BGEU	X5, X6, 2(PC)				// 63f46200

	// 2.6: Load and Store Instructions
	LW	(X5), X6				// 03a30200
	LW	4(X5), X6				// 03a34200
	LWU	(X5), X6				// 03e30200
	LWU	4(X5), X6				// 03e34200
	LH	(X5), X6				// 03930200
	LH	4(X5), X6				// 03934200
	LHU	(X5), X6				// 03d30200
	LHU	4(X5), X6				// 03d34200
	LB	(X5), X6				// 03830200
	LB	4(X5), X6				// 03834200
	LBU	(X5), X6				// 03c30200

	VRSQRT28SD X8, X6, K1, X6                          // 62d2cd09cdf0 or 62d2cd29cdf0 or 62d2cd49cdf0
	VRSQRT28SD X6, X6, K1, X6                          // 62f2cd09cdf6 or 62f2cd29cdf6 or 62f2cd49cdf6
	VRSQRT28SD X0, X6, K1, X6                          // 62f2cd09cdf0 or 62f2cd29cdf0 or 62f2cd49cdf0

	VPCONFLICTD X6, K6, X6                             // 62f27d0ec4f6
	VPCONFLICTD X1, K6, X6                             // 62f27d0ec4f1
	VPCONFLICTD X8, K6, X6                             // 62d27d0ec4f0
	VPCONFLICTD 15(R8), K6, X6                         // 62d27d0ec4b00f000000
	VPCONFLICTD (BP), K6, X6                           // 62f27d0ec47500
	VPCONFLICTD X6, K6, X17                            // 62e27d0ec4ce

	VPDPBUSD X1, X28, K2, X6                           // 62f21d0250f1
	VPDPBUSD -15(R14)(R15*1), X28, K2, X6              // 62921d0250b43ef1ffffff
	VPDPBUSD -15(BX), X28, K2, X6                      // 62f21d0250b3f1ffffff
	VPDPBUSD X15, X8, K2, X6                           // 62d23d0a50f7
	VPDPBUSD X11, X8, K2, X6                           // 62d23d0a50f3

	JALR	RA, (X5)

	// Restore g, stack pointer. X10 is return value.
	MOV	0(X2), g
	CALL	runtime·save_g(SB)
	MOV	(g_stack+stack_hi)(g), X5
	MOV	8(X2), X6
	SUB	X6, X5, X6
	MOV	X6, X2

	MOVW	X10, ret+16(FP)
	RET

// func asminit()
TEXT runtime·asminit(SB),NOSPLIT|NOFRAME,$0-0
	RET

// reflectcall: call a function with the given argument list

	MOVOU	16(SI), X1
	MOVOU	32(SI), X2
	MOVOU	48(SI), X3
	MOVOU	-64(SI)(BX*1), X4
	MOVOU	-48(SI)(BX*1), X5
	MOVOU	-32(SI)(BX*1), X6
	MOVOU	-16(SI)(BX*1), X7
	MOVOU	X0, (DI)
	MOVOU	X1, 16(DI)
	MOVOU	X2, 32(DI)
	MOVOU	X3, 48(DI)
	MOVOU	X4, -64(DI)(BX*1)
	MOVOU	X5, -48(DI)(BX*1)
	MOVOU	X6, -32(DI)(BX*1)
	MOVOU	X7, -16(DI)(BX*1)
	RET
move_129through256:
	MOVOU	(SI), X0
	MOVOU	16(SI), X1
	MOVOU	32(SI), X2

	var x3 uint64
	var x4 uint64
	x3, x4 = bits.Add64(arg1[1], arg2[1], uint64(fiatScalarUint1(x2)))
	var x5 uint64
	var x6 uint64
	x5, x6 = bits.Add64(arg1[2], arg2[2], uint64(fiatScalarUint1(x4)))
	var x7 uint64
	var x8 uint64
	x7, x8 = bits.Add64(arg1[3], arg2[3], uint64(fiatScalarUint1(x6)))
	var x9 uint64
	var x10 uint64
	x9, x10 = bits.Sub64(x1, 0x5812631a5cf5d3ed, uint64(0x0))
	var x11 uint64
	var x12 uint64

			x0, x4, x8, x12 = quarterRound(x0, x4, x8, x12)
			x1, x5, x9, x13 = quarterRound(x1, x5, x9, x13)
			x2, x6, x10, x14 = quarterRound(x2, x6, x10, x14)
			x3, x7, x11, x15 = quarterRound(x3, x7, x11, x15)

			// Diagonal round.
			x0, x5, x10, x15 = quarterRound(x0, x5, x10, x15)
			x1, x6, x11, x12 = quarterRound(x1, x6, x11, x12)
			x2, x7, x8, x13 = quarterRound(x2, x7, x8, x13)
			x3, x4, x9, x14 = quarterRound(x3, x4, x9, x14)

	var x3 uint64
	var x4 uint64
	x3, x4 = bits.Add64(arg1[1], arg2[1], uint64(p256Uint1(x2)))
	var x5 uint64
	var x6 uint64
	x5, x6 = bits.Add64(arg1[2], arg2[2], uint64(p256Uint1(x4)))
	var x7 uint64
	var x8 uint64
	x7, x8 = bits.Add64(arg1[3], arg2[3], uint64(p256Uint1(x6)))
	var x9 uint64
	var x10 uint64
	x9, x10 = bits.Sub64(x1, 0xffffffffffffffff, uint64(0x0))
	var x11 uint64
	var x12 uint64

	var x3 uint64
	var x4 uint64
	x3, x4 = bits.Add64(arg1[1], arg2[1], uint64(p224Uint1(x2)))
	var x5 uint64
	var x6 uint64
	x5, x6 = bits.Add64(arg1[2], arg2[2], uint64(p224Uint1(x4)))
	var x7 uint64
	var x8 uint64
	x7, x8 = bits.Add64(arg1[3], arg2[3], uint64(p224Uint1(x6)))
	var x9 uint64
	var x10 uint64
	x9, x10 = bits.Sub64(x1, uint64(0x1), uint64(0x0))
	var x11 uint64
	var x12 uint64