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。
    - **params** - 参数打包成数组：
        - **input0_dims** - input0的维度信息数组（int*）。
        - **input1_dims** - input1的维度信息数组（int*）。
        - **output_dims** - output的维度信息数组（int*）。
        - **strides0** - input0的步长数组（int*）。
        - **strides1** - input1的步长数组（int*）。
        - **strides_output** - output的步长数组（int*）。
        - **num_dims** - 维度数（int）。
    - **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_square_difference_s(int8_t* input0, int8_t* input1, int8_t* output, long long *params, int core_mask)
.. c:function:: void i16_square_difference_s(int16_t* input0, int16_t* input1, int16_t* output, long long *params, int core_mask)
.. c:function:: void i32_square_difference_s(int32_t* input0, int32_t* input1, int32_t* output, long long *params, int core_mask)
.. c:function:: void hp_square_difference_s(half* input0, half* input1, half* output, long long *params, int core_mask)
.. c:function:: void fp_square_difference_s(float* input0, float* input1, float* output, long long *params, int core_mask)
.. c:function:: void dp_square_difference_s(double* input0, double* input1, double* output, long long *params, int core_mask)
.. c:function:: void c64_square_difference_s(float* input0, float* input1, float* output, long long *params, int core_mask)
.. c:function:: void c128_square_difference_s(double* input0, double* input1, double* output, long long *params, int core_mask)

**C调用示例：**

.. code-block:: c
    :linenos:
    :emphasize-lines: 45

    //FT78NE示例
    #include <stdio.h>
    #include <squaredifference.h>

    int main(int argc, char* argv[]) {
        float* input0 = (float*)0x81000000;
        float* input1 = (float*)0x82001000;
        float* output = (float*)0x83002000;
        float* check = (float*)0x84003000;
        int *strides0 = (int*)0x85004000;
        int *strides1 = (int*)0x86005300;
        int *strides_output = (int*)0x87006000;

        // same shape
        int input0_dims[] = {4, 8, 16};  // 2x2
        int input1_dims[] = {4, 8, 16};  // 2x2
        int output_dims[] = {4, 8, 16};      // 2x2
        int num_dims = 3;
        
        unsigned long long params[9];
        params[0] = (unsigned long long)input0_dims;
        params[1] = (unsigned long long)input1_dims;
        params[2] = (unsigned long long)output_dims;
        params[3] = (unsigned long long)strides0;
        params[4] = (unsigned long long)strides1;
        params[5] = (unsigned long long)strides_output;
        params[6] = (unsigned long long)num_dims;
        
        int total_input0 = get_total_elements(num_dims, input0_dims);  
        int total_input1 = get_total_elements(num_dims, input1_dims);
        int total_output = get_total_elements(num_dims, output_dims);

        srand(time(0));

        int i;
        for (i = 0; i < total_input0; ++i) {
            input0[i] = (float)(rand() % 100) / 10.0f;
        }

        for (i = 0; i < total_input1; ++i) {
            input1[i] = (float)(rand() % 100) / 10.0f;
        }

        int core_mask = 0x0f;
        fp_square_difference_s(input0, input1, output, params, core_mask);
        return 0;
    }

**私有存储版本:**

.. c:function:: void i8_square_difference_p(int8_t* input0, int8_t* input1, int8_t* output, long long *params)
.. c:function:: void i16_square_difference_p(int16_t* input0, int16_t* input1, int16_t* output, long long *params)
.. c:function:: void i32_square_difference_p(int32_t* input0, int32_t* input1, int32_t* output, long long *params)
.. c:function:: void hp_square_difference_p(half* input0, half* input1, half* output, long long *params)
.. c:function:: void fp_square_difference_p(float* input0, float* input1, float* output, long long *params   )
.. c:function:: void dp_square_difference_p(double* input0, double* input1, double* output, long long *params)
.. c:function:: void c64_square_difference_p(float* input0, float* input1, float* output, long long *params)
.. c:function:: void c128_square_difference_p(double* input0, double* input1, double* output, long long *params)

**C调用示例：**

.. code-block:: c
    :linenos:
    :emphasize-lines: 44

    //FT04NE示例
    #include <stdio.h>
    #include <squaredifference.h>

    int main(int argc, char* argv[]) {
         float* input0 = (float*)0x10010000;
        float* input1 = (float*)0x10020000;
        float* output = (float*)0x10030000;
        float* check = (float*)0x10040000;
        int *strides0 = (int*)0x10050000;
        int *strides1 = (int*)0x10053000;
        int *strides_output = (int*)0x10056000;

        // same shape
        int input0_dims[] = {4, 8, 16};  // 2x2
        int input1_dims[] = {4, 8, 16};  // 2x2
        int output_dims[] = {4, 8, 16};      // 2x2
        int num_dims = 3;
        
        unsigned long long params[9];
        params[0] = (unsigned long long)input0_dims;
        params[1] = (unsigned long long)input1_dims;
        params[2] = (unsigned long long)output_dims;
        params[3] = (unsigned long long)strides0;
        params[4] = (unsigned long long)strides1;
        params[5] = (unsigned long long)strides_output;
        params[6] = (unsigned long long)num_dims;
        
        int total_input0 = get_total_elements(num_dims, input0_dims);  
        int total_input1 = get_total_elements(num_dims, input1_dims);
        int total_output = get_total_elements(num_dims, output_dims);

        srand(time(0));

        int i;
        for (i = 0; i < total_input0; ++i) {
            input0[i] = (float)(rand() % 100) / 10.0f;
        }

        for (i = 0; i < total_input1; ++i) {
            input1[i] = (float)(rand() % 100) / 10.0f;
        }

        fp_square_difference_p(input0, input1, output, params);
        return 0;
    }

