imm32|Imm32S, Acc|Byte|Word|Dword|Qword }
-xor, 0x80/6, APX_F, W|Modrm|CheckOperandSize|No_sSuf|DstVVVV|EVexMap4|NF, { Imm8|Imm16|Imm32|Imm32S, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-xor, 0x80/6, 0, W|Modrm|No_sSuf|HLEPrefixLock, { Imm8|Imm16|Imm32|Imm32S, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-
-// clr with 1 operand is really xor with 2 operands.
-clr, 0x30, 0, W|Modrm|No_sSuf|RegKludge|Optimize, { Reg8|Reg16|Reg32|Reg64 }
-
-adc, 0x10, APX_F, D|C|W|CheckOperandSize|Modrm|No_sSuf|DstVVVV|EVexMap4, { Reg8|Reg16|Reg32|Reg64, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-adc, 0x10, 0, D|W|CheckOperandSize|Modrm|No_sSuf|HLEPrefixLock, { Reg8|Reg16|Reg32|Reg64, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-adc, 0x83/2, APX_F, Modrm|CheckOperandSize|No_bSuf|No_sSuf|DstVVVV|EVexMap4, { Imm8S, Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg16|Reg32|Reg64 }
-adc, 0x83/2, 0, Modrm|No_bSuf|No_sSuf|HLEPrefixLock, { Imm8S, Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-adc, 0x14, 0, W|No_sSuf, { Imm8|Imm16|Imm32|Imm32S, Acc|Byte|Word|Dword|Qword }
-adc, 0x80/2, APX_F, W|Modrm|CheckOperandSize|No_sSuf|DstVVVV|EVexMap4, { Imm8|Imm16|Imm32|Imm32S, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-adc, 0x80/2, 0, W|Modrm|No_sSuf|HLEPrefixLock, { Imm8|Imm16|Imm32|Imm32S, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-
 <incdec:opc, inc:0, dec:1>
 
 <incdec>, 0x40 | (<incdec:opc> << 3), No64, No_bSuf|No_sSuf|No_qSuf, { Reg16|Reg32 }

[PATCH 4/7] x86: templatize shift/rotate insns

[Jan Beulich]

With the multitude of new APX templates, it finally becomes desirable to
further remove redundancy by also templatizing basic arithmetic insns.
Continue with the "ordinary" shift and rotate ones.

While there also drop the APX form with Imm1 omitted. Other shift insns
as well as ROR/ROL were deliberately left without this form as well. Note
that there's also no testsuite adjustment needed for this, indicating
that the form wasn't tested either.

Furthermore since RCL/RCR already had non-NDD APX forms, those end up
being added for the other 6 mnemonics, too.
---
Seeing the resulting block here in particular, what would people think
of (partially) tabulating this (and then perhaps also others):

<sr>, 0xd0/<sr:opc>, APX_F, W|Modrm|No_sSuf|CheckOperandSize|DstVVVV|EVexMap4|<sr:nf>, { Imm1, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
<sr>, 0xd0/<sr:opc>,     0, W|Modrm|No_sSuf,                                           { Imm1, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
<sr>, 0xd0/<sr:opc>, APX_F, W|Modrm|No_sSuf|EVexMap4|<sr:nf>,                          { Imm1, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
<sr>, 0xc0/<sr:opc>, APX_F, W|Modrm|No_sSuf|CheckOperandSize|DstVVVV|EVexMap4|<sr:nf>, { <sr:imm8>, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
<sr>, 0xc0/<sr:opc>,  i186, W|Modrm|No_sSuf,                                           { <sr:imm8>, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
<sr>, 0xc0/<sr:opc>, APX_F, W|Modrm|No_sSuf|EVexMap4|<sr:nf>,                          { <sr:imm8>, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
<sr>, 0xd2/<sr:opc>, APX_F, W|Modrm|No_sSuf|CheckOperandSize|DstVVVV|EVexMap4|<sr:nf>, { ShiftCount, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
<sr>, 0xd2/<sr:opc>,     0, W|Modrm|No_sSuf,                                           { ShiftCount, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
<sr>, 0xd2/<sr:opc>, APX_F, W|Modrm|No_sSuf|EVexMap4|<sr:nf>,                          { ShiftCount, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
<sr>, 0xd0/<sr:opc>,     0, W|Modrm|No_sSuf,                                           { Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }

That'll be longer lines, yes, but it is quite a bit easier to see
similarities as well as differences.

--- a/opcodes/i386-opc.tbl
+++ b/opcodes/i386-opc.tbl
@@ -407,77 +407,28 @@ imul, 0x69, i186, Modrm|No_bSuf|No_sSuf|
 
 <div>
 
-rol, 0xd0/0, APX_F, W|Modrm|No_sSuf|CheckOperandSize|DstVVVV|EVexMap4|NF, { Imm1, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-rol, 0xd0/0, 0, W|Modrm|No_sSuf, { Imm1, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-rol, 0xc0/0, APX_F, W|Modrm|No_sSuf|CheckOperandSize|DstVVVV|EVexMap4|NF, { Imm8|Imm8S, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-rol, 0xc0/0, i186, W|Modrm|No_sSuf, { Imm8|Imm8S, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-rol, 0xd2/0, APX_F, W|Modrm|No_sSuf|CheckOperandSize|DstVVVV|EVexMap4|NF, { ShiftCount, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-rol, 0xd2/0, 0, W|Modrm|No_sSuf, { ShiftCount, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-rol, 0xd0/0, 0, W|Modrm|No_sSuf, { Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
+<sr:opc:imm8:nf, +
+    rol:0:Imm8|Imm8S:NF, +
+    ror:1:Imm8|Imm8S:NF, +
+    rcl:2:Imm8:, +
+    rcr:3:Imm8:, +
+    sal:4:Imm8:NF, +
+    shl:4:Imm8:NF, +
+    shr:5:Imm8:NF, +
+    sar:7:Imm8:NF>
+
+<sr>, 0xd0/<sr:opc>, APX_F, W|Modrm|No_sSuf|CheckOperandSize|DstVVVV|EVexMap4|<sr:nf>, { Imm1, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
+<sr>, 0xd0/<sr:opc>, 0, W|Modrm|No_sSuf, { Imm1, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
+<sr>, 0xd0/<sr:opc>, APX_F, W|Modrm|No_sSuf|EVexMap4|<sr:nf>, { Imm1, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
+<sr>, 0xc0/<sr:opc>, APX_F, W|Modrm|No_sSuf|CheckOperandSize|DstVVVV|EVexMap4|<sr:nf>, { <sr:imm8>, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
+<sr>, 0xc0/<sr:opc>, i186, W|Modrm|No_sSuf, { <sr:imm8>, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
+<sr>, 0xc0/<sr:opc>, APX_F, W|Modrm|No_sSuf|EVexMap4|<sr:nf>, { <sr:imm8>, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
+<sr>, 0xd2/<sr:opc>, APX_F, W|Modrm|No_sSuf|CheckOperandSize|DstVVVV|EVexMap4|<sr:nf>, { ShiftCount, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
+<sr>, 0xd2/<sr:opc>, 0, W|Modrm|No_sSuf, { ShiftCount, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
+<sr>, 0xd2/<sr:opc>, APX_F, W|Modrm|No_sSuf|EVexMap4|<sr:nf>, { ShiftCount, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
+<sr>, 0xd0/<sr:opc>, 0, W|Modrm|No_sSuf, { Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
 
-ror, 0xd0/1, APX_F, W|Modrm|No_sSuf|CheckOperandSize|DstVVVV|EVexMap4|NF, { Imm1, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-ror, 0xd0/1, 0, W|Modrm|No_sSuf, { Imm1, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-ror, 0xc0/1, APX_F, W|Modrm|No_sSuf|CheckOperandSize|DstVVVV|EVexMap4|NF, { Imm8|Imm8S, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-ror, 0xc0/1, i186, W|Modrm|No_sSuf, { Imm8|Imm8S, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-ror, 0xd2/1, APX_F, W|Modrm|No_sSuf|CheckOperandSize|DstVVVV|EVexMap4|NF, { ShiftCount, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-ror, 0xd2/1, 0, W|Modrm|No_sSuf, { ShiftCount, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-ror, 0xd0/1, 0, W|Modrm|No_sSuf, { Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-
-rcl, 0xd0/2, APX_F, W|Modrm|No_sSuf|CheckOperandSize|DstVVVV|EVexMap4, { Imm1, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-rcl, 0xd0/2, 0, W|Modrm|No_sSuf, { Imm1, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-rcl, 0xd0/2, APX_F, W|Modrm|No_sSuf|EVexMap4, { Imm1, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-rcl, 0xc0/2, APX_F, W|Modrm|No_sSuf|CheckOperandSize|DstVVVV|EVexMap4, { Imm8, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-rcl, 0xc0/2, i186, W|Modrm|No_sSuf, { Imm8, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-rcl, 0xc0/2, APX_F, W|Modrm|No_sSuf|EVexMap4, { Imm8, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-rcl, 0xd2/2, APX_F, W|Modrm|No_sSuf|CheckOperandSize|DstVVVV|EVexMap4, { ShiftCount, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-rcl, 0xd2/2, 0, W|Modrm|No_sSuf, { ShiftCount, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-rcl, 0xd2/2, APX_F, W|Modrm|No_sSuf|EVexMap4, { ShiftCount, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-rcl, 0xd0/2, 0, W|Modrm|No_sSuf, { Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-rcl, 0xd0/2, APX_F, W|Modrm|No_sSuf|EVexMap4, { Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-
-rcr, 0xd0/3, APX_F, W|Modrm|No_sSuf|CheckOperandSize|DstVVVV|EVexMap4, { Imm1, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-rcr, 0xd0/3, 0, W|Modrm|No_sSuf, { Imm1, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-rcr, 0xd0/3, APX_F, W|Modrm|No_sSuf|EVexMap4, { Imm1, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-rcr, 0xc0/3, APX_F, W|Modrm|No_sSuf|CheckOperandSize|DstVVVV|EVexMap4, { Imm8, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-rcr, 0xc0/3, i186, W|Modrm|No_sSuf, { Imm8, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-rcr, 0xc0/3, APX_F, W|Modrm|No_sSuf|EVexMap4, { Imm8, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-rcr, 0xd2/3, APX_F, W|Modrm|No_sSuf|CheckOperandSize|DstVVVV|EVexMap4, { ShiftCount, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-rcr, 0xd2/3, 0, W|Modrm|No_sSuf, { ShiftCount, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-rcr, 0xd2/3, APX_F, W|Modrm|No_sSuf|EVexMap4, { ShiftCount, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-rcr, 0xd0/3, 0, W|Modrm|No_sSuf, { Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-rcr, 0xd0/3, APX_F, W|Modrm|No_sSuf|EVexMap4, { Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-
-sal, 0xd0/4, APX_F, W|Modrm|No_sSuf|CheckOperandSize|DstVVVV|EVexMap4|NF, { Imm1, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-sal, 0xd0/4, 0, W|Modrm|No_sSuf, { Imm1, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-sal, 0xc0/4, APX_F, W|Modrm|No_sSuf|CheckOperandSize|DstVVVV|EVexMap4|NF, { Imm8, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-sal, 0xc0/4, i186, W|Modrm|No_sSuf, { Imm8, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-sal, 0xd2/4, APX_F, W|Modrm|No_sSuf|CheckOperandSize|DstVVVV|EVexMap4|NF, { ShiftCount, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-sal, 0xd2/4, 0, W|Modrm|No_sSuf, { ShiftCount, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-sal, 0xd0/4, 0, W|Modrm|No_sSuf, { Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-
-shl, 0xd0/4, APX_F, W|Modrm|No_sSuf|CheckOperandSize|DstVVVV|EVexMap4|NF, { Imm1, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-shl, 0xd0/4, 0, W|Modrm|No_sSuf, { Imm1, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-shl, 0xc0/4, APX_F, W|Modrm|No_sSuf|CheckOperandSize|DstVVVV|EVexMap4|NF, { Imm8, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-shl, 0xc0/4, i186, W|Modrm|No_sSuf, { Imm8, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-shl, 0xd2/4, APX_F, W|Modrm|No_sSuf|CheckOperandSize|DstVVVV|EVexMap4|NF, { ShiftCount, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-shl, 0xd2/4, 0, W|Modrm|No_sSuf, { ShiftCount, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-shl, 0xd0/4, 0, W|Modrm|No_sSuf, { Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-
-shr, 0xd0/5, APX_F, W|Modrm|No_sSuf|CheckOperandSize|DstVVVV|EVexMap4|NF, { Imm1, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-shr, 0xd0/5, 0, W|Modrm|No_sSuf, { Imm1, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-shr, 0xc0/5, APX_F, W|Modrm|No_sSuf|CheckOperandSize|DstVVVV|EVexMap4|NF, { Imm8, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-shr, 0xc0/5, i186, W|Modrm|No_sSuf, { Imm8, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-shr, 0xd2/5, APX_F, W|Modrm|No_sSuf|CheckOperandSize|DstVVVV|EVexMap4|NF, { ShiftCount, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-shr, 0xd2/5, 0, W|Modrm|No_sSuf, { ShiftCount, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-shr, 0xd0/5, 0, W|Modrm|No_sSuf, { Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-
-sar, 0xd0/7, APX_F, W|Modrm|No_sSuf|CheckOperandSize|DstVVVV|EVexMap4|NF, { Imm1, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-sar, 0xd0/7, 0, W|Modrm|No_sSuf, { Imm1, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-sar, 0xc0/7, APX_F, W|Modrm|No_sSuf|CheckOperandSize|DstVVVV|EVexMap4|NF, { Imm8, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-sar, 0xc0/7, i186, W|Modrm|No_sSuf, { Imm8, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-sar, 0xd2/7, APX_F, W|Modrm|No_sSuf|CheckOperandSize|DstVVVV|EVexMap4|NF, { ShiftCount, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
-sar, 0xd2/7, 0, W|Modrm|No_sSuf, { ShiftCount, Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-sar, 0xd0/7, 0, W|Modrm|No_sSuf, { Reg8|Reg16|Reg32|Reg64|Unspecified|BaseIndex }
+<sr>
 
 shld, 0x24, APX_F, Modrm|CheckOperandSize|No_bSuf|No_sSuf|DstVVVV|EVexMap4|NF, { Imm8, Reg16|Reg32|Reg64, Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg16|Reg32|Reg64 }
 shld, 0xfa4, i386, Modrm|CheckOperandSize|No_bSuf|No_sSuf, { Imm8, Reg16|Reg32|Reg64, Reg16|Reg32|Reg64|Unspecified|BaseIndex }

[PATCH 5/7] x86: templatize shift-double insns

[Jan Beulich]

With the multitude of new APX templates, it finally becomes desirable to
further remove redundancy by also templatizing basic arithmetic insns.
Continue with the shift-double ones.

While there also drop the APX form with ShiftCount omitted. Other shift
and rotate insns were deliberately left without this form as well. Note
that there's also no testsuite adjustment needed for this, indicating
that the form wasn't tested either.

--- a/opcodes/i386-opc.tbl
+++ b/opcodes/i386-opc.tbl
@@ -430,19 +430,15 @@ imul, 0x69, i186, Modrm|No_bSuf|No_sSuf|
 
 <sr>
 
-shld, 0x24, APX_F, Modrm|CheckOperandSize|No_bSuf|No_sSuf|DstVVVV|EVexMap4|NF, { Imm8, Reg16|Reg32|Reg64, Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg16|Reg32|Reg64 }
-shld, 0xfa4, i386, Modrm|CheckOperandSize|No_bSuf|No_sSuf, { Imm8, Reg16|Reg32|Reg64, Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-shld, 0xa5, APX_F, Modrm|CheckOperandSize|No_bSuf|No_sSuf|DstVVVV|EVexMap4|NF, { ShiftCount, Reg16|Reg32|Reg64, Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg16|Reg32|Reg64 }
-shld, 0xfa5, i386, Modrm|CheckOperandSize|No_bSuf|No_sSuf, { ShiftCount, Reg16|Reg32|Reg64, Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-shld, 0xa5, APX_F, Modrm|CheckOperandSize|No_bSuf|No_sSuf|DstVVVV|EVexMap4|NF, { Reg16|Reg32|Reg64, Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg16|Reg32|Reg64 }
-shld, 0xfa5, i386, Modrm|CheckOperandSize|No_bSuf|No_sSuf, { Reg16|Reg32|Reg64, Reg16|Reg32|Reg64|Unspecified|BaseIndex }
+<shd:opc, l:0, r:8>
 
-shrd, 0x2c, APX_F, Modrm|CheckOperandSize|No_bSuf|No_sSuf|DstVVVV|EVexMap4|NF, { Imm8, Reg16|Reg32|Reg64, Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg16|Reg32|Reg64 }
-shrd, 0xfac, i386, Modrm|CheckOperandSize|No_bSuf|No_sSuf, { Imm8, Reg16|Reg32|Reg64, Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-shrd, 0xad, APX_F, Modrm|CheckOperandSize|No_bSuf|No_sSuf|DstVVVV|EVexMap4|NF, { ShiftCount, Reg16|Reg32|Reg64, Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg16|Reg32|Reg64 }
-shrd, 0xfad, i386, Modrm|CheckOperandSize|No_bSuf|No_sSuf, { ShiftCount, Reg16|Reg32|Reg64, Reg16|Reg32|Reg64|Unspecified|BaseIndex }
-shrd, 0xad, APX_F, Modrm|CheckOperandSize|No_bSuf|No_sSuf|DstVVVV|EVexMap4|NF, { Reg16|Reg32|Reg64, Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg16|Reg32|Reg64 }
-shrd, 0xfad, i386, Modrm|CheckOperandSize|No_bSuf|No_sSuf, { Reg16|Reg32|Reg64, Reg16|Reg32|Reg64|Unspecified|BaseIndex }
+sh<shd>d, 0x24 | <shd:opc>, APX_F, Modrm|CheckOperandSize|No_bSuf|No_sSuf|DstVVVV|EVexMap4|NF, { Imm8, Reg16|Reg32|Reg64, Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg16|Reg32|Reg64 }
+sh<shd>d, 0x0fa4 | <shd:opc>, i386, Modrm|CheckOperandSize|No_bSuf|No_sSuf, { Imm8, Reg16|Reg32|Reg64, Reg16|Reg32|Reg64|Unspecified|BaseIndex }
+sh<shd>d, 0xa5 | <shd:opc>, APX_F, Modrm|CheckOperandSize|No_bSuf|No_sSuf|DstVVVV|EVexMap4|NF, { ShiftCount, Reg16|Reg32|Reg64, Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg16|Reg32|Reg64 }
+sh<shd>d, 0x0fa5 | <shd:opc>, i386, Modrm|CheckOperandSize|No_bSuf|No_sSuf, { ShiftCount, Reg16|Reg32|Reg64, Reg16|Reg32|Reg64|Unspecified|BaseIndex }
+sh<shd>d, 0x0fa5 | <shd:opc>, i386, Modrm|CheckOperandSize|No_bSuf|No_sSuf, { Reg16|Reg32|Reg64, Reg16|Reg32|Reg64|Unspecified|BaseIndex }
+
+<shd>
 
 // Control transfer instructions.
 call, 0xe8, No64, JumpDword|ImplicitStackOp|DefaultSize|No_bSuf|No_sSuf|No_qSuf|BNDPrefixOk, { Disp16|Disp32 }

[PATCH 6/7] x86: templatize ADX insns

[Jan Beulich]

It's only two of them, but still better to reduce redundancy.

--- a/opcodes/i386-opc.tbl
+++ b/opcodes/i386-opc.tbl
@@ -2046,12 +2046,11 @@ xcryptofb, 0xf30fa7e8, PadLock, NoSuf|Re
 xstore, 0xfa7c0, PadLock, NoSuf|RepPrefixOk, {}
 
 // Multy-precision Add Carry, rdseed instructions.
-adcx, 0x6666, ADX&APX_F, C|Modrm|CheckOperandSize|No_bSuf|No_wSuf|No_sSuf|DstVVVV|EVexMap4, { Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64, Reg32|Reg64 }
-adcx, 0x660f38f6, ADX, Modrm|CheckOperandSize|IgnoreSize|No_bSuf|No_wSuf|No_sSuf, { Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64 }
-adcx, 0x6666, ADX&APX_F, Modrm|CheckOperandSize|No_bSuf|No_wSuf|No_sSuf|EVexMap4, { Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64 }
-adox, 0xf366, ADX&APX_F, C|Modrm|CheckOperandSize|No_bSuf|No_wSuf|No_sSuf|DstVVVV|EVexMap4, { Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64, Reg32|Reg64 }
-adox, 0xf30f38f6, ADX, Modrm|CheckOperandSize|IgnoreSize|No_bSuf|No_wSuf|No_sSuf, { Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64 }
-adox, 0xf366, ADX&APX_F, Modrm|CheckOperandSize|No_bSuf|No_wSuf|No_sSuf|EVexMap4, { Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64 }
+<adx:pfx, c:66, o:f3>
+ad<adx>x, 0x<adx:pfx>66, ADX&APX_F, C|Modrm|CheckOperandSize|No_bSuf|No_wSuf|No_sSuf|DstVVVV|EVexMap4, { Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64, Reg32|Reg64 }
+ad<adx>x, 0x<adx:pfx>0f38f6, ADX, Modrm|CheckOperandSize|IgnoreSize|No_bSuf|No_wSuf|No_sSuf, { Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64 }
+ad<adx>x, 0x<adx:pfx>66, ADX&APX_F, Modrm|CheckOperandSize|No_bSuf|No_wSuf|No_sSuf|EVexMap4, { Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64 }
+<adx>
 rdseed, 0xfc7/7, RdSeed, Modrm|NoSuf, { Reg16|Reg32|Reg64 }
 
 // SMAP instructions.

[PATCH 7/7] x86: templatize RAO-INT insns

[Jan Beulich]

It's only four of them, but still better to reduce redundancy.

--- a/opcodes/i386-opc.tbl
+++ b/opcodes/i386-opc.tbl
@@ -3388,14 +3388,10 @@ wrmsrlist, 0xf30f01c6, MSRLIST, NoSuf, {
 
 // RAO-INT instructions.
 
-aadd, 0xf38fc, RAO_INT, Modrm|IgnoreSize|CheckOperandSize|NoSuf, { Reg32|Reg64, Dword|Qword|Unspecified|BaseIndex }
-aadd, 0xfc, RAO_INT&APX_F, Modrm|CheckOperandSize|NoSuf|EVexMap4, { Reg32|Reg64, Dword|Qword|Unspecified|BaseIndex }
-aand, 0x660f38fc, RAO_INT, Modrm|IgnoreSize|CheckOperandSize|NoSuf, { Reg32|Reg64, Dword|Qword|Unspecified|BaseIndex }
-aand, 0x66fc, RAO_INT&APX_F, Modrm|CheckOperandSize|NoSuf|EVexMap4, { Reg32|Reg64, Dword|Qword|Unspecified|BaseIndex }
-aor, 0xf20f38fc, RAO_INT, Modrm|IgnoreSize|CheckOperandSize|NoSuf, { Reg32|Reg64, Dword|Qword|Unspecified|BaseIndex }
-aor, 0xf2fc, RAO_INT&APX_F, Modrm|CheckOperandSize|NoSuf|EVexMap4, { Reg32|Reg64, Dword|Qword|Unspecified|BaseIndex }
-axor, 0xf30f38fc, RAO_INT, Modrm|IgnoreSize|CheckOperandSize|NoSuf, { Reg32|Reg64, Dword|Qword|Unspecified|BaseIndex }
-axor, 0xf3fc, RAO_INT&APX_F, Modrm|CheckOperandSize|NoSuf|EVexMap4, { Reg32|Reg64, Dword|Qword|Unspecified|BaseIndex }
+<rao:pfx, add:, and:66, or:f2, xor:f3>
+a<rao>, 0x<rao:pfx>0f38fc, RAO_INT, Modrm|IgnoreSize|CheckOperandSize|NoSuf, { Reg32|Reg64, Dword|Qword|Unspecified|BaseIndex }
+a<rao>, 0x<rao:pfx>fc, RAO_INT&APX_F, Modrm|CheckOperandSize|NoSuf|EVexMap4, { Reg32|Reg64, Dword|Qword|Unspecified|BaseIndex }
+<rao>
 
 // RAO-INT instructions end.
 

RE: [PATCH 0/7] x86: templatize various ALU insn templates

[Cui, Lili]

> With the multitude of new APX templates, it finally becomes desirable to
> further remove redundancy by also templatizing basic arithmetic insns.
> 
> Unlike indicated previously, I think at least part of this would better go ahead of
> the APX NF patch. This is because some of what needs adding explicitly there is
> being added implicitly here (patches 3 and 4 at least), in order to avoid losing
> templates we already had (prematurely added by the APX NDD patch, imo).
> 
> Note that patches 4 and 5 also drop certain templates again which imo were
> added by mistake in the course of the NDD work. See the descriptions of those
> patches.
> 
> 1: templatize INC/DEC
> 2: templatize unary ALU insns
> 3: templatize binary ALU insns
> 4: templatize shift/rotate insns
> 5: templatize shift-double insns
> 6: templatize ADX insns
> 7: templatize RAO-INT insns
> 

Thanks for the cleanup, I reviewed the patches, and they are ok for me, I will rebase the NF patch after you submit them.

Lili.