Improve Span.Count#103728

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 2 commits into from
Jun 21, 2024
Merged

Improve Span.Count #103728

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5421ed4
Improve Span.Count
MihaZupan Jun 19, 2024
f5c1e6e
Fix indentation
MihaZupan Jun 19, 2024
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
79 changes: 23 additions & 56 deletions src/libraries/System.Private.CoreLib/src/System/SpanHelpers.T.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -3786,92 +3786,59 @@ public static int CountValueType<T>(ref T current, T value, int length) where T
{
Vector512<T> targetVector = Vector512.Create(value);
ref T oneVectorAwayFromEnd = ref Unsafe.Subtract(ref end, Vector512<T>.Count);
do
while (Unsafe.IsAddressLessThan(ref current, ref oneVectorAwayFromEnd))
Comment thread
stephentoub marked this conversation as resolved.
{
count += BitOperations.PopCount(Vector512.Equals(Vector512.LoadUnsafe(ref current), targetVector).ExtractMostSignificantBits());
current = ref Unsafe.Add(ref current, Vector512<T>.Count);
}
while (!Unsafe.IsAddressGreaterThan(ref current, ref oneVectorAwayFromEnd));

// If there are just a few elements remaining, then processing these elements by the scalar loop
// is cheaper than doing bitmask + popcount on the full last vector. To avoid complicated type
// based checks, other remainder-count based logic to determine the correct cut-off, for simplicity
// a half-vector size is chosen (based on benchmarks).
uint remaining = (uint)Unsafe.ByteOffset(ref current, ref end) / (uint)Unsafe.SizeOf<T>();
if (remaining > Vector512<T>.Count / 2)
{
ulong mask = Vector512.Equals(Vector512.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();

// The mask contains some elements that may be double-checked, so shift them away in order to get the correct pop-count.
uint overlaps = (uint)Vector512<T>.Count - remaining;
mask >>= (int)overlaps;
count += BitOperations.PopCount(mask);

return count;
}
// Count the last vector and mask off the elements that were already counted (number of elements between oneVectorAwayFromEnd and current).
ulong mask = Vector512.Equals(Vector512.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();
mask >>= (int)((nuint)Unsafe.ByteOffset(ref oneVectorAwayFromEnd, ref current) / (uint)Unsafe.SizeOf<T>());
count += BitOperations.PopCount(mask);
}
else if (Vector256.IsHardwareAccelerated && length >= Vector256<T>.Count)
{
Vector256<T> targetVector = Vector256.Create(value);
ref T oneVectorAwayFromEnd = ref Unsafe.Subtract(ref end, Vector256<T>.Count);
do
while (Unsafe.IsAddressLessThan(ref current, ref oneVectorAwayFromEnd))
{
count += BitOperations.PopCount(Vector256.Equals(Vector256.LoadUnsafe(ref current), targetVector).ExtractMostSignificantBits());
current = ref Unsafe.Add(ref current, Vector256<T>.Count);
}
while (!Unsafe.IsAddressGreaterThan(ref current, ref oneVectorAwayFromEnd));

// If there are just a few elements remaining, then processing these elements by the scalar loop
// is cheaper than doing bitmask + popcount on the full last vector. To avoid complicated type
// based checks, other remainder-count based logic to determine the correct cut-off, for simplicity
// a half-vector size is chosen (based on benchmarks).
uint remaining = (uint)Unsafe.ByteOffset(ref current, ref end) / (uint)Unsafe.SizeOf<T>();
if (remaining > Vector256<T>.Count / 2)
Comment thread
stephentoub marked this conversation as resolved.
{
uint mask = Vector256.Equals(Vector256.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();

// The mask contains some elements that may be double-checked, so shift them away in order to get the correct pop-count.
uint overlaps = (uint)Vector256<T>.Count - remaining;
mask >>= (int)overlaps;
count += BitOperations.PopCount(mask);

return count;
}
// Count the last vector and mask off the elements that were already counted (number of elements between oneVectorAwayFromEnd and current).
uint mask = Vector256.Equals(Vector256.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();
mask >>= (int)((nuint)Unsafe.ByteOffset(ref oneVectorAwayFromEnd, ref current) / (uint)Unsafe.SizeOf<T>());
count += BitOperations.PopCount(mask);
}
else
{
Vector128<T> targetVector = Vector128.Create(value);
ref T oneVectorAwayFromEnd = ref Unsafe.Subtract(ref end, Vector128<T>.Count);
do
while (Unsafe.IsAddressLessThan(ref current, ref oneVectorAwayFromEnd))
{
count += BitOperations.PopCount(Vector128.Equals(Vector128.LoadUnsafe(ref current), targetVector).ExtractMostSignificantBits());
current = ref Unsafe.Add(ref current, Vector128<T>.Count);
}
while (!Unsafe.IsAddressGreaterThan(ref current, ref oneVectorAwayFromEnd));

uint remaining = (uint)Unsafe.ByteOffset(ref current, ref end) / (uint)Unsafe.SizeOf<T>();
if (remaining > Vector128<T>.Count / 2)
{
uint mask = Vector128.Equals(Vector128.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();

// The mask contains some elements that may be double-checked, so shift them away in order to get the correct pop-count.
uint overlaps = (uint)Vector128<T>.Count - remaining;
mask >>= (int)overlaps;
count += BitOperations.PopCount(mask);

return count;
}
// Count the last vector and mask off the elements that were already counted (number of elements between oneVectorAwayFromEnd and current).
uint mask = Vector128.Equals(Vector128.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();
mask >>= (int)((nuint)Unsafe.ByteOffset(ref oneVectorAwayFromEnd, ref current) / (uint)Unsafe.SizeOf<T>());
count += BitOperations.PopCount(mask);
}
}

while (Unsafe.IsAddressLessThan(ref current, ref end))
else
{
if (current.Equals(value))
while (Unsafe.IsAddressLessThan(ref current, ref end))
{
count++;
}
if (current.Equals(value))
{
count++;
}

current = ref Unsafe.Add(ref current, 1);
current = ref Unsafe.Add(ref current, 1);
}
}

return count;
Expand Down
, 'i'); if (__m === '*' || __re.test(location.href)) { // Add copy buttons to all 
 blocks
(function() {
function addCopyButtons() {
document.querySelectorAll('pre code').forEach(function(codeBlock) {
if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;
codeBlock.parentElement.setAttribute('data-copy-added', 'true');
var btn = document.createElement('button');
btn.textContent = 'Copy';
btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';
btn.onmouseover = function() { this.style.opacity = '1'; };
btn.onmouseout = function() { this.style.opacity = '0.7'; };
btn.onclick = function() {
navigator.clipboard.writeText(codeBlock.textContent).then(function() {
btn.textContent = 'Copied!';
setTimeout(function() { btn.textContent = 'Copy'; }, 1500);
});
};
codeBlock.parentElement.style.position = 'relative';
codeBlock.parentElement.appendChild(btn);
});
}
addCopyButtons();
// Re-run on dynamic content
var observer = new MutationObserver(addCopyButtons);
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '

Skip to content
Improve Span.Count#103728

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 2 commits into

from

Jun 21, 2024
 Merged


Improve Span.Count
#103728
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
5421ed4

Improve Span.Count


MihaZupan Jun 19, 2024
f5c1e6e

Fix indentation


MihaZupan Jun 19, 2024

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


79 changes: 23 additions & 56 deletions
src/libraries/System.Private.CoreLib/src/System/SpanHelpers.T.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3786,92 +3786,59 @@ public static int CountValueType<T>(ref T current, T value, int length) where T
 {
 Vector512<T> targetVector = Vector512.Create(value);
 ref T oneVectorAwayFromEnd = ref Unsafe.Subtract(ref end, Vector512<T>.Count);
do
while (Unsafe.IsAddressLessThan(ref current, ref oneVectorAwayFromEnd))
Comment thread
stephentoub marked this conversation as resolved.

 {
 count += BitOperations.PopCount(Vector512.Equals(Vector512.LoadUnsafe(ref current), targetVector).ExtractMostSignificantBits());
 current = ref Unsafe.Add(ref current, Vector512<T>.Count);
 }
 while (!Unsafe.IsAddressGreaterThan(ref current, ref oneVectorAwayFromEnd));

 // If there are just a few elements remaining, then processing these elements by the scalar loop
 // is cheaper than doing bitmask + popcount on the full last vector. To avoid complicated type
 // based checks, other remainder-count based logic to determine the correct cut-off, for simplicity
 // a half-vector size is chosen (based on benchmarks).
 uint remaining = (uint)Unsafe.ByteOffset(ref current, ref end) / (uint)Unsafe.SizeOf<T>();
 if (remaining > Vector512<T>.Count / 2)
 {
 ulong mask = Vector512.Equals(Vector512.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();

 // The mask contains some elements that may be double-checked, so shift them away in order to get the correct pop-count.
 uint overlaps = (uint)Vector512<T>.Count - remaining;
 mask >>= (int)overlaps;
 count += BitOperations.PopCount(mask);

 return count;
 }
 // Count the last vector and mask off the elements that were already counted (number of elements between oneVectorAwayFromEnd and current).
 ulong mask = Vector512.Equals(Vector512.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();
 mask >>= (int)((nuint)Unsafe.ByteOffset(ref oneVectorAwayFromEnd, ref current) / (uint)Unsafe.SizeOf<T>());
 count += BitOperations.PopCount(mask);
 }
 else if (Vector256.IsHardwareAccelerated && length >= Vector256<T>.Count)
 {
 Vector256<T> targetVector = Vector256.Create(value);
 ref T oneVectorAwayFromEnd = ref Unsafe.Subtract(ref end, Vector256<T>.Count);
do
while (Unsafe.IsAddressLessThan(ref current, ref oneVectorAwayFromEnd))
 {
 count += BitOperations.PopCount(Vector256.Equals(Vector256.LoadUnsafe(ref current), targetVector).ExtractMostSignificantBits());
 current = ref Unsafe.Add(ref current, Vector256<T>.Count);
 }
 while (!Unsafe.IsAddressGreaterThan(ref current, ref oneVectorAwayFromEnd));

 // If there are just a few elements remaining, then processing these elements by the scalar loop
 // is cheaper than doing bitmask + popcount on the full last vector. To avoid complicated type
 // based checks, other remainder-count based logic to determine the correct cut-off, for simplicity
 // a half-vector size is chosen (based on benchmarks).
 uint remaining = (uint)Unsafe.ByteOffset(ref current, ref end) / (uint)Unsafe.SizeOf<T>();
 if (remaining > Vector256<T>.Count / 2)
Comment thread
stephentoub marked this conversation as resolved.

 {
 uint mask = Vector256.Equals(Vector256.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();

 // The mask contains some elements that may be double-checked, so shift them away in order to get the correct pop-count.
 uint overlaps = (uint)Vector256<T>.Count - remaining;
 mask >>= (int)overlaps;
 count += BitOperations.PopCount(mask);

 return count;
 }
 // Count the last vector and mask off the elements that were already counted (number of elements between oneVectorAwayFromEnd and current).
 uint mask = Vector256.Equals(Vector256.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();
 mask >>= (int)((nuint)Unsafe.ByteOffset(ref oneVectorAwayFromEnd, ref current) / (uint)Unsafe.SizeOf<T>());
 count += BitOperations.PopCount(mask);
 }
 else
 {
 Vector128<T> targetVector = Vector128.Create(value);
 ref T oneVectorAwayFromEnd = ref Unsafe.Subtract(ref end, Vector128<T>.Count);
do
while (Unsafe.IsAddressLessThan(ref current, ref oneVectorAwayFromEnd))
 {
 count += BitOperations.PopCount(Vector128.Equals(Vector128.LoadUnsafe(ref current), targetVector).ExtractMostSignificantBits());
 current = ref Unsafe.Add(ref current, Vector128<T>.Count);
 }
 while (!Unsafe.IsAddressGreaterThan(ref current, ref oneVectorAwayFromEnd));

 uint remaining = (uint)Unsafe.ByteOffset(ref current, ref end) / (uint)Unsafe.SizeOf<T>();
 if (remaining > Vector128<T>.Count / 2)
 {
 uint mask = Vector128.Equals(Vector128.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();

 // The mask contains some elements that may be double-checked, so shift them away in order to get the correct pop-count.
 uint overlaps = (uint)Vector128<T>.Count - remaining;
 mask >>= (int)overlaps;
 count += BitOperations.PopCount(mask);

 return count;
 }
 // Count the last vector and mask off the elements that were already counted (number of elements between oneVectorAwayFromEnd and current).
 uint mask = Vector128.Equals(Vector128.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();
 mask >>= (int)((nuint)Unsafe.ByteOffset(ref oneVectorAwayFromEnd, ref current) / (uint)Unsafe.SizeOf<T>());
 count += BitOperations.PopCount(mask);
 }
 }

 while (Unsafe.IsAddressLessThan(ref current, ref end))
 else
 {
if (current.Equals(value))
while (Unsafe.IsAddressLessThan(ref current, ref end))
 {
 count++;
 }
 if (current.Equals(value))
 {
 count++;
 }

 current = ref Unsafe.Add(ref current, 1);
 current = ref Unsafe.Add(ref current, 1);
 }
 }

 return count;
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Force GitHub README to respect dark mode
(function() {
var style = document.createElement('style');
style.textContent = '
.markdown-body {
color-scheme: dark light;
}
.markdown-body pre { background: #161b22 !important; }
.markdown-body code { background: rgba(110, 118, 129, 0.4) !important; }
.markdown-body table th, .markdown-body table td { border-color: #30363d !important; }
.markdown-body img { background: #0d1117; }
.markdown-body blockquote { border-left-color: #8b949e; }
.markdown-body hr { border-color: #30363d; }
';
document.head.appendChild(style);
})();
}
} catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Improve Span.Count#103728

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 2 commits into

from

Jun 21, 2024
 Merged


Improve Span.Count
#103728
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
5421ed4

Improve Span.Count


MihaZupan Jun 19, 2024
f5c1e6e

Fix indentation


MihaZupan Jun 19, 2024

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


79 changes: 23 additions & 56 deletions
src/libraries/System.Private.CoreLib/src/System/SpanHelpers.T.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3786,92 +3786,59 @@ public static int CountValueType<T>(ref T current, T value, int length) where T
 {
 Vector512<T> targetVector = Vector512.Create(value);
 ref T oneVectorAwayFromEnd = ref Unsafe.Subtract(ref end, Vector512<T>.Count);
do
while (Unsafe.IsAddressLessThan(ref current, ref oneVectorAwayFromEnd))
Comment thread
stephentoub marked this conversation as resolved.

 {
 count += BitOperations.PopCount(Vector512.Equals(Vector512.LoadUnsafe(ref current), targetVector).ExtractMostSignificantBits());
 current = ref Unsafe.Add(ref current, Vector512<T>.Count);
 }
 while (!Unsafe.IsAddressGreaterThan(ref current, ref oneVectorAwayFromEnd));

 // If there are just a few elements remaining, then processing these elements by the scalar loop
 // is cheaper than doing bitmask + popcount on the full last vector. To avoid complicated type
 // based checks, other remainder-count based logic to determine the correct cut-off, for simplicity
 // a half-vector size is chosen (based on benchmarks).
 uint remaining = (uint)Unsafe.ByteOffset(ref current, ref end) / (uint)Unsafe.SizeOf<T>();
 if (remaining > Vector512<T>.Count / 2)
 {
 ulong mask = Vector512.Equals(Vector512.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();

 // The mask contains some elements that may be double-checked, so shift them away in order to get the correct pop-count.
 uint overlaps = (uint)Vector512<T>.Count - remaining;
 mask >>= (int)overlaps;
 count += BitOperations.PopCount(mask);

 return count;
 }
 // Count the last vector and mask off the elements that were already counted (number of elements between oneVectorAwayFromEnd and current).
 ulong mask = Vector512.Equals(Vector512.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();
 mask >>= (int)((nuint)Unsafe.ByteOffset(ref oneVectorAwayFromEnd, ref current) / (uint)Unsafe.SizeOf<T>());
 count += BitOperations.PopCount(mask);
 }
 else if (Vector256.IsHardwareAccelerated && length >= Vector256<T>.Count)
 {
 Vector256<T> targetVector = Vector256.Create(value);
 ref T oneVectorAwayFromEnd = ref Unsafe.Subtract(ref end, Vector256<T>.Count);
do
while (Unsafe.IsAddressLessThan(ref current, ref oneVectorAwayFromEnd))
 {
 count += BitOperations.PopCount(Vector256.Equals(Vector256.LoadUnsafe(ref current), targetVector).ExtractMostSignificantBits());
 current = ref Unsafe.Add(ref current, Vector256<T>.Count);
 }
 while (!Unsafe.IsAddressGreaterThan(ref current, ref oneVectorAwayFromEnd));

 // If there are just a few elements remaining, then processing these elements by the scalar loop
 // is cheaper than doing bitmask + popcount on the full last vector. To avoid complicated type
 // based checks, other remainder-count based logic to determine the correct cut-off, for simplicity
 // a half-vector size is chosen (based on benchmarks).
 uint remaining = (uint)Unsafe.ByteOffset(ref current, ref end) / (uint)Unsafe.SizeOf<T>();
 if (remaining > Vector256<T>.Count / 2)
Comment thread
stephentoub marked this conversation as resolved.

 {
 uint mask = Vector256.Equals(Vector256.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();

 // The mask contains some elements that may be double-checked, so shift them away in order to get the correct pop-count.
 uint overlaps = (uint)Vector256<T>.Count - remaining;
 mask >>= (int)overlaps;
 count += BitOperations.PopCount(mask);

 return count;
 }
 // Count the last vector and mask off the elements that were already counted (number of elements between oneVectorAwayFromEnd and current).
 uint mask = Vector256.Equals(Vector256.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();
 mask >>= (int)((nuint)Unsafe.ByteOffset(ref oneVectorAwayFromEnd, ref current) / (uint)Unsafe.SizeOf<T>());
 count += BitOperations.PopCount(mask);
 }
 else
 {
 Vector128<T> targetVector = Vector128.Create(value);
 ref T oneVectorAwayFromEnd = ref Unsafe.Subtract(ref end, Vector128<T>.Count);
do
while (Unsafe.IsAddressLessThan(ref current, ref oneVectorAwayFromEnd))
 {
 count += BitOperations.PopCount(Vector128.Equals(Vector128.LoadUnsafe(ref current), targetVector).ExtractMostSignificantBits());
 current = ref Unsafe.Add(ref current, Vector128<T>.Count);
 }
 while (!Unsafe.IsAddressGreaterThan(ref current, ref oneVectorAwayFromEnd));

 uint remaining = (uint)Unsafe.ByteOffset(ref current, ref end) / (uint)Unsafe.SizeOf<T>();
 if (remaining > Vector128<T>.Count / 2)
 {
 uint mask = Vector128.Equals(Vector128.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();

 // The mask contains some elements that may be double-checked, so shift them away in order to get the correct pop-count.
 uint overlaps = (uint)Vector128<T>.Count - remaining;
 mask >>= (int)overlaps;
 count += BitOperations.PopCount(mask);

 return count;
 }
 // Count the last vector and mask off the elements that were already counted (number of elements between oneVectorAwayFromEnd and current).
 uint mask = Vector128.Equals(Vector128.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();
 mask >>= (int)((nuint)Unsafe.ByteOffset(ref oneVectorAwayFromEnd, ref current) / (uint)Unsafe.SizeOf<T>());
 count += BitOperations.PopCount(mask);
 }
 }

 while (Unsafe.IsAddressLessThan(ref current, ref end))
 else
 {
if (current.Equals(value))
while (Unsafe.IsAddressLessThan(ref current, ref end))
 {
 count++;
 }
 if (current.Equals(value))
 {
 count++;
 }

 current = ref Unsafe.Add(ref current, 1);
 current = ref Unsafe.Add(ref current, 1);
 }
 }

 return count;
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Highlight search terms from Google/DuckDuckGo/Bing referrer
(function() {
var ref = document.referrer;
var terms = [];
if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) {
var url = new URL(ref);
var q = url.searchParams.get('q') || url.searchParams.get('p');
if (q) {
terms = q.split(/\s+/).filter(function(t) { return t.length > 2; });
}
}
if (terms.length === 0) return;
var style = document.createElement('style');
style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }';
document.head.appendChild(style);
function highlight(node) {
if (node.nodeType === 3) { // text node
var text = node.textContent;
var found = false;
terms.forEach(function(term) {
var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\]\\]/g, '\\') + ')', 'gi');
if (regex.test(text)) {
found = true;
var frag = document.createDocumentFragment();
var parts = text.split(regex);
parts.forEach(function(part, i) {
if (i % 2 === 0) {
frag.appendChild(document.createTextNode(part));
} else {
var span = document.createElement('span');
span.className = 'userscript-highlight';
span.textContent = part;
frag.appendChild(span);
}
});
node.parentNode.replaceChild(frag, node);
}
});
} else if (node.nodeType === 1 && node.childNodes) { // element
var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT'];
if (!skipTags.includes(node.tagName)) {
Array.from(node.childNodes).forEach(highlight);
}
}
}
highlight(document.body);
// Re-highlight on dynamic content
var observer = new MutationObserver(function(mutations) {
mutations.forEach(function(m) {
m.addedNodes.forEach(function(node) {
if (node.nodeType === 1 || node.nodeType === 3) highlight(node);
});
});
});
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Improve Span.Count#103728

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 2 commits into

from

Jun 21, 2024
 Merged


Improve Span.Count
#103728
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
5421ed4

Improve Span.Count


MihaZupan Jun 19, 2024
f5c1e6e

Fix indentation


MihaZupan Jun 19, 2024

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


79 changes: 23 additions & 56 deletions
src/libraries/System.Private.CoreLib/src/System/SpanHelpers.T.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3786,92 +3786,59 @@ public static int CountValueType<T>(ref T current, T value, int length) where T
 {
 Vector512<T> targetVector = Vector512.Create(value);
 ref T oneVectorAwayFromEnd = ref Unsafe.Subtract(ref end, Vector512<T>.Count);
do
while (Unsafe.IsAddressLessThan(ref current, ref oneVectorAwayFromEnd))
Comment thread
stephentoub marked this conversation as resolved.

 {
 count += BitOperations.PopCount(Vector512.Equals(Vector512.LoadUnsafe(ref current), targetVector).ExtractMostSignificantBits());
 current = ref Unsafe.Add(ref current, Vector512<T>.Count);
 }
 while (!Unsafe.IsAddressGreaterThan(ref current, ref oneVectorAwayFromEnd));

 // If there are just a few elements remaining, then processing these elements by the scalar loop
 // is cheaper than doing bitmask + popcount on the full last vector. To avoid complicated type
 // based checks, other remainder-count based logic to determine the correct cut-off, for simplicity
 // a half-vector size is chosen (based on benchmarks).
 uint remaining = (uint)Unsafe.ByteOffset(ref current, ref end) / (uint)Unsafe.SizeOf<T>();
 if (remaining > Vector512<T>.Count / 2)
 {
 ulong mask = Vector512.Equals(Vector512.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();

 // The mask contains some elements that may be double-checked, so shift them away in order to get the correct pop-count.
 uint overlaps = (uint)Vector512<T>.Count - remaining;
 mask >>= (int)overlaps;
 count += BitOperations.PopCount(mask);

 return count;
 }
 // Count the last vector and mask off the elements that were already counted (number of elements between oneVectorAwayFromEnd and current).
 ulong mask = Vector512.Equals(Vector512.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();
 mask >>= (int)((nuint)Unsafe.ByteOffset(ref oneVectorAwayFromEnd, ref current) / (uint)Unsafe.SizeOf<T>());
 count += BitOperations.PopCount(mask);
 }
 else if (Vector256.IsHardwareAccelerated && length >= Vector256<T>.Count)
 {
 Vector256<T> targetVector = Vector256.Create(value);
 ref T oneVectorAwayFromEnd = ref Unsafe.Subtract(ref end, Vector256<T>.Count);
do
while (Unsafe.IsAddressLessThan(ref current, ref oneVectorAwayFromEnd))
 {
 count += BitOperations.PopCount(Vector256.Equals(Vector256.LoadUnsafe(ref current), targetVector).ExtractMostSignificantBits());
 current = ref Unsafe.Add(ref current, Vector256<T>.Count);
 }
 while (!Unsafe.IsAddressGreaterThan(ref current, ref oneVectorAwayFromEnd));

 // If there are just a few elements remaining, then processing these elements by the scalar loop
 // is cheaper than doing bitmask + popcount on the full last vector. To avoid complicated type
 // based checks, other remainder-count based logic to determine the correct cut-off, for simplicity
 // a half-vector size is chosen (based on benchmarks).
 uint remaining = (uint)Unsafe.ByteOffset(ref current, ref end) / (uint)Unsafe.SizeOf<T>();
 if (remaining > Vector256<T>.Count / 2)
Comment thread
stephentoub marked this conversation as resolved.

 {
 uint mask = Vector256.Equals(Vector256.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();

 // The mask contains some elements that may be double-checked, so shift them away in order to get the correct pop-count.
 uint overlaps = (uint)Vector256<T>.Count - remaining;
 mask >>= (int)overlaps;
 count += BitOperations.PopCount(mask);

 return count;
 }
 // Count the last vector and mask off the elements that were already counted (number of elements between oneVectorAwayFromEnd and current).
 uint mask = Vector256.Equals(Vector256.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();
 mask >>= (int)((nuint)Unsafe.ByteOffset(ref oneVectorAwayFromEnd, ref current) / (uint)Unsafe.SizeOf<T>());
 count += BitOperations.PopCount(mask);
 }
 else
 {
 Vector128<T> targetVector = Vector128.Create(value);
 ref T oneVectorAwayFromEnd = ref Unsafe.Subtract(ref end, Vector128<T>.Count);
do
while (Unsafe.IsAddressLessThan(ref current, ref oneVectorAwayFromEnd))
 {
 count += BitOperations.PopCount(Vector128.Equals(Vector128.LoadUnsafe(ref current), targetVector).ExtractMostSignificantBits());
 current = ref Unsafe.Add(ref current, Vector128<T>.Count);
 }
 while (!Unsafe.IsAddressGreaterThan(ref current, ref oneVectorAwayFromEnd));

 uint remaining = (uint)Unsafe.ByteOffset(ref current, ref end) / (uint)Unsafe.SizeOf<T>();
 if (remaining > Vector128<T>.Count / 2)
 {
 uint mask = Vector128.Equals(Vector128.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();

 // The mask contains some elements that may be double-checked, so shift them away in order to get the correct pop-count.
 uint overlaps = (uint)Vector128<T>.Count - remaining;
 mask >>= (int)overlaps;
 count += BitOperations.PopCount(mask);

 return count;
 }
 // Count the last vector and mask off the elements that were already counted (number of elements between oneVectorAwayFromEnd and current).
 uint mask = Vector128.Equals(Vector128.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();
 mask >>= (int)((nuint)Unsafe.ByteOffset(ref oneVectorAwayFromEnd, ref current) / (uint)Unsafe.SizeOf<T>());
 count += BitOperations.PopCount(mask);
 }
 }

 while (Unsafe.IsAddressLessThan(ref current, ref end))
 else
 {
if (current.Equals(value))
while (Unsafe.IsAddressLessThan(ref current, ref end))
 {
 count++;
 }
 if (current.Equals(value))
 {
 count++;
 }

 current = ref Unsafe.Add(ref current, 1);
 current = ref Unsafe.Add(ref current, 1);
 }
 }

 return count;
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Strip utm_, fbclid, gclid, etc. from all links on page
(function() {
var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content',
'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid',
'ref', 'ref_src', 'source', 'medium', 'campaign'];
function cleanUrl(url) {
try {
var u = new URL(url, window.location.origin);
var changed = false;
trackingParams.forEach(function(p) {
if (u.searchParams.has(p)) {
u.searchParams.delete(p);
changed = true;
}
});
return changed ? u.toString() : url;
} catch (e) {
return url;
}
}
function cleanLinks() {
document.querySelectorAll('a[href]').forEach(function(a) {
var clean = cleanUrl(a.href);
if (clean !== a.href) a.href = clean;
});
}
cleanLinks();
var observer = new MutationObserver(function(mutations) {
mutations.forEach(function(m) {
m.addedNodes.forEach(function(node) {
if (node.nodeType === 1) {
if (node.tagName === 'A') cleanLinks();
node.querySelectorAll('a[href]').forEach(function(a) {
var clean = cleanUrl(a.href);
if (clean !== a.href) a.href = clean;
});
}
});
});
});
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); }
})();
(function(){
try {
var __m = "youtube.com";
var __re = new RegExp('^' + "youtube\\.com" + '

Skip to content
Improve Span.Count#103728

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 2 commits into

from

Jun 21, 2024
 Merged


Improve Span.Count
#103728
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
5421ed4

Improve Span.Count


MihaZupan Jun 19, 2024
f5c1e6e

Fix indentation


MihaZupan Jun 19, 2024

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


79 changes: 23 additions & 56 deletions
src/libraries/System.Private.CoreLib/src/System/SpanHelpers.T.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3786,92 +3786,59 @@ public static int CountValueType<T>(ref T current, T value, int length) where T
 {
 Vector512<T> targetVector = Vector512.Create(value);
 ref T oneVectorAwayFromEnd = ref Unsafe.Subtract(ref end, Vector512<T>.Count);
do
while (Unsafe.IsAddressLessThan(ref current, ref oneVectorAwayFromEnd))
Comment thread
stephentoub marked this conversation as resolved.

 {
 count += BitOperations.PopCount(Vector512.Equals(Vector512.LoadUnsafe(ref current), targetVector).ExtractMostSignificantBits());
 current = ref Unsafe.Add(ref current, Vector512<T>.Count);
 }
 while (!Unsafe.IsAddressGreaterThan(ref current, ref oneVectorAwayFromEnd));

 // If there are just a few elements remaining, then processing these elements by the scalar loop
 // is cheaper than doing bitmask + popcount on the full last vector. To avoid complicated type
 // based checks, other remainder-count based logic to determine the correct cut-off, for simplicity
 // a half-vector size is chosen (based on benchmarks).
 uint remaining = (uint)Unsafe.ByteOffset(ref current, ref end) / (uint)Unsafe.SizeOf<T>();
 if (remaining > Vector512<T>.Count / 2)
 {
 ulong mask = Vector512.Equals(Vector512.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();

 // The mask contains some elements that may be double-checked, so shift them away in order to get the correct pop-count.
 uint overlaps = (uint)Vector512<T>.Count - remaining;
 mask >>= (int)overlaps;
 count += BitOperations.PopCount(mask);

 return count;
 }
 // Count the last vector and mask off the elements that were already counted (number of elements between oneVectorAwayFromEnd and current).
 ulong mask = Vector512.Equals(Vector512.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();
 mask >>= (int)((nuint)Unsafe.ByteOffset(ref oneVectorAwayFromEnd, ref current) / (uint)Unsafe.SizeOf<T>());
 count += BitOperations.PopCount(mask);
 }
 else if (Vector256.IsHardwareAccelerated && length >= Vector256<T>.Count)
 {
 Vector256<T> targetVector = Vector256.Create(value);
 ref T oneVectorAwayFromEnd = ref Unsafe.Subtract(ref end, Vector256<T>.Count);
do
while (Unsafe.IsAddressLessThan(ref current, ref oneVectorAwayFromEnd))
 {
 count += BitOperations.PopCount(Vector256.Equals(Vector256.LoadUnsafe(ref current), targetVector).ExtractMostSignificantBits());
 current = ref Unsafe.Add(ref current, Vector256<T>.Count);
 }
 while (!Unsafe.IsAddressGreaterThan(ref current, ref oneVectorAwayFromEnd));

 // If there are just a few elements remaining, then processing these elements by the scalar loop
 // is cheaper than doing bitmask + popcount on the full last vector. To avoid complicated type
 // based checks, other remainder-count based logic to determine the correct cut-off, for simplicity
 // a half-vector size is chosen (based on benchmarks).
 uint remaining = (uint)Unsafe.ByteOffset(ref current, ref end) / (uint)Unsafe.SizeOf<T>();
 if (remaining > Vector256<T>.Count / 2)
Comment thread
stephentoub marked this conversation as resolved.

 {
 uint mask = Vector256.Equals(Vector256.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();

 // The mask contains some elements that may be double-checked, so shift them away in order to get the correct pop-count.
 uint overlaps = (uint)Vector256<T>.Count - remaining;
 mask >>= (int)overlaps;
 count += BitOperations.PopCount(mask);

 return count;
 }
 // Count the last vector and mask off the elements that were already counted (number of elements between oneVectorAwayFromEnd and current).
 uint mask = Vector256.Equals(Vector256.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();
 mask >>= (int)((nuint)Unsafe.ByteOffset(ref oneVectorAwayFromEnd, ref current) / (uint)Unsafe.SizeOf<T>());
 count += BitOperations.PopCount(mask);
 }
 else
 {
 Vector128<T> targetVector = Vector128.Create(value);
 ref T oneVectorAwayFromEnd = ref Unsafe.Subtract(ref end, Vector128<T>.Count);
do
while (Unsafe.IsAddressLessThan(ref current, ref oneVectorAwayFromEnd))
 {
 count += BitOperations.PopCount(Vector128.Equals(Vector128.LoadUnsafe(ref current), targetVector).ExtractMostSignificantBits());
 current = ref Unsafe.Add(ref current, Vector128<T>.Count);
 }
 while (!Unsafe.IsAddressGreaterThan(ref current, ref oneVectorAwayFromEnd));

 uint remaining = (uint)Unsafe.ByteOffset(ref current, ref end) / (uint)Unsafe.SizeOf<T>();
 if (remaining > Vector128<T>.Count / 2)
 {
 uint mask = Vector128.Equals(Vector128.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();

 // The mask contains some elements that may be double-checked, so shift them away in order to get the correct pop-count.
 uint overlaps = (uint)Vector128<T>.Count - remaining;
 mask >>= (int)overlaps;
 count += BitOperations.PopCount(mask);

 return count;
 }
 // Count the last vector and mask off the elements that were already counted (number of elements between oneVectorAwayFromEnd and current).
 uint mask = Vector128.Equals(Vector128.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();
 mask >>= (int)((nuint)Unsafe.ByteOffset(ref oneVectorAwayFromEnd, ref current) / (uint)Unsafe.SizeOf<T>());
 count += BitOperations.PopCount(mask);
 }
 }

 while (Unsafe.IsAddressLessThan(ref current, ref end))
 else
 {
if (current.Equals(value))
while (Unsafe.IsAddressLessThan(ref current, ref end))
 {
 count++;
 }
 if (current.Equals(value))
 {
 count++;
 }

 current = ref Unsafe.Add(ref current, 1);
 current = ref Unsafe.Add(ref current, 1);
 }
 }

 return count;
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Auto-enable theater mode on YouTube
(function() {
function tryTheater() {
var btn = document.querySelector('button[aria-label="Theater mode"], ytd-player #player button[title="Theater mode"]');
if (btn && !btn.classList.contains('activated')) {
btn.click();
}
}
// Try immediately
tryTheater();
// Try after navigation (SPA)
var lastUrl = location.href;
setInterval(function() {
if (location.href !== lastUrl) {
lastUrl = location.href;
setTimeout(tryTheater, 500);
}
}, 1000);
// Also try on player load
var observer = new MutationObserver(tryTheater);
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Improve Span.Count#103728

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 2 commits into

from

Jun 21, 2024
 Merged


Improve Span.Count
#103728
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
5421ed4

Improve Span.Count


MihaZupan Jun 19, 2024
f5c1e6e

Fix indentation


MihaZupan Jun 19, 2024

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


79 changes: 23 additions & 56 deletions
src/libraries/System.Private.CoreLib/src/System/SpanHelpers.T.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3786,92 +3786,59 @@ public static int CountValueType<T>(ref T current, T value, int length) where T
 {
 Vector512<T> targetVector = Vector512.Create(value);
 ref T oneVectorAwayFromEnd = ref Unsafe.Subtract(ref end, Vector512<T>.Count);
do
while (Unsafe.IsAddressLessThan(ref current, ref oneVectorAwayFromEnd))
Comment thread
stephentoub marked this conversation as resolved.

 {
 count += BitOperations.PopCount(Vector512.Equals(Vector512.LoadUnsafe(ref current), targetVector).ExtractMostSignificantBits());
 current = ref Unsafe.Add(ref current, Vector512<T>.Count);
 }
 while (!Unsafe.IsAddressGreaterThan(ref current, ref oneVectorAwayFromEnd));

 // If there are just a few elements remaining, then processing these elements by the scalar loop
 // is cheaper than doing bitmask + popcount on the full last vector. To avoid complicated type
 // based checks, other remainder-count based logic to determine the correct cut-off, for simplicity
 // a half-vector size is chosen (based on benchmarks).
 uint remaining = (uint)Unsafe.ByteOffset(ref current, ref end) / (uint)Unsafe.SizeOf<T>();
 if (remaining > Vector512<T>.Count / 2)
 {
 ulong mask = Vector512.Equals(Vector512.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();

 // The mask contains some elements that may be double-checked, so shift them away in order to get the correct pop-count.
 uint overlaps = (uint)Vector512<T>.Count - remaining;
 mask >>= (int)overlaps;
 count += BitOperations.PopCount(mask);

 return count;
 }
 // Count the last vector and mask off the elements that were already counted (number of elements between oneVectorAwayFromEnd and current).
 ulong mask = Vector512.Equals(Vector512.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();
 mask >>= (int)((nuint)Unsafe.ByteOffset(ref oneVectorAwayFromEnd, ref current) / (uint)Unsafe.SizeOf<T>());
 count += BitOperations.PopCount(mask);
 }
 else if (Vector256.IsHardwareAccelerated && length >= Vector256<T>.Count)
 {
 Vector256<T> targetVector = Vector256.Create(value);
 ref T oneVectorAwayFromEnd = ref Unsafe.Subtract(ref end, Vector256<T>.Count);
do
while (Unsafe.IsAddressLessThan(ref current, ref oneVectorAwayFromEnd))
 {
 count += BitOperations.PopCount(Vector256.Equals(Vector256.LoadUnsafe(ref current), targetVector).ExtractMostSignificantBits());
 current = ref Unsafe.Add(ref current, Vector256<T>.Count);
 }
 while (!Unsafe.IsAddressGreaterThan(ref current, ref oneVectorAwayFromEnd));

 // If there are just a few elements remaining, then processing these elements by the scalar loop
 // is cheaper than doing bitmask + popcount on the full last vector. To avoid complicated type
 // based checks, other remainder-count based logic to determine the correct cut-off, for simplicity
 // a half-vector size is chosen (based on benchmarks).
 uint remaining = (uint)Unsafe.ByteOffset(ref current, ref end) / (uint)Unsafe.SizeOf<T>();
 if (remaining > Vector256<T>.Count / 2)
Comment thread
stephentoub marked this conversation as resolved.

 {
 uint mask = Vector256.Equals(Vector256.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();

 // The mask contains some elements that may be double-checked, so shift them away in order to get the correct pop-count.
 uint overlaps = (uint)Vector256<T>.Count - remaining;
 mask >>= (int)overlaps;
 count += BitOperations.PopCount(mask);

 return count;
 }
 // Count the last vector and mask off the elements that were already counted (number of elements between oneVectorAwayFromEnd and current).
 uint mask = Vector256.Equals(Vector256.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();
 mask >>= (int)((nuint)Unsafe.ByteOffset(ref oneVectorAwayFromEnd, ref current) / (uint)Unsafe.SizeOf<T>());
 count += BitOperations.PopCount(mask);
 }
 else
 {
 Vector128<T> targetVector = Vector128.Create(value);
 ref T oneVectorAwayFromEnd = ref Unsafe.Subtract(ref end, Vector128<T>.Count);
do
while (Unsafe.IsAddressLessThan(ref current, ref oneVectorAwayFromEnd))
 {
 count += BitOperations.PopCount(Vector128.Equals(Vector128.LoadUnsafe(ref current), targetVector).ExtractMostSignificantBits());
 current = ref Unsafe.Add(ref current, Vector128<T>.Count);
 }
 while (!Unsafe.IsAddressGreaterThan(ref current, ref oneVectorAwayFromEnd));

 uint remaining = (uint)Unsafe.ByteOffset(ref current, ref end) / (uint)Unsafe.SizeOf<T>();
 if (remaining > Vector128<T>.Count / 2)
 {
 uint mask = Vector128.Equals(Vector128.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();

 // The mask contains some elements that may be double-checked, so shift them away in order to get the correct pop-count.
 uint overlaps = (uint)Vector128<T>.Count - remaining;
 mask >>= (int)overlaps;
 count += BitOperations.PopCount(mask);

 return count;
 }
 // Count the last vector and mask off the elements that were already counted (number of elements between oneVectorAwayFromEnd and current).
 uint mask = Vector128.Equals(Vector128.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();
 mask >>= (int)((nuint)Unsafe.ByteOffset(ref oneVectorAwayFromEnd, ref current) / (uint)Unsafe.SizeOf<T>());
 count += BitOperations.PopCount(mask);
 }
 }

 while (Unsafe.IsAddressLessThan(ref current, ref end))
 else
 {
if (current.Equals(value))
while (Unsafe.IsAddressLessThan(ref current, ref end))
 {
 count++;
 }
 if (current.Equals(value))
 {
 count++;
 }

 current = ref Unsafe.Add(ref current, 1);
 current = ref Unsafe.Add(ref current, 1);
 }
 }

 return count;
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Remove or un-stick sticky/fixed headers that block content
(function() {
function unstick() {
document.querySelectorAll('header, nav, [role="banner"], .header, .navbar, .sticky, .fixed-top, [style*="position: fixed"], [style*="position:sticky"]').forEach(function(el) {
if (el.style.position === 'fixed' || el.style.position === 'sticky' || getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') {
el.style.position = 'static';
el.style.top = 'auto';
el.style.zIndex = 'auto';
}
});
}
unstick();
var observer = new MutationObserver(unstick);
observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] });
})();
}
} catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Improve Span.Count#103728

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 2 commits into

from

Jun 21, 2024
 Merged


Improve Span.Count
#103728
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
5421ed4

Improve Span.Count


MihaZupan Jun 19, 2024
f5c1e6e

Fix indentation


MihaZupan Jun 19, 2024

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


79 changes: 23 additions & 56 deletions
src/libraries/System.Private.CoreLib/src/System/SpanHelpers.T.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3786,92 +3786,59 @@ public static int CountValueType<T>(ref T current, T value, int length) where T
 {
 Vector512<T> targetVector = Vector512.Create(value);
 ref T oneVectorAwayFromEnd = ref Unsafe.Subtract(ref end, Vector512<T>.Count);
do
while (Unsafe.IsAddressLessThan(ref current, ref oneVectorAwayFromEnd))
Comment thread
stephentoub marked this conversation as resolved.

 {
 count += BitOperations.PopCount(Vector512.Equals(Vector512.LoadUnsafe(ref current), targetVector).ExtractMostSignificantBits());
 current = ref Unsafe.Add(ref current, Vector512<T>.Count);
 }
 while (!Unsafe.IsAddressGreaterThan(ref current, ref oneVectorAwayFromEnd));

 // If there are just a few elements remaining, then processing these elements by the scalar loop
 // is cheaper than doing bitmask + popcount on the full last vector. To avoid complicated type
 // based checks, other remainder-count based logic to determine the correct cut-off, for simplicity
 // a half-vector size is chosen (based on benchmarks).
 uint remaining = (uint)Unsafe.ByteOffset(ref current, ref end) / (uint)Unsafe.SizeOf<T>();
 if (remaining > Vector512<T>.Count / 2)
 {
 ulong mask = Vector512.Equals(Vector512.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();

 // The mask contains some elements that may be double-checked, so shift them away in order to get the correct pop-count.
 uint overlaps = (uint)Vector512<T>.Count - remaining;
 mask >>= (int)overlaps;
 count += BitOperations.PopCount(mask);

 return count;
 }
 // Count the last vector and mask off the elements that were already counted (number of elements between oneVectorAwayFromEnd and current).
 ulong mask = Vector512.Equals(Vector512.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();
 mask >>= (int)((nuint)Unsafe.ByteOffset(ref oneVectorAwayFromEnd, ref current) / (uint)Unsafe.SizeOf<T>());
 count += BitOperations.PopCount(mask);
 }
 else if (Vector256.IsHardwareAccelerated && length >= Vector256<T>.Count)
 {
 Vector256<T> targetVector = Vector256.Create(value);
 ref T oneVectorAwayFromEnd = ref Unsafe.Subtract(ref end, Vector256<T>.Count);
do
while (Unsafe.IsAddressLessThan(ref current, ref oneVectorAwayFromEnd))
 {
 count += BitOperations.PopCount(Vector256.Equals(Vector256.LoadUnsafe(ref current), targetVector).ExtractMostSignificantBits());
 current = ref Unsafe.Add(ref current, Vector256<T>.Count);
 }
 while (!Unsafe.IsAddressGreaterThan(ref current, ref oneVectorAwayFromEnd));

 // If there are just a few elements remaining, then processing these elements by the scalar loop
 // is cheaper than doing bitmask + popcount on the full last vector. To avoid complicated type
 // based checks, other remainder-count based logic to determine the correct cut-off, for simplicity
 // a half-vector size is chosen (based on benchmarks).
 uint remaining = (uint)Unsafe.ByteOffset(ref current, ref end) / (uint)Unsafe.SizeOf<T>();
 if (remaining > Vector256<T>.Count / 2)
Comment thread
stephentoub marked this conversation as resolved.

 {
 uint mask = Vector256.Equals(Vector256.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();

 // The mask contains some elements that may be double-checked, so shift them away in order to get the correct pop-count.
 uint overlaps = (uint)Vector256<T>.Count - remaining;
 mask >>= (int)overlaps;
 count += BitOperations.PopCount(mask);

 return count;
 }
 // Count the last vector and mask off the elements that were already counted (number of elements between oneVectorAwayFromEnd and current).
 uint mask = Vector256.Equals(Vector256.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();
 mask >>= (int)((nuint)Unsafe.ByteOffset(ref oneVectorAwayFromEnd, ref current) / (uint)Unsafe.SizeOf<T>());
 count += BitOperations.PopCount(mask);
 }
 else
 {
 Vector128<T> targetVector = Vector128.Create(value);
 ref T oneVectorAwayFromEnd = ref Unsafe.Subtract(ref end, Vector128<T>.Count);
do
while (Unsafe.IsAddressLessThan(ref current, ref oneVectorAwayFromEnd))
 {
 count += BitOperations.PopCount(Vector128.Equals(Vector128.LoadUnsafe(ref current), targetVector).ExtractMostSignificantBits());
 current = ref Unsafe.Add(ref current, Vector128<T>.Count);
 }
 while (!Unsafe.IsAddressGreaterThan(ref current, ref oneVectorAwayFromEnd));

 uint remaining = (uint)Unsafe.ByteOffset(ref current, ref end) / (uint)Unsafe.SizeOf<T>();
 if (remaining > Vector128<T>.Count / 2)
 {
 uint mask = Vector128.Equals(Vector128.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();

 // The mask contains some elements that may be double-checked, so shift them away in order to get the correct pop-count.
 uint overlaps = (uint)Vector128<T>.Count - remaining;
 mask >>= (int)overlaps;
 count += BitOperations.PopCount(mask);

 return count;
 }
 // Count the last vector and mask off the elements that were already counted (number of elements between oneVectorAwayFromEnd and current).
 uint mask = Vector128.Equals(Vector128.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();
 mask >>= (int)((nuint)Unsafe.ByteOffset(ref oneVectorAwayFromEnd, ref current) / (uint)Unsafe.SizeOf<T>());
 count += BitOperations.PopCount(mask);
 }
 }

 while (Unsafe.IsAddressLessThan(ref current, ref end))
 else
 {
if (current.Equals(value))
while (Unsafe.IsAddressLessThan(ref current, ref end))
 {
 count++;
 }
 if (current.Equals(value))
 {
 count++;
 }

 current = ref Unsafe.Add(ref current, 1);
 current = ref Unsafe.Add(ref current, 1);
 }
 }

 return count;
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Universal Dark Mode - works on any site
(function() {
var enabled = true;
function applyDarkMode() {
if (!enabled) return;
// Create style element if it doesn't exist
var style = document.getElementById('universal-dark-mode-style');
if (!style) {
style = document.createElement('style');
style.id = 'universal-dark-mode-style';
document.head.appendChild(style);
}
// Dark mode CSS - inverts colors but preserves images/video
style.textContent = '
/* Invert everything except media */
html {
filter: invert(1) hue-rotate(180deg) !important;
background: #1a1a2e !important;
}
/* Restore images, videos, iframes, canvas */
img, video, iframe, canvas, svg, picture, [style*="background-image"] {
filter: invert(1) hue-rotate(180deg) !important;
}
/* Preserve specific elements that should not be inverted */
.no-dark-mode, .no-dark-mode *,
[data-theme="light"], [data-theme="light"],
.ace_editor, .ace_editor *,
.CodeMirror, .CodeMirror *,
.monaco-editor, .monaco-editor *,
.markdown-body pre, .markdown-body pre *,
.highlight, .highlight *,
pre code, pre code * {
filter: none !important;
}
/* Fix common UI elements */
.modal, .popup, .dropdown-menu, .tooltip, .popover {
filter: invert(1) hue-rotate(180deg) !important;
background: #2d2d44 !important;
border-color: #444 !important;
}
/* Scrollbars */
::-webkit-scrollbar { background: #1a1a2e !important; }
::-webkit-scrollbar-thumb { background: #444 !important; }
::-webkit-scrollbar-thumb:hover { background: #555 !important; }
/* Selection */
::selection { background: #4ecdc4 !important; color: #1a1a2e !important; }
::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; }
';
}
function removeDarkMode() {
var style = document.getElementById('universal-dark-mode-style');
if (style) style.remove();
}
// Toggle with Alt+Shift+D
document.addEventListener('keydown', function(e) {
if (e.altKey && e.shiftKey && e.key === 'D') {
e.preventDefault();
enabled = !enabled;
if (enabled) {
applyDarkMode();
console.log('[Universal Dark Mode] Enabled');
} else {
removeDarkMode();
console.log('[Universal Dark Mode] Disabled');
}
}
});
// Apply on load
applyDarkMode();
// Re-apply on dynamic content
var observer = new MutationObserver(function(mutations) {
if (enabled && !document.getElementById('universal-dark-mode-style')) {
applyDarkMode();
}
});
observer.observe(document.head, { childList: true });
console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle');
})();
}
} catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); }
})();
})();

Skip to content
Improve Span.Count#103728

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 2 commits into

from

Jun 21, 2024
 Merged


Improve Span.Count
#103728
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
5421ed4

Improve Span.Count


MihaZupan Jun 19, 2024
f5c1e6e

Fix indentation


MihaZupan Jun 19, 2024

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


79 changes: 23 additions & 56 deletions
src/libraries/System.Private.CoreLib/src/System/SpanHelpers.T.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3786,92 +3786,59 @@ public static int CountValueType<T>(ref T current, T value, int length) where T
 {
 Vector512<T> targetVector = Vector512.Create(value);
 ref T oneVectorAwayFromEnd = ref Unsafe.Subtract(ref end, Vector512<T>.Count);
do
while (Unsafe.IsAddressLessThan(ref current, ref oneVectorAwayFromEnd))
Comment thread
stephentoub marked this conversation as resolved.

 {
 count += BitOperations.PopCount(Vector512.Equals(Vector512.LoadUnsafe(ref current), targetVector).ExtractMostSignificantBits());
 current = ref Unsafe.Add(ref current, Vector512<T>.Count);
 }
 while (!Unsafe.IsAddressGreaterThan(ref current, ref oneVectorAwayFromEnd));

 // If there are just a few elements remaining, then processing these elements by the scalar loop
 // is cheaper than doing bitmask + popcount on the full last vector. To avoid complicated type
 // based checks, other remainder-count based logic to determine the correct cut-off, for simplicity
 // a half-vector size is chosen (based on benchmarks).
 uint remaining = (uint)Unsafe.ByteOffset(ref current, ref end) / (uint)Unsafe.SizeOf<T>();
 if (remaining > Vector512<T>.Count / 2)
 {
 ulong mask = Vector512.Equals(Vector512.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();

 // The mask contains some elements that may be double-checked, so shift them away in order to get the correct pop-count.
 uint overlaps = (uint)Vector512<T>.Count - remaining;
 mask >>= (int)overlaps;
 count += BitOperations.PopCount(mask);

 return count;
 }
 // Count the last vector and mask off the elements that were already counted (number of elements between oneVectorAwayFromEnd and current).
 ulong mask = Vector512.Equals(Vector512.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();
 mask >>= (int)((nuint)Unsafe.ByteOffset(ref oneVectorAwayFromEnd, ref current) / (uint)Unsafe.SizeOf<T>());
 count += BitOperations.PopCount(mask);
 }
 else if (Vector256.IsHardwareAccelerated && length >= Vector256<T>.Count)
 {
 Vector256<T> targetVector = Vector256.Create(value);
 ref T oneVectorAwayFromEnd = ref Unsafe.Subtract(ref end, Vector256<T>.Count);
do
while (Unsafe.IsAddressLessThan(ref current, ref oneVectorAwayFromEnd))
 {
 count += BitOperations.PopCount(Vector256.Equals(Vector256.LoadUnsafe(ref current), targetVector).ExtractMostSignificantBits());
 current = ref Unsafe.Add(ref current, Vector256<T>.Count);
 }
 while (!Unsafe.IsAddressGreaterThan(ref current, ref oneVectorAwayFromEnd));

 // If there are just a few elements remaining, then processing these elements by the scalar loop
 // is cheaper than doing bitmask + popcount on the full last vector. To avoid complicated type
 // based checks, other remainder-count based logic to determine the correct cut-off, for simplicity
 // a half-vector size is chosen (based on benchmarks).
 uint remaining = (uint)Unsafe.ByteOffset(ref current, ref end) / (uint)Unsafe.SizeOf<T>();
 if (remaining > Vector256<T>.Count / 2)
Comment thread
stephentoub marked this conversation as resolved.

 {
 uint mask = Vector256.Equals(Vector256.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();

 // The mask contains some elements that may be double-checked, so shift them away in order to get the correct pop-count.
 uint overlaps = (uint)Vector256<T>.Count - remaining;
 mask >>= (int)overlaps;
 count += BitOperations.PopCount(mask);

 return count;
 }
 // Count the last vector and mask off the elements that were already counted (number of elements between oneVectorAwayFromEnd and current).
 uint mask = Vector256.Equals(Vector256.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();
 mask >>= (int)((nuint)Unsafe.ByteOffset(ref oneVectorAwayFromEnd, ref current) / (uint)Unsafe.SizeOf<T>());
 count += BitOperations.PopCount(mask);
 }
 else
 {
 Vector128<T> targetVector = Vector128.Create(value);
 ref T oneVectorAwayFromEnd = ref Unsafe.Subtract(ref end, Vector128<T>.Count);
do
while (Unsafe.IsAddressLessThan(ref current, ref oneVectorAwayFromEnd))
 {
 count += BitOperations.PopCount(Vector128.Equals(Vector128.LoadUnsafe(ref current), targetVector).ExtractMostSignificantBits());
 current = ref Unsafe.Add(ref current, Vector128<T>.Count);
 }
 while (!Unsafe.IsAddressGreaterThan(ref current, ref oneVectorAwayFromEnd));

 uint remaining = (uint)Unsafe.ByteOffset(ref current, ref end) / (uint)Unsafe.SizeOf<T>();
 if (remaining > Vector128<T>.Count / 2)
 {
 uint mask = Vector128.Equals(Vector128.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();

 // The mask contains some elements that may be double-checked, so shift them away in order to get the correct pop-count.
 uint overlaps = (uint)Vector128<T>.Count - remaining;
 mask >>= (int)overlaps;
 count += BitOperations.PopCount(mask);

 return count;
 }
 // Count the last vector and mask off the elements that were already counted (number of elements between oneVectorAwayFromEnd and current).
 uint mask = Vector128.Equals(Vector128.LoadUnsafe(ref oneVectorAwayFromEnd), targetVector).ExtractMostSignificantBits();
 mask >>= (int)((nuint)Unsafe.ByteOffset(ref oneVectorAwayFromEnd, ref current) / (uint)Unsafe.SizeOf<T>());
 count += BitOperations.PopCount(mask);
 }
 }

 while (Unsafe.IsAddressLessThan(ref current, ref end))
 else
 {
if (current.Equals(value))
while (Unsafe.IsAddressLessThan(ref current, ref end))
 {
 count++;
 }
 if (current.Equals(value))
 {
 count++;
 }

 current = ref Unsafe.Add(ref current, 1);
 current = ref Unsafe.Add(ref current, 1);
 }
 }

 return count;
Expand Down