[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [f-cpu] Winograd DCT on my seul.org account



hi !

Juergen Goeritz wrote:
> On Sat, 20 Apr 2002, Yann Guidon wrote:
> >Juergen Goeritz wrote:
> >> On Sat, 20 Apr 2002, Yann Guidon wrote:
> >> >Juergen Goeritz wrote:
<snip cascade>

> >> I would not try to reduce the input capabilities for the
> >> developer. Lately I ported a pascal program to C that was
> >> heavily using overlays. It was a bit tedious. If I had
> >> a pascal compiler with linux capable of overlays I could
> >> have just saved me this work. And imagine you want to
> >> rewrite the whole fortran library stuff. Better don't!!!
> >
> >arrgggghhhhh....
> >
> >however, i found that expressing algos in VHDL was not so difficult,
> >though it needed some leaning. But it was easier to learn VHDL than C
> >(for me). C is used everywhere and one feels a bit forced, but VHDL
> >is often tought very superficially and the benefits are not apparent.
> 
> Please don't code software in VHDL - but this is just
> my personal view and you could argue with me about it.

and i won't give up this pleasure ;-)
i would be very interested to see how such a parallel langage could
be transformed into a sequential code.
At least, the parallelism issues will disappear.
The overload functions provide the user with transparent means
to apply their algorithms on different data types.
The event-driven model makes some more things easier (like
the way functions are synchronised).
I like these ideas :-)
I don't want to use the ADA model verbatim, however.

> I learned C because it is THE U**X language.
but it's an oooooold langage :-( and it's not adapted
to today's computers...

> >> In general I propose an additional step in the toolchain
> >> compile/optimize - assemble - link - optimize - load.
> >
> >i seem to have understood something like that.
> >Now my idea was something like
> > cpp - gcc - as=>simulates the dumb CPU and optimize<= - link - load
> 
> We are not so far apart. Just put 'link' to the left, too.
> Linking is a dumb task that need not be addressed by your
> optimization and thus should better be left out. Its like
> cpp - gcc - as - link => for the dumb CPU => optimze - load

i am not at ease with that.
However, if we can use GCC 3/4 with XML export of the IR,
[far in the future] this won't be a problem anymore.
The GLIBC could be compiled in XML form and the linker could
choose to use only the necessary parts (if you only use
printf in your program) or "link" to te usual interface.
If only printf is needed, the corresponding XML IR is integrated
to the program's representation and optimised with it.

> >maybe if we provide a simplified ISA to gcc, compilation and debug
> >would be simpler...
> 
> Hm, hm! Debugging is depending on whether you let gcc
> use a real opcode subset very simple. Otherwise you
> have to have a sort of '-O0' switch in your afterburner
> optimizer. Debugging on heavy optimized programs brings
> a hack of invisibilities anyway and thus could be skipped.
> If you debug you want to see as much as possible!

i meant : debug/development of our "optimiser".

It is not a good thing to optimise an untested code, btw.

> >but before you optimise, take some time to learn how
> >to do that. I know that i don't write enough papers
> >about it, but you already know that F-CPU is another
> >new type of beast which needs its own techniques
> >and mindset. It was designed almost as a Trojan Horse,
> >seeming quite similar to others (to not scare the execs
> >out there) but the guts and programming habits have
> >probably no equivalent.
> 
> When you have finished your next paper (explaining it
> in more detail and other optimzation hints) I could
> probably convince myself to start to code such a beast...

i'll try my best...

but i better write papers that bring some money back to
my pocket, too. My chocolate budget is very important ;-)

some months ago, i wrote a french article that started as the
french translation of the VHDL-HOWTO and i earned some
money. i'll try to do that from time to time.
However, the DCT optimisation paper is not likely to be accepted
by any magazine i know.

> >As a "HW guy", you certainly have enough background
> >to understand most things, so i'm only worried about
> >my own ability to teach them.
> Good teaching lessons BTW ;-)

does that mean that you learned something ?
if yes ==> oh great ! ;-)

> JG
WHYGEE
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*************************************************************
To unsubscribe, send an e-mail to majordomo@seul.org with
unsubscribe f-cpu       in the body. http://f-cpu.seul.org/