home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!sun-barr!west.West.Sun.COM!cronkite.Central.Sun.COM!texsun!exucom.exu.ericsson.se!news
- From: exuptr@exu.ericsson.se (exuptr@exu.ericsson.se)
- Newsgroups: comp.sys.ibm.pc.hardware
- Subject: Re: IDE controller cards
- Message-ID: <exuptr.609.716590448@exu.ericsson.se>
- Date: 15 Sep 92 20:54:08 GMT
- References: <1992Sep15.160153.8011@schbbs.mot.com>
- Sender: news@exu.ericsson.se
- Organization: Ericsson Network Systems, Inc.
- Lines: 26
- Nntp-Posting-Host: pc254167.exu.ericsson.se
-
- In article <1992Sep15.160153.8011@schbbs.mot.com> RRSE50@waccvm.corp.mot.com (John Pigott) writes:
- >From: RRSE50@waccvm.corp.mot.com (John Pigott)
- >Subject: Re: IDE controller cards
- >Date: 15 Sep 92 15:44:17 GMT
-
- >There is no significant difference between controller cards. All they con
- >of is an address decoder, and a line buffer. They have no effect on the s
- >of the data transfer. 700kb/s seems to be about the top speed you can get
- >a disk on the AT ISA bus.
-
- This would work out to about 5.6 Mbit/sec. On an 8MHz bus, assuming you
- could just force data on it every clock cycle, you could theoretically
- achieve 8M * 16 bit/sec, or 16MBytes/sec. In practise, you're looking at
- around 4 or 5 clocks, I think, so you should be able to get around 3 MBytes/
- sec, anyway.
-
- My IDE tests out at about 1,000 kBytes/sec, so I know better than 700 is
- possible. I've seen numbers as high as 1,500 kB/sec (without cache).
-
- ----------------------------------------------------------------------------
- "This must be Thursday. I never could get the hang of Thursdays"
- - Douglas Adams
- - Patrick Taylor (Arthur Dent)
- Ericsson Network Systems
- exuptr@exu.ericsson.se "Don't let the .se fool you"
- or exuptr@ZGNews.Lonestar.Org, exu.exuptr@memo.ericsson.se
-