[07/12] x86: fold VFPCLASSP{D,S} templates

Message ID 5B0EBA0C02000078001C70E6@prv1-mh.provo.novell.com
State Superseded
Headers show
Series
  • x86: various improvements
Related show

Commit Message

Jan Beulich May 30, 2018, 2:49 p.m.
These are special because they may not have a register operand to derive
the vector length from, which requires to also deal with the braodcast
case when determining vector length in build_evex_prefix().

Also drop IgnoreSize (and the now redundant size specifiers) from their
suffixed counterparts.

gas/
2018-05-30  Jan Beulich  <jbeulich@suse.com>

	* config/tc-i386.c (build_evex_prefix): Derive vector length
	from broadcast specification if necessary.
	(match_template): Also exclude broadcast when checking whether
	to reject 32-bit operands on pre-386.

opcodes/
2018-05-30  Jan Beulich  <jbeulich@suse.com>

	* i386-opc.tbl (vfpclasspd, vfpclassps): Fold.
	(vfpclasspdz, vfpclasspsz): Drop IgnoreSize and ZmmWord.
	(vfpclasspdx, vfpclasspsx): Drop IgnoreSize and XmmWord.
	(vfpclasspdy, vfpclasspsy): Drop IgnoreSize and YmmWord.
	* i386-tbl.h: Re-generate.

Patch

--- a/gas/config/tc-i386.c
+++ b/gas/config/tc-i386.c
@@ -3622,7 +3622,24 @@  build_evex_prefix (void)
 		  i.tm.opcode_modifier.evex = EVEX256;
 		else if (i.types[op].bitfield.xmmword)
 		  i.tm.opcode_modifier.evex = EVEX128;
-		else
+		else if (i.broadcast && (int) op == i.broadcast->operand)
+		  {
+		    switch ((i.tm.operand_types[op].bitfield.dword ? 4 : 8)
+			    * i.broadcast->type)
+		      {
+			case 64:
+			  i.tm.opcode_modifier.evex = EVEX512;
+			  break;
+			case 32:
+			  i.tm.opcode_modifier.evex = EVEX256;
+			  break;
+			case 16:
+			  i.tm.opcode_modifier.evex = EVEX128;
+			  break;
+			default:
+			  continue;
+		      }
+		  }
 		  continue;
 		break;
 	      }
@@ -5426,6 +5443,7 @@  match_template (char mnem_suffix)
 	  && flag_code != CODE_64BIT
 	  && (intel_syntax
 	      ? (!t->opcode_modifier.ignoresize
+	         && !t->opcode_modifier.broadcast
 		 && !intel_float_operand (t->name))
 	      : intel_float_operand (t->name) != 2)
 	  && ((!operand_types[0].bitfield.regmmx
--- a/opcodes/i386-opc.tbl
+++ b/opcodes/i386-opc.tbl
@@ -4578,19 +4578,15 @@  vextracti64x2, 3, 0x6639, None, 1, CpuAV
 vinsertf64x2, 4, 0x6618, None, 1, CpuAVX512DQ, Modrm|Masking=3|VexOpcode=2|VexVVVV=1|VexW=2|Disp8MemShift=4|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, RegXMM|Unspecified|BaseIndex, RegYMM|RegZMM, RegYMM|RegZMM }
 vinserti64x2, 4, 0x6638, None, 1, CpuAVX512DQ, Modrm|Masking=3|VexOpcode=2|VexVVVV=1|VexW=2|Disp8MemShift=4|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, RegXMM|Unspecified|BaseIndex, RegYMM|RegZMM, RegYMM|RegZMM }
 
-vfpclasspd, 3, 0x6666, None, 1, CpuAVX512DQ, Modrm|EVex=1|Masking=2|VexOpcode=2|VexW=2|Broadcast|Disp8MemShift=6|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, RegZMM|Qword|ZMMword|BaseIndex, RegMask }
-vfpclasspdz, 3, 0x6666, None, 1, CpuAVX512DQ, Modrm|EVex=1|Masking=2|VexOpcode=2|VexW=2|Broadcast|Disp8MemShift=6|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, RegZMM|Qword|ZMMword|Unspecified|BaseIndex, RegMask }
-vfpclasspd, 3, 0x6666, None, 1, CpuAVX512DQ|CpuAVX512VL, Modrm|EVex=2|Masking=2|VexOpcode=2|VexW=2|Broadcast|Disp8MemShift=4|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, RegXMM|Qword|XMMword|BaseIndex, RegMask }
-vfpclasspdx, 3, 0x6666, None, 1, CpuAVX512DQ|CpuAVX512VL, Modrm|EVex=2|Masking=2|VexOpcode=2|VexW=2|Broadcast|Disp8MemShift=4|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, RegXMM|Qword|XMMword|Unspecified|BaseIndex, RegMask }
-vfpclasspd, 3, 0x6666, None, 1, CpuAVX512DQ|CpuAVX512VL, Modrm|EVex=3|Masking=2|VexOpcode=2|VexW=2|Broadcast|Disp8MemShift=5|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, RegYMM|Qword|YMMword|BaseIndex, RegMask }
-vfpclasspdy, 3, 0x6666, None, 1, CpuAVX512DQ|CpuAVX512VL, Modrm|EVex=3|Masking=2|VexOpcode=2|VexW=2|Broadcast|Disp8MemShift=5|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, RegYMM|Qword|YMMword|Unspecified|BaseIndex, RegMask }
+vfpclasspd, 3, 0x6666, None, 1, CpuAVX512DQ, Modrm|Masking=2|VexOpcode=2|VexW=2|Broadcast|Disp8ShiftVL|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, RegXMM|RegYMM|RegZMM|Qword|BaseIndex, RegMask }
+vfpclasspdz, 3, 0x6666, None, 1, CpuAVX512DQ, Modrm|EVex=1|Masking=2|VexOpcode=2|VexW=2|Broadcast|Disp8MemShift=6|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, RegZMM|Qword|Unspecified|BaseIndex, RegMask }
+vfpclasspdx, 3, 0x6666, None, 1, CpuAVX512DQ|CpuAVX512VL, Modrm|EVex=2|Masking=2|VexOpcode=2|VexW=2|Broadcast|Disp8MemShift=4|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, RegXMM|Qword|Unspecified|BaseIndex, RegMask }
+vfpclasspdy, 3, 0x6666, None, 1, CpuAVX512DQ|CpuAVX512VL, Modrm|EVex=3|Masking=2|VexOpcode=2|VexW=2|Broadcast|Disp8MemShift=5|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, RegYMM|Qword|Unspecified|BaseIndex, RegMask }
 
-vfpclassps, 3, 0x6666, None, 1, CpuAVX512DQ, Modrm|EVex=1|Masking=2|VexOpcode=2|VexW=1|Broadcast|Disp8MemShift=6|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, RegZMM|Dword|ZMMword|BaseIndex, RegMask }
-vfpclasspsz, 3, 0x6666, None, 1, CpuAVX512DQ, Modrm|EVex=1|Masking=2|VexOpcode=2|VexW=1|Broadcast|Disp8MemShift=6|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, RegZMM|Dword|ZMMword|Unspecified|BaseIndex, RegMask }
-vfpclassps, 3, 0x6666, None, 1, CpuAVX512DQ|CpuAVX512VL, Modrm|EVex=2|Masking=2|VexOpcode=2|VexW=1|Broadcast|Disp8MemShift=4|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, RegXMM|Dword|XMMword|BaseIndex, RegMask }
-vfpclasspsx, 3, 0x6666, None, 1, CpuAVX512DQ|CpuAVX512VL, Modrm|EVex=2|Masking=2|VexOpcode=2|VexW=1|Broadcast|Disp8MemShift=4|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, RegXMM|Dword|XMMword|Unspecified|BaseIndex, RegMask }
-vfpclassps, 3, 0x6666, None, 1, CpuAVX512DQ|CpuAVX512VL, Modrm|EVex=3|Masking=2|VexOpcode=2|VexW=1|Broadcast|Disp8MemShift=5|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, RegYMM|Dword|YMMword|BaseIndex, RegMask }
-vfpclasspsy, 3, 0x6666, None, 1, CpuAVX512DQ|CpuAVX512VL, Modrm|EVex=3|Masking=2|VexOpcode=2|VexW=1|Broadcast|Disp8MemShift=5|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, RegYMM|Dword|YMMword|Unspecified|BaseIndex, RegMask }
+vfpclassps, 3, 0x6666, None, 1, CpuAVX512DQ, Modrm|Masking=2|VexOpcode=2|VexW=1|Broadcast|Disp8ShiftVL|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, RegXMM|RegYMM|RegZMM|Dword|BaseIndex, RegMask }
+vfpclasspsz, 3, 0x6666, None, 1, CpuAVX512DQ, Modrm|EVex=1|Masking=2|VexOpcode=2|VexW=1|Broadcast|Disp8MemShift=6|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, RegZMM|Dword|Unspecified|BaseIndex, RegMask }
+vfpclasspsx, 3, 0x6666, None, 1, CpuAVX512DQ|CpuAVX512VL, Modrm|EVex=2|Masking=2|VexOpcode=2|VexW=1|Broadcast|Disp8MemShift=4|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, RegXMM|Dword|Unspecified|BaseIndex, RegMask }
+vfpclasspsy, 3, 0x6666, None, 1, CpuAVX512DQ|CpuAVX512VL, Modrm|EVex=3|Masking=2|VexOpcode=2|VexW=1|Broadcast|Disp8MemShift=5|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, RegYMM|Dword|Unspecified|BaseIndex, RegMask }
 
 vpmovd2m, 2, 0xF339, None, 1, CpuAVX512DQ, Modrm|EVex=5|VexOpcode=1|VexW=1|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegXMM|RegYMM|RegZMM, RegMask }
 vpmovq2m, 2, 0xF339, None, 1, CpuAVX512DQ, Modrm|EVex=5|VexOpcode=1|VexW=2|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegXMM|RegYMM|RegZMM, RegMask }