MOVQ acc3, t1
	SHLQ $32, acc3
	MULQ p256const1<>(SB)
	SHRQ $32, t1
	ADDQ acc3, acc4
	ADCQ t1, acc5
	ADCQ AX, acc0
	ADCQ DX, acc1
	ADCQ $0, acc2
	// Copy result [255:0]
	MOVQ acc4, x_ptr
	MOVQ acc5, acc3
	MOVQ acc0, t0
	MOVQ acc1, t1
	// Subtract p256
	SUBQ $-1, acc4
	SBBQ p256const0<>(SB) ,acc5
	SBBQ $0, acc0
	SBBQ p256const1<>(SB), acc1
	SBBQ $0, acc2

	CMOVQCS x_ptr, acc4

#define x0 R19
#define x1 R20
#define x2 R21
#define x3 R22
#define y0 R23
#define y1 R24
#define y2 R25
#define y3 R26

#define const2 t2
#define const3 t3

DATA p256const0<>+0x00(SB)/8, $0x00000000ffffffff
DATA p256const1<>+0x00(SB)/8, $0xffffffff00000001
DATA p256ordK0<>+0x00(SB)/8, $0xccd1c8aaee00bc4f
DATA p256ord<>+0x00(SB)/8, $0xf3b9cac2fc632551
DATA p256ord<>+0x08(SB)/8, $0xbce6faada7179e84