The high level display code is not the primary problem (though I'm sure it could be improved). The issue is that we're using a graphics library (GDI+) from the .NET library that has ZERO hardware acceleration. This means that all vector rendering is done in software instead of utilizing the GPU that is in 90% of systems that were purchased in the last 3 years.
Eventually we will need to use an accelerated library that utilizes the hardware to do what we are trying to do. When we do that, we will chop off approx. 85% of the CPU ticks due to the display (which is a large portion of the total). These are things which I look forward to participating and enjoying. This message was brought to you by SDR and open source software. ;) Eric Wachsmann FlexRadio Systems > -----Original Message----- > From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] > radio.biz] On Behalf Of Bob McGwier > Sent: Friday, December 08, 2006 11:49 AM > To: Jim Lux > Cc: flexradio@flex-radio.biz > Subject: Re: [Flexradio] PlayStation 3 > > Professionally I have used dttsp running on a Linux box, processing 48 > ksps IQ data to process 15 kHz wide FM signals. On a Pentium III Xeon > rack mount server from Dell, we process in excess of 100 channels of > this data real time. This is in addition to supporting a Qt based GUI > and power spectral display (one channel at a time, channel may be picked > by cognitive DR or manually), taking firewire in with the 100 channels > on it delivered isochronously. The processor is not overburdened and > it is a 2 GHz Pentium III. The graphics display code in PowerSDR is > just not up to the task. > > Bob > N4HY > > > Jim Lux wrote: > > At 05:25 PM 12/7/2006, Charles Greene wrote > > > > > >> There's a write up on PS3 and writing game software for it in the > >> latest edition of IEEE Spectrum. I was just thinking about what a > >> super SDR you could have using it. Talk about some real fast DSP. > >> > > > > > > > > I have the impression that, most of the CPU in the current > > incarnation of PowerSDR is burned up in the GUI, not the DSP, > > right? All those pretty displays, band scopes, Windows GDI > > stuff. The actual signal processing hasn't changed much since the > > days when a 1GHz processor was considered adequate. > > > > Now, if you wanted to run hundreds of receivers covering 1.8-30 MHz > > simultaneously while synthesizing a phased array with 30 elements or > > something like that, you might need some more "cruch", but in that > > situation, I suspect that there are other aspects of the problem that > > will drive your design (like A/Ds, signal distribution, and such). > > > > > > > > > > > > > > > > > > > > _______________________________________________ > > FlexRadio mailing list > > FlexRadio@flex-radio.biz > > http://mail.flex-radio.biz/mailman/listinfo/flexradio_flex-radio.biz > > Archive Link: http://www.mail-archive.com/flexradio%40flex-radio.biz/ > > FlexRadio Homepage: http://www.flex-radio.com > > > > > > > -- > Robert W. McGwier, Ph.D. > Center for Communications Research > 805 Bunn Drive > Princeton, NJ 08540 > (609)-924-4600 > (sig required by employer) > > > > _______________________________________________ > FlexRadio mailing list > FlexRadio@flex-radio.biz > http://mail.flex-radio.biz/mailman/listinfo/flexradio_flex-radio.biz > Archive Link: http://www.mail-archive.com/flexradio%40flex-radio.biz/ > FlexRadio Homepage: http://www.flex-radio.com _______________________________________________ FlexRadio mailing list FlexRadio@flex-radio.biz http://mail.flex-radio.biz/mailman/listinfo/flexradio_flex-radio.biz Archive Link: http://www.mail-archive.com/flexradio%40flex-radio.biz/ FlexRadio Homepage: http://www.flex-radio.com
