<p dir="ltr">I'm curious about the plans forward with this. Test-bed to improve 'stock' GHC & back-end(s)? An actual full-fledged (& maintained) back-end? ...</p>
<p dir="ltr">Nicolas</p>
<p dir="ltr">On Jul 3, 2013 8:48 PM, "Ryan Newton" <<a href="mailto:rrnewton@gmail.com">rrnewton@gmail.com</a>> wrote:<br>
><br>
> 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.<br>
><br>
> The small bit that I know:<br>
> It is a new backend that takes Core from GHC and does the rest itself (including having a non-GHC runtime).<br>
> There are some patches to GHC (somewhere?) to support a new kind of initialization-only vector.<br>
> 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.<br>
> It handles a pretty sizable subset of the language, but is missing some things (e.g. asynchronous exceptions).<br>
> It is not released yet<br>
> On Tue, Jul 2, 2013 at 7:54 PM, Carter Schonwald <<a href="mailto:carter.schonwald@gmail.com">carter.schonwald@gmail.com</a>> wrote:<br>
>><br>
>> 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. <br>
>><br>
>> 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. <br>
>><br>
>><br>
>> On Tuesday, July 2, 2013, Ryan Newton wrote:<br>
>>><br>
>>> Gosh, sorry, yes it's not obvious from the list of accepted papers:<br>
>>><br>
>>> "Automatic SIMD Vectorization for Haskell" Leaf Petersen, Dominic Orchard and Neal Glew<br>
>>><br>
>>> One of the authors has a link for it but it appears there's no preprint up yet:<br>
>>> <a href="http://www.leafpetersen.com/leaf/publications.htm">http://www.leafpetersen.com/leaf/publications.htm</a><br>
>>><br>
>>><br>
>>><br>
>>><br>
>>><br>
>>><br>
>>> On Tue, Jul 2, 2013 at 5:36 AM, Nicolas Trangez <<a href="mailto:nicolas@incubaid.com">nicolas@incubaid.com</a>> wrote:<br>
>>>><br>
>>>> On Mon, 2013-07-01 at 12:05 -0400, Ryan Newton wrote:<br>
>>>> > Err, GCC replacement. But, ironically, GHC [backend] replacement as well,<br>
>>>> > as of the recent ICFP paper.<br>
>>>><br>
>>>> Got a link or reference?<br>
>>>><br>
>>>> Nicolas<br>
>>>><br>
>>>><br>
>>>> _______________________________________________<br>
>>>> ghc-devs mailing list<br>
>>>> <a href="mailto:ghc-devs@haskell.org">ghc-devs@haskell.org</a><br>
>>>> <a href="http://www.haskell.org/mailman/listinfo/ghc-devs">http://www.haskell.org/mailman/listinfo/ghc-devs</a><br>
>>><br>
>>><br>
><br>
</p>