SHA512ROUND(V4, V2, V0, V1, V3, V23, V27, V15, V16, V14, V19, V12)
	SHA512ROUND(V1, V4, V3, V0, V2, V24, V28, V16, V17, V15, V12, V13)

	SHA512ROUND(V0, V1, V2, V3, V4, V25, V29, V17, V18, V16, V13, V14)
	SHA512ROUND(V3, V0, V4, V2, V1, V26, V30, V18, V19, V17, V14, V15)
	SHA512ROUND(V2, V3, V1, V4, V0, V27, V31, V19, V12, V18, V15, V16)
	SHA512ROUND(V4, V2, V0, V1, V3, V28, V24, V12, V13, V19, V16, V17)

	// Load CNT, NONCE into V19
	LXVW4X (CNT)(R0), VS51

	// Clear V27
	VXOR V27, V27, V27

	// V28
	LXVW4X (CONSTBASE)(R11), VS60

	// Load mask constants for VPERMXOR
	LXVW4X (MASK)(R0), V20
	LXVW4X (MASK)(R20), V21

	// splat slot from V19 -> V26
	VSPLTW $0, V19, V26

	VSLDOI $4, V19, V27, V19
	VSLDOI $12, V27, V19, V19

	VADDUWM V26, V28, V26

	MOVD $10, R14
	MOVD R14, CTR

    T26 v26, T27 v27) {
  return internal::ValueArray27<T1, T2, T3, T4, T5, T6, T7, T8, T9, T10, T11,
      T12, T13, T14, T15, T16, T17, T18, T19, T20, T21, T22, T23, T24, T25,
      T26, T27>(v1, v2, v3, v4, v5, v6, v7, v8, v9, v10, v11, v12, v13, v14,
      v15, v16, v17, v18, v19, v20, v21, v22, v23, v24, v25, v26, v27);
}

      T26 v26, T27 v27) : v1_(v1), v2_(v2), v3_(v3), v4_(v4), v5_(v5), v6_(v6),
      v7_(v7), v8_(v8), v9_(v9), v10_(v10), v11_(v11), v12_(v12), v13_(v13),
      v14_(v14), v15_(v15), v16_(v16), v17_(v17), v18_(v18), v19_(v19),
      v20_(v20), v21_(v21), v22_(v22), v23_(v23), v24_(v24), v25_(v25),
      v26_(v26), v27_(v27) {}

  template <typename T>

	VLD1	(R0), [V0.S4, V1.S4]                       // load h(a,b,c,d,e,f,g,h)
	VLD1.P	64(R2), [V16.S4, V17.S4, V18.S4, V19.S4]
	VLD1.P	64(R2), [V20.S4, V21.S4, V22.S4, V23.S4]
	VLD1.P	64(R2), [V24.S4, V25.S4, V26.S4, V27.S4]
	VLD1	(R2), [V28.S4, V29.S4, V30.S4, V31.S4]     //load 64*4bytes K constant(K0-K63)

blockloop:

	VLD1.P	16(R1), [V4.B16]                            // load 16bytes message

#undef SEL2
#undef CAR1
#undef CAR2
#undef RED1
#undef RED2
#undef PL
#undef PH

// ---------------------------------------
// p256MulInternal
// V0-V3 V30,V31 - Not Modified
// V4-V15 V27-V29 - Volatile

#define CPOOL   R7

// Parameters
#define X0    V0 // Not modified
#define X1    V1 // Not modified
#define Y0    V2 // Not modified
#define Y1    V3 // Not modified

#define VCIPHER_1X9_KEYS(vin) \
	XXLOR VS1, VS1, V23; \
	XXLOR VS2, VS2, V24; \
	XXLOR VS3, VS3, V25; \
	XXLOR VS4, VS4, V26; \
	XXLOR VS5, VS5, V27; \
	VCIPHER vin, V23, vin; \
	VCIPHER vin, V24, vin; \
	VCIPHER vin, V25, vin; \
	VCIPHER vin, V26, vin; \
	VCIPHER vin, V27, vin; \
	XXLOR VS6, VS6, V23; \
	XXLOR VS7, VS7, V24; \
	XXLOR VS8, VS8, V25; \
	XXLOR VS9, VS9, V26; \
	VCIPHER vin, V23, vin; \

#define R_x0e0	R24
#define R_x0f0	R28
#define R_x100	R29
#define R_x110	R27


// V0-V7 are A-H
// V8-V23 are used for the message schedule
#define KI	V24
#define FUNC	V25
#define S0	V26
#define S1	V27
#define s0	V28
#define s1	V29
#define LEMASK	V31	// Permutation control register for little endian

// VPERM is needed on LE to switch the bytes

#ifdef GOARCH_ppc64le

#define R_x0e0	R24
#define R_x0f0	R25
#define R_x100	R26
#define R_x110	R27


// V0-V7 are A-H
// V8-V23 are used for the message schedule
#define KI	V24
#define FUNC	V25
#define S0	V26
#define S1	V27
#define s0	V28
#define s1	V29
#define LEMASK	V31 // Permutation control register for little endian

// 4 copies of each Kt, to fill all 4 words of a vector register
DATA  ·kcon+0x000(SB)/8, $0x428a2f98428a2f98

#define off16	R16
#define off32	R17
#define off48	R18
#define off64	R19
#define off80	R20
#define off96	R21
#define	off112	R22

#define const1	V24
#define const2	V25

#define byteswap	V26
#define mask_32bit	V27
#define mask_64bit	V28
#define zeroes		V29

#define MAX_SIZE	32*1024
#define REFLECT

TEXT ·ppc64SlicingUpdateBy8(SB), NOSPLIT|NOFRAME, $0-44
	MOVWZ	crc+0(FP), R3   // incoming crc