summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorstephentoub <stoub@microsoft.com>2015-10-14 11:29:11 -0400
committerstephentoub <stoub@microsoft.com>2015-10-14 16:18:25 -0400
commit4b8dadec3a89da8d9e4d12ad9b8b68b2cdc7fe91 (patch)
tree345bbe78c6a3ce9898028fe5e32d1d3a8e753680
parentf48b5ad56a6f6f584cb202c05f5b06c09b7adfbf (diff)
downloadcoreclr-4b8dadec3a89da8d9e4d12ad9b8b68b2cdc7fe91.tar.gz
coreclr-4b8dadec3a89da8d9e4d12ad9b8b68b2cdc7fe91.tar.bz2
coreclr-4b8dadec3a89da8d9e4d12ad9b8b68b2cdc7fe91.zip
Avoid brancing in ToLower/UpperAsciiInvariant(char)
Rather than comparing the input char against 'A'/'a' and 'Z'/'z', we simply trim off all but the lower 7 bits and do a lookup into a precomputed table. This is ~3-4x faster than the branching version.
-rw-r--r--src/mscorlib/corefx/System/Globalization/TextInfo.cs60
1 files changed, 48 insertions, 12 deletions
diff --git a/src/mscorlib/corefx/System/Globalization/TextInfo.cs b/src/mscorlib/corefx/System/Globalization/TextInfo.cs
index 7de2b67036..10fe1b63f3 100644
--- a/src/mscorlib/corefx/System/Globalization/TextInfo.cs
+++ b/src/mscorlib/corefx/System/Globalization/TextInfo.cs
@@ -237,15 +237,33 @@ namespace System.Globalization
return ChangeCase(str, toUpper: false);
}
- static private Char ToLowerAsciiInvariant(Char c)
+ private static Char ToLowerAsciiInvariant(Char c)
{
- if ('A' <= c && c <= 'Z')
- {
- c = (Char)(c | 0x20);
- }
- return c;
+ Contract.Assert(IsAscii(c));
+ return (Char)s_toLowerAsciiMapping[c & 0x7F];
}
+ private static readonly byte[] s_toLowerAsciiMapping = new byte[128]
+ {
+ // s_toLowerAsciiMapping[c] == invariant lower case value of c
+ 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
+ 0x08, 0x09, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
+ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17,
+ 0x18, 0x19, 0x1A, 0x1B, 0x1C, 0x1D, 0x1E, 0x1F,
+ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27,
+ 0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x2D, 0x2E, 0x2F,
+ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37,
+ 0x38, 0x39, 0x3A, 0x3B, 0x3C, 0x3D, 0x3E, 0x3F,
+ 0x40, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
+ 0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F,
+ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
+ 0x78, 0x79, 0x7A, 0x5B, 0x5C, 0x5D, 0x5E, 0x5F,
+ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
+ 0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F,
+ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
+ 0x78, 0x79, 0x7A, 0x7B, 0x7C, 0x7D, 0x7E, 0x7F
+ };
+
////////////////////////////////////////////////////////////////////////
//
// ToUpper
@@ -270,15 +288,33 @@ namespace System.Globalization
return ChangeCase(str, toUpper: true);
}
- static private Char ToUpperAsciiInvariant(Char c)
+ private static Char ToUpperAsciiInvariant(Char c)
{
- if ('a' <= c && c <= 'z')
- {
- c = (Char)(c & ~0x20);
- }
- return c;
+ Contract.Assert(IsAscii(c));
+ return (Char)s_toUpperAsciiMapping[c & 0x7F];
}
+ private static readonly byte[] s_toUpperAsciiMapping = new byte[128]
+ {
+ // s_toUpperAsciiMapping[c] == invariant upper case value of c
+ 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
+ 0x08, 0x09, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
+ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17,
+ 0x18, 0x19, 0x1A, 0x1B, 0x1C, 0x1D, 0x1E, 0x1F,
+ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27,
+ 0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x2D, 0x2E, 0x2F,
+ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37,
+ 0x38, 0x39, 0x3A, 0x3B, 0x3C, 0x3D, 0x3E, 0x3F,
+ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47,
+ 0x48, 0x49, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F,
+ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57,
+ 0x58, 0x59, 0x5A, 0x5B, 0x5C, 0x5D, 0x5E, 0x5F,
+ 0x60, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47,
+ 0x48, 0x49, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F,
+ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57,
+ 0x58, 0x59, 0x5A, 0x7B, 0x7C, 0x7D, 0x7E, 0x7F
+ };
+
static private bool IsAscii(Char c)
{
return c < 0x80;