Draft of segmented reduce optimization

[gevtushenko]

This PR applies a technique similar to one in segmented sort algorithm. Segments are partitioned and various thread groups are applied to various segment categories. While optimizing segmented reduction I introduced warp reduce agent and generalized reduce agent implementation. Below are speedups for small segment sizes, best speedup is about 66x:

Medium size segments experience minor slowdowns, but it can be addressed by further tuning:

Large size segments are not affected by optimization:

In the commits, there's an attempt to fuse small segments reduction with the partitioning stage. This optimization doesn't perform as well. My guess is that it slows down decoupled look-back at the partitioning stage or affects it's occupancy, which leads to overall slowdown.

In order not to break stream capture (if one is used), I incorporated a separate check for that. We might need to check stream capturing mode in our tests later.

[gevtushenko]

Experimented with a deterministic version of large segments optimization. Assigned a number of CTAs per each segment. The optimization is quite expensive in terms of the memory and requires about num_segments * (sizeof(int) + 4 * sizeof(AccumulatorT)). The speedup disappears as soon as there's about 16 large segments (particular number depends on the number of SMs), so I don't think it's worth it. Just in case, pushed and reverted mentioned optimization.