XXLXOR          V2, V16, V2; \
	XXLXOR          V3, V17, V3; \
	XXLXOR          V4, V18, V4

// Store output block from V1-V8
// in big endian order and
// Update blk_out by 128
#define STORE_OUTPUT_BLOCK128(blk_out) \
	P8_STXVB16X(V1,blk_out,R0); \
	P8_STXVB16X(V2,blk_out,R16); \
	P8_STXVB16X(V3,blk_out,R17); \
	P8_STXVB16X(V4,blk_out,R18); \
	P8_STXVB16X(V5,blk_out,R19); \
	P8_STXVB16X(V6,blk_out,R20); \