19 Oct
2010
19 Oct
'10
6:41 a.m.
On 19.10.2010, at 02:15, David Abrahams wrote:
I don't understand what you're talking about in that section above, but I think you're making things too complicated because you're fixated on the idea of a heterogeneous sequence. Here's a simple extension to the hierarchical algorithm formulation that I think could accomodate SIMD. The key change is the segment_fill function, which gives us an additional customization point with which to capture SIMD segments
Oh, that's nice. Sebastian