Xref: utzoo comp.realtime:1408 comp.dsp:1795 Path: utzoo!utgpu!news-server.csri.toronto.edu!rpi!zaphod.mps.ohio-state.edu!swrinde!cs.utexas.edu!asuvax!ncar!gatech!taco!pesun.ncsu.edu!dwayne From: dwayne@pesun.ncsu.edu (Dwayne Allen Sorrell) Newsgroups: comp.realtime,comp.dsp Subject: Re: Experiences with HyperFlo or PC/M Message-ID: <1991Jun18.022523.18761@ncsu.edu> Date: 18 Jun 91 02:25:23 GMT References: <1620@aoa.UUCP> Sender: news@ncsu.edu (USENET News System) Distribution: usa Organization: NC State Univ. Precision Engineering Center Lines: 28 In article <1620@aoa.UUCP> moose@aoa.UUCP () writes: >We are considering buying several boards from a company called Pacific >Cyber/Metrix Inc. They manufacture a board with 3 C30's & 1 68030/68882. >They also sell software/hardware (HyperFlo) to distribute the processing >over several processors/boards. Has anyone had any good/bad things >they would like to tell/warn us about? Well, we bought a HyperFlo board for real-time research. However, we were going to try a configuration PC/M had never tried before. We wanted to put it in a Sun cardcage. That didn't work for several reasons. Now we are scraping funds to buy it a new VME cardcage, and a VME to VME bus adaptor. So, I haven't gotten a chance to use ours yet. Nevertheless, I have read much of the documentation and it looks like a nifty board. The board provides a 4-Mbyte VMEbus "window" address which is configurable with jumpers (for the addr at power up) and by registers. Possible window addresses go from 0x80000000 to 0xbfffffff. So you better have a P2 connector on your bus. Now here's something to watch out for: When the board is powered up, it looks for an application image starting at VMEbus address 0x2000000. This address cannot be changed. This can cause problems if you have another physical device at that address. -- Dwayne Allen Sorrell dwayne@pesun.ncsu.edu NC State University (919) 737-3141 Precision Enginering Center Real-time/graphics programmer for hire