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 -- Hal Daume III "Computer science is no more about computers | hdaume@isi.edu than astronomy is about telescopes." -Dijkstra | www.isi.edu/~hdaume
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
-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 On Tuesday 22 January 2002 23:59, Hal Daume III wrote:
I'm open to all ideas...
Here is one: a matlab like matrix based language that is compiled into efficient parallel shared-nothing code. You can go for dense or sparse matrices, and allow imperative features or not. The compiler decides all data distribution/replication. The general case is too difficult but you could take a very limited language, ie array expressions with a few operations like A <- A^T * (B + C * C ) An easier one would use HPF style hints from the programmer for data distribution. distribute A checker-board B <- f (A * A^T) The compiler would align B with A, ie infer B's distribution from A's looking at the statement above. Thanks, - -- Eray Ozkural (exa) <erayo@cs.bilkent.edu.tr> Comp. Sci. Dept., Bilkent University, Ankara www: http://www.cs.bilkent.edu.tr/~erayo GPG public key fingerprint: 360C 852F 88B0 A745 F31B EA0F 7C07 AE16 874D 539C -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.0.6 (GNU/Linux) Comment: For info see http://www.gnupg.org iD8DBQE8TiR4fAeuFodNU5wRAmsdAJ9eAsQ9gj6g4hAqGljonvL34ZX5hACgpvlr wEnS4v5eljrvR5J02FfOi8g= =LJbf -----END PGP SIGNATURE-----
participants (3)
-
Eray Ozkural (exa) -
Hal Daume III -
Nicolas Oury