[Csnd] Csound on FPGA - is it fixed-point style?
| Date | 2024-10-03 01:57 |
| From | Aaron Krister Johnson |
| Subject | [Csnd] Csound on FPGA - is it fixed-point style? |
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 areOr - was the FPGA referred to capable of using floating-point? |
| Date | 2024-10-03 07:04 |
| From | Victor Lazzarini <000010b17ddd988e-dmarc-request@LISTSERV.HEANET.IE> |
| Subject | Re: [Csnd] Csound on FPGA - is it fixed-point style? |
|
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.
Prof. Victor Lazzarini
Maynooth University
Ireland
On 3 Oct 2024, at 01:57, Aaron Krister Johnson <akjmicro@gmail.com> wrote:
|
| Date | 2024-10-03 16:39 |
| From | Aaron Krister Johnson |
| Subject | Re: [Csnd] Csound on FPGA - is it fixed-point style? |
Got it, Victor, thanks for the clarification! On Wed, Oct 2, 2024 at 11:04 PM Victor Lazzarini <000010b17ddd988e-dmarc-request@listserv.heanet.ie> wrote:
|