dag@fciva.FRANKLIN.COM (Daniel A. Graifer) (03/02/89)
Recent articles in both the Washington Post and The Wall Street Journal have hyped a new Intel chip with "record high densities". The articles contained essentially nothing of a technical nature. Does anyone know anything more about this chip? Just thought I'd ask! Dan
rogers@orion.SRC.Honeywell.COM (Brynn Rogers) (03/04/89)
In article <455@fciva.FRANKLIN.COM> dag@fciva.UUCP (Daniel A. Graifer) writes: >Recent articles in both the Washington Post and The Wall Street Journal >have hyped a new Intel chip with "record high densities". The articles >contained essentially nothing of a technical nature. Does anyone know >anything more about this chip? >Just thought I'd ask! > Dan In todays marketplace section of the minneapolis star tribune the was a large picture of this chip. '... 1 million transistor microprocessor introduced monday by Intel ...' it goes on into about a quarter page of drivel about what microprocessers do, with statements like ' 100 transistors would fit across a human hair', and analogys like '... streets and alleys with traffic controled by signals at intersections ....[insert more blah blah blah]'. The few bits of information (information density of this article is 1%) that it seems to state are: a) 'The Intel chip is particularly adapted for graphics...' b) '... expected to hit the market later this year ...' c) '... transistors ... switch on and off roughly 50 million times a second.' d) in the picture approx 1/6 of the chip appears to be RAM. (on chip cache?) e) from the picture it is not a RISC, but definatly a CISC machine. Is this the 80486 we have all been waiting for?? 'Seek out new life and civilizations' | Brynn Rogers Honeywell S&RC "Honey, come see what I | UUCP: rogers@orion.uucp found in the refrigerator!" | !: {umn-cs,ems,bthpyb}!srcsip!rogers | Internet: rogers@src.honeywell.com
bobmon@iuvax.cs.indiana.edu (RAMontante) (03/04/89)
-Is this the 80486 we have all been waiting for??
The comp.arch newsgroup has been all agog about this. It was apparently
known as the N-10, is now called the i860. In scanning Intel's "official"
posting about it, I see little to think is is related to the misbegotten
80x86 line (aHEM). For example, it includes 32 32-bit general-purpose
registers. As I understand it, much of its performance derives from the
ability to execute one integer operation and two floating-point operations
simultaneously, with "all" instructions (be they single-op or multi-op)
taking 3 clock cycles. (Don't quote me.) A few excerpts follow (see
comp.arch for the full 125-line Intel statement) (spelling errors in the
following were in the original posting too):
____________
The following information is taken from the i860 TM 64-Bit Microprocessor
data sheet order number 240296-001. [ ... ]
i860 64-bit Microprocessor
Highlights:
Parallel Architecture: 3 instructions Clock
- one integer or control instruction
- up to to Floating Point Instructions
High Performance Design
- 33.3/40 MHz Clock Rate
- 80 MFLOP Peak Single Precision MFLOPs
- 60 MFLOP Peak Double Precision MFLOPs
- 64-bit External Data Bus
- 64-bit Internal Instruction Cache Bus
- 128-bit Internal Data Cache Bus
Measured Performance with Current Compilers
- 24 Megawhetsones (40 MHz)
- 83K Dhrystones (40 MHz)
Highly Integrated
- 32/64-bit Pipelined Floating-Point Adder and Multipler
- 32-bit Integer and Control Unit
- 64-Bit 3-D Graphics Unit
- Paging Unitg with TLB
- 4K Byte Instruction Cache
- 8K Byte Data Cache
[ technical descriptions deleted ...
There is a meta-interesting line: ]
{Editors note the i860 CPU's paging mechanism is the same
as the 386 CPU.}
So I guess it is partially misbegotten :-) I can't tell if this is a
comment by the Intel poster, a comment by someone who edited the posting, or
an instruction to magazine editors who might use this posting...
--
Those who do not understand MSDOS are | Bob Montante (bobmon@cs.indiana.edu)
condemned to write glowingly of it in | Computer Science Department
slick, short-lived magazines. | Indiana University, Bloomington INpavlov@hscfvax.harvard.edu (G.Pavlov) (03/05/89)
In article <18098@srcsip.UUCP>, rogers@orion.SRC.Honeywell.COM (Brynn Rogers) writes: > > In todays marketplace section of the minneapolis star tribune the was a > large picture of this chip. > '... 1 million transistor microprocessor introduced monday by Intel ...' > > Is this the 80486 we have all been waiting for?? No. > > .... (information density of this article is 1%) .... Are you talking about YOUR article ? :-) greg pavlov, fstrf, amherst, ny
mjt@super.ORG (Michael J. Tighe) (03/05/89)
In article <18098@srcsip.UUCP> rogers@orion.UUCP (Brynn Rogers) writes: [stuff about Intel chip deleted] >Is this the 80486 we have all been waiting for?? No, it is the new i860 chip, which is being discussed in comp.arch. -- ------------- Michael Tighe internet: mjt@super.org uunet: ...!uunet!super!mjt
james@bigtex.cactus.org (James Van Artsdalen) (03/06/89)
In <18098@srcsip.UUCP>, rogers@orion.UUCP (Brynn Rogers) wrote: > In article <455@fciva.FRANKLIN.COM> dag@fciva.UUCP (Daniel A. Graifer): > >Recent articles in both the Washington Post and The Wall Street Journal > >have hyped a new Intel chip with "record high densities". Sounds like hype to me.... > [...] The few bits of information (information density of this > article is 1%) that it seems to state are: > a) 'The Intel chip is particularly adapted for graphics...' > b) '... expected to hit the market later this year ...' > e) from the picture it is not a RISC, but definatly a CISC machine. 1 million devices, and you can tell from a newspaper picture that it is definitely a CISC and not a RISC? Did the silicon say "CISC" on it somewhere? I think it could be hard to tell a uCode store from a large register file at a glance... > Is this the 80486 we have all been waiting for?? Nope. It's probably the i860 (aka N-10) you've read about in Infoworld and such recently. The "graphics" part is what gives it away. The 486 is supposed to be just a fast 386 (ie, no new architecture), whereas the WSJ and others indicate that the i860 started life as a graphics coprocessor before becoming a CPU. -- James R. Van Artsdalen james@bigtex.cactus.org "Live Free or Die" DCC Corporation 9505 Arboretum Blvd Austin TX 78759 512-338-8789
grumpy@edg1.UUCP (Eric Schwarz) (03/07/89)
In article <18098@srcsip.UUCP>, rogers@orion.SRC.Honeywell.COM (Brynn Rogers) writes: > > Is this the 80486 we have all been waiting for?? No, it's the 80860. There is a description of the chip in comp.arch. The 80486 will not be that big an improvement over the 80386 (other that speed). Eric Schwarz uunet\!edg1!grumpy