Article View: comp.sys.next.hardware
Article #1144Re: DSP chips are NOT dinosaurs
From: Louis A. Mamakos
Date: Thu, 01 Oct 1992 22:08
Date: Thu, 01 Oct 1992 22:08
43 lines
2727 bytes
2727 bytes
In article <1992Oct1.192347.17114@netcom.com> abell@netcom.com (Steven T. Abell) writes: >louie@sayshell.umd.edu (Louis A. Mamakos) writes: >> Serial ports don't have to interrupt on every character. If there >> were a moderately intelligent serial controller, plus DMA support for >> the I/O transfers, then things could be quite zippy, thank you. > >The validity of this line of thinking depends on what you're doing. >If your idea of serial port traffic consists of unixy transfers, >DMA'd serial ports are great. But if you're exchanging messages in some >higher-level protocol, such as is often encountered in machine-control apps, >this doesn't work very well. A device like the 8530 used by NeXT will >scratch its nose on Sunday if you ask it to, but that's only with respect >to hardware protocol. It still needs some user-programmable software protocol >smarts to back it up. Adding an 8-bit CPU to back the serial ports would make >serial loads just disappear, as far as the main processor is concerned, for a >far wider class of applications. This isn't always the case. If you choose some serial encapsulation that the 8530 supports (like HDLC), you can arrange to have it interrupt you and terminate the DMA transfer when it receives an entire frame. This should work *better* than the normal UNIXy sort of transfers. I'd be very, very happy if this was the case and NeXT also brought out the TX/RX clocks for the 8530 channels. You ought to be able to support a synchronous PPP connection fairly well. Of course, that assumes that: * The DMA channels come back in future hardware * NeXT would document the interface for talking to the serial controllers, which they have not done in the past. Note that it *is* possible; consider how the MIDI driver works.. It may be simpler to build a box with something like a 68332 or 68340, an ethernet interface a some mix of low and high performance serial interfaces. Talk to it using TCP/IP over the ethernet. You might actually convince someone to build such a box as long as they think they have a market for it (e.g., Sun platforms). louie
Technical Details
Message-ID:
<1992Oct1.220854.22464@ni.umd.edu>Path:
arc1-ca.pugleaf.net!sparky!uunet!gatech!darwin.sura.net!haven.umd.edu!ni.umd.edu!sayshell.umd.edu!louieReferences:
<1aehh5INNa0r@stephen.cs.ubc.ca> <1992Oct1.154555.5001@ni.umd.edu> <1992Oct1.192347.17114@netcom.com>Show Full Headers
Complete Article Headers
Newsgroups: comp.sys.next.hardware Path: arc1-ca.pugleaf.net!sparky!uunet!gatech!darwin.sura.net!haven.umd.edu!ni.umd.edu!sayshell.umd.edu!louie From: louie@sayshell.umd.edu (Louis A. Mamakos) Subject: Re: DSP chips are NOT dinosaurs Message-ID: <1992Oct1.220854.22464@ni.umd.edu> Sender: usenet@ni.umd.edu (USENET News System) Nntp-Posting-Host: sayshell.umd.edu Organization: University of Maryland, College Park References: <1aehh5INNa0r@stephen.cs.ubc.ca> <1992Oct1.154555.5001@ni.umd.edu> <1992Oct1.192347.17114@netcom.com> Date: Thu, 1 Oct 1992 22:08:54 GMT Lines: 44