hugeloop:
	CMPQ	BX, $64
	JB	bigloop
	MOVOU	(SI), X0
	MOVOU	(DI), X1
	MOVOU	16(SI), X2
	MOVOU	16(DI), X3
	MOVOU	32(SI), X4
	MOVOU	32(DI), X5
	MOVOU	48(SI), X6
	MOVOU	48(DI), X7
	PCMPEQB	X1, X0
	PCMPEQB	X3, X2
	PCMPEQB	X5, X4
	PCMPEQB	X7, X6
	PAND	X2, X0
	PAND	X6, X4
	PAND	X4, X0
	PMOVMSKB X0, DX
	ADDQ	$64, SI
	ADDQ	$64, DI
	SUBQ	$64, BX
	CMPL	DX, $0xffff
	JEQ	hugeloop
	XORQ	AX, AX	// return 0
	RET

	// If less than 8 bytes, do single byte copies.
	MOV	$8, X9
	BLT	X12, X9, f_loop4_check

	// Check alignment - if alignment differs we have to do one byte at a time.
	AND	$7, X10, X5
	AND	$7, X11, X6
	BNE	X5, X6, f_loop8_unaligned_check
	BEQZ	X5, f_loop_check

	// Move one byte at a time until we reach 8 byte alignment.
	SUB	X5, X9, X5
	SUB	X5, X12, X12
f_align:
	SUB	$1, X5
	MOVB	0(X11), X14
	MOVB	X14, 0(X10)

// Code generated by mkpreempt.go; DO NOT EDIT.

#include "go_asm.h"
#include "textflag.h"

TEXT ·asyncPreempt(SB),NOSPLIT|NOFRAME,$0-0
	MOV X1, -464(X2)
	SUB $464, X2
	MOV X5, 8(X2)
	MOV X6, 16(X2)
	MOV X7, 24(X2)
	MOV X8, 32(X2)
	MOV X9, 40(X2)
	MOV X10, 48(X2)
	MOV X11, 56(X2)
	MOV X12, 64(X2)
	MOV X13, 72(X2)
	MOV X14, 80(X2)
	MOV X15, 88(X2)
	MOV X16, 96(X2)
	MOV X17, 104(X2)
	MOV X18, 112(X2)

	SHUFPS $0x10, X0, X4
	PXOR X4, X0
	SHUFPS $0x8c, X0, X4
	PXOR X4, X0
	PXOR X1, X0

	MOVAPS X2, X5
	MOVAPS X2, X6
	PSLLDQ $0x4, X5
	PSHUFD $0xff, X0, X3
	PXOR X3, X2
	PXOR X5, X2

	MOVAPS X0, X1
	SHUFPS $0x44, X0, X6
	MOVUPS X6, (BX)
	SHUFPS $0x4e, X2, X1
	MOVUPS X1, 16(BX)
	ADDQ $32, BX
	RET

TEXT _expand_key_192b<>(SB),NOSPLIT,$0
	PSHUFD $0x55, X1, X1

	TEQ	R1, R5
	BNE Y7

X7:
	MOVW	$0, R1
	MOVW	R1, c+28(FP)
	RET


// func shrVU(z, x []Word, s uint) (c Word)
TEXT ·shrVU(SB),NOSPLIT,$0
	MOVW	z_len+4(FP), R5
	TEQ	$0, R5
	BEQ	X6

	MOVW	z+0(FP), R1
	MOVW	x+12(FP), R2
	ADD	R5<<2, R1, R5
	MOVW	s+24(FP), R3
	TEQ	$0, R3	// shift 0 is special
	BEQ Y6
	SUB	$4, R5	// stop one word early
	MOVW	$32, R4
	SUB	R3, R4
	MOVW	$0, R7

	p256OrdSqr(t, x, 1)          // _10100
	p256OrdMul(_10101, t, _1)    // _10101
	p256OrdSqr(x, _10101, 1)     // _101010
	p256OrdMul(_101111, _101, x) // _101111
	p256OrdMul(x, _10101, x)     // _111111 = x6
	p256OrdSqr(t, x, 2)          // _11111100
	p256OrdMul(t, t, _11)        // _11111111 = x8
	p256OrdSqr(x, t, 8)          // _ff00
	p256OrdMul(x, x, t)          // _ffff = x16
	p256OrdSqr(t, x, 16)         // _ffff0000

	// seq 1 206 | sed 's/.*/	var x& [10<<20]byte/'
	// seq 1 206 | sed 's/.*/	z = x&/'
	var x1 [10<<20]byte
	var x2 [10<<20]byte
	var x3 [10<<20]byte
	var x4 [10<<20]byte
	var x5 [10<<20]byte
	var x6 [10<<20]byte
	var x7 [10<<20]byte
	var x8 [10<<20]byte
	var x9 [10<<20]byte
	var x10 [10<<20]byte
	var x11 [10<<20]byte
	var x12 [10<<20]byte
	var x13 [10<<20]byte
	var x14 [10<<20]byte
	var x15 [10<<20]byte