This is the mail archive of the binutils@sourceware.org mailing list for the binutils project.

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]
Other format:	[Raw text]

[PATCH 1/9] x86: XOP VPHADD* / VPHSUB* are VEX.W0

From: "Jan Beulich" <JBeulich at suse dot com>
To: <binutils at sourceware dot org>
Cc: "H.J. Lu" <hjl dot tools at gmail dot com>
Date: Thu, 11 Oct 2018 00:52:02 -0600
Subject: [PATCH 1/9] x86: XOP VPHADD* / VPHSUB* are VEX.W0
References: <5BBE1F7502000078001F07CC@prv1-mh.provo.novell.com>

Also avoid introducing further uses of VexW=1, by introducing and using
VexW0 at this occasion. Move the marker past all #define-s.

opcodes/
2018-10-10  Jan Beulich  <jbeulich@suse.com>

	* i386-opc.tbl (VexW0, VexW1): New.
	(vphadd*, vphsub*): Use VexW0 on XOP variants.
	* i386-tbl.h: Re-generate.

--- a/opcodes/i386-opc.tbl
+++ b/opcodes/i386-opc.tbl
@@ -26,10 +26,12 @@
 #define Size32 Size=SIZE32
 #define Size64 Size=SIZE64
 
-### MARKER ###
-
+#define VexW0 VexW=VEXW0
+#define VexW1 VexW=VEXW1
 #define VexWIG VexW=VEXWIG
 
+### MARKER ###
+
 // Move instructions.
 // We put the 64bit displacement first and we only mark constants
 // larger than 32bit as Disp64.
@@ -2638,21 +2640,21 @@ vpcomtrueud,  3, 0xee, 0x7, 1, CpuXOP, M
 vpcomtrueuq,  3, 0xef, 0x7, 1, CpuXOP, Modrm|VexOpcode=3|VexVVVV=1|VexW=1|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Vex|ImmExt, { RegXMM|Unspecified|BaseIndex, RegXMM, RegXMM }
 vpcomtrueuw,  3, 0xed, 0x7, 1, CpuXOP, Modrm|VexOpcode=3|VexVVVV=1|VexW=1|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Vex|ImmExt, { RegXMM|Unspecified|BaseIndex, RegXMM, RegXMM }
 vpcomtruew,   3, 0xcd, 0x7, 1, CpuXOP, Modrm|VexOpcode=3|VexVVVV=1|VexW=1|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Vex|ImmExt, { RegXMM|Unspecified|BaseIndex, RegXMM, RegXMM }
-vphaddbd,   2, 0xc2, None, 1, CpuXOP, Modrm|VexOpcode=4|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|Vex, { RegXMM|Unspecified|BaseIndex, RegXMM }
-vphaddbq,   2, 0xc3, None, 1, CpuXOP, Modrm|VexOpcode=4|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|Vex, { RegXMM|Unspecified|BaseIndex, RegXMM }
-vphaddbw,   2, 0xc1, None, 1, CpuXOP, Modrm|VexOpcode=4|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|Vex, { RegXMM|Unspecified|BaseIndex, RegXMM }
-vphadddq,   2, 0xcb, None, 1, CpuXOP, Modrm|VexOpcode=4|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|Vex, { RegXMM|Unspecified|BaseIndex, RegXMM }
-vphaddubd,  2, 0xd2, None, 1, CpuXOP, Modrm|VexOpcode=4|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|Vex, { RegXMM|Unspecified|BaseIndex, RegXMM }
-vphaddubq,  2, 0xd3, None, 1, CpuXOP, Modrm|VexOpcode=4|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|Vex, { RegXMM|Unspecified|BaseIndex, RegXMM }
-vphaddubw,  2, 0xd1, None, 1, CpuXOP, Modrm|VexOpcode=4|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|Vex, { RegXMM|Unspecified|BaseIndex, RegXMM }
-vphaddudq,  2, 0xdb, None, 1, CpuXOP, Modrm|VexOpcode=4|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|Vex, { RegXMM|Unspecified|BaseIndex, RegXMM }
-vphadduwd,  2, 0xd6, None, 1, CpuXOP, Modrm|VexOpcode=4|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|Vex, { RegXMM|Unspecified|BaseIndex, RegXMM }
-vphadduwq,  2, 0xd7, None, 1, CpuXOP, Modrm|VexOpcode=4|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|Vex, { RegXMM|Unspecified|BaseIndex, RegXMM }
-vphaddwd,   2, 0xc6, None, 1, CpuXOP, Modrm|VexOpcode=4|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|Vex, { RegXMM|Unspecified|BaseIndex, RegXMM }
-vphaddwq,   2, 0xc7, None, 1, CpuXOP, Modrm|VexOpcode=4|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|Vex, { RegXMM|Unspecified|BaseIndex, RegXMM }
-vphsubbw,   2, 0xe1, None, 1, CpuXOP, Modrm|VexOpcode=4|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|Vex, { RegXMM|Unspecified|BaseIndex, RegXMM }
-vphsubdq,   2, 0xe3, None, 1, CpuXOP, Modrm|VexOpcode=4|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|Vex, { RegXMM|Unspecified|BaseIndex, RegXMM }
-vphsubwd,   2, 0xe2, None, 1, CpuXOP, Modrm|VexOpcode=4|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|Vex, { RegXMM|Unspecified|BaseIndex, RegXMM }
+vphaddbd,   2, 0xc2, None, 1, CpuXOP, Modrm|VexOpcode=4|VexW0|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|Vex, { RegXMM|Unspecified|BaseIndex, RegXMM }
+vphaddbq,   2, 0xc3, None, 1, CpuXOP, Modrm|VexOpcode=4|VexW0|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|Vex, { RegXMM|Unspecified|BaseIndex, RegXMM }
+vphaddbw,   2, 0xc1, None, 1, CpuXOP, Modrm|VexOpcode=4|VexW0|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|Vex, { RegXMM|Unspecified|BaseIndex, RegXMM }
+vphadddq,   2, 0xcb, None, 1, CpuXOP, Modrm|VexOpcode=4|VexW0|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|Vex, { RegXMM|Unspecified|BaseIndex, RegXMM }
+vphaddubd,  2, 0xd2, None, 1, CpuXOP, Modrm|VexOpcode=4|VexW0|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|Vex, { RegXMM|Unspecified|BaseIndex, RegXMM }
+vphaddubq,  2, 0xd3, None, 1, CpuXOP, Modrm|VexOpcode=4|VexW0|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|Vex, { RegXMM|Unspecified|BaseIndex, RegXMM }
+vphaddubw,  2, 0xd1, None, 1, CpuXOP, Modrm|VexOpcode=4|VexW0|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|Vex, { RegXMM|Unspecified|BaseIndex, RegXMM }
+vphaddudq,  2, 0xdb, None, 1, CpuXOP, Modrm|VexOpcode=4|VexW0|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|Vex, { RegXMM|Unspecified|BaseIndex, RegXMM }
+vphadduwd,  2, 0xd6, None, 1, CpuXOP, Modrm|VexOpcode=4|VexW0|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|Vex, { RegXMM|Unspecified|BaseIndex, RegXMM }
+vphadduwq,  2, 0xd7, None, 1, CpuXOP, Modrm|VexOpcode=4|VexW0|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|Vex, { RegXMM|Unspecified|BaseIndex, RegXMM }
+vphaddwd,   2, 0xc6, None, 1, CpuXOP, Modrm|VexOpcode=4|VexW0|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|Vex, { RegXMM|Unspecified|BaseIndex, RegXMM }
+vphaddwq,   2, 0xc7, None, 1, CpuXOP, Modrm|VexOpcode=4|VexW0|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|Vex, { RegXMM|Unspecified|BaseIndex, RegXMM }
+vphsubbw,   2, 0xe1, None, 1, CpuXOP, Modrm|VexOpcode=4|VexW0|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|Vex, { RegXMM|Unspecified|BaseIndex, RegXMM }
+vphsubdq,   2, 0xe3, None, 1, CpuXOP, Modrm|VexOpcode=4|VexW0|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|Vex, { RegXMM|Unspecified|BaseIndex, RegXMM }
+vphsubwd,   2, 0xe2, None, 1, CpuXOP, Modrm|VexOpcode=4|VexW0|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|Vex, { RegXMM|Unspecified|BaseIndex, RegXMM }
 vpmacsdd,   4, 0x9e, None, 1, CpuXOP, Modrm|VexOpcode=3|VexSources=2|VexVVVV=1|VexW=1|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Vex, { RegXMM, RegXMM|Unspecified|BaseIndex, RegXMM, RegXMM }
 vpmacsdqh,  4, 0x9f, None, 1, CpuXOP, Modrm|VexOpcode=3|VexSources=2|VexVVVV=1|VexW=1|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Vex, { RegXMM, RegXMM|Unspecified|BaseIndex, RegXMM, RegXMM }
 vpmacsdql,  4, 0x97, None, 1, CpuXOP, Modrm|VexOpcode=3|VexSources=2|VexVVVV=1|VexW=1|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Vex, { RegXMM, RegXMM|Unspecified|BaseIndex, RegXMM, RegXMM }

References:
- [PATCH 0/9] x86: further adjustments to {,E}VEX.{W,L} handling
  - From: Jan Beulich

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]