Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!sun-barr!lll-winken!uunet!isis!nyx!bscott From: bscott@nyx.UUCP (Ben Scott) Newsgroups: comp.sys.amiga Subject: Re: Amiga competitiveness Summary: Bits and Bytes Message-ID: <2208@nyx.UUCP> Date: 3 Oct 90 00:18:38 GMT References: <90271.190320UH2@psuvm.psu.edu> <420@caslon.cs.arizona.edu> <1091@ucsvc.ucs.unimelb.edu.au> Reply-To: bscott@nyx.UUCP (Ben Scott) Organization: The Raster Image Lines: 46 In article <1091@ucsvc.ucs.unimelb.edu.au> U3364521@ucsvc.ucs.unimelb.edu.au (Lou Cavallo) writes: >CJ> Example #2: an Amiga's hard disk, even with FFS, is *ridiculously* slow >CJ> compared to the _identical_ hard disk running DOS or UNIX/386. This >CJ> is based on empirical observation doing heavy C compiles on a 2000 Empirical observation during compiles? What does that have to do with it? The compiler may have been slow but I've yet to see any PC disk interface outperform a good Amiga setup. Their bus just doesn't hack it. Plus their version of DMA stops the CPU entirely, whereas ours allows processing to continue on almost normally. >I have seen a Quantum 40 Meg equipped 386 DX apparently out perform (2 Mbits >per sec benchmark) quoted A2000 Quantum 40 Meg throughputs but the 386 had a >32 bit buss... {which qualitatively explains its approx 2x throughput over a 2 megaBITS per second on the '386? A 2091 with Quantum can get 800K, sometimes 900K per second, and that's kiloBYTES. 2 megabits is maybe 250K per second. ---- >Moreover as Dave Haynie could attest to, the A2000 Zorro II buss is old news >in todays terms. The new Zorro III buss hits 20 Mbits/sec (Dave?) and Acorns MegaBYTES, BYTES!! >ARM III chipset can hit about 38 Mbits/sec I think (can validate anyone ?). Can't say on this one, but 38 megabits per second is slower than Zorro II, which is roughly 60 megabits per second taking both "halves" into account. (7.5 megaBYTES per second, that is, or twice 3.75 megs) This can be a major issue these days, especially as some new ads are trying to confuse the issue by using "MB" which is ambiguous - they may say that some new card is capable of 20 MB (or "Mb") per second (I won't name names) and they mean megaBITS, which still sounds good until you realize that A: it's only with special hard drives and B: the 2091 or I presume the Hardframe would do just as well (probably better) with these new drives, without hogging the CPU and turning off interrupts... . <<<>>> -- .---------------------------------------------------------------------------. |Ben Scott, professional goof-off and consultant at The Raster Image, Denver| |FIDO point address 1:104/421.2, bscott@nyx.cs.du.edu, or BBS (303)424-9831 | |"Quantum Mechanics: The dreams that || The Raster Image IS responsible for| | stuff is made of..." - Michael Sinz || everything I say! ** Amiga Power**| `-------------------------------------'`------------------------------------'