Imperial College London > Talks@ee.imperial > CAS Talks > CG: Optimizing FPGA Speed using Custom Precision

CG: Optimizing FPGA Speed using Custom Precision

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact George A Constantinides.

With the continuing exploration of accelerating iterative methods on FPG As, in this upcoming seminar, I will present the latest results obtained from analyzing the speed-up of an FPGA vs a CPU (in double precision) by reducing the word-length. I will also show a plot of the different number of iterations obtained from performing every sum reduction (of the CG method) sequentially or in a tree, for the current MPC Citation Model Aircraft testbench. In addition, I will show and request feedback on a preliminary poster on for the banded implementation paper that is to be presented at FPT ’08.

This talk is part of the CAS Talks series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

Changes to Talks@imperial | Privacy and Publicity