gpucoder.batchedMatrixMultiply
Optimized GPU implementation of batched matrix multiply operation
Syntax
Description
[
performs matrix-matrix multiplication of a batch of matricesD
1,D
2] = gpucoder.batchedMatrixMultiply(A
1,B
1,A
2,B
2)A1,B1
andA2, B2
. Thegpucoder.batchedMatrixMultiply
function performs matrix-matrix multiplication of the form:
where
is a scalar multiplication factor,A
,B
, andD
are matrices with dimensionsm
-by-k
,k
-by-n
, andm
-by-n
respectively. You can optionally transpose or hermitian-conjugateA
andB
. By default,
is set to one and the matrices are not transposed. To specify a different scalar multiplication factor and perform transpose operations on the input matrices, use theName,Value
pair arguments.
All the batches passed to thegpucoder.batchedMatrixMultiply
function must be uniform. That is, all instances must have the same dimensionsm,n,k
.
___= gpucoder.batchedMatrixMultiply(___,
performs batched matrix multiply operation by using the options specified by one or moreName,Value
)Name,Value
pair arguments.
Examples
Input Arguments
Output Arguments
See Also
Apps
Functions
codegen
|coder.gpu.kernel
|coder.gpu.kernelfun
|gpucoder.stridedMatrixMultiply
|gpucoder.batchedMatrixMultiplyAdd
|gpucoder.stridedMatrixMultiplyAdd