90 lines
3.6 KiB
ReStructuredText
90 lines
3.6 KiB
ReStructuredText
Squaredifference
|
||
=================
|
||
|
||
逐元素计算两个输入数组对应元素的差的平方。
|
||
|
||
.. math::
|
||
|
||
\text{output}_i = (\text{input0}_i - \text{input1}_i)^2
|
||
|
||
对于输入 `input0` 和 `input1` 中对应位置的每个元素，计算它们差的平方值。
|
||
|
||
输入：
|
||
- **input0** - 第一个输入数据地址。
|
||
- **input1** - 第二个输入数据地址。
|
||
- **length** - 计算长度（对于复数类型，指复数的个数）。
|
||
- **core_mask** - 核掩码（仅共享存储版本需要）。
|
||
|
||
输出：
|
||
- **output** - 计算结果地址，其大小与输入相同。
|
||
|
||
支持平台：
|
||
``FT78NE``
|
||
``MT7004``
|
||
|
||
.. note::
|
||
- FT78NE 支持fp32, int8, int16, int32, fp64, cplx64, cplx128
|
||
- MT7004 支持fp16, fp32, int16, int32, cplx64
|
||
|
||
**共享存储版本:**
|
||
|
||
.. c:function:: void i8_squaredifference_s(int8_t* input0, int8_t* input1, int8_t* output, int length, int core_mask)
|
||
.. c:function:: void i16_squaredifference_s(int16_t* input0, int16_t* input1, int16_t* output, int length, int core_mask)
|
||
.. c:function:: void i32_squaredifference_s(int32_t* input0, int32_t* input1, int32_t* output, int length, int core_mask)
|
||
.. c:function:: void hp_squaredifference_s(half* input0, half* input1, half* output, int length, int core_mask)
|
||
.. c:function:: void fp_squaredifference_s(float* input0, float* input1, float* output, int length, int core_mask)
|
||
.. c:function:: void dp_squaredifference_s(double* input0, double* input1, double* output, int length, int core_mask)
|
||
.. c:function:: void c64_squaredifference_s(float* input0, float* input1, float* output, int length, int core_mask)
|
||
.. c:function:: void c128_squaredifference_s(double* input0, double* input1, double* output, int length, int core_mask)
|
||
|
||
**C调用示例：**
|
||
|
||
.. code-block:: c
|
||
:linenos:
|
||
:emphasize-lines: 11
|
||
|
||
//FT78NE示例
|
||
#include <stdio.h>
|
||
#include <squaredifference.h>
|
||
|
||
int main(int argc, char* argv[]) {
|
||
float *input0 = (float *)0xA0000000; // 第一个输入在DDR空间
|
||
float *input1 = (float *)0xA1000000; // 第二个输入在DDR空间
|
||
float *output = (float *)0xB0000000; // output
|
||
int length = 1000;
|
||
int core_mask = 0xff;
|
||
fp_squaredifference_s(input0, input1, output, length, core_mask);
|
||
return 0;
|
||
}
|
||
|
||
**私有存储版本:**
|
||
|
||
.. c:function:: void i8_squaredifference_p(int8_t* input0, int8_t* input1, int8_t* output, int length)
|
||
.. c:function:: void i16_squaredifference_p(int16_t* input0, int16_t* input1, int16_t* output, int length)
|
||
.. c:function:: void i32_squaredifference_p(int32_t* input0, int32_t* input1, int32_t* output, int length)
|
||
.. c:function:: void hp_squaredifference_p(half* input0, half* input1, half* output, int length)
|
||
.. c:function:: void fp_squaredifference_p(float* input0, float* input1, float* output, int length)
|
||
.. c:function:: void dp_squaredifference_p(double* input0, double* input1, double* output, int length)
|
||
.. c:function:: void c64_squaredifference_p(float* input0, float* input1, float* output, int length)
|
||
.. c:function:: void c128_squaredifference_p(double* input0, double* input1, double* output, int length)
|
||
|
||
**C调用示例：**
|
||
|
||
.. code-block:: c
|
||
:linenos:
|
||
:emphasize-lines: 10
|
||
|
||
//FT78NE示例
|
||
#include <stdio.h>
|
||
#include <squaredifference.h>
|
||
|
||
int main(int argc, char* argv[]) {
|
||
float *input0 = (float *)0x10000000; // 第一个输入在L2空间
|
||
float *input1 = (float *)0x10001000; // 第二个输入在L2空间
|
||
float *output = (float *)0x10002000; // output
|
||
int length = 1000;
|
||
fp_squaredifference_p(input0, input1, output, length);
|
||
return 0;
|
||
}
|
||
|