[Csnd] Csound on FPGA - is it fixed-point style?

The Csound Mailinglist
1

I remember a post in the last few months about Csound on a field-programmable gate array (FPGA).

It is my understanding that in general FPGA hardware uses, or tends to used fixed-point math and processing as opposed to floating-point. Does that mean that there are

forks or versions of Csound out there that are written using fixed-point math?

Or - was the FPGA referred to capable of using floating-point?

Csound mailing list Csound@listserv.heanet.ie https://listserv.heanet.ie/cgi-bin/wa?A0=CSOUND Send bugs reports to https://github.com/csound/csound/issues Discussions of bugs and features can be posted here

2

yes, fixed-point may benefit some things but you can also have floating-point.

However to answer your question, there is no version of Csound using fixed point that I know of. In the case of the FPGA board, Csound is running on the arm processor with specific processing code (e.g. reverbsc) ported to the FPGA. That works like a co-processor, offloading some of the work from the cpu, and also handling IO.

best

Prof. Victor Lazzarini
Maynooth University
Ireland

3

Got it, Victor, thanks for the clarification!