Article View: comp.arch
Article #20694Myrias (was: Re: looking for >32-bit address space)
From: Steve Schoettler
Date: Fri, 07 Apr 1989 17:41
Date: Fri, 07 Apr 1989 17:41
51 lines
2685 bytes
2685 bytes
In article <12289@reed.UUCP> mdr@reed.UUCP (Mike Rutenberg) writes:
>
>Total aside: Does the Myrias machine exist yet? How come nobody is
>willing to post a description of it? I've heard some really unusual
>stories, but have seen nothing at all solid.
>--
>Mike Rutenberg Reed College, Portland Oregon (503)239-4434 (home)
>BITNET: mdr@reed.bitnet UUCP: uunet!tektronix!reed!mdr
Well, Chris hasn't responded, so here goes...
I think they finally got their act together and have built an
interesting machine. Here's some already published information from
the COMPCON '89 proceedings:
They have developed an ISA to support translation to other target
architectures and to provide parallelism to the programmer.
Compilation occurs in two phases: a front-end, from C or Fortran to the ISA,
and a back-end, from the ISA to some target microprocessor.
They liken microcoded machines such as the VAX or 370 to a RISC
interpreting their ISA. This may be similar to MIPS U-code or
the intermediate code of the HP Precision architecture.
The ISA to target machine translation is transparent to the programmer,
and all implementations are object-code compatible.
now I quote:
"To date, there have been three implementations of the G ISA:
- on a 68000-based parallel system (SPS-I)
- on a Sun 3 workstation, with simulated parallelism (PPWB)
- on a 68020-based parallel system (SPS-2)
The SPS-1 system was used by Myrias for proof-of-concept, and for software
development, from the beginning of 1987 to mid-1989. The PPWB (parallel
programmer's workbench) is available as a tool for potential customers
to evaluate the programming environment or do program development. The
Myrias SPS-2, announced in late 1988, is available for commercial sale
in configurations ranging from 60 to over 1,000 processors."
"Design has started on an implementation using a new RISC cpu."
Sorry if this sounds commercial. I have no relationship with Myrias.
--
Steve Schoettler
shs@uts.amdahl.com
{sun,decwrl,pyramid,ames,uunet}!amdahl!shs
Amdahl Corp., M/S 213, 1250 E. Arques Ave, Sunnyvale, CA 94088
Technical Details
Message-ID:
<16.ok3eIdN10100JP4.@amdahl.uts.amdahl.com>Path:
arc1-ca.pugleaf.net!utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!tut.cis.ohio-state.edu!bloom-beacon!apple!amdahl!shsReferences:
<1032@myrias.UUCP> <12289@reed.UUCP>Show Full Headers
Complete Article Headers
Path: arc1-ca.pugleaf.net!utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!tut.cis.ohio-state.edu!bloom-beacon!apple!amdahl!shs From: shs@uts.amdahl.com (Steve Schoettler) Newsgroups: comp.arch Subject: Myrias (was: Re: looking for >32-bit address space) Message-ID: <16.ok3eIdN10100JP4.@amdahl.uts.amdahl.com> Date: 7 Apr 89 17:41:17 GMT References: <1032@myrias.UUCP> <12289@reed.UUCP> Reply-To: shs@amdahl.uts.amdahl.com (Steve Schoettler) Organization: Amdahl Corporation, Sunnyvale CA Lines: 51