herman@marlin.NOSC.MIL (John W. Herman) (10/23/90)
-- I saw an ad for a chip or chip set that professed to be able to perform a fixed point or block floating point FFT in 96 microsecond but now I can't find it. If you know the name of the company that makes this chip or chipset, I would appreciate your sending it to me. Thank you. -- John Herman ARPA: herman@marlin.nosc.mil Phome: (619)553-1466 Naval Ocean System Center Code 712 271 Catalina Blvd San Diego, Ca. 92512-5000
bwhite@oucsace.cs.OHIOU.EDU (Bill White) (10/24/90)
In article <1642@marlin.NOSC.MIL> herman@marlin.nosc.mil.UUCP (John W. Herman) writes: >I saw an ad for a chip or chip set that professed to be able to >perform a fixed point or block floating point FFT in 96 microsecond >but now I can't find it. If you know the name of the company that >makes this chip or chipset, I would appreciate your sending it to >me. Thank you. Actually, if anyone finds out about such a beast (or any other FFT chip (set)), I'd like to hear about it too. Maybe the best thing would just be to post responses. -- | Bill White Internet: bwhite@oucsace.cs.ohiou.edu | | MURPHY'S FIFTH COROLLARY: | | Left to themselves, things tend to go from bad | | to worse. |
a143@mindlink.UUCP (Ed Meyer) (10/25/90)
John, for fast FFTs, it's hard to beat Array Micro's unit (if memory serves, it's called a DASP6100). I think the set will allow you to do a real 64K FFT in aroun 1 to 2 milli-seconds. If memory serves, a real 256 FFT can be calculated in _realtime_ for a 0 to 20 kHz spectrum. I don't have Array Micro's number off hand but they are in the US. Maybe someone else has their number. Or, failing that, I could find it out in a day-or-three.
herman@marlin.NOSC.MIL (John W. Herman) (10/30/90)
-- The following is the message I sent. -- I saw an ad for a chip or chip set that professed to be able to perform a fixed point or block floating point FFT in 96 microsecond but now I can't find it. If you know the name of the company that makes this chip or chipset, I would appreciate your sending it to me. Thank you. -- The information I received is as follows: --- From marlin!nosc!dog.ee.lbl.gov!hellgate.utah.edu!cs.utexas.edu!usc!zaphod.mps.ohio-state.edu!van-bc!rsoft!mindlink!a143 Mon Oct 29 13:11:59 PST 1990 John, for fast FFTs, it's hard to beat Array Micro's unit (if memory serves, it's called a DASP6100). I think the set will allow you to do a real 64K FFT in aroun 1 to 2 milli-seconds. If memory serves, a real 256 FFT can be calculated in _realtime_ for a 0 to 20 kHz spectrum. I don't have Array Micro's number off hand but they are in the US. Maybe someone else has their number. Or, failing that, I could find it out in a day-or-three. --- From marlin!nosc!ucsd!ucbvax!hplabs!hpl-opus!hpnmdla!sheppard Mon Oct 29 13:24:17 PST 1990 I believe that was announced by Plessey recently. Try: Plessey Semiconductors Scotts Valley, Ca, (408) 438-2900 Roger- -- Thank you both very much. The ad I saw was for the Plessey PDSP16510 which will perform a block scaled fixed point FFT in 96 microseconds. -- John Herman ARPA: herman@marlin.nosc.mil Phome: (619)553-1466 Naval Ocean System Center Code 712 271 Catalina Blvd San Diego, Ca. 92512-5000