home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!crdgw1!rdsunx.crd.ge.com!ariel!davidsen
- From: davidsen@ariel.crd.GE.COM (william E Davidsen)
- Newsgroups: comp.sys.intel
- Subject: Re: Intel's new performance test iCOMP
- Message-ID: <1992Dec22.164333.4349@crd.ge.com>
- Date: 22 Dec 92 16:43:33 GMT
- References: <92353.39992.J056600@LMSC5.IS.LMSC.LOCKHEED.COM> <1992Dec19.031237.4870@ucsu.Colorado.EDU>
- Sender: usenet@crd.ge.com (Required for NNTP)
- Reply-To: davidsen@crd.ge.com (bill davidsen)
- Organization: GE Corporate R&D Center, Schenectady NY
- Lines: 16
- Nntp-Posting-Host: ariel.crd.ge.com
-
- In article <1992Dec19.031237.4870@ucsu.Colorado.EDU>, gonzaled@ucsu.Colorado.EDU (LGV/MC) writes:
-
- | From PC Magazine, December 8, 1992:
- | "The current iCOMP index is made up of four weighted components: 16-bit
- | integer (67 percent), 16-bit floating point (3 percent), 32-bit integer
- | (25 percent), and 32-bit floating point (5 percent).
-
- My Intel manual doesn't even indicate that 16 bit FP exists, just 32,
- 64 and 80 bit IEEE temp format. Since all the processors are 32 bit
- internal, I'm not sure what any of this means, or why they completely
- ignored double precision (64 bit) fp.
-
- I tend to ignore any benchmark without source, this one particularly.
- --
- bill davidsen, GE Corp. R&D Center; Box 8; Schenectady NY 12345
- Keyboard controller has been disabled, press F1 to continue.
-