aclblasHgemm

Applicable Products

Product	Supported
Ascend 950PR / Ascend 950DT	×
Atlas A3 training products / Atlas A3 inference products	√
Atlas A2 training products / Atlas A2 inference products	√
Atlas 200I/500 A2 inference products	√
Atlas inference products	√
Atlas training products	√

Function Usage

Computes matrix-matrix multiplication: C = αAB + βC. Both the input and output are of data type FLOAT16. This API is asynchronous.

Prototype

      
       
         
         
           aclError aclblasHgemm(aclTransType transA,
aclTransType transB,
aclTransType transC,
int m,
int n,
int k,
const aclFloat16 *alpha,
const aclFloat16 *matrixA,
int lda,
const aclFloat16 *matrixB,
int ldb,
const aclFloat16 *beta,
aclFloat16 *matrixC,
int ldc,
aclComputeType type,
aclrtStream stream)

          

        

      
     

Parameters

Parameter	Input/Output	Description
transA	Input	Transpose flag of matrix A. For details about the type definition, see aclTransType.
transB	Input	Transpose flag of matrix B. For details about the type definition, see aclTransType.
transC	Input	Transpose flag of matrix C. For details about the type definition, see aclTransType. Currently, the value can only be ACL_TRANS_N.
m	Input	Number of rows in matrix A and matrix C.
n	Input	Number of columns in matrix B and matrix C.
k	Input	Number of columns in matrix A and number of rows in matrix B.
alpha	Input	Pointer to scalar α used for executing the multiplication operation. For the type definition, see aclFloat16.
matrixA	Input	Pointer to matrix A. For the type definition, see aclFloat16.
lda	Input	Leading dimension of matrix A. For row-major transpose, lda is the number of columns of matrix A. This parameter is reserved and can only be set to –1.
matrixB	Input	Pointer to matrix B. For the type definition, see aclFloat16.
ldb	Input	Leading dimension of matrix B. For row-major transpose, ldb is the number of columns of matrix B. This parameter is reserved and can only be set to –1.
beta	Input	Pointer to scalar β used for executing the multiplication operation. For the type definition, see aclFloat16.
matrixC	Input and output	Pointer to matrix C. For the type definition, see aclFloat16.
ldc	Input	Leading dimension of matrix C. This parameter is reserved and can only be set to –1.
type	Input	Computation precision type (high precision by default). For details about the type definition, see aclComputeType.
stream	Input	Stream where the operator is executed. For the type definition, see aclrtStream.

Returns

0 on success; else, failure. For details, see aclError.

Parent topic: CBLAS APIs