home *** CD-ROM | disk | FTP | other *** search
- Xref: sparky comp.sys.ibm.pc.hardware:22247 misc.forsale.computers:30450
- Path: sparky!uunet!zaphod.mps.ohio-state.edu!moe.ksu.ksu.edu!matt.ksu.ksu.edu!news
- From: nan@matt.ksu.ksu.edu (Nan Zou)
- Newsgroups: comp.sys.ibm.pc.hardware,misc.forsale.computers
- Subject: Re: i486 info wanted
- Date: 20 Aug 1992 01:45:22 -0500
- Organization: Kansas State University
- Lines: 45
- Message-ID: <16vf22INN6fi@matt.ksu.ksu.edu>
- References: <1992Aug11.053032.3560@egf-bbs.uucp> <1992Aug18.195718.21382@mksol.dseg.ti.com>
- NNTP-Posting-Host: matt.ksu.ksu.edu
-
- mccall@mksol.dseg.ti.com (fred j mccall 575-3539) writes:
- >mike@egf-bbs.uucp (System Operator) writes:
-
- [...]
- >>So, could someone give me a brief rundown of the difference 'tween an '386
- >>and '486, and in the '486-class machines, what is the difference 'tween
- >>'486SX, '486DX and '486DX/2.
-
- [ explanations and good advice ]
-
- >I opted for a 486-50DX on an EISA motherboard. This comes in around
- >22.5 MIPS (which is about SPARCStation 2 and Sun SPARC IPX country).
-
- MIPS aren't really a good measure of processor performance, especially
- between CISC and RISC machines. According to the SPECmarks I have (if you
- believe that), a 486-50 wipes the floor with a SPARC 2 in integer perfor-
- mance, and is right up there with an HP9000 710 "Snake".
-
- [ from comp.benchmarks ]
-
- Here are some SPECint92 and SPECfp92 figures from a table in Microprocessor
- Report.
-
- System clock cache SPECint92 SPECfp92
- ------ ----- ----- --------- --------
- Sun SS-10/30 36 0+36k 44.2 52.9
- Sun SS-10/41 40 1M+36k 52.6 64.7
- Sun SS-2 40 0+64k 21.8 22.8
- MIPS Magnum 50/100 0+16k 36.8 40.0
- SGI Crimson 50/100 1M+16k 61.7 63.4
- HP 710 50 0+96k 31.6 47.6
- HP 750 66 0+512k 48.1 75.0
- IBM 340 33 0+40k 27.7 51.9
- IBM 560 50 0+72k 42.0 85.6
- Intel Xpress (486) 50 256k+8k 30.1 14.0
-
- [ end excerpt ]
-
- The 486 sucks rocks at floating point, which is to be expected.
-
- Note: I only pass along this info, but make no claim wrt its validity.
- If you dispute these figures, go argue with the editors of Microprocessor
- Report.
-
- -- Nan
-