How to pipeline High Throughput Multiply function?

[Prashant_dsp]

I need a routine to do multiply and accumalate on two memories of size
1024.(i.e multiply individual indices and add all the products). I am using a
single cycle timed loop working at 40 MHz to do the same. But since the High
Throughput Multiply function takes more time, I get a timing violation
error.The same code works perfectly at 20 MHz. But I want this function to work
at a rate greater than 40 MHz. I understand that this can be done with
pipelining.

It would be helpful, if you could point me to an example code showing how
it is done.

Thank you,
Prashant

[Peter_W]

Hi Prashant,

A very helpful walkthrough we have can be found at the link below, it outlines what pipelining is and how to implement it with simple code. After going through that you should try to determine where you can break down the functions in your code and then if you get stuck or it still won't fit into the time frame you are looking for, I would suggest posting your code so that we can look at it and help you along from there.

Regards,

Peter W.

[Peter_W · Accepted solution]

...and by "the link below" I meant in the next post...

http://zone.ni.com/devzone/cda/tut/p/id/3749

Regards,

Peter W.