[PATCH v2 4/4] x86: fold F16C VEX and EVEX templates

[Jan Beulich <jbeulich@suse.com>]

Following the folding of some generic AVX/AVX2 templates with their
AVX512F counterpart ones, do this for F16C ones as well, requiring one
further adjustment to cpu_flags_match(). Note that there is a slight
asymmetry with the FMA checks, resulting from the various vector lengths
having separate insn templates here, but being a single combined one
(each) for FMA.
---
TBD: Unlike for FMA the gains aren't as big yet the code changes are
     slightly bigger. The change may therefore be deemed to not be worth
     it.
---
v2: Eliminate unwanted side effect.

--- a/gas/config/tc-i386.c
+++ b/gas/config/tc-i386.c
@@ -1926,9 +1926,12 @@ cpu_flags_match (const insn_template *t)
 		{
 		  x.bitfield.cpuavx512f = 0;
 		  x.bitfield.cpuavx512vl = 0;
-		  if (x.bitfield.cpufma && !cpu.bitfield.cpufma)
+		  if ((x.bitfield.cpufma && !cpu.bitfield.cpufma)
+		      || (x.bitfield.cpuf16c && !cpu.bitfield.cpuf16c))
 		    x.bitfield.cpuavx = 0;
 		}
+	      else if (cpu.bitfield.cpuf16c)
+		x.bitfield.cpuavx512vl = 0;
 	    }
 	}
 
@@ -1953,6 +1956,8 @@ cpu_flags_match (const insn_template *t)
 		   : cpu.bitfield.cpuavx)
 		  && (!x.bitfield.cpufma || cpu.bitfield.cpufma
 		      || cpu_arch_flags.bitfield.cpuavx512f)
+		  && (!x.bitfield.cpuf16c || cpu.bitfield.cpuf16c
+		      || 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
@@ -1793,10 +1793,10 @@ rdgsbase, 0xf30fae/1, FSGSBase, Modrm|Ig
 rdrand, 0xfc7/6, RdRnd, Modrm|NoSuf, { Reg16|Reg32|Reg64 }
 wrfsbase, 0xf30fae/2, FSGSBase, Modrm|IgnoreSize|NoSuf, { Reg32|Reg64 }
 wrgsbase, 0xf30fae/3, FSGSBase, Modrm|IgnoreSize|NoSuf, { Reg32|Reg64 }
-vcvtph2ps, 0x6613, F16C, Modrm|Vex|Space0F38|VexW0|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
-vcvtph2ps, 0x6613, F16C, Modrm|Vex=2|Space0F38|VexW=1|NoSuf, { Unspecified|BaseIndex|RegXMM, RegYMM }
-vcvtps2ph, 0x661d, F16C, Modrm|Vex|Space0F3A|VexW0|NoSuf, { Imm8, RegXMM, Qword|Unspecified|BaseIndex|RegXMM }
-vcvtps2ph, 0x661d, F16C, Modrm|Vex=2|Space0F3A|VexW=1|NoSuf, { Imm8, RegYMM, Unspecified|BaseIndex|RegXMM }
+vcvtph2ps, 0x6613, F16C|AVX|AVX512F|AVX512VL, Modrm|Vex128|EVex128|Masking|Space0F38|VexW0|Disp8MemShift=3|NoSuf, { RegXMM|Qword|Unspecified|BaseIndex, RegXMM }
+vcvtph2ps, 0x6613, F16C|AVX|AVX512F|AVX512VL, Modrm|Vex256|EVex256|Masking|Space0F38|VexW0|Disp8MemShift=4|NoSuf, { RegXMM|Unspecified|BaseIndex, RegYMM }
+vcvtps2ph, 0x661D, F16C|AVX|AVX512F|AVX512VL, Modrm|Vex128|EVex128|Masking|Space0F3A|VexW0|Disp8MemShift=3|NoSuf, { Imm8, RegXMM, RegXMM|Qword|Unspecified|BaseIndex }
+vcvtps2ph, 0x661D, F16C|AVX|AVX512F|AVX512VL, Modrm|Vex256|EVex256|Masking|Space0F3A|VexW0|Disp8MemShift=4|NoSuf, { Imm8, RegYMM, RegXMM|Unspecified|BaseIndex }
 
 // FMA instructions
 
@@ -2525,15 +2525,9 @@ vcvtdq2pd, 0xF3E6, AVX512F|AVX512VL, Mod
 vcvtudq2pd, 0xF37A, AVX512F|AVX512VL, Modrm|EVex128|Masking|Space0F|VexW0|Broadcast|Disp8MemShift=3|NoSuf, { RegXMM|Dword|Qword|Unspecified|BaseIndex, RegXMM }
 vcvtudq2pd, 0xF37A, AVX512F|AVX512VL, Modrm|EVex256|Masking|Space0F|VexW0|Broadcast|Disp8MemShift=4|NoSuf, { RegXMM|Dword|Unspecified|BaseIndex, RegYMM }
 
-vcvtph2ps, 0x6613, AVX512F|AVX512VL, Modrm|EVex=2|Masking|Space0F38|VexW0|Disp8MemShift=3|NoSuf, { RegXMM|Qword|Unspecified|BaseIndex, RegXMM }
-vcvtph2ps, 0x6613, AVX512F|AVX512VL, Modrm|EVex=3|Masking|Space0F38|VexW=1|Disp8MemShift=4|NoSuf, { RegXMM|Unspecified|BaseIndex, RegYMM }
-
 vcvtps2pd, 0x5A, AVX512F|AVX512VL, Modrm|EVex128|Masking|Space0F|VexW0|Broadcast|Disp8MemShift=3|NoSuf, { RegXMM|Dword|Qword|Unspecified|BaseIndex, RegXMM }
 vcvtps2pd, 0x5A, AVX512F|AVX512VL, Modrm|EVex256|Masking|Space0F|VexW0|Broadcast|Disp8MemShift=4|NoSuf, { RegXMM|Dword|Unspecified|BaseIndex, RegYMM }
 
-vcvtps2ph, 0x661D, AVX512F|AVX512VL, Modrm|EVex128|Masking|Space0F3A|VexW0|Disp8MemShift=3|NoSuf, { Imm8, RegXMM, RegXMM|Qword|Unspecified|BaseIndex }
-vcvtps2ph, 0x661D, AVX512F|AVX512VL, Modrm|EVex256|Masking|Space0F3A|VexW0|Disp8MemShift=4|NoSuf, { Imm8, RegYMM, RegXMM|Unspecified|BaseIndex }
-
 vmovddup, 0xF212, AVX512F|AVX512VL, Modrm|EVex=2|Masking|Space0F|VexW1|Disp8MemShift=3|NoSuf, { RegXMM|Qword|Unspecified|BaseIndex, RegXMM }
 
 vpmovdb, 0xF331, AVX512F|AVX512VL, Modrm|EVex=2|Masking|Space0F38|VexW0|Disp8MemShift=2|NoSuf, { RegXMM, RegXMM|Dword|Unspecified|BaseIndex }