MUL	X8, X6, X8	// z_lo[0] = x[0] * y
	ADD	X8, X10, X21	// z_lo[0] = x[0] * y + z[0]
	SLTU	X8, X21, X22
	ADD	X9, X22, X9	// z_hi[0] = x[0] * y + z[0]
	ADD	X21, X29, X10	// z_lo[0] = x[0] * y + z[0] + c
	SLTU	X21, X10, X22
	ADD	X9, X22, X29	// next c

	MULHU	X11, X6, X12	// z_hi[1] = x[1] * y
	MUL	X11, X6, X11	// z_lo[1] = x[1] * y
	ADD	X11, X13, X21	// z_lo[1] = x[1] * y + z[1]
	SLTU	X11, X21, X22
	ADD	X12, X22, X12	// z_hi[1] = x[1] * y + z[1]

	VPCLMULQDQ $127, X22, X21, X15                     // 6233550044fe7f or 6233d50044fe7f
	VPCLMULQDQ $127, X7, X21, X15                      // 6273550044ff7f or 6273d50044ff7f
	VPCLMULQDQ $127, X19, X21, X15                     // 6233550044fb7f or 6233d50044fb7f
	VPCLMULQDQ $127, -17(BP)(SI*8), X21, X15           // 6273550044bcf5efffffff7f or 6273d50044bcf5efffffff7f

loop16:
	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
	ADD	$16, X10
	ADD	$16, X11
	SUB	$16, X12
	BGE	X12, X23, loop16
	BEQZ	X12, eq

loop4_check:
	MOV	$4, X23
	BLT	X12, X23, loop1
loop4:
	MOVBU	0(X10), X19
	MOVBU	0(X11), X20
	MOVBU	1(X10), X21
	MOVBU	1(X11), X22
	BNE	X19, X20, not_eq
	BNE	X21, X22, not_eq
	MOVBU	2(X10), X14

	VPMADD52HUQ X7, X11, K1, X21                       // 62e2a509b5ef
	VPMADD52HUQ X0, X11, K1, X21                       // 62e2a509b5e8
	VPMADD52HUQ 17(SP)(BP*2), X11, K1, X21             // 62e2a509b5ac6c11000000
	VPMADD52HUQ -7(DI)(R8*4), X11, K1, X21             // 62a2a509b5ac87f9ffffff
	VPMADD52HUQ X7, X31, K1, X21                       // 62e28501b5ef
	VPMADD52HUQ X0, X31, K1, X21                       // 62e28501b5e8

TEXT	asancall<>(SB), NOSPLIT, $0-0
	MOV	X2, X8		// callee-saved
	BEQZ	g, g0stack	// no g, still on a system stack
	MOV	g_m(g), X21
	MOV	m_g0(X21), X21
	BEQ	X21, g, g0stack

	MOV	(g_sched+gobuf_sp)(X21), X2

g0stack:
	JALR	RA, X14
	MOV	X8, X2

	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
	BGE	X12, X9, f_loop64
	BEQZ	X12, done

f_loop32_check:
	MOV	$32, X9

	V4FNMADDSS (R15), [X11-X14], K4, X11               // 6252270cab1f or 6252272cab1f or 6252274cab1f
	V4FNMADDSS -17(BP)(SI*8), [X21-X24], K4, X11       // 62725704ab9cf5efffffff or 62725724ab9cf5efffffff or 62725744ab9cf5efffffff
	V4FNMADDSS (R15), [X21-X24], K4, X11               // 62525704ab1f or 62525724ab1f or 62525744ab1f

	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
	_ = x23
	_ = x24
	_ = x25

	VGF2P8AFFINEQB $82, X22, X21, K1, X15              // 6233d501cefe52
	VGF2P8AFFINEQB $82, X7, X21, K1, X15               // 6273d501ceff52
	VGF2P8AFFINEQB $82, X19, X21, K1, X15              // 6233d501cefb52
	VGF2P8AFFINEQB $82, 17(SP)(BP*2), X21, K1, X15     // 6273d501cebc6c1100000052
	VGF2P8AFFINEQB $82, -7(DI)(R8*4), X21, K1, X15     // 6233d501cebc87f9ffffff52

	VAESDECLAST 15(DX)(BX*4), X31, X9                  // 62720500df8c9a0f000000 or 62728500df8c9a0f000000
	VAESDECLAST X21, X3, X9                            // 62326508dfcd or 6232e508dfcd
	VAESDECLAST X21, X5, X7                            // 62b25508dffd or 62b2d508dffd
	VAESDECLAST X21, X31, X7                           // 62b20500dffd or 62b28500dffd
	VAESDECLAST X1, X31, X7                            // 62f20500dff9 or 62f28500dff9