170 lines
6.6 KiB
ReStructuredText
170 lines
6.6 KiB
ReStructuredText
Equal
|
||
=================
|
||
|
||
逐元素计算两个输入是否相等
|
||
|
||
.. math::
|
||
|
||
output_i = \begin{cases}
|
||
\text{True}, & \text{if } Input0_i = Input1_i \\
|
||
\text{False}, & \text{if } Input0_i \neq Input1_i
|
||
\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, cplx64, cplx128
|
||
- MT7004 支持fp16, fp32, int16, int32, cplx64
|
||
|
||
**共享存储版本：**
|
||
|
||
.. c:function:: void i8_equal_s(int8_t* Input0, int8_t* Input1, bool* output, long long *params, int core_mask)
|
||
.. c:function:: void i16_equal_s(int16_t* Input0, int16_t* Input1, bool* output, long long *params, int core_mask)
|
||
.. c:function:: void i32_equal_s(int* Input0, int* Input1, bool* output, long long *params, int core_mask)
|
||
.. c:function:: void hp_equal_s(half* Input0, half* Input1, bool* output, long long *params, int core_mask)
|
||
.. c:function:: void fp_equal_s(float* Input0, float* Input1, bool* output, long long *params, int core_mask)
|
||
.. c:function:: void dp_equal_s(double* Input0, double* Input1, bool* output, long long *params, int core_mask)
|
||
.. c:function:: void c64_equal_s(float* Input0, float* Input1, bool* output, long long *params, int core_mask)
|
||
.. c:function:: void c128_equal_s(double* Input0, double* Input1, bool* output, long long *params, int core_mask)
|
||
|
||
**C调用示例：**
|
||
|
||
.. code-block:: c
|
||
:linenos:
|
||
:emphasize-lines: 47
|
||
|
||
//FT78NE示例
|
||
#include <stdio.h>
|
||
#include <equal.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_equal_s(input0, input1, output, params, core_mask);//调用汇编
|
||
return 0;
|
||
}
|
||
|
||
|
||
**私有存储版本：**
|
||
|
||
.. c:function:: void i8_equal_p(int8_t *Input0, int8_t *Input1, bool *output, long long *params)
|
||
.. c:function:: void i16_equal_p(int16_t *Input0, int16_t *Input1, bool *output, long long *params)
|
||
.. c:function:: void i32_equal_p(int32_t *Input0, int32_t *Input1, bool *output, long long *params)
|
||
.. c:function:: void hp_equal_p(half* Input0, half* Input1, bool* output, long long *params)
|
||
.. c:function:: void fp_equal_p(float* Input0, float* Input1, bool* output, long long *params)
|
||
.. c:function:: void dp_equal_p(double* Input0, double* Input1, bool* output, long long *params)
|
||
.. c:function:: void c64_equal_p(float *Input0, float *Input1, bool *output, long long *params)
|
||
.. c:function:: void c128_equal_p(double *Input0, double *Input1, bool *output, long long *params)
|
||
|
||
**C调用示例：**
|
||
|
||
.. code-block:: c
|
||
:linenos:
|
||
:emphasize-lines: 47
|
||
|
||
//FT78NE示例
|
||
#include <stdio.h>
|
||
#include <equal.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_equal_p(input0, input1, output, params);//调用汇编
|
||
return 0;
|
||
} |