GitLab

The timers are mapped to a std::string. The basic ones (P2L, P2M, M2M,
M2P, M2L, L2L, L2P, P2P) have a constexpr definition. Any new timer can
be added by calling `Timers["timer name"];`.

This unifies the interface of uniform and adaptive algorithms.

The P2L computes particles contributions using vectorized units. Each
computation result is then reduced to the local expansion.

When the particle count is not a multiple of the vector size,
computation is done with extra zero-initialised particles. This
behaviour is problematic with 1/r matrix kernel family when the
interpolation point is the origin (0,0,0). The extra particles
contribution is then Not-A-Number and the reduction propagates this to
the full local expansion.

To mitigate this issue, the last (nb_particles % vector_size) particles
are computed one by one.

The neighbours no longer need to be ordered by their index relative to
the center node. There may be more than 14 neighbours to compute with.