Re: [boost] Accelerating algorithms with SIMD - Segmented iterators and alternatives

Subject: Re: [boost] Accelerating algorithms with SIMD - Segmented iterators and alternatives
From: David Abrahams (dave_at_[hidden])
Date: 2010-10-14 04:26:35

At Wed, 13 Oct 2010 17:34:57 -0300,
Felipe Magno de Almeida wrote:
> 
> At first I thought that segmented iterators were what I needed. But
> then trying to work with it. I found that segmented iterators would
> differentiate segment iterators from local iterators in a way that
> didn't work in a tree-like structure.

Yes, they are designed to deal with a segmentation depth that's known
at compile-time.

> The nodes of the trees had to be moved to be the first in the local
> sequence because only local iterators are dereferenced in
> segmented-aware algorithms. This meant that segmented iterators
> weren't completely overhead-free.

Right.  Trees have any storage at internal nodes, which is another way
they differ from the kinds of structures segmented iterators work on.

> This doesn't mean segmented iterators aren't good, just that the
> use-case that I tried didn't seem to fit it.

Makes sense.

-- 
Dave Abrahams
BoostPro Computing
http://www.boostpro.com