x86: support AVX10.1 vector size restrictions

Recognize "/<number>" suffixes on both -march=+avx10.1 and the
corresponding .arch directive, setting an upper bound on the vector size
that insns may use. Such a restriction can be reset by setting a new base
architecture, by using a suffix-less form, by disabling AVX10, or by
enabling any other VEX/EVEX-based vector extension.

While for most insns we can suppress their use with too wide operands
via registers becoming unavailable (or in Intel syntax memory operand
size specifiers not being recognized), mask register insns have to have
their minimum required vector size specified in a new attribute. (Of
course this new attribute could also be used on other insns.)

Note that .insn continues to be permitted to emit EVEX{512,256} (and
VEX256 ones) encodings regardless of vector size restrictions in place.
Of course these can't be expressed using zmm (or ymm) operands then,
but need using the EVEX.512.* forms (broadcast forms may be usable right
now, but this may go away so shouldn't be relied upon). This is why no
assertions should be added to build_{e,}vex_prefix().

1 files changed, 22 insertions, 19 deletions

diff --git a/opcodes/i386-opc.tbl b/opcodes/i386-opc.tbl
index 0381523..49d35ee 100644
--- a/opcodes/i386-opc.tbl
+++ b/opcodes/i386-opc.tbl
@@ -131,6 +131,9 @@
 #define EVexLIG EVex=EVEXLIG
 #define EVexDYN EVex=EVEXDYN
 
+#define Vsz256 Vsz=VSZ256
+#define Vsz512 Vsz=VSZ512
+
 // The EVEX purpose of StaticRounding appears only together with SAE. Re-use
 // the bit to mark commutative VEX encodings where swapping the source
 // operands may allow to switch from 3-byte to 2-byte VEX encoding.
@@ -987,9 +990,9 @@ pause, 0xf390, i186, NoSuf, {}
     b:0:VexW0:Byte:AVX512DQ:66:AVX512VBMI, +
     w:1:VexW1:Word:AVX512F::AVX512BW>
 
-<dq:opc:vexw:vexw64:elem:cpu64:gpr:kpfx, +
-    d:0:VexW0::Dword::Reg32:66, +
-    q:1:VexW1:VexW1:Qword:x64:Reg64:>
+<dq:opc:vexw:vexw64:elem:cpu64:gpr:kpfx:kvsz, +
+    d:0:VexW0::Dword::Reg32:66:Vsz256, +
+    q:1:VexW1:VexW1:Qword:x64:Reg64::Vsz512>
 
 emms, 0xf77, MMX, NoSuf, {}
 // These really shouldn't allow for Reg64 (movq is the right mnemonic for
@@ -2619,22 +2622,22 @@ vpmovzxwq, 0x6634, AVX512F|AVX512VL, Modrm|EVex=3|Masking|Space0F38|VexWIG|Disp8
 
 // AVX512BW instructions.
 
-kadd<dq>, 0x<dq:kpfx>4a, AVX512BW, Modrm|Vex256|Space0F|VexVVVV|VexW1|NoSuf, { RegMask, RegMask, RegMask }
-kand<dq>, 0x<dq:kpfx>41, AVX512BW, Modrm|Vex256|Space0F|VexVVVV|VexW1|NoSuf, { RegMask, RegMask, RegMask }
-kandn<dq>, 0x<dq:kpfx>42, AVX512BW, Modrm|Vex256|Space0F|VexVVVV|VexW1|NoSuf|Optimize, { RegMask, RegMask, RegMask }
-kmov<dq>, 0x<dq:kpfx>90, AVX512BW, Modrm|Vex128|Space0F|VexW1|NoSuf, { RegMask|<dq:elem>|Unspecified|BaseIndex, RegMask }
-kmov<dq>, 0x<dq:kpfx>91, AVX512BW, Modrm|Vex128|Space0F|VexW1|NoSuf, { RegMask, <dq:elem>|Unspecified|BaseIndex }
-kmov<dq>, 0xf292, AVX512BW, D|Modrm|Vex128|Space0F|<dq:vexw64>|NoSuf, { <dq:gpr>, RegMask }
-knot<dq>, 0x<dq:kpfx>44, AVX512BW, Modrm|Vex128|Space0F|VexW1|NoSuf, { RegMask, RegMask }
-kor<dq>, 0x<dq:kpfx>45, AVX512BW, Modrm|Vex256|Space0F|VexVVVV|VexW1|NoSuf, { RegMask, RegMask, RegMask }
-kortest<dq>, 0x<dq:kpfx>98, AVX512BW, Modrm|Vex128|Space0F|VexW1|NoSuf, { RegMask, RegMask }
-ktest<dq>, 0x<dq:kpfx>99, AVX512BW, Modrm|Vex128|Space0F|VexW1|NoSuf, { RegMask, RegMask }
-kxnor<dq>, 0x<dq:kpfx>46, AVX512BW, Modrm|Vex256|Space0F|VexVVVV|VexW1|NoSuf, { RegMask, RegMask, RegMask }
-kxor<dq>, 0x<dq:kpfx>47, AVX512BW, Modrm|Vex256|Space0F|VexVVVV|VexW1|NoSuf|Optimize, { RegMask, RegMask, RegMask }
-kunpckdq, 0x4B, AVX512BW, Modrm|Vex256|Space0F|VexVVVV|VexW1|NoSuf, { RegMask, RegMask, RegMask }
-kunpckwd, 0x4B, AVX512BW, Modrm|Vex256|Space0F|VexVVVV|VexW0|NoSuf, { RegMask, RegMask, RegMask }
-kshiftl<dq>, 0x6633, AVX512BW, Modrm|Vex128|Space0F3A|<dq:vexw>|NoSuf, { Imm8, RegMask, RegMask }
-kshiftr<dq>, 0x6631, AVX512BW, Modrm|Vex128|Space0F3A|<dq:vexw>|NoSuf, { Imm8, RegMask, RegMask }
+kadd<dq>, 0x<dq:kpfx>4a, AVX512BW, Modrm|Vex256|Space0F|VexVVVV|VexW1|<dq:kvsz>|NoSuf, { RegMask, RegMask, RegMask }
+kand<dq>, 0x<dq:kpfx>41, AVX512BW, Modrm|Vex256|Space0F|VexVVVV|VexW1|<dq:kvsz>|NoSuf, { RegMask, RegMask, RegMask }
+kandn<dq>, 0x<dq:kpfx>42, AVX512BW, Modrm|Vex256|Space0F|VexVVVV|VexW1|<dq:kvsz>|NoSuf|Optimize, { RegMask, RegMask, RegMask }
+kmov<dq>, 0x<dq:kpfx>90, AVX512BW, Modrm|Vex128|Space0F|VexW1|<dq:kvsz>|NoSuf, { RegMask|<dq:elem>|Unspecified|BaseIndex, RegMask }
+kmov<dq>, 0x<dq:kpfx>91, AVX512BW, Modrm|Vex128|Space0F|VexW1|<dq:kvsz>|NoSuf, { RegMask, <dq:elem>|Unspecified|BaseIndex }
+kmov<dq>, 0xf292, AVX512BW, D|Modrm|Vex128|Space0F|<dq:vexw64>|<dq:kvsz>|NoSuf, { <dq:gpr>, RegMask }
+knot<dq>, 0x<dq:kpfx>44, AVX512BW, Modrm|Vex128|Space0F|VexW1|<dq:kvsz>|NoSuf, { RegMask, RegMask }
+kor<dq>, 0x<dq:kpfx>45, AVX512BW, Modrm|Vex256|Space0F|VexVVVV|VexW1|<dq:kvsz>|NoSuf, { RegMask, RegMask, RegMask }
+kortest<dq>, 0x<dq:kpfx>98, AVX512BW, Modrm|Vex128|Space0F|VexW1|<dq:kvsz>|NoSuf, { RegMask, RegMask }
+ktest<dq>, 0x<dq:kpfx>99, AVX512BW, Modrm|Vex128|Space0F|VexW1|<dq:kvsz>|NoSuf, { RegMask, RegMask }
+kxnor<dq>, 0x<dq:kpfx>46, AVX512BW, Modrm|Vex256|Space0F|VexVVVV|VexW1|<dq:kvsz>|NoSuf, { RegMask, RegMask, RegMask }
+kxor<dq>, 0x<dq:kpfx>47, AVX512BW, Modrm|Vex256|Space0F|VexVVVV|VexW1|<dq:kvsz>|NoSuf|Optimize, { RegMask, RegMask, RegMask }
+kunpckdq, 0x4B, AVX512BW, Modrm|Vex256|Space0F|VexVVVV|VexW1|Vsz512|NoSuf, { RegMask, RegMask, RegMask }
+kunpckwd, 0x4B, AVX512BW, Modrm|Vex256|Space0F|VexVVVV|VexW0|Vsz256|NoSuf, { RegMask, RegMask, RegMask }
+kshiftl<dq>, 0x6633, AVX512BW, Modrm|Vex128|Space0F3A|<dq:vexw>|<dq:kvsz>|NoSuf, { Imm8, RegMask, RegMask }
+kshiftr<dq>, 0x6631, AVX512BW, Modrm|Vex128|Space0F3A|<dq:vexw>|<dq:kvsz>|NoSuf, { Imm8, RegMask, RegMask }
 
 vdbpsadbw, 0x6642, AVX512BW, Modrm|Masking|Space0F3A|VexVVVV|VexW0|Disp8ShiftVL|CheckOperandSize|NoSuf, { Imm8|Imm8S, RegXMM|RegYMM|RegZMM|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }