Switched to Parallel LINQ

README.md

@@ -13,12 +13,20 @@ WhiteRabbit.exe < wordlist
 Performance
 ===========
 
-This solution is not optimized for multi-threading.
+This solution is partially optimized for multi-threading.
 
-Nevertheless, the performance on Sandy Bridge @2.8GHz is as follows:
+Single-threaded performance on Sandy Bridge @2.8GHz is as follows:
 
 * If only phrases of at most 3 words are allowed, then it takes 2.5 seconds to find and check all anagrams; all relevant hashes are solved in first 0.4 seconds;
 
 * If phrases of 4 words are allowed as well, then it takes 40 seconds to find and check all anagrams; all hashes are solved in first 3 seconds;
 
 For comparison, certain other solutions available on GitHub seem to require 3 hours to find all 3-word anagrams (i.e. this solution is faster by a factor of 4000 in 3-word case).
+
+Anagrams generation is not parallelized, as even single-threaded performance for 4-word anagrams is high enough; and 5-word (or larger) anagrams are frequent enough for most of the time being spent on computing hashes, with full CPU load.
+
+Multi-threaded performance is as follows:
+
+* If only phrases of at most 4 words are allowed, then it takes 20 seconds to find and check all anagrams; all hashes are solved in first 1.5 seconds
+
+* If phrases of 5 words are allowed as well, then all hashes are solved in first 29 seconds. Around 50% of time is spent on MD5 computations for correct anagrams, so there is not a lot to optimize further.

WhiteRabbit/Program.cs

@@ -35,15 +35,11 @@
 
             var expectedHashesAsVectors = expectedHashes.Select(hash => new Vector<byte>(HexadecimalStringToByteArray(hash))).ToArray();
 
-            var result = processor.GeneratePhrases(ReadInput())
+            processor.GeneratePhrases(ReadInput())
                 .Select(phraseBytes => new { phraseBytes, hashVector = ComputeHashVector(phraseBytes) })
                 .Where(tuple => expectedHashesAsVectors.Contains(tuple.hashVector))
-                .Select(tuple => new { phrase = Encoding.ASCII.GetString(tuple.phraseBytes), hash = VectorToHexadecimalString(tuple.hashVector) });
+                .Select(tuple => new { phrase = Encoding.ASCII.GetString(tuple.phraseBytes), hash = VectorToHexadecimalString(tuple.hashVector) })
-
+                .ForAll(phraseInfo => Console.WriteLine($"Found phrase for {phraseInfo.hash}: {phraseInfo.phrase} (spent {stopwatch.Elapsed})"));
-            foreach (var phraseInfo in result)
-            {
-                Console.WriteLine($"Found phrase for {phraseInfo.hash}: {phraseInfo.phrase} (spent {stopwatch.Elapsed})");
-            }
 
             stopwatch.Stop();
             Console.WriteLine($"Total time spent: {stopwatch.Elapsed}");

WhiteRabbit/StringsProcessor.cs

@@ -21,7 +21,7 @@
 
         private VectorsProcessor VectorsProcessor { get; }
 
-        public IEnumerable<byte[]> GeneratePhrases(IEnumerable<byte[]> words)
+        public ParallelQuery<byte[]> GeneratePhrases(IEnumerable<byte[]> words)
         {
             // Dictionary of vectors to array of words represented by this vector
             var formattedWords = words

WhiteRabbit/VectorsProcessor.cs

@@ -33,11 +33,12 @@
         private long Iterations { get; set; } = 0;
 
         // Produces all sequences of vectors with the target sum
-        public IEnumerable<Vector<byte>[]> GenerateSequences(IEnumerable<Vector<byte>> vectors)
+        public ParallelQuery<Vector<byte>[]> GenerateSequences(IEnumerable<Vector<byte>> vectors)
         {
             var filteredVectors = this.FilterVectors(vectors);
             var dictionary = ImmutableStack.Create(filteredVectors.ToArray());
-            var unorderedSequences = this.GenerateUnorderedSequences(this.Target, ImmutableStack.Create<Vector<byte>>(), dictionary);
+            var unorderedSequences = this.GenerateUnorderedSequences(this.Target, ImmutableStack.Create<Vector<byte>>(), dictionary)
+                .AsParallel();
             var allSequences = unorderedSequences.SelectMany(this.GeneratePermutations);
 
             return allSequences;