vaddrelu/vsubrelu

功能说明

以block(32Byte)为单位完成以下计算，一次完成8个block的计算。

[dst] = ReLU([src0] + [src1])

函数原型

void vaddrelu(__ubuf__ half *dst, __ubuf__ half *src0, __ubuf__ half *src1, uint8_t repeat, uint8_t dstBlockStride, uint8_t src0BlockStride, uint8_t src1BlockStride, uint8_t dstRepeatStride, uint8_t src0RepeatStride, uint8_t src1RepeatStride); 
 
void vaddrelu(__ubuf__ float *dst, __ubuf__ float *src0, __ubuf__ float *src1, uint8_t repeat, uint8_t dstBlockStride, uint8_t src0BlockStride, uint8_t src1BlockStride, uint8_t dstRepeatStride, uint8_t src0RepeatStride, uint8_t src1RepeatStride); 
 
void vaddrelu(__ubuf__ int16_t *dst, __ubuf__ int16_t *src0, __ubuf__ int16_t *src1, uint8_t repeat, uint8_t dstBlockStride, uint8_t src0BlockStride, uint8_t src1BlockStride, uint8_t dstRepeatStride, uint8_t src0RepeatStride, uint8_t src1RepeatStride);

// vsubrelu 
void vsubrelu(__ubuf__ half *dst, __ubuf__ half *src0, __ubuf__ half *src1, uint8_t repeat, uint8_t dstBlockStride, uint8_t src0BlockStride, uint8_t src1BlockStride, uint8_t dstRepeatStride, uint8_t src0RepeatStride, uint8_t src1RepeatStride); 
 
void vsubrelu(__ubuf__ float *dst, __ubuf__ float *src0, __ubuf__ float *src1, uint8_t repeat, uint8_t dstBlockStride, uint8_t src0BlockStride, uint8_t src1BlockStride, uint8_t dstRepeatStride, uint8_t src0RepeatStride, uint8_t src1RepeatStride); 
 
void vsubrelu(__ubuf__ int16_t *dst, __ubuf__ int16_t *src0, __ubuf__ int16_t *src1, uint8_t repeat, uint8_t dstBlockStride, uint8_t src0BlockStride, uint8_t src1BlockStride, uint8_t dstRepeatStride, uint8_t src0RepeatStride, uint8_t src1RepeatStride);

流水类型

PIPE_V