SHA512ROUND0(7, X11, X12, X13, X14, X15, X16, X17, X10)
	SHA512ROUND0(8, X10, X11, X12, X13, X14, X15, X16, X17)
	SHA512ROUND0(9, X17, X10, X11, X12, X13, X14, X15, X16)
	SHA512ROUND0(10, X16, X17, X10, X11, X12, X13, X14, X15)
	SHA512ROUND0(11, X15, X16, X17, X10, X11, X12, X13, X14)
	SHA512ROUND0(12, X14, X15, X16, X17, X10, X11, X12, X13)
	SHA512ROUND0(13, X13, X14, X15, X16, X17, X10, X11, X12)

check32:
	// X6 contains $32
	BLT	X5, X6, compare16
compare32:
	MOV	0(X10), X15
	MOV	0(X12), X16
	MOV	8(X10), X17
	MOV	8(X12), X18
	BNE	X15, X16, cmp8a
	BNE	X17, X18, cmp8b
	MOV	16(X10), X15
	MOV	16(X12), X16
	MOV	24(X10), X17
	MOV	24(X12), X18
	BNE	X15, X16, cmp8a
	BNE	X17, X18, cmp8b
	ADD	$32, X10
	ADD	$32, X12
	SUB	$32, X5
	BGE	X5, X6, compare32
	BEQZ	X5, cmp_len

check16:
	MOV	$16, X6

	MOV	$64, X9
	BLT	X12, X9, f_loop32_check
f_loop64:
	MOV	0(X11), X14
	MOV	8(X11), X15
	MOV	16(X11), X16
	MOV	24(X11), X17
	MOV	32(X11), X18
	MOV	40(X11), X19
	MOV	48(X11), X20
	MOV	56(X11), X21
	MOV	X14, 0(X10)
	MOV	X15, 8(X10)
	MOV	X16, 16(X10)
	MOV	X17, 24(X10)
	MOV	X18, 32(X10)
	MOV	X19, 40(X10)
	MOV	X20, 48(X10)
	MOV	X21, 56(X10)
	ADD	$64, X10
	ADD	$64, X11
	SUB	$64, X12

	VRSQRT28SD (DX), X6, K1, X17                       // 62e2cd09cd0a or 62e2cd29cd0a or 62e2cd49cd0a
	VRSQRT28SD X8, X1, K1, X17                         // 62c2f509cdc8 or 62c2f529cdc8 or 62c2f549cdc8
	VRSQRT28SD X6, X1, K1, X17                         // 62e2f509cdce or 62e2f529cdce or 62e2f549cdce
	VRSQRT28SD X0, X1, K1, X17                         // 62e2f509cdc8 or 62e2f529cdc8 or 62e2f549cdc8

	VPCONFLICTD (BP), K6, X6                           // 62f27d0ec47500
	VPCONFLICTD X6, K6, X17                            // 62e27d0ec4ce
	VPCONFLICTD X1, K6, X17                            // 62e27d0ec4c9
	VPCONFLICTD X8, K6, X17                            // 62c27d0ec4c8
	VPCONFLICTD 15(R8), K6, X17                        // 62c27d0ec4880f000000
	VPCONFLICTD (BP), K6, X17                          // 62e27d0ec44d00

	ADD	X15, X22, X15	// z_hi[2] = x[2] * y + z[2]
	ADD	X21, X29, X16	// z_lo[2] = x[2] * y + z[2] + c
	SLTU	X21, X16, X22
	ADD	X15, X22, X29	// next c

	MULHU	X17, X6, X18	// z_hi[3] = x[3] * y
	MUL	X17, X6, X17	// z_lo[3] = x[3] * y
	ADD	X17, X19, X21	// z_lo[3] = x[3] * y + z[3]
	SLTU	X17, X21, X22
	ADD	X18, X22, X18	// z_hi[3] = x[3] * y + z[3]
	ADD	X21, X29, X19	// z_lo[3] = x[3] * y + z[3] + c
	SLTU	X21, X19, X22
	ADD	X18, X22, X29	// next c

loop32:
	MOV	0(X10), X19
	MOV	0(X11), X20
	MOV	8(X10), X21
	MOV	8(X11), X22
	BNE	X19, X20, not_eq
	BNE	X21, X22, not_eq
	MOV	16(X10), X14
	MOV	16(X11), X15
	MOV	24(X10), X16
	MOV	24(X11), X17
	BNE	X14, X15, not_eq
	BNE	X16, X17, not_eq
	ADD	$32, X10
	ADD	$32, X11
	SUB	$32, X12
	BGE	X12, X9, loop32
	BEQZ	X12, eq

loop16_check:
	MOV	$16, X23
	BLT	X12, X23, loop4_check
loop16:
	MOV	0(X10), X19

	var x10, x11, x12, x13, x14, x15, x16, x17, x18, x19 int
	var x20, x21, x22, x23, x24, x25, x26, x27, x28, x29 int
	var x30, x31, x32 int

	_ = x00
	_ = x01
	_ = x02
	_ = x03
	_ = x04
	_ = x05
	_ = x06
	_ = x07
	_ = x08
	_ = x09

	_ = x10
	_ = x11
	_ = x12
	_ = x13
	_ = x14
	_ = x15
	_ = x16
	_ = x17
	_ = x18
	_ = x19

	_ = x20
	_ = x21
	_ = x22

	{"d1884e711701ad81abe0c77a3b0ea12e19ba9af64077286c72fc602d", "abcdefg", "sha\x02\xc1\x05\x9e\xd86|\xd5\a0p\xdd\x17\xf7\x0eY9\xff\xc0\v1...

	//	_110    = 2*_11
	//	_111    = 1 + _110
	//	_111000 = _111 << 3
	//	_111111 = _111 + _111000
	//	x12     = _111111 << 6 + _111111
	//	x14     = x12 << 2 + _11
	//	x17     = x14 << 3 + _111
	//	x31     = x17 << 14 + x14
	//	x48     = x31 << 17 + x17
	//	x96     = x48 << 48 + x48
	//	x127    = x96 << 31 + x31
	//	return    x127 << 97 + x96
	//

	var z = new(P224Element).Set(e)
	var t0 = new(P224Element)