El 27/09/2017 a las 18:23, Thorsten Ottosen via Boost escribió:
For 32-bit release mode on windows 7 64 bit with intel i7-2700K:
[...]
So basically the same as your results. The case for segment size 32 and a non-trivial lambda does show some speedup, doesn't it?
For 64-bit release mode on windows 7 64 bit with intel i7-2700K:
[...]
I don't know why a 64-bit program would be slower, but there seems to be a larger difference here.
I have no idea: ints are the same size in 64-bit mode, so the resulting structures are basically the same, I'd say. Anyway, there does seem to be cases where the difference is substantial, which could merit having specialized versions of std algorithms for batch_deque (or more generally, as discussed also in this thread, for segmented structures). I can try to help with that since I did something similar for Boost.PolyCollection (with an additional feature, namely type restitution, which is not applicable here). Joaquín M López Muñoz