PVR%bgerug51.earn@NSS.CS.UCL.AC.UK (Patrick Van Renterghem / Transputer Lab) (04/10/89)
Intel's new device, the I860, will again get a lot of attention in the
magazines. Most of these articles will be written by Intel employees and
are not always very realistic, to say the least. Messages from people who
have used and benchmarked this processor are highly appreciated.
I have a question for the network:
David Moody told me that Intel would introduce a transputer-like processor
on the market, with a much higher performance and bandwith. Does anyone
know if this is going to be a new chip, or something like this:
_________
| IC012 |
---|-|---
_________ ___|_|___ _________
| IC012 |-------| |-------| IC012 |
--------- | I 860 | ---------
_________ | | _________
| IC012 |-------| |-------| IC012 |
--------- ---|-|--- ---------
___|_|___
| IC012 |
---------
where IC012's are comparable with the IMS C012, but interface to a 100 Mbit/s
serial, byte acknowledged, point-to-point link. And manufactured by Intel
of course. Remark that I have given it 6 links.
Apart from the design of the IC012's, how difficult would the design around
the 860 be ? All by all, a full-blown version of the I860 would give it a
performance of 5 to 10 times the performance of an T801-30 and a little bit
more for vectorizable applications.
Any remarks on the 860, comparing it to transputers ?
I personally think plugging 10 transputers together would be a lot easier
than the Intel design, and more cost-effective, reliable, scalable, ...
But it pushes Inmos to develop and market their T810 (with a 2-4 times
performance increase in real applications, with 50 % faster links and
with 16 kB SRAM) just a little bit faster.
Patrickjab@loral.UUCP (Jeff A. Brooks) (04/11/89)
In article <8904101212.AA05679@uk.ac.ox.prg> PVR%bgerug51.earn@NSS.CS.UCL.AC.UK (Patrick Van Renterghem / Transputer Lab) writes: > >I have a question for the network: > > [...] >David Moody told me that Intel would introduce a transputer-like processor >on the market, with a much higher performance and bandwith. Does anyone >know if this is going to be a new chip, or something like this: > > [Diagram of I860 connected to six IC012's and description deleted] > >Any remarks on the 860, comparing it to transputers ? > > [...] > >Patrick An article in the Feb. 1989 "EE Product News" announced that Intel was working on a transputer clone called iWARP. The article was very short and didn't include many details just overall performance propaganda. Quotes from the article: The chip is capable of executing instructions at 20 MIPS ... ... has 256 bytes of high speed program cache RAM ... ... includes an on-chip floating point number cruncher... a digram shows: 160 Mbyte/sec local memory interface 4 input & 4 output 40 Mbyte/sec ports I called Intel about the chip and one of the marketing guys confirmed that the project exists and is being used as a special purpose processor for the Autonomous Vehicle project as well as for SDI. He also said that it was a Large Instruction Word (LIW), memory to memory machine aimed at signal and image processing systems. They plan to market the processor at the system level except for military applications. Single board arrays for Sun workstations was one application he mentioned specifically. Target languages are Fortran and C. In my opinion the iWARP is a completely different beast than the transputer. I mean the unique thing about the transputer is its asynchronous serial links. I bet that the only way the iWARP can get that 40byte/s transfer rate on those ports is via synchronous parallel transfers which shoots any link switch designs down. (Maybe thats why he called it a memory to memory machine :-). It seems that it would be very useful as a signal or image processor but not something as broad scoped as a parallel processor. Jeff
lohnert@b21.UUCP (Frieder Lohnert) (04/11/89)
In article <8904101212.AA05679@uk.ac.ox.prg>, PVR%bgerug51.earn@NSS.CS.UCL.AC.UK (Patrick Van Renterghem / Transputer Lab) writes: > > Intel's new device, the I860, will again get a lot of attention in the > magazines. Most of these articles will be written by Intel employees and > are not always very realistic, to say the least. Messages from people who > have used and benchmarked this processor are highly appreciated. > > I have a question for the network: > > David Moody told me that Intel would introduce a transputer-like processor > on the market, with a much higher performance and bandwith. Does anyone > know if this is going to be a new chip, or something like this: > The new INTEL Transputer-like (?) device is called iWARP. Reference: Proc. Supercomputing '88, Nov. '88, Orlando, Florida, pp. 330 By the way, does anyone know INMOS plans for future TRANSPUTERs ? ------------------------------------------------------------------------------- | Dr. F.Lohnert AEG Research Institute Berlin | | Parallel Processing Group Hollaenderstr. 31-34 | | E-mail: ..!mcvax!unido!b21!lohnert D-1000 Berlin 51 | | Phone: (..49-30) 4501-251 Telefax: (..49-30) 4556098 | -------------------------------------------------------------------------------