This came up randomly because of a typo, but rather than respond for them I've changed the thread name to something descriptive and copies the authors of the paper.

The small bit that I know:

It is a new backend that takes Core from GHC and does the rest itself (including having a non-GHC runtime).
There are some patches to GHC (somewhere?) to support a new kind of initialization-only vector.
The IFLC backend uses a strict intermediate representation and performs auto-vectorization on loops. In particular, the paper evaluates the technique on loops from (slightly modified) REPA and vector library code.
It handles a pretty sizable subset of the language, but is missing some things (e.g. asynchronous exceptions).
It is not released yet

On Tue, Jul 2, 2013 at 7:54 PM, Carter Schonwald <carter.schonwald@gmail.com> wrote:

What branch is that work in? I've not seen mention of it in the commit logs. I'd really love to see how they're Doing it.

Likewise, it's worth remarking that a carefullywritten simd primop that explicitly uses the instruction intrinsics can easily be 1.5-2x faster than auto vectorized simd code. I've some examples I tested for matrix multiplication where the performance is robustly In that range.

On Tuesday, July 2, 2013, Ryan Newton wrote:

Gosh, sorry, yes it's not obvious from the list of accepted papers:

"Automatic SIMD Vectorization for Haskell" Leaf Petersen, Dominic Orchard and Neal Glew

One of the authors has a link for it but it appears there's no preprint up yet:

http://www.leafpetersen.com/leaf/publications.htm

On Tue, Jul 2, 2013 at 5:36 AM, Nicolas Trangez <nicolas@incubaid.com> wrote:

On Mon, 2013-07-01 at 12:05 -0400, Ryan Newton wrote:
> Err, GCC replacement. But, ironically, GHC [backend] replacement as well,
> as of the recent ICFP paper.

Got a link or reference?

Nicolas

_______________________________________________
ghc-devs mailing list
ghc-devs@haskell.org
http://www.haskell.org/mailman/listinfo/ghc-devs