rind 0.1.3

Pure-Rust cryptography for MoQ, forked from graviola
Documentation
// Copyright 2015-2016 The OpenSSL Project Authors. All Rights Reserved.
// SPDX-License-Identifier: Apache-2.0
//
// Generated by admin/import-aws-lc from aws-lc 91c93a8eb860e51482a871a8772cb9b1b310baea:
// generated-src/linux-aarch64/crypto/fipsmodule/vpaes-armv8.S, which aws-lc generates from crypto/fipsmodule/aes/asm/vpaes-armv8.pl.
// Do not edit by hand.
	// extract rcon from xmm8
	movi	v4.16b, #0			// vpxor	%xmm4,	%xmm4,	%xmm4
	ext	v1.16b, v8.16b, v4.16b, #15	// vpalignr	$15,	%xmm8,	%xmm4,	%xmm1
	ext	v8.16b, v8.16b, v8.16b, #15	// vpalignr	$15,	%xmm8,	%xmm8,	%xmm8
	eor	v7.16b, v7.16b, v1.16b		// vpxor	%xmm1,	%xmm7,	%xmm7

	// rotate
	dup	v0.4s, v0.s[3]			// vpshufd	$0xFF,	%xmm0,	%xmm0
	ext	v0.16b, v0.16b, v0.16b, #1	// vpalignr	$1,	%xmm0,	%xmm0,	%xmm0

	// fall through...

	// low round: same as high round, but no rotation and no rcon.
	// smear xmm7
	ext	v1.16b, v4.16b, v7.16b, #12	// vpslldq	$4,	%xmm7,	%xmm1
	eor	v7.16b, v7.16b, v1.16b		// vpxor	%xmm1,	%xmm7,	%xmm7
	ext	v4.16b, v4.16b, v7.16b, #8	// vpslldq	$8,	%xmm7,	%xmm4

	// subbytes
	and	v1.16b, v0.16b, v17.16b		// vpand	%xmm9,	%xmm0,	%xmm1		# 0 = k
	ushr	v0.16b, v0.16b, #4		// vpsrlb	$4,	%xmm0,	%xmm0		# 1 = i
	eor	v7.16b, v7.16b, v4.16b		// vpxor	%xmm4,	%xmm7,	%xmm7
	tbl	v2.16b, {{v19.16b}}, v1.16b	// vpshufb	%xmm1,	%xmm11,	%xmm2		# 2 = a/k
	eor	v1.16b, v1.16b, v0.16b		// vpxor	%xmm0,	%xmm1,	%xmm1		# 0 = j
	tbl	v3.16b, {{v18.16b}}, v0.16b	// vpshufb	%xmm0, 	%xmm10,	%xmm3		# 3 = 1/i
	eor	v3.16b, v3.16b, v2.16b		// vpxor	%xmm2,	%xmm3,	%xmm3		# 3 = iak = 1/i + a/k
	tbl	v4.16b, {{v18.16b}}, v1.16b	// vpshufb	%xmm1,	%xmm10,	%xmm4		# 4 = 1/j
	eor	v7.16b, v7.16b, v16.16b		// vpxor	.Lk_s63(%rip),	%xmm7,	%xmm7
	tbl	v3.16b, {{v18.16b}}, v3.16b	// vpshufb	%xmm3,	%xmm10,	%xmm3		# 2 = 1/iak
	eor	v4.16b, v4.16b, v2.16b		// vpxor	%xmm2,	%xmm4,	%xmm4		# 4 = jak = 1/j + a/k
	tbl	v2.16b, {{v18.16b}}, v4.16b	// vpshufb	%xmm4,	%xmm10,	%xmm2		# 3 = 1/jak
	eor	v3.16b, v3.16b, v1.16b		// vpxor	%xmm1,	%xmm3,	%xmm3		# 2 = io
	eor	v2.16b, v2.16b, v0.16b		// vpxor	%xmm0,	%xmm2,	%xmm2		# 3 = jo
	tbl	v4.16b, {{v23.16b}}, v3.16b	// vpshufb	%xmm3,	%xmm13,	%xmm4		# 4 = sbou
	tbl	v1.16b, {{v22.16b}}, v2.16b	// vpshufb	%xmm2,	%xmm12,	%xmm1		# 0 = sb1t
	eor	v1.16b, v1.16b, v4.16b		// vpxor	%xmm4,	%xmm1,	%xmm1		# 0 = sbox output

	// add in smeared stuff
	eor	v0.16b, v1.16b, v7.16b		// vpxor	%xmm7,	%xmm1,	%xmm0
	eor	v7.16b, v1.16b, v7.16b		// vmovdqa	%xmm0,	%xmm7
	ret