home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!zaphod.mps.ohio-state.edu!cis.ohio-state.edu!magnus.acs.ohio-state.edu!usenet.ins.cwru.edu!slc6!trier
- From: trier@slc6.ins.cwru.edu (Stephen C. Trier)
- Newsgroups: comp.programming
- Subject: Re: Semaphores, Swap, or Test_And_Set
- Date: 22 Dec 1992 17:05:47 GMT
- Organization: Case Western Reserve University, Cleveland OH (USA)
- Lines: 33
- Message-ID: <1h7htbINNdg6@usenet.INS.CWRU.Edu>
- References: <1992Dec18.195139.15322@umbc3.umbc.edu> <1h53bpINNabh@usenet.INS.CWRU.Edu> <1992Dec22.055727.8056@nestmoi.rain.com>
- NNTP-Posting-Host: slc6.ins.cwru.edu
-
- In article <1992Dec22.055727.8056@nestmoi.rain.com> jim@nestmoi.rain.com (Jim Chorn) writes:
- >This will only work on multiprocessors if the lock prefix is supported by
- >the processor. For example, if the multiprocessor system is tightly
- >coupled and each processor supports a coherent cache but the cache
- >ignores the processor lock signal this may not work.
-
- Ah, finally! It sounds like I've found someone who knows something about
- the nitty-gritty of these ghastly CPUs.
-
- I've been trying to figure out whether that LOCK prefix is necessary when
- sharing the code between several virtual 8086s running on one 386. I have
- been unable to get a clear answer to this question -- is the LOCK prefix
- useful only for multiprocessors that take advantage of it, or does it also
- make the instruction noninterruptible?
-
- An answer to the effect of, "A 386 instruction is never interruptible" is
- OK, too -- I haven't been able to dig that sort of information out of the
- references I can find. Everything provides application-level information,
- but none of the info I need about exactly when an interrupt or exception
- can take place. It seems strange, since this information is readily avail-
- able for the 680[234]0. Why isn't the 386/486 as well documented? (Maybe
- I'm looking in the wrong place?)
-
- By the way, someone sent me mail about a typo in my assembly code. There's
- one point where it says, "mov bx, word ptr [bx+4]". That should be "mov
- bx, word ptr [bp+4]". It is a transcription error, my fault, and the bp
- version is what was in the original.
-
- --
- Stephen Trier "We want to offer you a price that you
- Network software type just can't afford to take advantage of."
- Case Western Reserve University - Sales blurb from HSC Software
- trier@ins.cwru.edu
-