home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.arch
- Path: sparky!uunet!charon.amdahl.com!pacbell.com!mips!sdd.hp.com!usc!elroy.jpl.nasa.gov!decwrl!deccrl!news.crl.dec.com!jg
- From: jg@crl.dec.com (Jim Gettys)
- Subject: Re: PA-RISC Virt Addr > 32 bits (was Re: Caches and Hashing)
- Message-ID: <1992Aug20.210612.10281@crl.dec.com>
- Sender: news@crl.dec.com (USENET News System)
- Organization: DEC Cambridge Research Lab
- References: <Bt5DKp.z0@netnews.jhuapl.edu> <1360024@aspen.NSA.HP.COM> <baQk02L41el501@JUTS.ccc.amdahl.com>
- Date: Thu, 20 Aug 1992 21:06:12 GMT
- Lines: 27
-
- In article <baQk02L41el501@JUTS.ccc.amdahl.com> haw30@macaw.ccc.amdahl.com (Henry A Worth) writes:
- >In article <1360024@aspen.NSA.HP.COM> morris@aspen.NSA.HP.COM (Dale Morris) writes:
- >>
- >> Although the user-visible virtual address space in current PA-RISC
- >> products is 32-bit, PA machines actually implement a larger virtual
- >> address space (48 bits in the snakes workstations). This large global
- >> address space is used by the OS in many ways to improve performance.
- >
- > Is the >32 bit virtual addressing strictly limited to the OS, or is
- >it possible for user processes to map multiple address spaces and use
- >"far pointers"? If not, is there any announced intent to provide
- >such features in future OS's? Likewise, does anyone know if >32 bit
- >virtual addressing in user processes is (or will be) supported in OS's
- >for the MIPS R4000 or IBM RS6000 (and, of course in a few years there will
- >be the SPARC-64, late to the party again ;-) )?
- >
-
- This message composed on a Digital Alpha workstation running OSF/1
- with full 64 bit support.
-
- More need not be said.
- Jim Gettys
-
-
- --
- Digital Equipment Corporation
- Cambridge Research Laboratory
-