home *** CD-ROM | disk | FTP | other *** search
- Xref: sparky comp.sys.intel:1559 comp.sys.ibm.pc.hardware:22455
- Newsgroups: comp.sys.intel,comp.sys.ibm.pc.hardware
- Path: sparky!uunet!cs.utexas.edu!hellgate.utah.edu!asylum.cs.utah.edu!clark
- From: clark%asylum.cs.utah.edu@cs.utah.edu (Charles Clark)
- Subject: Re: Help - Cyrix processors, anyone know for sure?
- Date: 22 Aug 92 23:54:48 MDT
- Message-ID: <1992Aug22.235448.28070@hellgate.utah.edu>
- Followup-To: comp.sys.ibm.pc.hardware,comp.sys.intel
- Summary: Cache invalidation cycles?
- Keywords: Intel, P5, Cyrix, 486DLC, i386, Gomez
- Sender: clark@cs.utah.edu
- Organization: University of Utah, CS Dept
- References: <1992Aug13.215958.4016@bcars64a.bnr.ca> <Bt91A8.212@nntp-sc.Intel.COM> <1992Aug21.170154.23076@tandon.com>
- Lines: 17
-
- In article <1992Aug21.170154.23076@tandon.com> tdbear@tandon.com (Tom Barrett) writes:
- >
- >The external cache controller doesn't need to be aware of the
- >Cyrix internal cache because they did something smart... as
- >long as the 386 socket has a real HOLD signal going to it, the
- >Cyrix can be programmed to flush it's internal write-through
- >cache on each DMA.
-
- All this talk of flushing, I've got to ask...
-
- Why aren't cache line invalidations used? Obviously, something is missing
- or they wouldn't resort to flushing the entire cache... What is it about
- 386 based systems that make this impossible?
-
- Thanks,
-
- --Charles
-