🚀 go-pugleaf

RetroBBS NetNews Server

Inspired by RockSolid Light RIP Retro Guy

Article View: comp.arch
Article #10971

Re: MIPS and MHz

#10971
From: Walter Bays
Date: Mon, 16 Nov 1992 18:30
46 lines
2708 bytes
In article 8937@odin.corp.sgi.com, mash@mash.wpd.sgi.com (John R. Mashey) writes:
>CFP92: Apogee C & FORTRAN 0.82 Alpha with integrated Kuck (for Classic & LX)
>	Sun C & FORTRAN 3.0 Alpha + Kuck (for SS10s) 
>...

Also:
	Sun C & FORTRAN 2.0.1 (Solaris 1 and Solaris 2) available now
	Apogee C & FORTRAN 1.0 (Solaris 1) available now
	8 or 10 other compilers listed in recent UNIX World and SunWorld articles

>Hence:
>	If you want best Dhrystone- MIPS rating, use Apogee C
>	If you want best SPECint92, use Sun C in 5/93
>	If you want best SPECfp92, use Apogee (soon, for low-end), or
>			Sun (in 5/93 for SS10s)
>	If you want best LINPACK, use Apogee (soon)

No, I cannot recommend a compiler for you, but if you want the best
performance for *your* application, you have several compilers to
choose from.

Or if you want the best development environment, you have several
compilers to choose from.  Or support for the most languages, or best
support library availability, or the most robust code, or lowest price, ...

For hardware, the standard benchmarks give you an initial filter of
systems based on performance before making a final selection based on
your application performance, plus other factors.  However for
software, in the X86 and SPARC worlds where there are several competing
compilers, you can also use standard benchmarks as an initial filter if
performance is most important to you.  Of course if another factor is
most important you'll use that to filter instead.

Actually, for most systems now you do at least have two choices of
compiler - the other being Gnu.

The analogue between software and hardware extends to buying system A
now with the expectation of upgrading to system A1 later - you like
current performance plus growth path.  You can also buy compiler B now
with the expectation of upgrading to version B1 later.

---
These are my personal opinions, not those of Sun or SPEC.
Walter Bays                                         walter.bays@eng.sun.com
Sun Microsystems,  2550 Garcia Ave.,  MTV15-404,  Mountain View,  CA  94043
(415) 336-3689     SPEC Steering Committee Chairman      FAX (415) 968-4873
Technical Details
Message-ID: <lgfq6kINN7u5@exodus.Eng.Sun.COM>
Path: arc1-ca.pugleaf.net!sparky!uunet!walter!att-out!pacbell.com!sgiblab!darwin.sura.net!wupost!cs.utexas.edu!sun-barr!news2me.EBay.Sun.COM!exodus.Eng.Sun.COM!zarquon!walter
References: <1992Nov16.005122.8937@odin.corp.sgi.com>

Show Full Headers
Complete Article Headers
Path: arc1-ca.pugleaf.net!sparky!uunet!walter!att-out!pacbell.com!sgiblab!darwin.sura.net!wupost!cs.utexas.edu!sun-barr!news2me.EBay.Sun.COM!exodus.Eng.Sun.COM!zarquon!walter
From: walter@zarquon.Eng.Sun.COM (Walter Bays)
Newsgroups: comp.arch
Subject: Re: MIPS and MHz
Date: 16 Nov 1992 18:30:44 GMT
Organization: Sun Microsystems
Lines: 47
Distribution: world
Message-ID: <lgfq6kINN7u5@exodus.Eng.Sun.COM>
References: <1992Nov16.005122.8937@odin.corp.sgi.com>
Reply-To: walter@zarquon.Eng.Sun.COM
NNTP-Posting-Host: zarquon