Mailing List ArchiveSupport open source code!
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]Re: tlug: Linux news
- To: tlug@example.com
- Subject: Re: tlug: Linux news
- From: "Stephen J. Turnbull" <turnbull@example.com>
- Date: Mon, 17 Feb 1997 17:24:37 +0900
- In-reply-to: Your message of "Mon, 17 Feb 1997 15:59:29 +0900." <330801D0.78952DEE@example.com>
- Reply-To: tlug@example.com
- Sender: owner-tlug
-------------------------------------------------------- tlug note from "Stephen J. Turnbull" <turnbull@example.com> -------------------------------------------------------- >>>>> "Jim" == Jim Schweizer <schweiz@example.com> writes: Jim> Is there a 64 bit Linux available for the Intel platform? I Jim> haven't heard of it... Nope. As far as I know, there *isn't* a 64-bit Intel platform (but I'm real fuzzy on the 860 series). The Pentium does memory transfers on a 64-bit bus, and if you build with "Pentium" as the target platform optimizations for that bus will be done (to the extent that GCC does them, and there may be a few hacks in the kernel code). However, all peripherals run on the 32-bit wide PCI bus as far as I know. Also, it's not clear to me what "64-bit OS" means. 32-bit was important, because 16-bit address spaces are not big enough for modern software, and 16-bit color falls somewhat short of true color. This is not true for the jump between 32 and 64 bits. It's clear that in the medium term there will be systems that start to feel constrained by a 4GB address space, but for practical purposes the 32-bit linear address space for memory and 32-bit color space for video (and note that a 4096x4096 screen even at 32-bit color "only" takes up 64MB, so GUI considerations seem unlikely to use up gigamemory memory until we get 3D displays) are about as much as you could possibly need at the moment. Of course there are optimizations that can be done, and computations will be faster. But it seems to me that from the point of view of kernel development RISCiness and instruction sets are much more important issues. An article that bears on these issues is in the Jan 1997 Communications of the ACM, on Intel's "MMX" technology (the multimedia instruction set that will be built into future iAPX processors). It's quite clear from that article that from the multimedia standpoint the bandwidth advantages of a 64-bit bus require a lot of algorithmic tuning; I feel that 64-bit-ness does not really change the way system programming is done. Steve ----------------------------------------------------------------- a word from the sponsor will appear below ----------------------------------------------------------------- The TLUG mailing list is proudly sponsored by TWICS - Japan's First Public-Access Internet System. Now offering 20,000 yen/year flat rate Internet access with no time charges. Full line of corporate Internet and intranet products are available. info@example.com Tel: 03-3351-5977 Fax: 03-3353-6096
- References:
- tlug: Linux news
- From: Jim Schweizer <schweiz@example.com>
Home | Main Index | Thread Index
- Prev by Date: tlug: Linux news
- Next by Date: tlug: Job opening at ODI Japan
- Prev by thread: tlug: Linux news
- Next by thread: tlug: Job opening at ODI Japan
- Index(es):
Home Page Mailing List Linux and Japan TLUG Members Links