From: Jan Beulich <jbeulich@suse.com>
To: Binutils <binutils@sourceware.org>
Cc: "H.J. Lu" <hjl.tools@gmail.com>
Subject: [PATCH 2/4] x86: fold VAES/VPCLMULQDQ VEX and EVEX templates
Date: Fri, 15 Sep 2023 10:48:06 +0200 [thread overview]
Message-ID: <7fb71e79-5846-1ae6-6446-d91c507afef4@suse.com> (raw)
In-Reply-To: <0690c179-ac98-d127-5ff4-b5abb725b6ae@suse.com>
Following the folding of some generic AVX/AVX2 templates with their
AVX512F counterpart ones, do this for VAES and VPCLMULQDQ ones as well.
--- a/gas/config/tc-i386.c
+++ b/gas/config/tc-i386.c
@@ -1942,7 +1942,17 @@ cpu_flags_match (const insn_template *t)
cpu = cpu_flags_and (x, cpu);
if (!cpu_flags_all_zero (&cpu))
{
- if (x.bitfield.cpuavx)
+ if (t->cpu.bitfield.cpuavx && t->cpu.bitfield.cpuavx512f)
+ {
+ if ((need_evex_encoding ()
+ ? cpu.bitfield.cpuavx512f
+ : cpu.bitfield.cpuavx)
+ && (!x.bitfield.cpugfni || cpu.bitfield.cpugfni)
+ && (!x.bitfield.cpuvaes || cpu.bitfield.cpuvaes)
+ && (!x.bitfield.cpuvpclmulqdq || cpu.bitfield.cpuvpclmulqdq))
+ match |= CPU_FLAGS_ARCH_MATCH;
+ }
+ else if (x.bitfield.cpuavx)
{
/* We need to check a few extra flags with AVX. */
if (cpu.bitfield.cpuavx
@@ -1957,9 +1967,7 @@ cpu_flags_match (const insn_template *t)
{
/* We need to check a few extra flags with AVX512F. */
if (cpu.bitfield.cpuavx512f
- && (!x.bitfield.cpugfni || cpu.bitfield.cpugfni)
- && (!x.bitfield.cpuvaes || cpu.bitfield.cpuvaes)
- && (!x.bitfield.cpuvpclmulqdq || cpu.bitfield.cpuvpclmulqdq))
+ && (!x.bitfield.cpugfni || cpu.bitfield.cpugfni))
match |= CPU_FLAGS_ARCH_MATCH;
}
else
--- a/opcodes/i386-opc.tbl
+++ b/opcodes/i386-opc.tbl
@@ -2068,20 +2068,20 @@ vsm4rnds4, 0xf2da, SM4, Modrm|Space0F38|
// VAES
-vaesdec, 0x66de, VAES, Modrm|Vex|Space0F38|VexVVVV|VexWIG|CheckOperandSize|NoSuf, { RegXMM|RegYMM|Unspecified|BaseIndex, RegXMM|RegYMM, RegXMM|RegYMM }
-vaesdeclast, 0x66df, VAES, Modrm|Vex|Space0F38|VexVVVV|VexWIG|CheckOperandSize|NoSuf, { RegXMM|RegYMM|Unspecified|BaseIndex, RegXMM|RegYMM, RegXMM|RegYMM }
-vaesenc, 0x66dc, VAES, Modrm|Vex|Space0F38|VexVVVV|VexWIG|CheckOperandSize|NoSuf, { RegXMM|RegYMM|Unspecified|BaseIndex, RegXMM|RegYMM, RegXMM|RegYMM }
-vaesenclast, 0x66dd, VAES, Modrm|Vex|Space0F38|VexVVVV|VexWIG|CheckOperandSize|NoSuf, { RegXMM|RegYMM|Unspecified|BaseIndex, RegXMM|RegYMM, RegXMM|RegYMM }
+vaesdec, 0x66de, VAES|AVX|AVX512F, Modrm|Vex|EVexDYN|Space0F38|VexWIG|VexVVVV|Disp8ShiftVL|CheckOperandSize|NoSuf, { RegXMM|RegYMM|RegZMM|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
+vaesdeclast, 0x66df, VAES|AVX|AVX512F, Modrm|Vex|EVexDYN|Space0F38|VexWIG|VexVVVV|Disp8ShiftVL|CheckOperandSize|NoSuf, { RegXMM|RegYMM|RegZMM|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
+vaesenc, 0x66dc, VAES|AVX|AVX512F, Modrm|Vex|EVexDYN|Space0F38|VexWIG|VexVVVV|Disp8ShiftVL|CheckOperandSize|NoSuf, { RegXMM|RegYMM|RegZMM|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
+vaesenclast, 0x66dd, VAES|AVX|AVX512F, Modrm|Vex|EVexDYN|Space0F38|VexWIG|VexVVVV|Disp8ShiftVL|CheckOperandSize|NoSuf, { RegXMM|RegYMM|RegZMM|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
// VAES instructions end
// VPCLMULQDQ instructions
-vpclmulqdq, 0x6644, VPCLMULQDQ, Modrm|Vex|Space0F3A|VexWIG|VexVVVV|CheckOperandSize|NoSuf, { Imm8|Imm8S, Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
-vpclmullqlqdq, 0x6644/0x00, VPCLMULQDQ, Modrm|Vex|Space0F3A|VexWIG|VexVVVV|CheckOperandSize|NoSuf|ImmExt, { Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
-vpclmulhqlqdq, 0x6644/0x01, VPCLMULQDQ, Modrm|Vex|Space0F3A|VexWIG|VexVVVV|CheckOperandSize|NoSuf|ImmExt, { Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
-vpclmullqhqdq, 0x6644/0x10, VPCLMULQDQ, Modrm|Vex|Space0F3A|VexWIG|VexVVVV|CheckOperandSize|NoSuf|ImmExt, { Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
-vpclmulhqhqdq, 0x6644/0x11, VPCLMULQDQ, Modrm|Vex|Space0F3A|VexWIG|VexVVVV|CheckOperandSize|NoSuf|ImmExt, { Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
+vpclmulqdq, 0x6644, VPCLMULQDQ|AVX|AVX512F, Modrm|Space0F3A|Vex|EVexDYN|VexWIG|VexVVVV|Disp8ShiftVL|CheckOperandSize|NoSuf, { Imm8|Imm8S, RegXMM|RegYMM|RegZMM|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
+vpclmullqlqdq, 0x6644/0x00, VPCLMULQDQ|AVX|AVX512F, Modrm|Space0F3A|Vex|EVexDYN|VexWIG|VexVVVV|Disp8ShiftVL|CheckOperandSize|NoSuf|ImmExt, { RegXMM|RegYMM|RegZMM|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
+vpclmulhqlqdq, 0x6644/0x01, VPCLMULQDQ|AVX|AVX512F, Modrm|Space0F3A|Vex|EVexDYN|VexWIG|VexVVVV|Disp8ShiftVL|CheckOperandSize|NoSuf|ImmExt, { RegXMM|RegYMM|RegZMM|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
+vpclmullqhqdq, 0x6644/0x10, VPCLMULQDQ|AVX|AVX512F, Modrm|Space0F3A|Vex|EVexDYN|VexWIG|VexVVVV|Disp8ShiftVL|CheckOperandSize|NoSuf|ImmExt, { RegXMM|RegYMM|RegZMM|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
+vpclmulhqhqdq, 0x6644/0x11, VPCLMULQDQ|AVX|AVX512F, Modrm|Space0F3A|Vex|EVexDYN|VexWIG|VexVVVV|Disp8ShiftVL|CheckOperandSize|NoSuf|ImmExt, { RegXMM|RegYMM|RegZMM|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
// VPCLMULQDQ instructions end
@@ -2932,25 +2932,6 @@ vgf2p8affineqb, 0x66ce, GFNI|AVX512F, Mo
// AVX512 + GFNI instructions end
-// AVX512 + VAES instructions
-
-vaesdec, 0x66de, VAES|AVX512F, Modrm|Space0F38|VexWIG|VexVVVV|Disp8ShiftVL|CheckOperandSize|NoSuf, { RegXMM|RegYMM|RegZMM|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
-vaesdeclast, 0x66df, VAES|AVX512F, Modrm|Space0F38|VexWIG|VexVVVV|Disp8ShiftVL|CheckOperandSize|NoSuf, { RegXMM|RegYMM|RegZMM|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
-vaesenc, 0x66dc, VAES|AVX512F, Modrm|Space0F38|VexWIG|VexVVVV|Disp8ShiftVL|CheckOperandSize|NoSuf, { RegXMM|RegYMM|RegZMM|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
-vaesenclast, 0x66dd, VAES|AVX512F, Modrm|Space0F38|VexWIG|VexVVVV|Disp8ShiftVL|CheckOperandSize|NoSuf, { RegXMM|RegYMM|RegZMM|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
-
-// AVX512 + VAES instructions end
-
-// AVX512 + VPCLMULQDQ instructions
-
-vpclmulqdq, 0x6644, VPCLMULQDQ|AVX512F, Modrm|Space0F3A|VexWIG|VexVVVV|Disp8ShiftVL|CheckOperandSize|NoSuf, { Imm8|Imm8S, RegXMM|RegYMM|RegZMM|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
-vpclmullqlqdq, 0x6644/0x00, VPCLMULQDQ|AVX512F, Modrm|Space0F3A|VexWIG|VexVVVV|Disp8ShiftVL|CheckOperandSize|NoSuf|ImmExt, { RegXMM|RegYMM|RegZMM|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
-vpclmulhqlqdq, 0x6644/0x01, VPCLMULQDQ|AVX512F, Modrm|Space0F3A|VexWIG|VexVVVV|Disp8ShiftVL|CheckOperandSize|NoSuf|ImmExt, { RegXMM|RegYMM|RegZMM|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
-vpclmullqhqdq, 0x6644/0x10, VPCLMULQDQ|AVX512F, Modrm|Space0F3A|VexWIG|VexVVVV|Disp8ShiftVL|CheckOperandSize|NoSuf|ImmExt, { RegXMM|RegYMM|RegZMM|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
-vpclmulhqhqdq, 0x6644/0x11, VPCLMULQDQ|AVX512F, Modrm|Space0F3A|VexWIG|VexVVVV|Disp8ShiftVL|CheckOperandSize|NoSuf|ImmExt, { RegXMM|RegYMM|RegZMM|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
-
-// AVX512 + VPCLMULQDQ instructions end
-
// INVLPGB instructions
invlpgb, 0xf01fe, INVLPGB, NoSuf, {}
next prev parent reply other threads:[~2023-09-15 8:48 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-09-15 8:46 [PATCH 0/4] x86: fold a number of " Jan Beulich
2023-09-15 8:47 ` [PATCH 1/4] x86: fold certain " Jan Beulich
2023-09-15 8:48 ` Jan Beulich [this message]
2023-09-15 8:48 ` [PATCH RFC 3/4] x86: fold FMA " Jan Beulich
2023-09-15 8:49 ` [PATCH RFC 4/4] x86: fold F16C " Jan Beulich
2023-09-18 1:58 ` [PATCH 0/4] x86: fold a number of " Hongtao Liu
2023-09-18 5:47 ` Cui, Lili
2023-09-18 9:38 ` Jan Beulich
2023-09-18 11:18 ` Cui, Lili
2023-09-18 11:49 ` Jan Beulich
2023-09-18 12:03 ` Cui, Lili
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=7fb71e79-5846-1ae6-6446-d91c507afef4@suse.com \
--to=jbeulich@suse.com \
--cc=binutils@sourceware.org \
--cc=hjl.tools@gmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).