ideas for compiler project

Nicolas Oury Nicolas.Oury@ens-lyon.fr
Wed, 23 Jan 2002 00:49:28 +0100


Hello,
This can be totzlly silly and i don't know if it hs been already done but 
pure functionnal languages, like Haskell, make some parallelism appears, 
because the order of evaluation of expression isn't important for the result 
in  evaluation. I think you could try to use that in order to fill well a 
VLIW or SIMD architecture (like multimedia extension of common processors).

Maybe this isn't original at all or silly or not usefull.
I'm not a specialist.
Best regards,
Nicolas Oury
> Hi All,
>
> I'm currently taking a class in compiler optimization for high performance
> computing (i.e., parallel architectures, including VLIW, FPGA, multimedia
> extension architectures, systems-on-a-chip, etc).  It's the second of two
> graduate level compiler courses, and it purely project based.  And the
> project is of our choosing.
>
> The professor has made some suggested projects, which I could do, but none
> of them are really FP specific.  I'm curious if anyone has any ideas of a
> project I could do.  I'm looking for something that's open, yet
> constrained, etc (standard semester-long-project-course stuff), hopefully
> having to do with optimizations specifically for FPLs, or at least ones
> that would benefit them.
>
> I'm open to all ideas...
>
>  - Hal