ni,??o&jodsnd,tp&az,oh,??p&i&-on,fles,?o&hbew,tksedeerf,?tf&e&moh,vres,?ym,??r&e&gatop,ppepteews,su-xunil-a-si,?gmtrec,vdmac,?s&a&ila&nyd,snd,?nymsd,?b&alfmw,bevres,?d&ikcet.3s,ylimaf,?eirfotatophcuoc,j,koob-daer,ltbup,nd&-won,deerf,emoh,golb,kcud,mood,nyd:.&emoh,og,?,ps,rvd,tog,uolc,?s&a-skcik,ndd,?tnemhcattaomb,u,?t&ce&jorparodef.&duolc,gts.so.ppa,so.ppa,?riderbew,?e&ews-yrev-si,nretni&ehtfodne,fodne,??hgink-a-si,oi-allizom,s&ixetn&od,seod,?o&h-emag,l-si,?rifyam,??ue:.&a&-q,c,?cm,dc,e&b,d,e,i,...

ni,??o&jodsnd,tp&az,oh,??p&i&-on,fles,?o&hbew,tksedeerf,?tf&e&moh,vres,?ym,??r&e&gatop,ppepteews,su-xunil-a-si,?gmtrec,vdmac,?s&a&ila&nyd,snd,?nymsd,?b&alfmw,bevres,?d&ikcet.3s,ylimaf,?eirfotatophcuoc,j,koob-daer,ltbup,nd&-won,deerf,emoh,golb,kcud,mood,nyd:.&emoh,og,?,ps,rvd,tog,uolc,?s&a-skcik,ndd,?tnemhcattaomb,u,?t&ce&jorparodef.&duolc,gts.so.ppa,so.ppa,?riderbew,?e&ews-yrev-si,nretni&ehtfodne,fodne,??hgink-a-si,oi-allizom,s&ixetn&od,seod,?o&h-emag,l-si,?rifyam,??ue:.&a&-q,c,?cm,dc,e&b,d,e,i,...

TEXT ·p256PointAddAffineAsm(SB), NOSPLIT, $16-48
	MOVD res+0(FP), P3ptr
	MOVD in1+8(FP), P1ptr
	MOVD in2+16(FP), P2ptr

	MOVD $p256mul<>+0x00(SB), CPOOL

	MOVD $16, R16
	MOVD $32, R17
	MOVD $48, R18
	MOVD $64, R19
	MOVD $80, R20
	MOVD $96, R21
	MOVD $112, R22
	MOVD $128, R23
	MOVD $144, R24
	MOVD $160, R25
	MOVD $104, R26 // offset of sign+24(FP)

	MOVD	$9, R12
	B	runtime·callbackasm1(SB)
	MOVD	$10, R12
	B	runtime·callbackasm1(SB)
	MOVD	$11, R12
	B	runtime·callbackasm1(SB)
	MOVD	$12, R12
	B	runtime·callbackasm1(SB)
	MOVD	$13, R12
	B	runtime·callbackasm1(SB)
	MOVD	$14, R12
	B	runtime·callbackasm1(SB)
	MOVD	$15, R12
	B	runtime·callbackasm1(SB)
	MOVD	$16, R12
	B	runtime·callbackasm1(SB)
	MOVD	$17, R12
	B	runtime·callbackasm1(SB)
	MOVD	$18, R12

	MOVD	$0x11110000, R1               // MOVD	$286326784, R1              // 2122a2d2
	MOVD	$0xaaaa0000aaaa1111, R1       // MOVD	$-6149102338357718767, R1   // 212282d24155b5f24155f5f2
	MOVD	$0x1111ffff1111aaaa, R1       // MOVD	$1230045644216969898, R1    // a1aa8a922122a2f22122e2f2
	MOVD	$0, R1                        // e1031faa
	MOVD	$-1, R1                       // 01008092

TEXT asmtest(SB),DUPOK|NOSPLIT,$0
	// move constants
	MOVD $1, R3                     // 38600001
	MOVD $-1, R4                    // 3880ffff
	MOVD $65535, R5                 // 6005ffff
	MOVD $65536, R6                 // 3cc00001
	MOVD $-32767, R5                // 38a08001
	MOVD $-32768, R6                // 38c08000
	MOVD $1234567, R5               // 6405001260a5d687 or 0600001238a0d687

#define CAR1M V25

#define MK0   V30
#define K0    V31
TEXT ·p256OrdMul<>(SB), NOSPLIT, $0
	MOVD res+0(FP), res_ptr
	MOVD in1+8(FP), x_ptr
	MOVD in2+16(FP), y_ptr

	VZERO T2
	MOVD  $p256ordK0<>+0x00(SB), R4

	// VLEF    $3, 0(R4), K0
	WORD $0xE7F40000
	BYTE $0x38
	BYTE $0x03
	MOVD $p256ord<>+0x00(SB), R4
	VL   16(R4), M0
	VL   0(R4), M1

	VL   (0*16)(x_ptr), X0

		{name: "DIVWU", argLength: 2, reg: gp21tmp, asm: "DIVWU", resultInArg0: true, clobberFlags: true}, // arg0 / arg1

		{name: "MODD", argLength: 2, reg: gp21tmp, asm: "MODD", resultInArg0: true, clobberFlags: true}, // arg0 % arg1
		{name: "MODW", argLength: 2, reg: gp21tmp, asm: "MODW", resultInArg0: true, clobberFlags: true}, // arg0 % arg1

		// for these instructions on power8.

		// For sizes >= 64 generate a loop as follows:

		// Set up loop counter in CTR, used by BC
		//       XXLXOR VS32,VS32,VS32
		//	 MOVD len/32,REG_TMP
		//	 MOVD REG_TMP,CTR
		//       MOVD $16,REG_TMP
		//	 loop:
		//	 STXVD2X VS32,(R0)(R20)
		//	 STXVD2X VS32,(R31)(R20)
		//	 ADD  $32,R20
		//	 BC   16, 0, loop
		//

		mask := byte(int32(^t) >> 31)
		b := payload[len(payload)-1-i]
		good &^= mask&paddingLen ^ mask&b
	}

	// We AND together the bits of good and replicate the result across
	// all the bits.
	good &= good << 4
	good &= good << 2
	good &= good << 1
	good = uint8(int8(good) >> 7)

	// Zero the padding length on error. This ensures any unchecked bytes