Less
=================

逐元素计算第一个输入 (Input0) 的元素是否小于第二个输入 (Input1) 的对应元素。该算子支持广播机制。

.. math::

    output_i = \begin{cases}
    \text{True}, & \text{if } Input0_0 < Input1_i \text{ (Input0 is broadcasted)} \\
    \text{True}, & \text{if } Input0_i < Input1_0 \text{ (Input1 is broadcasted)} \\
    \text{True}, & \text{if } Input0_i < Input1_i \text{ (No broadcast)} \\
    \text{False}, & \text{otherwise}
    \end{cases}

输入：
    - **Input0** - 第一个输入数据地址。
    - **Input1** - 第二个输入数据地址。
    - **params** - 其他参数打包成数组：
        - **input0_dims** - input0 的维度。
        - **input1_dims** - input1的维度。
        - **output_dims** - output的维度。
        - **strides0** - Input0 的步长，大小为8*sizeof(int)
        - **strides1** - Input1 的步长，大小为8*sizeof(int)
        - **strides_output** - Output 的步长，大小为8*sizeof(int)
        - **num_dims** - 维度数量。
    - **core_mask** - 核掩码（仅共享存储版本需要）。

输出：
    - **Output** - 计算结果地址。

支持平台：
    ``FT78NE``
    ``MT7004``

.. note::
    - FT78NE 支持int8, int16, int32, fp32, fp64
    - MT7004 支持fp16, fp32, int16, int32

**共享存储版本:**

.. c:function:: void i8_less_s(int8_t* Input0, int8_t* Input1, bool* output, long long *params, int core_mask)
.. c:function:: void i16_less_s(int16_t* Input0, int16_t* Input1, bool* output, long long *params, int core_mask)
.. c:function:: void i32_less_s(int32_t* Input0, int32_t* Input1, bool* output, long long *params, int core_mask)
.. c:function:: void hp_less_s(half* Input0, half* Input1, bool* output, long long *params, int core_mask)
.. c:function:: void fp_less_s(float* Input0, float* Input1, bool* output, long long *params, int core_mask)
.. c:function:: void dp_less_s(double* Input0, double* Input1, bool* output, long long *params, int core_mask)

**C调用示例：**

.. code-block:: c
    :linenos:
    :emphasize-lines: 46

    //FT78NE示例
    #include <stdio.h>
    #include <less.h> // 假设头文件名为 less.h
    int main(int argc, char* argv[]) {
        float *input0 = (float *)0x81000000;
        float *input1 = (float *)0x82000000;
        bool *output = (bool *)0x83000000;
        int *strides0 = (int*)0x84000000;
        int *strides1 = (int*)0x85000000;
        int *strides_output = (int*)0x86000000;

        int i = 0;

        srand(seed++);

        float f_min = -100.0;
        float f_max = 100.0;

        // same shape
        int input0_dims[] = {4, 8, 17};  // 2x2
        int input1_dims[] = {4, 8, 17};  // 2x2
        int output_dims[] = {4, 8, 17};      // 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);
        
        for(i = 0;i < total_input0;++i) {
            input0[i] = f_min + ((float)rand() / (float)RAND_MAX) * (f_max - f_min);
        }

        for(i = 0;i < total_input1;++i) {
            input1[i] = f_min + ((float)rand() / (float)RAND_MAX) * (f_max - f_min);
        }
        int core_mask = 0b1111;
        fp_less_s(input0, input1, output, params, core_mask);//调用汇编
        return 0;
    }

**私有存储版本:**

.. c:function:: void i8_less_p(int8_t* Input0, int8_t* Input1, bool* output, long long *params)
.. c:function:: void i16_less_p(int16_t* Input0, int16_t* Input1, bool* output, long long *params)
.. c:function:: void i32_less_p(int32_t* Input0, int32_t* Input1, bool* output, long long *params)
.. c:function:: void hp_less_p(half* Input0, half* Input1, bool* output, long long *params)
.. c:function:: void fp_less_p(float* Input0, float* Input1, bool* output, long long *params)
.. c:function:: void dp_less_p(double* Input0, double* Input1, bool* output, long long *params)

    
**C调用示例：**

.. code-block:: c
    :linenos:
    :emphasize-lines: 46

    //FT04示例
    #include <stdio.h>
    #include <less.h> // 假设头文件名为 less.h
    int main(int argc, char* argv[]) {
        float *input0 = (float *)0x10010000;
        float *input1 = (float *)0x10020000;
        bool *output = (bool *)0x10030000;
        int *strides0 = (int*)0x10050000;
        int *strides1 = (int*)0x10060000;
        int *strides_output = (int*)0x10070000;

        int i = 0;

        srand(seed++);

        float f_min = -100.0;
        float f_max = 100.0;

        // same shape
        int input0_dims[] = {4, 8, 17};  // 2x2
        int input1_dims[] = {4, 8, 17};  // 2x2
        int output_dims[] = {4, 8, 17};      // 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);
        
        for(i = 0;i < total_input0;++i) {
            input0[i] = f_min + ((float)rand() / (float)RAND_MAX) * (f_max - f_min);
        }

        for(i = 0;i < total_input1;++i) {
            input1[i] = f_min + ((float)rand() / (float)RAND_MAX) * (f_max - f_min);
        }
       
        fp_less_p(input0, input1, output, params);//调用汇编
        return 0;
    }