Re: End of optimization...

"norm@plumpirate.com" <channahr@comcast.net>
4 Aug 2003 00:05:42 -0400

          From comp.compilers

Related articles
[4 earlier articles]
Re: End of optimization... walter@bytecraft.com (Walter Banks) (2003-07-17)
Re: End of optimization... mayan@sandbridgetech.com (2003-07-21)
Re: End of optimization... walter@bytecraft.com (Walter Banks) (2003-07-23)
Re: End of optimization... nej22@cl.cam.ac.uk (2003-07-25)
Re: End of optimization... fjh@cs.mu.oz.au (Fergus Henderson) (2003-07-25)
Re: End of optimization... Robert@Knighten.org (2003-07-31)
Re: End of optimization... channahr@comcast.net (norm@plumpirate.com) (2003-08-04)
Re: End of optimization... qsmgmt@earthlink.net (Alan Lehotsky) (2003-08-04)
Re: End of optimization... fjh@cs.mu.oz.au (Fergus Henderson) (2003-08-04)
Re: End of optimization... Robert@Knighten.org (2003-08-10)
Re: End of optimization... Robert@Knighten.org (2003-08-10)
| List of all articles for this month |

From: "norm@plumpirate.com" <channahr@comcast.net>
Newsgroups: comp.compilers
Date: 4 Aug 2003 00:05:42 -0400
Organization: Comcast Online
References: 03-07-026 03-07-068 03-07-151 03-07-179 03-07-200
Keywords: optimize, practice
Posted-Date: 04 Aug 2003 00:05:42 EDT

Just to add one data point, graphics devices are just starting to
become programmable, with several early forms of high level languages
under development.


Such languages and the supporting hardware, look somewhat general
purpose but have a lot of specialized graphics features, so compilers
for these languages are hard to produce automatically.


For example, the chips that ATI makes have a large number of vector
registers each of length four, which I think would be hard to express
to some general compiler generator tool.


Optimization is very important to graphic chip compilers, because the
only reason people buy graphic processors is that they outperform
stock cpus.


"Robert L. Knighten" <Robert@Knighten.org> wrote in message
> mayan@sandbridgetech.com writes:
> > >Compilers only make sense for platforms - i.e. for some kind of
> > >generally programmable hardware for which a moderate number of
> > >applications will be developed.
>
> Fergus Henderson <fjh@cs.mu.oz.au> writes:
> > I think this ignores technology improvements which mean that it is
> > possible to cheaply generate a somewhat optimizing compiler for
> > a new chip, by just giving a machine description for the new chip.


[Gee, I was writing programs for programmable graphics systems like
the Evans and Sutherland LDS-1 and IDI Idiiom in 1970. But it was
all in assembler back then. -John]





Post a followup to this message

Return to the comp.compilers page.
Search the comp.compilers archives again.