Faster crc32 implementation (#1294)

* Add Pclmulqdq intrinsic

* Implement crc32 in terms of pclmulqdq

* Address PR comments

1 files changed, 20 insertions, 18 deletions

diff --git a/ARMeilleure/Optimizations.cs b/ARMeilleure/Optimizations.cs
index b486c5d2..fa06a410 100644
--- a/ARMeilleure/Optimizations.cs
+++ b/ARMeilleure/Optimizations.cs
@@ -8,15 +8,16 @@ namespace ARMeilleure
 
         public static bool FastFP { get; set; } = true;
 
-        public static bool UseSseIfAvailable    { get; set; } = true;
-        public static bool UseSse2IfAvailable   { get; set; } = true;
-        public static bool UseSse3IfAvailable   { get; set; } = true;
-        public static bool UseSsse3IfAvailable  { get; set; } = true;
-        public static bool UseSse41IfAvailable  { get; set; } = true;
-        public static bool UseSse42IfAvailable  { get; set; } = true;
-        public static bool UsePopCntIfAvailable { get; set; } = true;
-        public static bool UseAvxIfAvailable    { get; set; } = true;
-        public static bool UseAesniIfAvailable  { get; set; } = true;
+        public static bool UseSseIfAvailable       { get; set; } = true;
+        public static bool UseSse2IfAvailable      { get; set; } = true;
+        public static bool UseSse3IfAvailable      { get; set; } = true;
+        public static bool UseSsse3IfAvailable     { get; set; } = true;
+        public static bool UseSse41IfAvailable     { get; set; } = true;
+        public static bool UseSse42IfAvailable     { get; set; } = true;
+        public static bool UsePopCntIfAvailable    { get; set; } = true;
+        public static bool UseAvxIfAvailable       { get; set; } = true;
+        public static bool UseAesniIfAvailable     { get; set; } = true;
+        public static bool UsePclmulqdqIfAvailable { get; set; } = true;
 
         public static bool ForceLegacySse
         {
@@ -24,14 +25,15 @@ namespace ARMeilleure
             set => HardwareCapabilities.ForceLegacySse = value;
         }
 
-        internal static bool UseSse    => UseSseIfAvailable    && HardwareCapabilities.SupportsSse;
-        internal static bool UseSse2   => UseSse2IfAvailable   && HardwareCapabilities.SupportsSse2;
-        internal static bool UseSse3   => UseSse3IfAvailable   && HardwareCapabilities.SupportsSse3;
-        internal static bool UseSsse3  => UseSsse3IfAvailable  && HardwareCapabilities.SupportsSsse3;
-        internal static bool UseSse41  => UseSse41IfAvailable  && HardwareCapabilities.SupportsSse41;
-        internal static bool UseSse42  => UseSse42IfAvailable  && HardwareCapabilities.SupportsSse42;
-        internal static bool UsePopCnt => UsePopCntIfAvailable && HardwareCapabilities.SupportsPopcnt;
-        internal static bool UseAvx    => UseAvxIfAvailable    && HardwareCapabilities.SupportsAvx && !ForceLegacySse;
-        internal static bool UseAesni  => UseAesniIfAvailable  && HardwareCapabilities.SupportsAesni;
+        internal static bool UseSse       => UseSseIfAvailable       && HardwareCapabilities.SupportsSse;
+        internal static bool UseSse2      => UseSse2IfAvailable      && HardwareCapabilities.SupportsSse2;
+        internal static bool UseSse3      => UseSse3IfAvailable      && HardwareCapabilities.SupportsSse3;
+        internal static bool UseSsse3     => UseSsse3IfAvailable     && HardwareCapabilities.SupportsSsse3;
+        internal static bool UseSse41     => UseSse41IfAvailable     && HardwareCapabilities.SupportsSse41;
+        internal static bool UseSse42     => UseSse42IfAvailable     && HardwareCapabilities.SupportsSse42;
+        internal static bool UsePopCnt    => UsePopCntIfAvailable    && HardwareCapabilities.SupportsPopcnt;
+        internal static bool UseAvx       => UseAvxIfAvailable       && HardwareCapabilities.SupportsAvx && !ForceLegacySse;
+        internal static bool UseAesni     => UseAesniIfAvailable     && HardwareCapabilities.SupportsAesni;
+        internal static bool UsePclmulqdq => UsePclmulqdqIfAvailable && HardwareCapabilities.SupportsPclmulqdq;
     }
 }
\ No newline at end of file