To see details on the template parameters for the Matrix Vector Multiply, see API Reference Overview.
NOTE: Maximum matrix dimensions per kernel. Maximum memory accessible by a kernel is 32kB for AIE. The maximum matrix dimensions per kernel is limited by the memory requirements and how much memory is available.
A matrix_vector_mul design needs to allocate memory for the following:
- iobuffer Size A = Input matrix A of size TP_DIM_A x TP_DIM_B x sizeof(TT_DATA_A).
- iobuffer Size B = Input vector B of size TP_DIM_B x sizeof(TT_DATA_B).
- iobuffer Size Out = Output vector of size TP_DIM_A x sizeof(TT_DATA_OUT).
Furthermore, if these buffers are ping-pong buffers, their memory requirement doubles in size. This can be reduced by using the single_buffer constraint on the buffer.
The cascading feature of the Matrix-Vector Multiply can be used if the size of the matrix and vector exceeds the maximum memory of a single kernel. This works as the matrix and vector data will be split across multiple kernels resulting in a reduced per-kernel memory usage.