Matrix Multiplication Algorithm

Question

Hello, Can anyone recommends me what is best way to multiply rectangular matrices that minimizes the combinational function?? I have written matrix multiplication code but total combinational functional are exceeding the maximum comb. functional of the device????

On searching some forums, I have found that one can do the multiplication using SRAM..I need some documentation on it?? How to use SRAM? and how it can be used for matrix multiplication...where can i found documentation on it??

altera_forum · Answer

Use bigger device is one solution

altera_forum · Answer

If you try implementing the code in NIOSII you could have a function for multiplication. You could also instantiate a LPM_MULT multiplier from the IP catlog to be the function that carries out the multiplication in your code. And for the SRAM thing you could try referring to the following link https://www.altera.com/solutions/technology/external-memory/sram.html. I am not sure how helpful the link would be. Thanks.

altera_forum · Answer

--- Quote Start ---

If you try implementing the code in NIOSII you could have a function for multiplication. You could also instantiate a LPM_MULT multiplier from the IP catlog to be the function that carries out the multiplication in your code. And for the SRAM thing you could try referring to the following link https://www.altera.com/solutions/technology/external-memory/sram.html. I am not sure how helpful the link would be. Thanks.

--- Quote End ---

Can you please tell me how to use megafunction??? some pdf document explanation???

altera_forum · Answer

Hi,  the documentation for using the LPM_MULT and other arithmetic Ip cores can be found at https://www.altera.com/content/dam/altera-www/global/en_us/pdfs/literature/ug/ug_lpm_alt_mfug.pdf

Forum Discussion

Matrix Multiplication Algorithm

4 Replies

Recent Discussions

DE1-SoC project compiles, but board programming fails 42% through

Compatibility and Configuration of Arria10 Devices with and without HPS

USB Blaster conflicts with other FTDI devices result in PC crash

MAX10 Single end I/O low/high speed bank frequency

Device migration about DD and DA