ee161agt@sdccs5.UUCP (03/13/84)
[] I have a crystal-ball study on my desk chock-full of predictions for the semiconductor industry in the next decade. Some of it I agree with. ( they predict 4M-bit Drams by 1992 ) Some of it I don't. In particular I wonder about this: "64 bits will be the common word-size of mP's by 1992." I'm not saying it's not technologically feasable to build a 64 bit Microprocessor; I'm wondering who would want or need one. Perhaps I'm short- sighted, but I can't see much performance or utility gain from a jump from 32 to 64 bits. 32 Data : 32 bits = 2 = 4,294,967,296 64 64 bits = 2 = 18,446,744,073,709,551,616 How many times do you use a number > 4 billion ? Is it reasonable to make data paths 8 bytes wide to allow for such rare cases ? I think you'd be better off doing this kind of math in double-precision. Floating point ? I don't do too much crunching, but I would expect 64 bits of double precision on a 32 bit machine would give you plenty of precision. Bus bandwidth: I'm all for decreasing the memory bottle-neck with a over-large memory bus, just don't increase the word size of the mP to do it. 64 data & 64 address pins ? That's 128 pins to start with without any multiplexing. I'd sure like to see those chips, they'd have pins sprouting from everywhere. Address : same as above. A 32 bit, 4 giga-byte virtual address space might get a bit small in the next decade, but is that any reason to go to 18,446,744 tera-bytes. ( don't even know prefixes above tera- ) How about 40 bit words or 48 bit words, anything but 64. I expect systems-on-a-chip long before 64 bit mP's. I'd prefer a cache, memory-management, I/O, even memory on the CPU chip before they start expanding the data & address paths. Any other views on micros beyond 32 bits ? Paul van de Graaf sdcsvax!sdccs5!ee161agt U. C. San Diego
kurt@fluke.UUCP (Kurt Guntheroth) (03/15/84)
What's next? I don't think its 64 bit micros, but how about 36 bits? I
think we will see LSI implementations of some popular architectures from the
60's-70's. What about IBM 360 type architectures. I heard IBM was making
a micro right now that emulated some larger IBM architecture. DEC is making
a LSI vax, but how about an LSI pdp-10?
Watch out hexadecimal, the octal microprocessors are coming!
--
Kurt Guntheroth
John Fluke Mfg. Co., Inc.
{uw-beaver,decvax!microsof,ucbvax!lbl-csam,allegra,ssc-vax}!fluke!kurtbcw@duke.UUCP (Bruce C. Wright) (03/16/84)
64 bit machines are usually only interesting for special purpose computations. In some cases, 64 bit double precision can indeed be too small (astronomers for example often want to have very good precision even after subtracting two large numbers), but even on a 32-bit machine this can be done easily by having an extended precision (quad precision) like the VAX does with G- and H- floating point. But 64 bits to run a spreadsheet? Give me a break! 64 bits isn't even considered necessary in the large corporation mainframe environment, and if it had any economic significance for anything other than special- purpose computations (a la Cray I), then those corporations would have the megabucks required to make it happen in that world. If it isn't necessary for the big mainframes, it almost certainly isn't necessary on micros! Bruce C. Wright
jas@druxy.UUCP (ShanklandJA) (03/19/84)
Phil Ngai says:
barf. I hate octal.
Right! If God had wanted us to work with octal rather than hexadecimal,
She would have only given us eight fingers. :-)
Jim Shankland
..!ihnp4!druxy!jasron%brl-tgr@sri-unix.UUCP (03/19/84)
From: Ron Natalie <ron@brl-tgr> I don't expect you'll see the LSI-10 because DEC doesn't seem to be interested in coming out with *ANY* new processors in the 36 bit line. This is because they claim they don't want to get into competition with their own PDP/VAX products. IBM mainframes are still only 32 bits. UNIVAC doesn't seem to be moving into the PC business except to sell a japanese PC clone. -Ron
ron%brl-tgr@sri-unix.UUCP (03/19/84)
From: Ron Natalie <ron@brl-tgr> OK...before any body bothers to point this out, I don't really think IBM is interested in building a 7090 series micro. -Ron
hal@cornell.UUCP (Hal Perkins) (03/20/84)
There's really two issues here... First, is there any good reason for an
64-bit architecture as seen by the programmer? And second, is there any
good reason for 64-bit datapaths on a chip? My own bias is that 32-bit
integers and registers are wide enough for most anything--of course, this
may just be because that's been good enough for most large machines for
a long time, and my cultural blinders may prevent me from seeing a
good reason for 64-bit general registers. :-)
But 64-bit datapaths are a different story. It might be a useful way
to build a high-performance chip (64 bits on or off the chip each cycle).
There's a number of mainframes (like the big IBM machines) that have 64-bit
implementations of 32-bit architectures. The issue of what the programmer
sees is separate from (but related to) how the hardware designer implements it.
Hal Perkins UUCP: {decvax|vax135|...}!cornell!hal
Cornell Computer Science ARPA: hal@cornell BITNET: hal@crnlcsphil@amd70.UUCP (Phil Ngai) (03/24/84)
barf. I hate octal.
(there, that should start some flames)
--
Phil Ngai (408) 988-7777 {ucbvax,decwrl,ihnp4,allegra,intelca}!amd70!philhenry@utzoo.UUCP (Henry Spencer) (03/25/84)
But God did give us only 8 fingers. The thumbs are parity bits.
Octal forever!
--
Henry Spencer @ U of Toronto Zoology
{allegra,ihnp4,linus,decvax}!utzoo!henryaccuncg@ecsvax.UUCP (03/28/84)
Re: utzoo.3674 - What next, 64 bit micros? Eight fingers? Wouldn't that imply hexadecimal--in fact, an entire byte? I once taught a second-grade class how to count (in binary) to 1,000 (decimal) on the fingers (and thumbs) of two hands. Try it: You'll LIKE it! T. W. Hildebrandt Academic Computer Center UNC-Greensboro Greensboro, NC 27412