Rewrite Model with bitmask wave and AC-4 propagator (~5x speedup)

.serena/.gitignore

@@ -0,0 +1,2 @@
+/cache
+/project.local.yml

.serena/project.yml

@@ -0,0 +1,133 @@
+# the name by which the project can be referenced within Serena
+project_name: "wave-function-collapse-ruby"
+
+
+# list of languages for which language servers are started; choose from:
+#   al                  angular             ansible             bash                clojure
+#   cpp                 cpp_ccls            crystal             csharp              csharp_omnisharp
+#   dart                elixir              elm                 erlang              fortran
+#   fsharp              go                  groovy              haskell             haxe
+#   hlsl                html                java                json                julia
+#   kotlin              lean4               lua                 luau                markdown
+#   matlab              msl                 nix                 ocaml               pascal
+#   perl                php                 php_phpactor        powershell          python
+#   python_jedi         python_ty           r                   rego                ruby
+#   ruby_solargraph     rust                scala               scss                solidity
+#   svelte              swift               systemverilog       terraform           toml
+#   typescript          typescript_vts      vue                 yaml                zig
+#   (This list may be outdated. For the current list, see values of Language enum here:
+#   https://github.com/oraios/serena/blob/main/src/solidlsp/ls_config.py
+#   For some languages, there are alternative language servers, e.g. csharp_omnisharp, ruby_solargraph.)
+# Note:
+#   - For C, use cpp
+#   - For JavaScript, use typescript
+#   - For Angular projects, use angular (subsumes typescript+html; requires `npm install` in the project root)
+#   - For Svelte projects, use svelte (subsumes typescript/javascript for .svelte projects; requires npm)
+#   - For SCSS / Sass / plain CSS, use scss (some-sass-language-server handles all three)
+#   - For Free Pascal/Lazarus, use pascal
+# Special requirements:
+#   Some languages require additional setup/installations.
+#   See here for details: https://oraios.github.io/serena/01-about/020_programming-languages.html#language-servers
+# When using multiple languages, the first language server that supports a given file will be used for that file.
+# The first language is the default language and the respective language server will be used as a fallback.
+# Note that when using the JetBrains backend, language servers are not used and this list is correspondingly ignored.
+languages:
+- ruby
+
+# the encoding used by text files in the project
+# For a list of possible encodings, see https://docs.python.org/3.11/library/codecs.html#standard-encodings
+encoding: "utf-8"
+
+# line ending convention to use when writing source files.
+# Possible values: unset (use global setting), "lf", "crlf", or "native" (platform default)
+# This does not affect Serena's own files (e.g. memories and configuration files), which always use native line endings.
+line_ending:
+
+# The language backend to use for this project.
+# If not set, the global setting from serena_config.yml is used.
+# Valid values: LSP, JetBrains
+# Note: the backend is fixed at startup. If a project with a different backend
+# is activated post-init, an error will be returned.
+language_backend:
+
+# whether to use project's .gitignore files to ignore files
+ignore_all_files_in_gitignore: true
+
+# advanced configuration option allowing to configure language server-specific options.
+# Maps the language key to the options.
+# Have a look at the docstring of the constructors of the LS implementations within solidlsp (e.g., for C# or PHP) to see which options are available.
+# No documentation on options means no options are available.
+ls_specific_settings: {}
+
+# list of additional workspace folder paths for cross-package reference support (e.g. in monorepos).
+# Paths can be absolute or relative to the project root.
+# Each folder is registered as an LSP workspace folder, enabling language servers to discover
+# symbols and references across package boundaries.
+# Currently supported for: TypeScript.
+# Example:
+#   additional_workspace_folders:
+#     - ../sibling-package
+#     - ../shared-lib
+additional_workspace_folders: []
+
+# list of additional paths to ignore in this project.
+# Same syntax as gitignore, so you can use * and **.
+# Note: global ignored_paths from serena_config.yml are also applied additively.
+ignored_paths: []
+
+# whether the project is in read-only mode
+# If set to true, all editing tools will be disabled and attempts to use them will result in an error
+# Added on 2025-04-18
+read_only: false
+
+# list of tool names to exclude.
+# This extends the existing exclusions (e.g. from the global configuration)
+# Find the list of tools here: https://oraios.github.io/serena/01-about/035_tools.html
+excluded_tools: []
+
+# list of tools to include that would otherwise be disabled (particularly optional tools that are disabled by default).
+# This extends the existing inclusions (e.g. from the global configuration).
+# Find the list of tools here: https://oraios.github.io/serena/01-about/035_tools.html
+included_optional_tools: []
+
+# fixed set of tools to use as the base tool set (if non-empty), replacing Serena's default set of tools.
+# This cannot be combined with non-empty excluded_tools or included_optional_tools.
+# Find the list of tools here: https://oraios.github.io/serena/01-about/035_tools.html
+fixed_tools: []
+
+# list of mode names that are to be activated by default, overriding the setting in the global configuration.
+# The full set of modes to be activated is base_modes (from global config) + default_modes + added_modes.
+# If the setting is undefined/empty, the default_modes from the global configuration (serena_config.yml) apply.
+# Otherwise, this overrides the setting from the global configuration (serena_config.yml).
+# Therefore, you can set this to [] if you do not want the default modes defined in the global config to apply
+# for this project.
+# This setting can, in turn, be overridden by CLI parameters (--mode).
+# See https://oraios.github.io/serena/02-usage/050_configuration.html#modes
+default_modes:
+
+# list of mode names to be activated additionally for this project, e.g. ["query-projects"]
+# The full set of modes to be activated is base_modes (from global config) + default_modes + added_modes.
+# See https://oraios.github.io/serena/02-usage/050_configuration.html#modes
+added_modes:
+
+# initial prompt for the project. It will always be given to the LLM upon activating the project
+# (contrary to the memories, which are loaded on demand).
+initial_prompt: ""
+
+# time budget (seconds) per tool call for the retrieval of additional symbol information
+# such as docstrings or parameter information.
+# This overrides the corresponding setting in the global configuration; see the documentation there.
+# If null or missing, use the setting from the global configuration.
+symbol_info_budget:
+
+# list of regex patterns which, when matched, mark a memory entry as read‑only.
+# Extends the list from the global configuration, merging the two lists.
+read_only_memory_patterns: []
+
+# list of regex patterns for memories to completely ignore.
+# Matching memories will not appear in list_memories or activate_project output
+# and cannot be accessed via read_memory or write_memory.
+# To access ignored memory files, use the read_file tool on the raw file path.
+# Extends the list from the global configuration, merging the two lists.
+# Example: ["_archive/.*", "_episodes/.*"]
+ignored_memory_patterns: []

bin/benchmark

@@ -3,17 +3,13 @@
 
 $LOAD_PATH.unshift File.expand_path("../lib", __dir__)
 
-require "benchmark"
 require "json"
 require "wave_function_collapse"
 
-WIDTH = 20
-HEIGHT = 20
+TILE_PATH = File.expand_path("../assets/map.tsj", __dir__)
 
-srand(WIDTH * HEIGHT)
-
-json = JSON.load_file!("assets/map.tsj")
-tiles =
+def build_tiles
+  json = JSON.load_file(TILE_PATH)
   json["wangsets"].last["wangtiles"].map do |tile|
     prob = json["tiles"]&.find { |t| t["id"] == tile["tileid"] }&.fetch("probability")
     WaveFunctionCollapse::Tile.new(
@@ -22,33 +18,139 @@ tiles =
       probability: prob
     )
   end
-times = []
+end
+
+GC_STAT_KEYS = %i[total_allocated_objects malloc_increase_bytes minor_gc_count major_gc_count].freeze
+
+def gc_delta(before, after)
+  GC_STAT_KEYS.each_with_object({}) { |k, h| h[k] = after[k] - before[k] }
+end
+
+def run_once(klass, tiles, w, h)
+  GC.start
+  gc_before = GC.stat
+  t0 = Process.clock_gettime(Process::CLOCK_MONOTONIC)
+  model = klass.new(tiles, w, h)
+  model.solve
+  iters = 1
+  until model.complete?
+    model.iterate
+    iters += 1
+  end
+  elapsed = Process.clock_gettime(Process::CLOCK_MONOTONIC) - t0
+  gc_after = GC.stat
+  [elapsed, iters, gc_delta(gc_before, gc_after)]
+end
+
+def median(xs)
+  s = xs.sort
+  n = s.length
+  n.odd? ? s[n / 2] : (s[n / 2 - 1] + s[n / 2]) / 2.0
+end
 
-puts RUBY_DESCRIPTION unless ENV["CI"]
+tiles = build_tiles
 
-times = 10.times.map { |i|
-  time = Benchmark.realtime {
+if ENV["CI"]
+  # CI contract: 10 runs of 20x20 on the new Model, JSON output for the
+  # github-action-benchmark workflow. Do not change without updating the workflow.
+  WIDTH = 20
+  HEIGHT = 20
+  srand(WIDTH * HEIGHT)
+  times = 10.times.map {
+    t0 = Process.clock_gettime(Process::CLOCK_MONOTONIC)
     model = WaveFunctionCollapse::Model.new(tiles, WIDTH, HEIGHT)
-    print "Run ##{i + 1}: Benchmark for Model(grid=#{model.width}x#{model.height} entropy=#{model.max_entropy})… " unless ENV["CI"]
     model.solve
-    until model.complete?
-      model.iterate
-    end
+    model.iterate until model.complete?
+    Process.clock_gettime(Process::CLOCK_MONOTONIC) - t0
   }
-  puts "Finished in #{time.round(2)}s" unless ENV["CI"]
-  time
-}
-
-average = times.sum / times.size
-if ENV["CI"]
   puts JSON.dump([
-    { name: "Average time", unit: "Seconds", value: average },
-    { name: "Slowest time", unit: "Seconds", value: times.max },
-    { name: "Fastest time", unit: "Seconds", value: times.min },
-    { name: "P90", unit: "Seconds", value: times.sort[8] }
+    {name: "Average time", unit: "Seconds", value: times.sum / times.size},
+    {name: "Slowest time", unit: "Seconds", value: times.max},
+    {name: "Fastest time", unit: "Seconds", value: times.min},
+    {name: "P90", unit: "Seconds", value: times.sort[8]}
   ])
+  exit
+end
+
+yjit_status = defined?(RubyVM::YJIT) && RubyVM::YJIT.enabled? ? "on" : "off"
+zjit_status = defined?(RubyVM::ZJIT) && RubyVM::ZJIT.enabled? ? "on" : "off"
+puts RUBY_DESCRIPTION
+puts "Tiles loaded: #{tiles.size}, YJIT=#{yjit_status}, ZJIT=#{zjit_status}"
+puts
+
+# Accepts either "N" (treated as NxN) or "WxH" entries.
+def parse_sizes(str)
+  str.split(",").map do |tok|
+    tok = tok.strip
+    if tok.include?("x")
+      w, h = tok.split("x", 2).map(&:to_i)
+      [w, h]
+    else
+      n = tok.to_i
+      [n, n]
+    end
+  end
+end
+
+# SIZES overrides both lists. Otherwise each model uses its own *_SIZES var if
+# set, or falls back to the other model's setting, or finally its own default.
+shared = ENV["SIZES"]
+legacy_env = ENV["LEGACY_SIZES"]
+new_env = ENV["NEW_SIZES"]
+legacy_sizes = parse_sizes(shared || legacy_env || new_env || "10,15,20,25,30")
+new_sizes = parse_sizes(shared || new_env || legacy_env || "10,15,20,30,50,64x36,75,100")
+runs = Integer(ENV["RUNS"] || "3")
+skip_legacy = ARGV.include?("--no-legacy")
+show_gc = ENV["GC_STATS"]
+
+# Header widths match the data printf below so columns align.
+# Data: "%-8s %-9s %-7d %9.3fs %9.3fs %12.0f %10d" (+ GC: %12d %14d %8d %8d)
+# %9.3fs renders as 10 chars (9 numeric + literal 's').
+if show_gc
+  printf("%-8s %-9s %-7s %10s %10s %12s %10s %12s %14s %8s %8s\n",
+    "Model", "Grid", "Cells", "Median", "Best", "Obs/sec", "Iters",
+    "Alloc/run", "Malloc B/run", "MinorGC", "MajorGC")
+  printf("%-8s %-9s %-7s %10s %10s %12s %10s %12s %14s %8s %8s\n",
+    "-----", "----", "-----", "------", "----", "-------", "-----",
+    "---------", "------------", "-------", "-------")
 else
-  puts "Average time: #{average}"
-  puts "Slowest time: #{times.max}"
-  puts "Fastest time: #{times.min}"
+  printf("%-8s %-9s %-7s %10s %10s %12s %10s\n",
+    "Model", "Grid", "Cells", "Median", "Best", "Obs/sec", "Iters")
+  printf("%-8s %-9s %-7s %10s %10s %12s %10s\n",
+    "-----", "----", "-----", "------", "----", "-------", "-----")
+end
+
+[
+  [WaveFunctionCollapse::LegacyModel, skip_legacy ? [] : legacy_sizes, "Legacy"],
+  [WaveFunctionCollapse::Model, new_sizes, "New"]
+].each do |klass, sizes, label|
+  sizes.each do |(w, h)|
+    cells = w * h
+    grid = "#{w}x#{h}"
+    printf("%-8s %-9s %-7d ", label, grid, cells)
+    $stdout.flush
+    times = []
+    iters_seen = 0
+    gc_deltas = []
+    runs.times do |r|
+      srand(cells * 1000 + r + 1)
+      elapsed, iters, gc = run_once(klass, tiles, w, h)
+      times << elapsed
+      iters_seen = iters
+      gc_deltas << gc
+    end
+    med = median(times)
+    best = times.min
+    if show_gc
+      avg = ->(k) { gc_deltas.sum { |g| g[k] } / gc_deltas.size }
+      printf("%9.3fs %9.3fs %12.0f %10d %12d %14d %8d %8d\n",
+        med, best, iters_seen / med, iters_seen,
+        avg.call(:total_allocated_objects), avg.call(:malloc_increase_bytes),
+        avg.call(:minor_gc_count), avg.call(:major_gc_count))
+    else
+      printf("%9.3fs %9.3fs %12.0f %10d\n",
+        med, best, iters_seen / med, iters_seen)
+    end
+  end
+  puts
 end