diff mbox series

[RFC,3/4] x86: fold FMA VEX and EVEX templates

Message ID 737ed0bc-7dc2-19e6-5138-8891f0c2fd15@suse.com
State New
Headers
Series x86: fold a number of VEX and EVEX templates |

Checks

Context Check Description
linaro-tcwg-bot/tcwg_binutils_check--master-arm success Testing passed
linaro-tcwg-bot/tcwg_binutils_build--master-aarch64 success Testing passed
linaro-tcwg-bot/tcwg_binutils_build--master-arm success Testing passed
linaro-tcwg-bot/tcwg_binutils_check--master-aarch64 success Testing passed

Commit Message

Jan Beulich Sept. 15, 2023, 8:48 a.m. UTC 
  Following the folding of some generic AVX/AVX2 templates with their
AVX512F counterpart ones, do this for FMA ones as well, requiring one
further adjustment to cpu_flags_match(). Note that this has a perhaps
unexpected effect, resulting from FMA not being listed as a prereq of
AVX512F: With just the latter enabled, VEX-encodings can now be
emitted (but still not 128- or 256-bit EVEX-encodings, where AVX512VL
of course continues to be required).
---
RFC: Considering earlier discussion, the mentioned side effect likely
     means we don't really want this change, despite the significant
     reduction of the number of templates.
diff mbox series

Patch

--- a/gas/config/tc-i386.c
+++ b/gas/config/tc-i386.c
@@ -1947,6 +1947,8 @@  cpu_flags_match (const insn_template *t)
 	      if ((need_evex_encoding ()
 		   ? cpu.bitfield.cpuavx512f
 		   : cpu.bitfield.cpuavx)
+		  && (!x.bitfield.cpufma || cpu.bitfield.cpufma
+		      || cpu_arch_flags.bitfield.cpuavx512f)
 		  && (!x.bitfield.cpugfni || cpu.bitfield.cpugfni)
 		  && (!x.bitfield.cpuvaes || cpu.bitfield.cpuvaes)
 		  && (!x.bitfield.cpuvpclmulqdq || cpu.bitfield.cpuvpclmulqdq))
--- a/opcodes/i386-opc.tbl
+++ b/opcodes/i386-opc.tbl
@@ -1802,16 +1802,21 @@  vcvtps2ph, 0x661d, F16C, Modrm|Vex=2|Spa
 
 <fma:opc, 132:10, 213:20, 231:30>
 
-vfmadd<fma>p<sd>, 0x6688 | 0x<fma:opc>, FMA, Modrm|Vex|Space0F38|VexVVVV|<sd:vexw>|CheckOperandSize|NoSuf, { Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
-vfmadd<fma>s<sd>, 0x6689 | 0x<fma:opc>, FMA, Modrm|VexLIG|Space0F38|VexVVVV|<sd:vexw>|NoSuf, { <sd:elem>|Unspecified|BaseIndex|RegXMM, RegXMM, RegXMM }
-vfmaddsub<fma>p<sd>, 0x6686 | 0x<fma:opc>, FMA, Modrm|Vex|Space0F38|VexVVVV|<sd:vexw>|CheckOperandSize|NoSuf, { Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
-vfmsub<fma>p<sd>, 0x668a | 0x<fma:opc>, FMA, Modrm|Vex|Space0F38|VexVVVV|<sd:vexw>|CheckOperandSize|NoSuf, { Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
-vfmsub<fma>s<sd>, 0x668b | 0x<fma:opc>, FMA, Modrm|VexLIG|Space0F38|VexVVVV|<sd:vexw>|NoSuf, { <sd:elem>|Unspecified|BaseIndex|RegXMM, RegXMM, RegXMM }
-vfmsubadd<fma>p<sd>, 0x6687 | 0x<fma:opc>, FMA, Modrm|Vex|Space0F38|VexVVVV|<sd:vexw>|CheckOperandSize|NoSuf, { Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
-vfnmadd<fma>p<sd>, 0x668c | 0x<fma:opc>, FMA, Modrm|Vex|Space0F38|VexVVVV|<sd:vexw>|CheckOperandSize|NoSuf, { Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
-vfnmadd<fma>s<sd>, 0x668d | 0x<fma:opc>, FMA, Modrm|VexLIG|Space0F38|VexVVVV|<sd:vexw>|NoSuf, { <sd:elem>|Unspecified|BaseIndex|RegXMM, RegXMM, RegXMM }
-vfnmsub<fma>p<sd>, 0x668e | 0x<fma:opc>, FMA, Modrm|Vex|Space0F38|VexVVVV|<sd:vexw>|CheckOperandSize|NoSuf, { Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
-vfnmsub<fma>s<sd>, 0x668f | 0x<fma:opc>, FMA, Modrm|VexLIG|Space0F38|VexVVVV|<sd:vexw>|NoSuf, { <sd:elem>|Unspecified|BaseIndex|RegXMM, RegXMM, RegXMM }
+<sdh:cpu:cpudq:fma:ppfx:spfx:pfx:spc1:spc2:opc:vex:vexlig:vexw:elem, +
+    s:AVX512F:AVX512DQ:FMA|AVX|AVX512F::f3:66:Space0F:Space0F38:0:Vex|EVexDYN:VexLIG|EVexLIG:VexW0:Dword, +
+    d:AVX512F:AVX512DQ:FMA|AVX|AVX512F:66:f2:66:Space0F:Space0F38:1:Vex|EVexDYN:VexLIG|EVexLIG:VexW1:Qword, +
+    h:AVX512_FP16:AVX512_FP16:AVX512_FP16::f3::EVexMap5:EVexMap6:0::EVexLIG:VexW0:Word>
+
+vfmadd<fma>p<sdh>, 0x6688 | 0x<fma:opc>, <sdh:fma>, Modrm|<sdh:vex>|Masking|<sdh:spc2>|VexVVVV|<sdh:vexw>|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf|StaticRounding|SAE, { RegXMM|RegYMM|RegZMM|<sdh:elem>|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
+vfmadd<fma>s<sdh>, 0x6689 | 0x<fma:opc>, <sdh:fma>, Modrm|<sdh:vexlig>|Masking|<sdh:spc2>|VexVVVV|<sdh:vexw>|Disp8MemShift|NoSuf|StaticRounding|SAE, { RegXMM|<sdh:elem>|Unspecified|BaseIndex, RegXMM, RegXMM }
+vfmaddsub<fma>p<sdh>, 0x6686 | 0x<fma:opc>, <sdh:fma>, Modrm|<sdh:vex>|Masking|<sdh:spc2>|VexVVVV|<sdh:vexw>|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf|StaticRounding|SAE, { RegXMM|RegYMM|RegZMM|<sdh:elem>|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
+vfmsub<fma>p<sdh>, 0x668a | 0x<fma:opc>, <sdh:fma>, Modrm|<sdh:vex>|Masking|<sdh:spc2>|VexVVVV|<sdh:vexw>|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf|StaticRounding|SAE, { RegXMM|RegYMM|RegZMM|<sdh:elem>|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
+vfmsub<fma>s<sdh>, 0x668b | 0x<fma:opc>, <sdh:fma>, Modrm|<sdh:vexlig>|Masking|<sdh:spc2>|VexVVVV|<sdh:vexw>|Disp8MemShift|NoSuf|StaticRounding|SAE, { RegXMM|<sdh:elem>|Unspecified|BaseIndex, RegXMM, RegXMM }
+vfmsubadd<fma>p<sdh>, 0x6687 | 0x<fma:opc>, <sdh:fma>, Modrm|<sdh:vex>|Masking|<sdh:spc2>|VexVVVV|<sdh:vexw>|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf|StaticRounding|SAE, { RegXMM|RegYMM|RegZMM|<sdh:elem>|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
+vfnmadd<fma>p<sdh>, 0x668c | 0x<fma:opc>, <sdh:fma>, Modrm|<sdh:vex>|Masking|<sdh:spc2>|VexVVVV|<sdh:vexw>|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf|StaticRounding|SAE, { RegXMM|RegYMM|RegZMM|<sdh:elem>|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
+vfnmadd<fma>s<sdh>, 0x668d | 0x<fma:opc>, <sdh:fma>, Modrm|<sdh:vexlig>|Masking|<sdh:spc2>|VexVVVV|<sdh:vexw>|Disp8MemShift|NoSuf|StaticRounding|SAE, { RegXMM|<sdh:elem>|Unspecified|BaseIndex, RegXMM, RegXMM }
+vfnmsub<fma>p<sdh>, 0x668e | 0x<fma:opc>, <sdh:fma>, Modrm|<sdh:vex>|Masking|<sdh:spc2>|VexVVVV|<sdh:vexw>|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf|StaticRounding|SAE, { RegXMM|RegYMM|RegZMM|<sdh:elem>|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
+vfnmsub<fma>s<sdh>, 0x668f | 0x<fma:opc>, <sdh:fma>, Modrm|<sdh:vexlig>|Masking|<sdh:spc2>|VexVVVV|<sdh:vexw>|Disp8MemShift|NoSuf|StaticRounding|SAE, { RegXMM|<sdh:elem>|Unspecified|BaseIndex, RegXMM, RegXMM }
 
 // HLE prefixes
 
@@ -2087,11 +2092,6 @@  vpclmulhqhqdq, 0x6644/0x11, VPCLMULQDQ|A
 
 // AVX512F instructions.
 
-<sdh:cpu:cpudq:ppfx:spfx:pfx:spc1:spc2:opc:vexw:elem, +
-    s:AVX512F:AVX512DQ::f3:66:Space0F:Space0F38:0:VexW0:Dword, +
-    d:AVX512F:AVX512DQ:66:f2:66:Space0F:Space0F38:1:VexW1:Qword, +
-    h:AVX512_FP16:AVX512_FP16::f3::EVexMap5:EVexMap6:0:VexW0:Word>
-
 // <Exy> is used for EVEX instructions with x/y suffixes.
 <Exy:vl:attr:sr:sae:src:dst, +
     $z::EVex512|Disp8MemShift=6:StaticRounding|SAE:SAE:RegZMM|Unspecified|BaseIndex:RegYMM, +
@@ -2255,17 +2255,6 @@  vgetmants<sdh>, 0x<sdh:pfx>27, <sdh:cpu>
 vrndscalep<sdh>, 0x<sdh:pfx>08 | <sdh:opc>, <sdh:cpu>, Modrm|Masking|Space0F3A|<sdh:vexw>|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf|SAE, { Imm8, RegXMM|RegYMM|RegZMM|<sdh:elem>|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM }
 vrndscales<sdh>, 0x<sdh:pfx>0a | <sdh:opc>, <sdh:cpu>, Modrm|EVexLIG|Masking|Space0F3A|VexVVVV|<sdh:vexw>|Disp8MemShift|NoSuf|SAE, { Imm8, RegXMM|<sdh:elem>|Unspecified|BaseIndex, RegXMM, RegXMM }
 
-vfmadd<fma>p<sdh>, 0x6688 | 0x<fma:opc>, <sdh:cpu>, Modrm|Masking|<sdh:spc2>|VexVVVV|<sdh:vexw>|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf|StaticRounding|SAE, { RegXMM|RegYMM|RegZMM|<sdh:elem>|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
-vfmadd<fma>s<sdh>, 0x6689 | 0x<fma:opc>, <sdh:cpu>, Modrm|EVexLIG|Masking|<sdh:spc2>|VexVVVV|<sdh:vexw>|Disp8MemShift|NoSuf|StaticRounding|SAE, { RegXMM|<sdh:elem>|Unspecified|BaseIndex, RegXMM, RegXMM }
-vfmaddsub<fma>p<sdh>, 0x6686 | 0x<fma:opc>, <sdh:cpu>, Modrm|Masking|<sdh:spc2>|VexVVVV|<sdh:vexw>|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf|StaticRounding|SAE, { RegXMM|RegYMM|RegZMM|<sdh:elem>|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
-vfmsub<fma>p<sdh>, 0x668a | 0x<fma:opc>, <sdh:cpu>, Modrm|Masking|<sdh:spc2>|VexVVVV|<sdh:vexw>|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf|StaticRounding|SAE, { RegXMM|RegYMM|RegZMM|<sdh:elem>|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
-vfmsub<fma>s<sdh>, 0x668b | 0x<fma:opc>, <sdh:cpu>, Modrm|EVexLIG|Masking|<sdh:spc2>|VexVVVV|<sdh:vexw>|Disp8MemShift|NoSuf|StaticRounding|SAE, { RegXMM|<sdh:elem>|Unspecified|BaseIndex, RegXMM, RegXMM }
-vfmsubadd<fma>p<sdh>, 0x6687 | 0x<fma:opc>, <sdh:cpu>, Modrm|Masking|<sdh:spc2>|VexVVVV|<sdh:vexw>|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf|StaticRounding|SAE, { RegXMM|RegYMM|RegZMM|<sdh:elem>|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
-vfnmadd<fma>p<sdh>, 0x668c | 0x<fma:opc>, <sdh:cpu>, Modrm|Masking|<sdh:spc2>|VexVVVV|<sdh:vexw>|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf|StaticRounding|SAE, { RegXMM|RegYMM|RegZMM|<sdh:elem>|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
-vfnmadd<fma>s<sdh>, 0x668d | 0x<fma:opc>, <sdh:cpu>, Modrm|EVexLIG|Masking|<sdh:spc2>|VexVVVV|<sdh:vexw>|Disp8MemShift|NoSuf|StaticRounding|SAE, { RegXMM|<sdh:elem>|Unspecified|BaseIndex, RegXMM, RegXMM }
-vfnmsub<fma>p<sdh>, 0x668e | 0x<fma:opc>, <sdh:cpu>, Modrm|Masking|<sdh:spc2>|VexVVVV|<sdh:vexw>|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf|StaticRounding|SAE, { RegXMM|RegYMM|RegZMM|<sdh:elem>|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
-vfnmsub<fma>s<sdh>, 0x668f | 0x<fma:opc>, <sdh:cpu>, Modrm|EVexLIG|Masking|<sdh:spc2>|VexVVVV|<sdh:vexw>|Disp8MemShift|NoSuf|StaticRounding|SAE, { RegXMM|<sdh:elem>|Unspecified|BaseIndex, RegXMM, RegXMM }
-
 vscalefp<sdh>, 0x662c, <sdh:cpu>, Modrm|Masking|<sdh:spc2>|VexVVVV|<sdh:vexw>|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf|StaticRounding|SAE, { RegXMM|RegYMM|RegZMM|<sdh:elem>|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
 vscalefs<sdh>, 0x662d, <sdh:cpu>, Modrm|EVexLIG|Masking|<sdh:spc2>|VexVVVV|<sdh:vexw>|Disp8MemShift|NoSuf|StaticRounding|SAE, { RegXMM|<sdh:elem>|Unspecified|BaseIndex, RegXMM, RegXMM }