Matrix Multiplication¶

riscv_status
riscv_mat_mult_f32
(const riscv_matrix_instance_f32 *pSrcA, const riscv_matrix_instance_f32 *pSrcB, riscv_matrix_instance_f32 *pDst)¶

riscv_status
riscv_mat_mult_fast_q15
(const riscv_matrix_instance_q15 *pSrcA, const riscv_matrix_instance_q15 *pSrcB, riscv_matrix_instance_q15 *pDst, q15_t *pState)¶

riscv_status
riscv_mat_mult_fast_q31
(const riscv_matrix_instance_q31 *pSrcA, const riscv_matrix_instance_q31 *pSrcB, riscv_matrix_instance_q31 *pDst)¶

riscv_status
riscv_mat_mult_q15
(const riscv_matrix_instance_q15 *pSrcA, const riscv_matrix_instance_q15 *pSrcB, riscv_matrix_instance_q15 *pDst, q15_t *pState)¶

riscv_status
riscv_mat_mult_q31
(const riscv_matrix_instance_q31 *pSrcA, const riscv_matrix_instance_q31 *pSrcB, riscv_matrix_instance_q31 *pDst)¶

group
MatrixMult
Multiplies two matrices.
Matrix multiplication is only defined if the number of columns of the first matrix equals the number of rows of the second matrix. Multiplying an
M x N
matrix with anN x P
matrix results in anM x P
matrix. When matrix size checking is enabled, the functions check: (1) that the inner dimensions ofpSrcA
andpSrcB
are equal; and (2) that the size of the output matrix equals the outer dimensions ofpSrcA
andpSrcB
.Functions

riscv_status
riscv_mat_mult_f32
(const riscv_matrix_instance_f32 *pSrcA, const riscv_matrix_instance_f32 *pSrcB, riscv_matrix_instance_f32 *pDst) Floatingpoint matrix multiplication.
 Return
The function returns either
RISCV_MATH_SIZE_MISMATCH
orRISCV_MATH_SUCCESS
based on the outcome of size checking. Parameters
[in] *pSrcA
: points to the first input matrix structure[in] *pSrcB
: points to the second input matrix structure[out] *pDst
: points to output matrix structure

riscv_status
riscv_mat_mult_fast_q15
(const riscv_matrix_instance_q15 *pSrcA, const riscv_matrix_instance_q15 *pSrcB, riscv_matrix_instance_q15 *pDst, q15_t *pState) Q15 matrix multiplication (fast variant).
Q15 matrix multiplication (fast variant) for RISCV Core with DSP enabled.
 Return
execution status
RISCV_MATH_SUCCESS : Operation successful
RISCV_MATH_SIZE_MISMATCH : Matrix size check failed
 Scaling and Overflow Behavior
The difference between the function riscv_mat_mult_q15() and this fast variant is that the fast variant use a 32bit rather than a 64bit accumulator. The result of each 1.15 x 1.15 multiplication is truncated to 2.30 format. These intermediate results are accumulated in a 32bit register in 2.30 format. Finally, the accumulator is saturated and converted to a 1.15 result.
The fast version has the same overflow behavior as the standard version but provides less precision since it discards the low 16 bits of each multiplication result. In order to avoid overflows completely the input signals must be scaled down. Scale down one of the input matrices by log2(numColsA) bits to avoid overflows, as a total of numColsA additions are computed internally for each output element.
 Remark
Refer to riscv_mat_mult_q15() for a slower implementation of this function which uses 64bit accumulation to provide higher precision.
 Parameters
[in] pSrcA
: points to the first input matrix structure[in] pSrcB
: points to the second input matrix structure[out] pDst
: points to output matrix structure[in] pState
: points to the array for storing intermediate results

riscv_status
riscv_mat_mult_fast_q31
(const riscv_matrix_instance_q31 *pSrcA, const riscv_matrix_instance_q31 *pSrcB, riscv_matrix_instance_q31 *pDst) Q31 matrix multiplication (fast variant).
Q31 matrix multiplication (fast variant) for RISCV Core with DSP enabled.
 Return
execution status
RISCV_MATH_SUCCESS : Operation successful
RISCV_MATH_SIZE_MISMATCH : Matrix size check failed
 Scaling and Overflow Behavior
The difference between the function riscv_mat_mult_q31() and this fast variant is that the fast variant use a 32bit rather than a 64bit accumulator. The result of each 1.31 x 1.31 multiplication is truncated to 2.30 format. These intermediate results are accumulated in a 32bit register in 2.30 format. Finally, the accumulator is saturated and converted to a 1.31 result.
The fast version has the same overflow behavior as the standard version but provides less precision since it discards the low 32 bits of each multiplication result. In order to avoid overflows completely the input signals must be scaled down. Scale down one of the input matrices by log2(numColsA) bits to avoid overflows, as a total of numColsA additions are computed internally for each output element.
 Remark
Refer to riscv_mat_mult_q31() for a slower implementation of this function which uses 64bit accumulation to provide higher precision.
 Parameters
[in] pSrcA
: points to the first input matrix structure[in] pSrcB
: points to the second input matrix structure[out] pDst
: points to output matrix structure

riscv_status
riscv_mat_mult_q15
(const riscv_matrix_instance_q15 *pSrcA, const riscv_matrix_instance_q15 *pSrcB, riscv_matrix_instance_q15 *pDst, q15_t *pState) Q15 matrix multiplication.
 Return
execution status
RISCV_MATH_SUCCESS : Operation successful
RISCV_MATH_SIZE_MISMATCH : Matrix size check failed
 Scaling and Overflow Behavior
The function is implemented using an internal 64bit accumulator. The inputs to the multiplications are in 1.15 format and multiplications yield a 2.30 result. The 2.30 intermediate results are accumulated in a 64bit accumulator in 34.30 format. This approach provides 33 guard bits and there is no risk of overflow. The 34.30 result is then truncated to 34.15 format by discarding the low 15 bits and then saturated to 1.15 format.
Refer to riscv_mat_mult_fast_q15() for a faster but less precise version of this function.
 Parameters
[in] pSrcA
: points to the first input matrix structure[in] pSrcB
: points to the second input matrix structure[out] pDst
: points to output matrix structure[in] pState
: points to the array for storing intermediate results (Unused)

riscv_status
riscv_mat_mult_q31
(const riscv_matrix_instance_q31 *pSrcA, const riscv_matrix_instance_q31 *pSrcB, riscv_matrix_instance_q31 *pDst) Q31 matrix multiplication.
 Return
execution status
RISCV_MATH_SUCCESS : Operation successful
RISCV_MATH_SIZE_MISMATCH : Matrix size check failed
 Scaling and Overflow Behavior
The function is implemented using an internal 64bit accumulator. The accumulator has a 2.62 format and maintains full precision of the intermediate multiplication results but provides only a single guard bit. There is no saturation on intermediate additions. Thus, if the accumulator overflows it wraps around and distorts the result. The input signals should be scaled down to avoid intermediate overflows. The input is thus scaled down by log2(numColsA) bits to avoid overflows, as a total of numColsA additions are performed internally. The 2.62 accumulator is right shifted by 31 bits and saturated to 1.31 format to yield the final result.
 Remark
Refer to riscv_mat_mult_fast_q31() for a faster but less precise implementation of this function.
 Parameters
[in] pSrcA
: points to the first input matrix structure[in] pSrcB
: points to the second input matrix structure[out] pDst
: points to output matrix structure

riscv_status