Refinement GPU: atom densities uploaded only when some B moved, one device copy, positions through a pinned buffer

Every evaluation uploaded both copies of the atoms' densities (the gather's and the gradient's) and their
boxes, although in a positions-only minimisation no B changes between two Refits. The engine now keeps one
copy (the gradient kernel reads ModelDensityGPU's atoms and boxes), uploads it only where some atom's
density was made again, and sends the positions from a pinned buffer without waiting. The densities that
are made again (every atom in a B minimisation) and the grid positions are worked out on the refinement's
threads. Same bits.

9yl4: upload 3.29 -> 0.56 s, host side 1.29 -> 0.61 s, refinement 22.3 -> 17.7 s; 5reo 4.8 -> 4.4 s
(RTX 5080, -N 8, loaded box).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015CeEGgpKdfkCTJb3YNMJcu
(cherry picked from commit 46c3b67c91aee0aec3473b0fb1a4945c00bda070)
(cherry picked from commit 0aebc98110c8155932af647d6204891aec662294)

image_analysis/structure_refinement/Refinement.cpp

@@ -611,7 +611,7 @@ void MakeEngine(Context &ctx, bool gpu, const RefinementSettings &settings, Logg
             const size_t budget = usable > settings.gpu_resident_bytes ? usable - settings.gpu_resident_bytes : 0;
             size_t bytes = 0;
             ctx.engine = MakeRefinementEngineGPU(device, ctx.cell, *ctx.sg, ctx.d_min, ctx.refl, ctx.Model(),
-                                                 ctx.b_ceiling, budget, &bytes);
+                                                 ctx.b_ceiling, budget, &bytes, settings.nthreads);
             if (ctx.engine)
                 ctx.scale_gpu = std::make_unique<ModelScaleGPUPool>(device, ctx.refl.Size(), 1);
             else