vector_dup
功能说明
该指令用于复制数据:
对于b16类型:将16位数据最多复制16*8个元素,写入目的地址。
对于b32类型:将32位数据最多复制8*8个元素,写入目的地址。
接口原型
void vector_dup(__ubuf__ bfloat16_t *dst, bfloat16_t src, uint8_t repeat, uint16_t dstBlockStride, uint16_t srcBlockStride, uint16_t dstRepeatStride, uint16_t srcRepeatStride); void vector_dup(__ubuf__ float *dst, float src, uint8_t repeat, uint16_t dstBlockStride, uint16_t srcBlockStride, uint16_t dstRepeatStride, uint16_t srcRepeatStride); void vector_dup(__ubuf__ int32_t *dst, int32_t src, uint8_t repeat, uint16_t dstBlockStride, uint16_t srcBlockStride, uint16_t dstRepeatStride, uint16_t srcRepeatStride); void vector_dup(__ubuf__ uint16_t *dst, uint16_t src, uint8_t repeat, uint16_t dstBlockStride, uint16_t srcBlockStride, uint16_t dstRepeatStride, uint16_t srcRepeatStride); void vector_dup(__ubuf__ uint32_t *dst, uint32_t src, uint8_t repeat, uint16_t dstBlockStride, uint16_t srcBlockStride, uint16_t dstRepeatStride, uint16_t srcRepeatStride); void vector_dup(__ubuf__ int16_t *dst, int16_t src, uint8_t repeat, uint16_t dstBlockStride, uint16_t srcBlockStride, uint16_t dstRepeatStride, uint16_t srcRepeatStride); void vector_dup(__ubuf__ half *dst, half src, uint8_t repeat, uint16_t dstBlockStride, uint16_t srcBlockStride, uint16_t dstRepeatStride, uint16_t srcRepeatStride);
流水类型
PIPE_V
父主题: UB内搬移