Update the old plots in the README.md and add benchmarks to docs

.github/workflows/Documenter.yml

@@ -53,6 +53,10 @@ jobs:
                     joinpath(output_directory, "machines_tlsph.png"))
             savefig(plot!(plot_machines_tlsph_deformation_grad(); title = ""),
                     joinpath(output_directory, "machines_tlsph_deformation_gradient.png"))
+            savefig(plot!(plot_implementations_wcsph(); title = ""),
+                    joinpath(output_directory, "implementations_wcsph.png"))
+            savefig(plot!(plot_update_strategies(); title = ""),
+                    joinpath(output_directory, "update_strategies.png"))
           '
       - name: Build and deploy
         env:

README.md

@@ -21,8 +21,8 @@
 - Designed as a "playground" to easily switch between different implementations and data
   structures
 - Common API over all implementations
-- Extensive benchmark suite to study different implementations (work in progress)
-- GPU compatibility (work in progress)
+- Extensive benchmark suite to study different implementations
+- GPU compatibility
 
 | Implementation  | Description | Features | Query | Update | GPU-compatible |
 | ------------- | ------------- | --- | :--: | :--: | :--: |
@@ -32,16 +32,13 @@
 
 ## Benchmarks by Implementation
 
-The following benchmarks were conducted on an AMD Ryzen Threadripper 3990X using 128 threads.
+The following benchmarks were conducted on an Intel Xeon W9-3475X using 36 threads.
 
 Benchmark of a single force computation step of a Weakly Compressible SPH (WCSPH) simulation:
-![wcsph](https://github.com/trixi-framework/PointNeighbors.jl/assets/44124897/ad5c378b-9ce2-4e6f-91dc-1e0da379b91f)
+![WCSPH benchmark by implementation](https://trixi-framework.org/PointNeighbors.jl/dev/assets/benchmarks/implementations_wcsph.png)
 
-Benchmark of an incremental update similar to a WCSPH simulation (note the log scale):
-![update](https://github.com/trixi-framework/PointNeighbors.jl/assets/44124897/71eac5c9-6aa5-4267-bc0b-4057c89f8b12)
-
-Benchmark of a full right-hand side evaluation of a WCSPH simulation (note the log scale):
-![rhs](https://github.com/trixi-framework/PointNeighbors.jl/assets/44124897/ac328a96-1b9f-4319-a785-dce9d862fd70)
+Benchmark of different neighborhood search update strategies:
+![Benchmark by update strategy](https://trixi-framework.org/PointNeighbors.jl/dev/assets/benchmarks/update_strategies.png)
 
 
 ## Benchmarks by Machine

benchmarks/plot_benchmarks.jl

@@ -41,6 +41,8 @@ function plot_benchmark!(p, n_particles_vec, times; kwargs...)
 
     plot!(p, n_particles_vec, n_particles_vec ./ times .* 1e-6;
           xaxis = :log, xticks = (n_particles_vec, xticks), linewidth = 2,
+          # Make sure the plot starts at y = 0.
+          ylimits = (0, Inf), widen = true,
           xlabel = "#particles", ylabel = "million particles processed per second",
           legend = :outerright, size = (700, 350), dpi = 600, margin = 4 * Plots.mm,
           palette = palette(:tab10), kwargs...)
@@ -86,7 +88,22 @@ benchmark_runtimes = (n_particles = [
                       n_particles_tlsph_deformation_grad_5090 = [
                           1000, 4096, 15625, 64000, 250047, 1030301, 4096000, 16387064,
                           42875000],
-                      tlsph_deformation_grad_5090_fp32 = [5.6569e-5; 6.894e-5; 7.6672e-5; 8.3602e-5; 0.000313116; 0.00099187; 0.003671176; 0.015459844; 0.041021319;;])
+                      tlsph_deformation_grad_5090_fp32 = [5.6569e-5; 6.894e-5; 7.6672e-5; 8.3602e-5; 0.000313116; 0.00099187; 0.003671176; 0.015459844; 0.041021319;;],
+                      # Benchmarking the difference between implementations on an
+                      # Intel Xeon W9-3475X (x36).
+                      # _, times = run_benchmark_default(benchmark_wcsph, ...)
+                      wcsph_w9_3475x_dictionary = [9.539e-5; 0.000507708; 0.001999838; 0.008442291; 0.034369512; 0.145935124; 0.581081578; 2.341472385; 9.445755411;;],
+                      wcsph_w9_3475x_fullgrid = [6.0765e-5; 0.000402875; 0.001569317; 0.006578832; 0.026040483; 0.108027132; 0.434874618; 1.755279267; 7.07428452;;],
+                      wcsph_w9_3475x_precomputed = [3.7762e-5; 0.000148563; 0.00054964; 0.002274807; 0.00899912; 0.037950566; 0.151298558; 0.607103175; 2.440462785;;],
+                      # NaN values are just placeholders because the benchmark took too long.
+                      wcsph_w9_3475x_trivial = [6.3518e-5; 0.000669186; 0.008641863; 0.135930064; 2.468379663; 43.607518925; NaN; NaN; NaN;;],
+                      # Benchmarking the difference between update strategies on an
+                      # Intel Xeon W9-3475X (x36).
+                      # _, times = run_benchmark_updates((10, 10, 10), 9)
+                      update_w9_3475x_parallel = [1.42395e-5; 1.9205e-5; 3.3569e-5; 7.6216e-5; 0.0001972665; 0.000657154; 0.002366056; 0.008558718; 0.0328478125;;],
+                      update_w9_3475x_parallel_incremental = [1.05465e-5; 1.41955e-5; 2.36415e-5; 6.3423e-5; 0.000185218; 0.0007833225; 0.0052182165; 0.025595217; 0.103340834;;],
+                      update_w9_3475x_semi_parallel = [1.00805e-5; 1.78505e-5; 4.28215e-5; 0.000153458; 0.0006931965; 0.0026806445; 0.0158252845; 0.079710013; 0.329653309;;],
+                      update_w9_3475x_precomputed = [0.000156829; 0.0005617385; 0.0021646195; 0.009024255; 0.0354495175; 0.1443668715; 0.5821228515; 2.341333004; 9.381562997;;])
 
 function plot_machines_wcsph()
     times = hcat(benchmark_runtimes.wcsph_5090_fp32,
@@ -132,3 +149,33 @@ function plot_machines_tlsph_deformation_grad()
 
     plot_benchmark!(p, benchmark_runtimes.n_particles, times; label = names)
 end
+
+function plot_implementations_wcsph()
+    times = hcat(benchmark_runtimes.wcsph_w9_3475x_precomputed,
+                 benchmark_runtimes.wcsph_w9_3475x_fullgrid,
+                 benchmark_runtimes.wcsph_w9_3475x_dictionary,
+                 benchmark_runtimes.wcsph_w9_3475x_trivial)
+
+    names = ["PrecomputedNeighborhoodSearch";;
+             "GNHS & FullGridCellList";;
+             "GridNeighborhoodSearch";;
+             "TrivialNeighborhoodSearch";;]
+
+    plot_benchmark(benchmark_runtimes.n_particles, times; label = names,
+                   title = "WCSPH on Intel Xeon W9-3475X (x36)")
+end
+
+function plot_update_strategies()
+    times = hcat(benchmark_runtimes.update_w9_3475x_parallel,
+                 benchmark_runtimes.update_w9_3475x_parallel_incremental,
+                 benchmark_runtimes.update_w9_3475x_semi_parallel,
+                 benchmark_runtimes.update_w9_3475x_precomputed)
+
+    names = ["GNHS & ParallelUpdate";;
+             "GNHS & ParallelIncrementalUpdate";;
+             "GNHS & SemiParallelUpdate";;
+             "PrecomputedNeighborhoodSearch";;]
+
+    plot_benchmark(benchmark_runtimes.n_particles, times; label = names,
+                   title = "Update strategies on Intel Xeon W9-3475X (x36)")
+end

benchmarks/run_benchmarks.jl

@@ -283,14 +283,36 @@ function run_benchmark_precomputed(benchmark, n_points_per_dimension, iterations
                   neighborhood_searches; names, parallelization_backend, kwargs...)
 end
 
-function create_full_grid_neighborhood_search(n_points_per_dimension)
+function run_benchmark_updates(n_points_per_dimension, iterations;
+                               parallelization_backend = PolyesterBackend(), kwargs...)
+    parallel = create_full_grid_neighborhood_search(n_points_per_dimension;
+                                                    update_strategy = ParallelUpdate())
+    parallel_incremental = create_full_grid_neighborhood_search(n_points_per_dimension;
+                                                                update_strategy = ParallelIncrementalUpdate())
+    semi_parallel = create_full_grid_neighborhood_search(n_points_per_dimension;
+                                                         update_strategy = SemiParallelUpdate())
+    precomputed_nhs = create_precomputed_neighborhood_search(parallel,
+                                                             parallelization_backend)
+    neighborhood_searches = (parallel, parallel_incremental, semi_parallel, precomputed_nhs)
+
+    names = ["GNHS with ParallelUpdate";;
+             "GNHS with ParallelIncrementalUpdate";;
+             "GNHS with SemiParallelUpdate";;
+             "PrecomputedNeighborhoodSearch";;]
+
+    run_benchmark(benchmark_update_alternating, n_points_per_dimension, iterations,
+                  neighborhood_searches; names, parallelization_backend, kwargs...)
+end
+
+function create_full_grid_neighborhood_search(n_points_per_dimension;
+                                              update_strategy = ParallelUpdate())
     NDIMS = length(n_points_per_dimension)
 
     min_corner = 0.0f0 .* n_points_per_dimension
     max_corner = Float32.(n_points_per_dimension ./ maximum(n_points_per_dimension))
     cell_list = FullGridCellList(; search_radius = 0.0f0, min_corner, max_corner)
     return GridNeighborhoodSearch{NDIMS}(; search_radius = 0.0f0, cell_list,
-                                         update_strategy = ParallelUpdate())
+                                         update_strategy)
 end
 
 function create_precomputed_neighborhood_search(grid_nhs, parallelization_backend)