Squashed 'externals/xbyak/' changes from d512551e..2794cde7

2794cde7 add xword, yword, etc. in Xbyak::util
fb9c04e4 fix document for vfpclassps
a51be78b fix test dependency
04fdfb1e update version
e6354f8b add vgf2p8mulb
09a12642 add gf2p8affineqb
d171ba0e add gf2p8affineinvqb
457f4fd0 add vpshufbitqmb
5af0ba39 add vpexpand{b,w}
e450f965 vpopcnt{d,q} supports ptr_b
48499eb1 add vpdpbusd(s), vpdpwssd(s)
9c745109 add vpdpbusd, vpdpbusds
0e1a11b4 add vpopcnt{b,w,d,q}
9acfc132 add vpshrd(v){w,d,q}
ac8de850 add vpshld(v){w,d,q}
f181c259 add vcompressb, vcompressw
5a402477 vpclmulqdq supports AVX-512
9e16b40b vaes* supports AVX-512
7fde08e0 add flags for intel's manual 319433-030.pdf
c5da3778 add test of v4fmaddps, vp4dpwssd, etc.
e4fc9d8a fix mpx encoding
d0b2fb62 add bnd(0xf2) prefix for MPX
f12b5678 use db for array
cd74ab44 remove bat file

git-subtree-dir: externals/xbyak
git-subtree-split: 2794cde79eb71e86490061cac9622ad0067b8d15
This commit is contained in:
MerryMage 2020-04-22 20:45:52 +01:00
parent 4ed09fda06
commit 9fb82036ca
16 changed files with 935 additions and 173 deletions

View file

@ -1,5 +1,5 @@
Xbyak 5.52 ; JIT assembler for x86(IA32), x64(AMD64, x86-64) by C++
Xbyak 5.601 ; JIT assembler for x86(IA32), x64(AMD64, x86-64) by C++
=============
Abstract
@ -128,7 +128,7 @@ vcvtpd2dq xmm19, [eax+32]{1to4} --> vcvtpd2dq(xmm19, yword_b [eax+32]);
vfpclassps k5{k3}, zword [rax+64], 5 --> vfpclassps(k5|k3, zword [rax+64], 5); // specify m512
vfpclasspd k5{k3}, [rax+64]{1to2}, 5 --> vfpclasspd(k5|k3, xword_b [rax+64], 5); // broadcast 64-bit to 128-bit
vfpclassps k5{k3}, [rax+64]{1to4}, 5 --> vfpclassps(k5|k3, xword_b [rax+64], 5); // broadcast 32-bit to 128-bit
vfpclassps k5{k3}, [rax+64]{1to4}, 5 --> vfpclassps(k5|k3, yword_b [rax+64], 5); // broadcast 64-bit to 256-bit
```
Remark
* k1, ..., k7 are new opmask registers.
@ -333,6 +333,9 @@ The header files under xbyak/ are independent of cybozulib.
History
-------------
* 2018/Jan/24 ver 5.601 add xword, yword, etc. into Xbyak::util namespace
* 2018/Jan/05 ver 5.60 support AVX-512 for Ice lake(319433-030.pdf)
* 2017/Aug/22 ver 5.53 fix mpx encoding, add bnd() prefix
* 2017/Aug/18 ver 5.52 fix align (thanks to MerryMage)
* 2017/Aug/17 ver 5.51 add multi-byte nop and align() uses it(thanks to inolen)
* 2017/Aug/08 ver 5.50 add mpx(thanks to magurosan)