ROUND1(DX,AX,BX,CX, 6,0x4787c62a,12);
	ROUND1(CX,DX,AX,BX, 7,0xa8304613,17);
	ROUND1(BX,CX,DX,AX, 8,0xfd469501,22);
	ROUND1(AX,BX,CX,DX, 9,0x698098d8, 7);
	ROUND1(DX,AX,BX,CX,10,0x8b44f7af,12);
	ROUND1(CX,DX,AX,BX,11,0xffff5bb1,17);
	ROUND1(BX,CX,DX,AX,12,0x895cd7be,22);
	ROUND1(AX,BX,CX,DX,13,0x6b901122, 7);
	ROUND1(DX,AX,BX,CX,14,0xfd987193,12);
	ROUND1(CX,DX,AX,BX,15,0xa679438e,17);

	MOVOU	X0, 80(DI)
	MOVOU	X0, 96(DI)
	MOVOU	X0, 112(DI)
	MOVOU	X0, -128(DI)(BX*1)
	MOVOU	X0, -112(DI)(BX*1)
	MOVOU	X0, -96(DI)(BX*1)
	MOVOU	X0, -80(DI)(BX*1)
	MOVOU	X0, -64(DI)(BX*1)
	MOVOU	X0, -48(DI)(BX*1)
	MOVOU	X0, -32(DI)(BX*1)
	MOVOU	X0, -16(DI)(BX*1)
	RET
nosse2:
	MOVL	BX, CX
	SHRL	$2, CX
	REP
	STOSL
	ANDL	$3, BX
	JNE	tail

	MULXQ 232(CX), R8, BX
	ADCXQ DI, R8
	ADOXQ 232(AX), R8
	MOVQ  R8, 232(AX)

	// Iteration 30
	MULXQ 240(CX), R8, DI
	ADCXQ BX, R8
	ADOXQ 240(AX), R8
	MOVQ  R8, 240(AX)

	// Iteration 31
	MULXQ 248(CX), R8, BX
	ADCXQ DI, R8
	ADOXQ 248(AX), R8
	MOVQ  R8, 248(AX)

	// Add back carry flags and return
	ADCXQ SI, BX
	ADOXQ SI, BX
	MOVQ  BX, c+24(FP)

	TESTL	BX, BX
	JEQ	move_0
	CMPL	BX, $2
	JBE	move_1or2
	CMPL	BX, $4
	JB	move_3
	JE	move_4
	CMPL	BX, $8
	JBE	move_5through8
	CMPL	BX, $16
	JBE	move_9through16
#ifdef GO386_softfloat
	JMP	nosse2
#endif
	CMPL	BX, $32
	JBE	move_17through32
	CMPL	BX, $64
	JBE	move_33through64
	CMPL	BX, $128
	JBE	move_65through128

nosse2:
/*

	ADCQ (BX), DX                           // 481313
	ADCQ (R11), DX                          // 491313
	ADCQ (BX), R11                          // 4c131b
	ADCQ (R11), R11                         // 4d131b
	ADCB (BX), DL                           // 1213
	ADCB (R11), DL                          // 411213
	ADCB (BX), R11                          // 44121b
	ADCB (R11), R11                         // 45121b

	MOVL x+12(FP), SI
	MOVL y+24(FP), BP
	MOVL r+28(FP), CX	// c = r
	MOVL z_len+4(FP), BX
	LEAL (DI)(BX*4), DI
	LEAL (SI)(BX*4), SI
	NEGL BX			// i = -n
	JMP E5

L5:	MOVL (SI)(BX*4), AX
	MULL BP
	ADDL CX, AX
	ADCL $0, DX
	MOVL AX, (DI)(BX*4)
	MOVL DX, CX
	ADDL $1, BX		// i++

E5:	CMPL BX, $0		// i < 0
	JL L5

	MOVL CX, c+32(FP)
	RET

	MOVOU	X15, -16(DI)(BX*1)
	RET
_129through256:
	MOVOU	X15, (DI)
	MOVOU	X15, 16(DI)
	MOVOU	X15, 32(DI)
	MOVOU	X15, 48(DI)
	MOVOU	X15, 64(DI)
	MOVOU	X15, 80(DI)
	MOVOU	X15, 96(DI)
	MOVOU	X15, 112(DI)
	MOVOU	X15, -128(DI)(BX*1)
	MOVOU	X15, -112(DI)(BX*1)
	MOVOU	X15, -96(DI)(BX*1)
	MOVOU	X15, -80(DI)(BX*1)
	MOVOU	X15, -64(DI)(BX*1)
	MOVOU	X15, -48(DI)(BX*1)
	MOVOU	X15, -32(DI)(BX*1)

TEXT ·StorepNoWB(SB), NOSPLIT, $0-16
	MOVQ	ptr+0(FP), BX
	MOVQ	val+8(FP), AX
	XCHGQ	AX, 0(BX)
	RET

TEXT ·Store(SB), NOSPLIT, $0-12
	MOVQ	ptr+0(FP), BX
	MOVL	val+8(FP), AX
	XCHGL	AX, 0(BX)
	RET

TEXT ·Store8(SB), NOSPLIT, $0-9
	MOVQ	ptr+0(FP), BX
	MOVB	val+8(FP), AX
	XCHGB	AX, 0(BX)
	RET

TEXT ·Store64(SB), NOSPLIT, $0-16
	MOVQ	ptr+0(FP), BX
	MOVQ	val+8(FP), AX
	XCHGQ	AX, 0(BX)
	RET

	MOVL	c, R9; \
	ADDL	b, a

	ROUND1(AX,BX,CX,DX, 1,0xd76aa478, 7);
	ROUND1(DX,AX,BX,CX, 2,0xe8c7b756,12);
	ROUND1(CX,DX,AX,BX, 3,0x242070db,17);
	ROUND1(BX,CX,DX,AX, 4,0xc1bdceee,22);
	ROUND1(AX,BX,CX,DX, 5,0xf57c0faf, 7);
	ROUND1(DX,AX,BX,CX, 6,0x4787c62a,12);
	ROUND1(CX,DX,AX,BX, 7,0xa8304613,17);
	ROUND1(BX,CX,DX,AX, 8,0xfd469501,22);
	ROUND1(AX,BX,CX,DX, 9,0x698098d8, 7);
	ROUND1(DX,AX,BX,CX,10,0x8b44f7af,12);

	MULQ   16(BX)
	ADDQ   AX, DI
	ADCQ   DX, SI

	// r0 += 19×a4×b1
	MOVQ   32(CX), AX
	IMUL3Q $0x13, AX, AX
	MULQ   8(BX)
	ADDQ   AX, DI
	ADCQ   DX, SI

	// r1 = a0×b1
	MOVQ (CX), AX
	MULQ 8(BX)
	MOVQ AX, R9
	MOVQ DX, R8

	// r1 += a1×b0
	MOVQ 8(CX), AX
	MULQ (BX)
	ADDQ AX, R9
	ADCQ DX, R8

	// r1 += 19×a2×b4
	MOVQ   16(CX), AX
	IMUL3Q $0x13, AX, AX
	MULQ   32(BX)
	ADDQ   AX, R9