use span to improve performance

jaredcnance · Jan 8, 2018 · e01fd32 · e01fd32
1 parent c91eb96
commit e01fd32
Show file tree

Hide file tree

Showing 4 changed files with 56 additions and 8 deletions.
diff --git a/API/API.csproj b/API/API.csproj
@@ -15,6 +15,7 @@
     <PackageReference Include="Microsoft.EntityFrameworkCore.SqlServer" Version="2.0.0" />
     <PackageReference Include="StackifyLib" Version="2.1.0" />
     <PackageReference Include="StackifyMiddleware" Version="2.0.3" />
+    <PackageReference Include="System.Memory" Version="4.4.0-*" />
   </ItemGroup>
 
   <ItemGroup>

diff --git a/API/Services/LevenshteinFuzzySearch.cs b/API/Services/LevenshteinFuzzySearch.cs
@@ -38,6 +38,47 @@ public int GetLevenshteinDistance(string str1, string str2)
             for (var i = 0; i <= n; d[i, 0] = i++) ;
             for (var j = 0; j <= m; d[0, j] = j++) ;
 
+            // Step 3
+            for (var i = 1; i <= n; i++)
+            {
+                //Step 4
+                for (var j = 1; j <= m; j++)
+                {
+                    // Step 5
+                    var a = str2.AsSpan().Slice(j - 1, 1)[0];
+                    var b = str1.AsSpan().Slice(i - 1, 1)[0];
+
+                    var cost = (a == b ? 0 : 1);
+
+                    // Step 6
+                    d[i, j] = Math.Min(Math.Min(d[i - 1, j] + 1, d[i, j - 1] + 1),
+                        d[i - 1, j - 1] + cost);
+                }
+            }
+
+            // Step 7
+            return d[n, m];
+        }
+
+        public int ComputeSimilarity_Baseline(string str1, string str2)
+        {
+            str1 = str1.ToLowerInvariant();
+            str2 = str2.ToLowerInvariant();
+
+            var n = str1.Length;
+
+            var m = str2.Length;
+
+            var d = new int[n + 1, m + 1];
+
+            // Step 1
+            if (n == 0) return m;
+            if (m == 0) return n;
+
+            // Step 2
+            for (var i = 0; i <= n; d[i, 0] = i++) ;
+            for (var j = 0; j <= m; d[0, j] = j++) ;
+
             // Step 3
             for (var i = 1; i <= n; i++)
             {

diff --git a/...t.Artifacts/results/Benchmarks.Services.FuzzySearch_Benchmarks-report-github.md b/...t.Artifacts/results/Benchmarks.Services.FuzzySearch_Benchmarks-report-github.md
@@ -7,12 +7,15 @@ Frequency=2533207 Hz, Resolution=394.7565 ns, Timer=TSC
   [Host]     : .NET Core 2.0.3 (Framework 4.6.25815.02), 64bit RyuJIT
   DefaultJob : .NET Core 2.0.3 (Framework 4.6.25815.02), 64bit RyuJIT
 
-```
-
 
-|              Method |             String1 |           String2 |         Mean |       Error |      StdDev |      Gen 0 |    Gen 1 |    Gen 2 |  Allocated |
+```
-|-------------------- |-------------------- |------------------ |-------------:|------------:|------------:|-----------:|---------:|---------:|-----------:|
+|                      Method |             String1 |           String2 |          Mean |       Error |      StdDev | Scaled |      Gen 0 |    Gen 1 |    Gen 2 |   Allocated |
-| **LevenshteinDistance** | **RandomString[10000]** | **RandomString[100]** | **35,775.90 us** | **601.6207 us** | **533.3210 us** | **21062.5000** | **875.0000** | **812.5000** | **66465.6 KB** |
+|---------------------------- |-------------------- |------------------ |--------------:|------------:|------------:|-------:|-----------:|---------:|---------:|------------:|
-| **LevenshteinDistance** |  **RandomString[1000]** | **RandomString[100]** |  **3,469.71 us** |  **34.6071 us** |  **28.8985 us** |  **2035.1563** | **128.9063** | **125.0000** | **6647.18 KB** |
+|         **LevenshteinDistance** | **RandomString[10000]** | **RandomString[100]** |  **8,261.118 us** |  **83.8376 us** |  **74.3198 us** |   **0.23** |   **992.1875** | **992.1875** | **992.1875** |  **3965.54 KB** |
-| **LevenshteinDistance** |   **RandomString[100]** | **RandomString[100]** |    **362.57 us** |   **4.7108 us** |   **4.1760 us** |   **216.3086** |        **-** |        **-** |  **665.34 KB** |
+| LevenshteinDistanceBaseline | RandomString[10000] | RandomString[100] | 35,506.764 us | 227.1435 us | 212.4702 us |   1.00 | 21062.5000 | 875.0000 | 812.5000 | 66465.62 KB |
-| **LevenshteinDistance** |    **RandomString[10]** | **RandomString[100]** |     **34.65 us** |   **0.2365 us** |   **0.2097 us** |    **21.8506** |        **-** |        **-** |   **67.16 KB** |
+|         **LevenshteinDistance** |  **RandomString[1000]** | **RandomString[100]** |    **866.979 us** |   **7.5294 us** |   **6.6746 us** |   **0.24** |   **124.0234** | **124.0234** | **124.0234** |   **397.18 KB** |
+| LevenshteinDistanceBaseline |  RandomString[1000] | RandomString[100] |  3,585.358 us |  45.1899 us |  42.2706 us |   1.00 |  2035.1563 | 128.9063 | 125.0000 |  6647.18 KB |
+|         **LevenshteinDistance** |   **RandomString[100]** | **RandomString[100]** |     **89.174 us** |   **1.0989 us** |   **1.0279 us** |   **0.24** |    **13.0615** |        **-** |        **-** |    **40.34 KB** |
+| LevenshteinDistanceBaseline |   RandomString[100] | RandomString[100] |    364.125 us |   4.8533 us |   4.5398 us |   1.00 |   216.3086 |        - |        - |   665.34 KB |
+|         **LevenshteinDistance** |    **RandomString[10]** | **RandomString[100]** |      **7.996 us** |   **0.0664 us** |   **0.0555 us** |   **0.23** |     **1.5106** |        **-** |        **-** |     **4.66 KB** |
+| LevenshteinDistanceBaseline |    RandomString[10] | RandomString[100] |     35.245 us |   0.3588 us |   0.3356 us |   1.00 |    21.8506 |        - |        - |    67.16 KB |
diff --git a/Benchmarks/Services/FuzzySearch_Benchmarks.cs b/Benchmarks/Services/FuzzySearch_Benchmarks.cs
@@ -32,6 +32,9 @@ public static IEnumerable<IParam> String2Values()
 
         [Benchmark]
         public int LevenshteinDistance() => _levenshteinFuzzySearch.ComputeSimilarity(String1.Value, String2.Value);
+
+        [Benchmark(Baseline = true)]
+        public int LevenshteinDistanceBaseline() => _levenshteinFuzzySearch.ComputeSimilarity_Baseline(String1.Value, String2.Value);
     }
 
     /// <remarks>