Hi,
To realize the multiplication of two matrices, it needs to be accelerated by LEA. The question now is that the data in the matrix are all integers. Can it be implemented with LEA peripherals? Is there any sample code for reference?
This thread has been locked.
If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.
Hi,
To realize the multiplication of two matrices, it needs to be accelerated by LEA. The question now is that the data in the matrix are all integers. Can it be implemented with LEA peripherals? Is there any sample code for reference?
Have you looked into the MSP DSP Library? It has APIs for matrix and vector additions, multiplications, etc, and will use the LEA if available on the device.
The problem there is that the data is assumed to be in one of the available fixed point formats. Which results in bit shifts to fix up the binary point after multiply and divide operations. Not compatible with simple integers.
**Attention** This is a public forum