[Discuss-gnuradio] Playstation 3
Cross-posting from hell... > From: Frank Brickle <[EMAIL PROTECTED]> > To: Bob McGwier <[EMAIL PROTECTED]> > Cc: Jim Lux <[EMAIL PROTECTED]>, flexradio@flex-radio.biz > > The 256KB per SPE, 256MB per PS3 limit is perhaps going to be more > of a problem in the short term. > I haven't looked much yet at the documentation on the Cell SDK > iso. Has somebody done a slick gather/scatter? ;-) > > 73 > Frank > AB2KT I'm working on it. The basic architecture supports scatter-gather with DMA chains. It's pretty easy to set up and each SPE has it's own DMA engine (called Memory Flow Controller (MFC)). You can DMA from main memory to/from SPE and SPE <-> SPE. The bandwidth of the EIB (SPE/PPE/IO interconnect) is about 180 GB/sec. The bandwidth to RAM is > 20 GB/sec. Not bad ;) > > I believe the difficulty in doing this with the Cell will be to schedule > > the 8 SPE's efficiently. Bayesian learning in EM will certainly fly at > > the (say) 50 GFlops we can expect to get upon optimization of the CDR > > code if we keep the SPE's flaming. I have no doubt in my mind that we > > can do blind learning about entire amateur bands and process them on the > > fly in the Cell on the PS3 with USB2 delivery of the data! The > > potential is just amazing now that it is here and upon us. I've got some ideas on scheduling this beast. You know you're in "full immersion mode" when you're dreaming about computer architecture. > Date: Fri, 08 Dec 2006 14:12:30 -0800 > From: Jim Lux <[EMAIL PROTECTED]> > Subject: Re: [Flexradio] PlayStation 3 > > At 07:42 AM 12/8/2006, Philip Covington wrote: > >On 12/8/06, Jim Lux <[EMAIL PROTECTED]> 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). > > > >Real time decoding of HDTV comes to mind... Porting the GNU Radio HDTV code to the Cell will serve as our test application. > So, you're already in a high data rate, high bandwidth > platform, and perhaps a software implementation isn't the best system > solution (i.e. why not put it into an FPGA?) FPGAs are great. I love them. On the other hand you get to work in floating point on the cell instead of fixed point. > From: Jim Lux <[EMAIL PROTECTED]> > Subject: Re: [Flexradio] PlayStation 3 > To: [EMAIL PROTECTED], Philip Covington <[EMAIL PROTECTED]> > The big thing going for a PS3 based solution is that because it's a > consumer device, it's cheap in a $/MFLOP sense. The question would > be whether, for a given application, you wind up spending more $ (or > time, which is the same, really) fitting your application into the > PS3 framework (to take advantage of the low hardware cost) than you'd > spend on a more expensive platform. I believe that I can port GNU Radio to the cell in such a way that most code "just runs faster." I think that 10 to 20x opteron performance is quite doable on the cell even with suboptimal scheduling. GNU Radio's data flow abstraction and the message passing stuff are inherently parallel. Busting it up into 256KB pieces shouldn't be too hard. I'm thinking about runtime linking of individual images for each SPE based on walking the GNU Radio flow graph. Eric ___ Discuss-gnuradio mailing list Discuss-gnuradio@gnu.org http://lists.gnu.org/mailman/listinfo/discuss-gnuradio
Re: [Discuss-gnuradio] Playstation 3
Eric Blossom wrote: I believe that I can port GNU Radio to the cell in such a way that most code "just runs faster." I think that 10 to 20x opteron performance is quite doable on the cell even with suboptimal scheduling. GNU Radio's data flow abstraction and the message passing stuff are inherently parallel. Busting it up into 256KB pieces shouldn't be too hard. I'm thinking about runtime linking of individual images for each SPE based on walking the GNU Radio flow graph. Eric Slobber, drool.8Mhz two-element interferometry, slobber, grunt. ___ Discuss-gnuradio mailing list Discuss-gnuradio@gnu.org http://lists.gnu.org/mailman/listinfo/discuss-gnuradio
Re: [Discuss-gnuradio] USRP/RFX2400 block diagram
Rohit Gupta wrote: > Hi, > > I am looking for USRP/RFX2400 bloack diagrams, but it seems that the > files at the link below are moved/deleted. If anybody has the diagrams > mentioned below, pls send them to me directly. Rohit, I believe you want to look in the usrp-hw repository: http://gnuradio.org/trac See the "Getting the USRP and associated Schematics" section; $ svn co http://gnuradio.org/svn/usrp-hw/trunk usrp-hw -Dan ___ Discuss-gnuradio mailing list Discuss-gnuradio@gnu.org http://lists.gnu.org/mailman/listinfo/discuss-gnuradio
Re: [Discuss-gnuradio] APT signals
G'day, I managed to capture the spectrum emitted by NOAA-12 for its entire pass; not quite sure anymore which one it was. Using a Diamond D130 discone antenna and a low noise broadband power amplifier (10-2000MHz, g=20dB, nf=3.5, po=+20dbm!!!) the signal was recorded utilizing the usrp_rx_cfile.py python script, a gain of 100, and decimation of 250 centered on 137.5MHz. It produced a very large file -rw-r--r-- 1 root wheel 1117519872 Dec 9 20:01 noaa-12.dat This a little more than 1GB and 419MB zipped. Do we have a place were it can be uploaded for other list members that are interested? My bandwidth isn't large enough to offer it to public from here. I was surprised how loud the signal was, considering the equipment used here, and how well the TVRX card performed. Now I'm really looking forward to shooting the big birds = geostationary satellites. BTW: Do we have an AFC block to compensate for doublershift or is this something we still need to implement? I looked through the documentation but failed to find anything there. cheerio Berndt On Saturday 09 December 2006 16:52, Berndt Josef Wulf wrote: > G'day, > > I'm looking for raw data. Don't you use the usrp_rx_cfile.py script to > capture frequency spectrum? > > e.g.: ./usrp_rx_cfile.py -d 32 -f 137.5M > > You may need to play with the options -R, -g, -N (subdev, gain and number > of samples) depending on your setup where > > -R [A|B] site where the tvrx is plugged in > -g <0..115> gain (default is mid-point @ 58) > -N number of samples (e.g samplerate * record time in sec) > > I usually have to specify the frequency and the decimation. > > I want to write my own decoder and an image sink to ultimately display the > pictures received and hence audio files want do the trick. > > cheerio Berndt > > On Saturday 09 December 2006 14:29, Bill Tracey wrote: > > Berndt, > > > > I can grab some APT audio with a USRP and Bob McGwier's rx apt code. > > Or are you looking for the raw data coming off the TVRF -- could probably > > do that as well but will need some pointers as to how to grab the raw > > sample off the TVRF card -- suppose one just takes the rxapt python code > > and hacks it to dump to a file sink? > > > > I've also got a Hamtronics R139 I can grab audio from -- although it's > > gotten a bit deaf of late. Pics from it can be seen @: > > http://oddjob.yi.org:/wxpics/index.html > > > > Regards, > > > > Bill > > > > At 10:44 PM 12/8/2006, you wrote: > > >G'day, > > > > > >Ok, let's try it this way: > > > > > >Is there someone with the equipment and time to record APT signals > > >transmitted > > >by NOAA satellites in the 137MHz band? Alternatively, geostationary > > > weather satellites transmit WEFAX pictures at around 1691MHz (Hey, were > > > are the guys that tuned into GPS spectrum which is right next door... > > > :-) > > > > > >I want to demodulate the AM/FM 2400Hz sub-carrier signal and display the > > >image. Currently I'm not in the position to capture the spectrum myself > > > due to lack of equipment but this is about to change. > > > > > >I can provide info on satellite passes and frequencies for your > > > location. > > > > > >cheerio Berndt > > > > > >On Wednesday 06 December 2006 14:20, Berndt Josef Wulf wrote: > > > > G'day, > > > > > > > > Has anyone sampled NOAA or METEOR signals in the 137MHz spectrum > > > > which they wouldn't mind sharing the spectrum data file(s)? > > ___ > Discuss-gnuradio mailing list > Discuss-gnuradio@gnu.org > http://lists.gnu.org/mailman/listinfo/discuss-gnuradio ___ Discuss-gnuradio mailing list Discuss-gnuradio@gnu.org http://lists.gnu.org/mailman/listinfo/discuss-gnuradio
