ARM Compute Library
17.03.1
|
Basic function to execute GEMMLowp on NEON. More...
#include <NEGEMMLowp.h>
Public Member Functions | |
NEGEMMLowp () | |
Constructor. More... | |
void | configure (const ITensor *a, const ITensor *b, ITensor *output, int32_t a_offset, int32_t b_offset, int32_t output_offset, int32_t output_mult_int, int32_t shift) |
Initialise the kernel's inputs, output. More... | |
void | run () override |
Run the kernels contained in the function. More... | |
Public Member Functions inherited from IFunction | |
virtual | ~IFunction ()=default |
Destructor. More... | |
Basic function to execute GEMMLowp on NEON.
This function calls the following NEON kernels:
Definition at line 47 of file NEGEMMLowp.h.
NEGEMMLowp | ( | ) |
Constructor.
void configure | ( | const ITensor * | a, |
const ITensor * | b, | ||
ITensor * | output, | ||
int32_t | a_offset, | ||
int32_t | b_offset, | ||
int32_t | output_offset, | ||
int32_t | output_mult_int, | ||
int32_t | shift | ||
) |
Initialise the kernel's inputs, output.
[in] | a | First input tensor (Matrix A). Data type supported: U8. |
[in] | b | Second input tensor (Matrix B). Data type supported: same as a |
[out] | output | Output tensor. Data type supported: same as a . |
[in] | a_offset | Offset to be added to each element of the matrix A. |
[in] | b_offset | Offset to be added to each element of the matrix B. |
[in] | output_offset | Offset to be added to each element of the output matrix |
[in] | output_mult_int | Value to be multiplied to each element of the output matrix |
[in] | shift | Number of bits to shift right the result. |
|
overridevirtual |
Run the kernels contained in the function.
For NEON kernels:
For OpenCL kernels:
Implements IFunction.