Path: utzoo!attcan!uunet!lll-winken!pacbell!hoptoad!unisoft!gethen!farren From: farren@gethen.UUCP (Michael J. Farren) Newsgroups: comp.sys.ibm.pc Subject: Re: GATHER and say NO to MCA! Message-ID: <1007@gethen.UUCP> Date: 7 Jul 88 13:24:51 GMT References: <42900016@uicsrd.csrd.uiuc.edu> <12400006@cpe> Reply-To: farren@gethen.UUCP (Michael J. Farren) Organization: There's Unix there in Oakland Lines: 20 In article <12400006@cpe> neese@cpe.UUCP writes: > >The implementation in the MC bus is better, but overhead is high. True >coprocessing is NOT damn near impossible. It takes more attention to detail. >Do your homework before making brash statements. My homework: 18 years of experience, including 8 years designing multi- processor systems, from S-100 bus to proprietary bit-slice systems. 6 years of experience with PC bus issues. And experience with all of the existing coprocessor cards for the PC (all that I know about, anyhow). Damn near impossible is what I said, and damn near impossible is what I meant. If doing true coprocessing on the PC (AT) bus is so trivial, why haven't we seen cards that work, and work well? -- Michael J. Farren | "INVESTIGATE your point of view, don't just {ucbvax, uunet, hoptoad}! | dogmatize it! Reflect on it and re-evaluate unisoft!gethen!farren | it. You may want to change your mind someday." gethen!farren@lll-winken.llnl.gov ----- Tom Reingold, from alt.flame