Skip to content

Add IndexOfAnyValues #78093

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
MihaZupan merged 9 commits into from
Nov 21, 2022
Merged

Add IndexOfAnyValues #78093

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
1e154c3
Add IndexOfAnyValues
MihaZupan Nov 19, 2022
c520667
Remove IAsciiSet special cases
MihaZupan Nov 19, 2022
a688c23
More tests
MihaZupan Nov 19, 2022
6548ed3
Move expensive tests back to OuterLoop
MihaZupan Nov 19, 2022
5b648d1
Tweak scalar paths
MihaZupan Nov 20, 2022
55817fe
Improve IndexOfAnyValues<T> summary
MihaZupan Nov 20, 2022
1e7684f
Add temporary MONO workaround
MihaZupan Nov 20, 2022
1d79940
Simplify IndexOfAny{1, 2, 3}Values
MihaZupan Nov 20, 2022
fef55c8
Remove redundant AND before shift
MihaZupan Nov 21, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
Remove IAsciiSet special cases
  • Loading branch information
@MihaZupan
MihaZupan committed Nov 19, 2022
commit c520667a9d121f8dd8a4f75952e6cb0f42fac761
2 changes: 0 additions & 2 deletions src/libraries/System.Private.CoreLib/src/System.Private.CoreLib.Shared.projitems
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -425,9 +425,7 @@
<Compile Include="$(MSBuildThisFileDirectory)System\IndexOfAnyValues\IndexOfAnyAsciiByteValues.cs" />
<Compile Include="$(MSBuildThisFileDirectory)System\IndexOfAnyValues\IndexOfAnyAsciiCharValues.cs" />
<Compile Include="$(MSBuildThisFileDirectory)System\IndexOfAnyValues\IndexOfAnyAsciiSearcher.cs" />
<Compile Include="$(MSBuildThisFileDirectory)System\IndexOfAnyValues\IndexOfAnyByteInAsciiSet.cs" />
<Compile Include="$(MSBuildThisFileDirectory)System\IndexOfAnyValues\IndexOfAnyByteValues.cs" />
<Compile Include="$(MSBuildThisFileDirectory)System\IndexOfAnyValues\IndexOfAnyCharInAsciiSet.cs" />
<Compile Include="$(MSBuildThisFileDirectory)System\IndexOfAnyValues\IndexOfAnyCharValuesProbabilistic.cs" />
<Compile Include="$(MSBuildThisFileDirectory)System\IndexOfAnyValues\IndexOfAnyLatin1CharValues.cs" />
<Compile Include="$(MSBuildThisFileDirectory)System\IndexOfAnyValues\IndexOfAnyValues.cs" />
Expand Down
92 changes: 0 additions & 92 deletions src/libraries/System.Private.CoreLib/src/System/IndexOfAnyValues/IndexOfAnyByteInAsciiSet.cs
View file
Open in desktop

This file was deleted.

93 changes: 0 additions & 93 deletions src/libraries/System.Private.CoreLib/src/System/IndexOfAnyValues/IndexOfAnyCharInAsciiSet.cs
View file
Open in desktop

This file was deleted.

90 changes: 0 additions & 90 deletions src/libraries/System.Private.CoreLib/src/System/IndexOfAnyValues/IndexOfAnyValues.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,43 +18,6 @@ namespace System.Buffers
/// </remarks>
public static class IndexOfAnyValues
{
#if DEBUG
static IndexOfAnyValues()
{
CheckAsciiSet<AsciiLetter>("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz");
CheckAsciiSet<AsciiLetterOrDigit>("0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz");
CheckAsciiSet<AsciiHexDigit>("0123456789ABCDEFabcdef");
CheckAsciiSet<AsciiHexDigitLower>("0123456789abcdef");
CheckAsciiSet<AsciiHexDigitUpper>("0123456789ABCDEF");
}

private static void CheckAsciiSet<TAsciiSet>(string set)
where TAsciiSet : IAsciiSet
{
byte[] byteSet = System.Text.Encoding.ASCII.GetBytes(set);

IndexOfAnyAsciiSearcher.ComputeBitmap<char>(set, out Vector128<byte> bitmap, out BitVector256 lookup);
Debug.Assert(bitmap == TAsciiSet.Bitmap);
Debug.Assert(lookup.GetCharValues().AsSpan().SequenceEqual(set));
Debug.Assert(lookup.GetByteValues().AsSpan().SequenceEqual(byteSet));

IndexOfAnyAsciiSearcher.ComputeBitmap<byte>(byteSet, out bitmap, out lookup);
Debug.Assert(bitmap == TAsciiSet.Bitmap);
Debug.Assert(lookup.GetCharValues().AsSpan().SequenceEqual(set));
Debug.Assert(lookup.GetByteValues().AsSpan().SequenceEqual(byteSet));

for (int i = 0; i < 256; i++)
{
Debug.Assert(TAsciiSet.Contains((char)i) == lookup.Contains256((char)i), $"{i}");
}

for (int i = 256; i <= char.MaxValue; i++)
{
Debug.Assert(!TAsciiSet.Contains((char)i), $"{i}");
}
}
#endif

/// <summary>
/// Creates an optimized representation of <paramref name="values"/> used for efficient searching.
/// </summary>
Expand Down Expand Up @@ -93,12 +56,6 @@ public static IndexOfAnyValues<byte> Create(ReadOnlySpan<byte> values)
{
IndexOfAnyAsciiSearcher.ComputeBitmap(values, out Vector128<byte> bitmap, out BitVector256 lookup);

if (bitmap == AsciiLetter.Bitmap) return IndexOfAnyByteInAsciiSet<AsciiLetter>.Instance;
if (bitmap == AsciiLetterOrDigit.Bitmap) return IndexOfAnyByteInAsciiSet<AsciiLetterOrDigit>.Instance;
if (bitmap == AsciiHexDigit.Bitmap) return IndexOfAnyByteInAsciiSet<AsciiHexDigit>.Instance;
if (bitmap == AsciiHexDigitLower.Bitmap) return IndexOfAnyByteInAsciiSet<AsciiHexDigitLower>.Instance;
if (bitmap == AsciiHexDigitUpper.Bitmap) return IndexOfAnyByteInAsciiSet<AsciiHexDigitUpper>.Instance;

return Sse3.IsSupported && lookup.Contains(0)
? new IndexOfAnyAsciiByteValues<IndexOfAnyAsciiSearcher.Ssse3HandleZeroInNeedle>(bitmap, lookup)
: new IndexOfAnyAsciiByteValues<IndexOfAnyAsciiSearcher.Default>(bitmap, lookup);
Expand Down Expand Up @@ -149,12 +106,6 @@ ref Unsafe.As<char, short>(ref MemoryMarshal.GetReference(values)),
{
IndexOfAnyAsciiSearcher.ComputeBitmap(values, out Vector128<byte> bitmap, out BitVector256 lookup);

if (bitmap == AsciiLetter.Bitmap) return IndexOfAnyCharInAsciiSet<AsciiLetter>.Instance;
if (bitmap == AsciiLetterOrDigit.Bitmap) return IndexOfAnyCharInAsciiSet<AsciiLetterOrDigit>.Instance;
if (bitmap == AsciiHexDigit.Bitmap) return IndexOfAnyCharInAsciiSet<AsciiHexDigit>.Instance;
if (bitmap == AsciiHexDigitLower.Bitmap) return IndexOfAnyCharInAsciiSet<AsciiHexDigitLower>.Instance;
if (bitmap == AsciiHexDigitUpper.Bitmap) return IndexOfAnyCharInAsciiSet<AsciiHexDigitUpper>.Instance;

return Sse3.IsSupported && lookup.Contains(0)
? new IndexOfAnyAsciiCharValues<IndexOfAnyAsciiSearcher.Ssse3HandleZeroInNeedle>(bitmap, lookup)
: new IndexOfAnyAsciiCharValues<IndexOfAnyAsciiSearcher.Default>(bitmap, lookup);
Expand Down Expand Up @@ -219,47 +170,6 @@ ref Unsafe.As<char, short>(ref MemoryMarshal.GetReference(values)),
return (IndexOfAnyValues<T>)(object)new IndexOfAnyValuesInRange<T>(min, max);
}

internal interface IAsciiSet
{
public static abstract Vector128<byte> Bitmap { get; }
public static abstract bool Contains(char c);
}

private readonly struct AsciiLetter : IAsciiSet
{
// IndexOfAnyAsciiSearcher.ComputeBitmap for "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"
public static Vector128<byte> Bitmap => Vector128.Create(160, 240, 240, 240, 240, 240, 240, 240, 240, 240, 240, 80, 80, 80, 80, 80);
public static bool Contains(char c) => char.IsAsciiLetter(c);
}

private readonly struct AsciiLetterOrDigit : IAsciiSet
{
// IndexOfAnyAsciiSearcher.ComputeBitmap for "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"
public static Vector128<byte> Bitmap => Vector128.Create(168, 248, 248, 248, 248, 248, 248, 248, 248, 248, 240, 80, 80, 80, 80, 80);
public static bool Contains(char c) => char.IsAsciiLetterOrDigit(c);
}

private readonly struct AsciiHexDigit : IAsciiSet
{
// IndexOfAnyAsciiSearcher.ComputeBitmap for "0123456789ABCDEFabcdef"
public static Vector128<byte> Bitmap => Vector128.Create(8, 88, 88, 88, 88, 88, 88, 8, 8, 8, 0, 0, 0, 0, 0, 0).AsByte();
public static bool Contains(char c) => char.IsAsciiHexDigit(c);
}

private readonly struct AsciiHexDigitLower : IAsciiSet
{
// IndexOfAnyAsciiSearcher.ComputeBitmap for "0123456789abcdef"
public static Vector128<byte> Bitmap => Vector128.Create(8, 72, 72, 72, 72, 72, 72, 8, 8, 8, 0, 0, 0, 0, 0, 0).AsByte();
public static bool Contains(char c) => char.IsAsciiHexDigitLower(c);
}

private readonly struct AsciiHexDigitUpper : IAsciiSet
{
// IndexOfAnyAsciiSearcher.ComputeBitmap for "0123456789ABCDEF"
public static Vector128<byte> Bitmap => Vector128.Create(8, 24, 24, 24, 24, 24, 24, 8, 8, 8, 0, 0, 0, 0, 0, 0).AsByte();
public static bool Contains(char c) => char.IsAsciiHexDigitUpper(c);
}

internal interface IStringContains
{
public static abstract bool Contains(string s, char value);
Expand Down