Subject: Re: [boost] Accelerating algorithms with SIMD - Segmented iterators and alternatives
From: David Abrahams (dave_at_[hidden])
Date: 2010-10-11 11:37:21
At Mon, 11 Oct 2010 16:19:13 +0100,
Mathias Gaunard wrote:
> I have already suggested such an alternative to segmented iterators
> (where I had a few misconceptions about segmented iterators, I thought
> they broke compatibility, but they don't, they still maintain the legacy
> non-segmented interface) there:
> with an example of how you could use that to iterate over a binary tree
> Converting from those things to a pair of iterators is possible through
> the use of a coroutine, as demonstrated in the example.
> I would like to have feedback on the general idea of providing tools
> to use SIMD with iterators and related algorithms,
> and ideas about whether there is sufficient interest in the
> alternative to iterators for me to develop them. The intent would
> be to submit both the alternative to iterators and the SIMD helpers
> to Boost.
Now that your misconceptions about segmented iterators are cleared up,
could you give a brief rundown of your alternative and its advantages?
If all I have to do is read your earlier post and ignore claims of
broken compatibility, just say so, but I don't want to waste time
trying to decipher it if it's substantially wrong.
-- Dave Abrahams BoostPro Computing http://www.boostpro.com