Skip to content

Remove some branches in OptimizedInboxTextEncoder.GetIndexOfFirstCharToEncode #130378

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 1 commit into from
Jul 9, 2026
Merged

Remove some branches in OptimizedInboxTextEncoder.GetIndexOfFirstCharToEncode #130378

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
67 changes: 29 additions & 38 deletions ...ries/System.Text.Encodings.Web/src/System/Text/Encodings/Web/OptimizedInboxTextEncoder.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -394,61 +394,52 @@ public int GetIndexOfFirstByteToEncode(ReadOnlySpan<byte> data)

public int GetIndexOfFirstCharToEncode(ReadOnlySpan<char> data)
{
int asciiCharsSkipped = 0;
_AssertThisNotNull(); // hoist "this != null" check out of hot loop below
Comment thread
MihaZupan marked this conversation as resolved.

int idx = 0;

Comment thread
MihaZupan marked this conversation as resolved.
#if NET
// First, try calling the SIMD-enabled version.
// The SIMD-enabled version handles only ASCII characters.
if (data.Length >= 8)
{
asciiCharsSkipped = data.IndexOfAnyExcept(_allowedAsciiChars);
idx = data.IndexOfAnyExcept(_allowedAsciiChars);

if ((uint)asciiCharsSkipped >= (uint)data.Length || char.IsAscii(data[asciiCharsSkipped]))
if ((uint)idx >= (uint)data.Length || char.IsAscii(data[idx]))
{
// We either processed the whole span (in which case asciiCharsSkipped is -1), or we've found a disallowed ASCII char.
return asciiCharsSkipped;
// We either processed the whole span (in which case idx is -1), or we've found a disallowed ASCII char.
return idx;
}

data = data.Slice(idx);
}
#endif

int idx = asciiCharsSkipped;

// If there's any leftover data, try consuming it now.

if ((uint)idx < (uint)data.Length)
// unroll the loop 8x
while (data.Length >= 8)
{
_AssertThisNotNull(); // hoist "this != null" check out of hot loop below

// Slicing keeps the indexed accesses below provably in-bounds, so the JIT
// elides the bounds checks just as the previous pointer-based loop did.
ReadOnlySpan<char> remaining = data.Slice(idx);

// unroll the loop 8x
while (remaining.Length >= 8)
{
if (!_allowedBmpCodePoints.IsCharAllowed(remaining[0])) { goto Return; }
if (!_allowedBmpCodePoints.IsCharAllowed(remaining[1])) { idx += 1; goto Return; }
if (!_allowedBmpCodePoints.IsCharAllowed(remaining[2])) { idx += 2; goto Return; }
if (!_allowedBmpCodePoints.IsCharAllowed(remaining[3])) { idx += 3; goto Return; }
if (!_allowedBmpCodePoints.IsCharAllowed(remaining[4])) { idx += 4; goto Return; }
if (!_allowedBmpCodePoints.IsCharAllowed(remaining[5])) { idx += 5; goto Return; }
if (!_allowedBmpCodePoints.IsCharAllowed(remaining[6])) { idx += 6; goto Return; }
if (!_allowedBmpCodePoints.IsCharAllowed(remaining[7])) { idx += 7; goto Return; }
idx += 8;
remaining = remaining.Slice(8);
}
if (!_allowedBmpCodePoints.IsCharAllowed(data[0])) { goto Return; }
if (!_allowedBmpCodePoints.IsCharAllowed(data[1])) { idx += 1; goto Return; }
if (!_allowedBmpCodePoints.IsCharAllowed(data[2])) { idx += 2; goto Return; }
if (!_allowedBmpCodePoints.IsCharAllowed(data[3])) { idx += 3; goto Return; }
if (!_allowedBmpCodePoints.IsCharAllowed(data[4])) { idx += 4; goto Return; }
if (!_allowedBmpCodePoints.IsCharAllowed(data[5])) { idx += 5; goto Return; }
if (!_allowedBmpCodePoints.IsCharAllowed(data[6])) { idx += 6; goto Return; }
if (!_allowedBmpCodePoints.IsCharAllowed(data[7])) { idx += 7; goto Return; }
idx += 8;
data = data.Slice(8);
}

foreach (char c in remaining)
{
if (!_allowedBmpCodePoints.IsCharAllowed(c)) { goto Return; }
idx++;
}
foreach (char c in data)
{
if (!_allowedBmpCodePoints.IsCharAllowed(c)) { goto Return; }
idx++;
}

Return:
return -1;

Debug.Assert(0 <= idx && idx <= data.Length);
return (idx == data.Length) ? -1 : idx;
Return:
return idx;
}

/// <summary>
Expand Down
Loading