mxnet

Functions  
dnnl_status_t DNNL_API  dnnl_sgemm (char transa, char transb, dnnl_dim_t M, dnnl_dim_t N, dnnl_dim_t K, float alpha, const float *A, dnnl_dim_t lda, const float *B, dnnl_dim_t ldb, float beta, float *C, dnnl_dim_t ldc) 
dnnl_status_t DNNL_API  dnnl_gemm_u8s8s32 (char transa, char transb, char offsetc, dnnl_dim_t M, dnnl_dim_t N, dnnl_dim_t K, float alpha, const uint8_t *A, dnnl_dim_t lda, uint8_t ao, const int8_t *B, dnnl_dim_t ldb, int8_t bo, float beta, int32_t *C, dnnl_dim_t ldc, const int32_t *co) 
dnnl_status_t DNNL_API  dnnl_gemm_s8s8s32 (char transa, char transb, char offsetc, dnnl_dim_t M, dnnl_dim_t N, dnnl_dim_t K, float alpha, const int8_t *A, dnnl_dim_t lda, int8_t ao, const int8_t *B, dnnl_dim_t ldb, int8_t bo, float beta, int32_t *C, dnnl_dim_t ldc, const int32_t *co) 
dnnl_status_t DNNL_API dnnl_gemm_s8s8s32  (  char  transa, 
char  transb,  
char  offsetc,  
dnnl_dim_t  M,  
dnnl_dim_t  N,  
dnnl_dim_t  K,  
float  alpha,  
const int8_t *  A,  
dnnl_dim_t  lda,  
int8_t  ao,  
const int8_t *  B,  
dnnl_dim_t  ldb,  
int8_t  bo,  
float  beta,  
int32_t *  C,  
dnnl_dim_t  ldc,  
const int32_t *  co  
) 
Performs integer matrixmatrix multiply on 8bit signed matrix A, 8bit signed matrix B, and 32bit signed resulting matrix C.
The operation is defined as:
C := alpha * (op(A)  A_offset) * (op(B)  B_offset) + beta * C + C_offset
where
op( X ) = X
or op( X ) = X**T
,alpha
and beta
are scalars, andA
, B
, and C
are matrices:op( A )
is an MxK
matrix,op( B )
is an KxN
matrix,C
is an MxN
matrix.A_offset
is an MxK
matrix with every element equal the ao
value,B_offset
is an KxN
matrix with every element equal the bo
value,C_offset
is an MxN
matrix which is defined by the co
array of size len
:offsetc = F
: the len
must be at least 1
,offsetc = C
: the len
must be at least max(1, m)
,offsetc = R
: the len
must be at least max(1, n)
,The matrices are assumed to be stored in rowmajor order (the elements in each of the matrix rows are contiguous in memory).
transa  Transposition flag for matrix A: 'N' or 'n' means A is not transposed, and 'T' or 't' means that A is transposed. 
transb  Transposition flag for matrix B: 'N' or 'n' means B is not transposed, and 'T' or 't' means that B is transposed. 
offsetc  Flag specifying how offsets should be applied to matrix C:

M  The M dimension. 
N  The N dimension. 
K  The K dimension. 
alpha  The alpha parameter that is used to scale the product of matrices A and B. 
A  A pointer to the A matrix data. 
lda  The leading dimension for the matrix A. 
ao  The offset value for the matrix A. 
B  A pointer to the B matrix data. 
ldb  The leading dimension for the matrix B. 
bo  The offset value for the matrix B. 
beta  The beta parameter that is used to scale the matrix C. 
C  A pointer to the C matrix data. 
ldc  The leading dimension for the matrix C. 
co  An array of offset values for the matrix C. The number of elements in the array depends on the value of offsetc . 
dnnl_status_t DNNL_API dnnl_gemm_u8s8s32  (  char  transa, 
char  transb,  
char  offsetc,  
dnnl_dim_t  M,  
dnnl_dim_t  N,  
dnnl_dim_t  K,  
float  alpha,  
const uint8_t *  A,  
dnnl_dim_t  lda,  
uint8_t  ao,  
const int8_t *  B,  
dnnl_dim_t  ldb,  
int8_t  bo,  
float  beta,  
int32_t *  C,  
dnnl_dim_t  ldc,  
const int32_t *  co  
) 
Performs integer matrixmatrix multiply on 8bit unsigned matrix A, 8bit signed matrix B, and 32bit signed resulting matrix C.
The operation is defined as:
C := alpha * (op(A)  A_offset) * (op(B)  B_offset) + beta * C + C_offset
where
op( X ) = X
or op( X ) = X**T
,alpha
and beta
are scalars, andA
, B
, and C
are matrices:op( A )
is an MxK
matrix,op( B )
is an KxN
matrix,C
is an MxN
matrix.A_offset
is an MxK
matrix with every element equal the ao
value,B_offset
is an KxN
matrix with every element equal the bo
value,C_offset
is an MxN
matrix which is defined by the co
array of size len
:offsetc = F
: the len
must be at least 1
,offsetc = C
: the len
must be at least max(1, m)
,offsetc = R
: the len
must be at least max(1, n)
,The matrices are assumed to be stored in rowmajor order (the elements in each of the matrix rows are contiguous in memory).
transa  Transposition flag for matrix A: 'N' or 'n' means A is not transposed, and 'T' or 't' means that A is transposed. 
transb  Transposition flag for matrix B: 'N' or 'n' means B is not transposed, and 'T' or 't' means that B is transposed. 
offsetc  Flag specifying how offsets should be applied to matrix C:

M  The M dimension. 
N  The N dimension. 
K  The K dimension. 
alpha  The alpha parameter that is used to scale the product of matrices A and B. 
A  A pointer to the A matrix data. 
lda  The leading dimension for the matrix A. 
ao  The offset value for the matrix A. 
B  A pointer to the B matrix data. 
ldb  The leading dimension for the matrix B. 
bo  The offset value for the matrix B. 
beta  The beta parameter that is used to scale the matrix C. 
C  A pointer to the C matrix data. 
ldc  The leading dimension for the matrix C. 
co  An array of offset values for the matrix C. The number of elements in the array depends on the value of offsetc . 
dnnl_status_t DNNL_API dnnl_sgemm  (  char  transa, 
char  transb,  
dnnl_dim_t  M,  
dnnl_dim_t  N,  
dnnl_dim_t  K,  
float  alpha,  
const float *  A,  
dnnl_dim_t  lda,  
const float *  B,  
dnnl_dim_t  ldb,  
float  beta,  
float *  C,  
dnnl_dim_t  ldc  
) 
Performs singleprecision matrixmatrix multiply.
The operation is defined as:
C := alpha * op( A ) * op( B ) + beta * C
where
op( X ) = X
or op( X ) = X**T
,alpha
and beta
are scalars, andA
, B
, and C
are matrices:op( A )
is an MxK
matrix,op( B )
is an KxN
matrix,C
is an MxN
matrix.The matrices are assumed to be stored in rowmajor order (the elements in each of the matrix rows are contiguous in memory).
transa  Transposition flag for matrix A: 'N' or 'n' means A is not transposed, and 'T' or 't' means that A is transposed. 
transb  Transposition flag for matrix B: 'N' or 'n' means B is not transposed, and 'T' or 't' means that B is transposed. 
M  The M dimension. 
N  The N dimension. 
K  The K dimension. 
alpha  The alpha parameter that is used to scale the product of matrices A and B. 
A  A pointer to the A matrix data. 
lda  The leading dimension for the matrix A. 
B  A pointer to the B matrix data. 
ldb  The leading dimension for the matrix B. 
beta  The beta parameter that is used to scale the matrix C. 
C  A pointer to the C matrix data. 
ldc  The leading dimension for the matrix C. 