crypto.kt128: when using incremental hashing, use SIMD when possible#25783

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
jedisct1 merged 1 commit into from
Nov 2, 2025
Merged

crypto.kt128: when using incremental hashing, use SIMD when possible #25783

Show file tree
Hide file tree
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
1 change: 1 addition & 0 deletions lib/std/crypto/benchmark.zig
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -30,6 +30,7 @@ const hashes = [_]Crypto{
Crypto{ .ty = crypto.hash.sha3.Shake256, .name = "shake-256" },
Crypto{ .ty = crypto.hash.sha3.TurboShake128(null), .name = "turboshake-128" },
Crypto{ .ty = crypto.hash.sha3.TurboShake256(null), .name = "turboshake-256" },
Crypto{ .ty = crypto.hash.sha3.KT128, .name = "kt128" },
Crypto{ .ty = crypto.hash.blake2.Blake2s256, .name = "blake2s" },
Crypto{ .ty = crypto.hash.blake2.Blake2b512, .name = "blake2b" },
Crypto{ .ty = crypto.hash.Blake3, .name = "blake3" },
Expand Down
136 changes: 113 additions & 23 deletions lib/std/crypto/kangarootwelve.zig
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -848,6 +848,10 @@ fn KTHash(
final_state: ?StateType, // Running TurboSHAKE state for final node
num_leaves: usize, // Count of leaves processed (after first chunk)

// SIMD chunk batching
pending_chunks: [8 * chunk_size]u8 align(cache_line_size), // Buffer for up to 8 chunks
pending_count: usize, // Number of complete chunks in pending_chunks

/// Initialize a KangarooTwelve hashing context.
/// The customization string is optional and used for domain separation.
pub fn init(options: Options) Self {
Expand All@@ -861,9 +865,48 @@ fn KTHash(
.first_chunk = null,
.final_state = null,
.num_leaves = 0,
.pending_chunks = undefined,
.pending_count = 0,
};
}

/// Flush all pending chunks using SIMD when possible
fn flushPendingChunks(self: *Self) void {
const cv_size = Variant.cv_size;

// Process all pending chunks using the largest SIMD batch sizes possible
while (self.pending_count > 0) {
// Try SIMD batches in decreasing size order
inline for ([_]usize{ 8, 4, 2 }) |batch_size| {
if (optimal_vector_len >= batch_size and self.pending_count >= batch_size) {
var leaf_cvs: [batch_size * cv_size]u8 align(cache_line_size) = undefined;
processLeaves(Variant, batch_size, self.pending_chunks[0 .. batch_size * chunk_size], &leaf_cvs);
self.final_state.?.update(&leaf_cvs);
self.num_leaves += batch_size;
self.pending_count -= batch_size;

// Shift remaining chunks to the front
if (self.pending_count > 0) {
const remaining_bytes = self.pending_count * chunk_size;
@memcpy(self.pending_chunks[0..remaining_bytes], self.pending_chunks[batch_size * chunk_size ..][0..remaining_bytes]);
}
break; // Continue outer loop to try next batch
}
}

// If no SIMD batch was possible, process one chunk with scalar code
if (self.pending_count > 0 and self.pending_count < 2) {
var cv_buffer: [64]u8 = undefined;
const cv_slice = MultiSliceView.init(self.pending_chunks[0..chunk_size], &[_]u8{}, &[_]u8{});
Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);
self.final_state.?.update(cv_buffer[0..cv_size]);
self.num_leaves += 1;
self.pending_count -= 1;
break; // No more chunks to process
}
}
}

/// Absorb data into the hash state.
/// Can be called multiple times to incrementally add data.
pub fn update(self: *Self, data: []const u8) void {
Expand DownExpand Up@@ -895,15 +938,21 @@ fn KTHash(
const padding = [_]u8{ 0x03, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 };
self.final_state.?.update(&padding);
} else {
// Subsequent chunks - process as leaf and absorb CV
const cv_size = Variant.cv_size;
var cv_buffer: [64]u8 = undefined; // Max CV size
const cv_slice = MultiSliceView.init(&self.buffer, &[_]u8{}, &[_]u8{});
Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);

// Absorb CV into final state immediately
self.final_state.?.update(cv_buffer[0..cv_size]);
self.num_leaves += 1;
// Add chunk to pending buffer for SIMD batch processing
@memcpy(self.pending_chunks[self.pending_count * chunk_size ..][0..chunk_size], &self.buffer);
self.pending_count += 1;

// Flush when we have enough chunks for optimal SIMD batch
// Determine best batch size for this architecture
const optimal_batch_size = comptime blk: {
if (optimal_vector_len >= 8) break :blk 8;
if (optimal_vector_len >= 4) break :blk 4;
if (optimal_vector_len >= 2) break :blk 2;
break :blk 1;
};
if (self.pending_count >= optimal_batch_size) {
self.flushPendingChunks();
}
}
self.buffer_len = 0;
}
Expand DownExpand Up@@ -931,24 +980,65 @@ fn KTHash(
return;
}

// Tree mode: we've already absorbed first_chunk + padding + intermediate CVs
// Now handle remaining buffer data
const remaining_with_custom_len = self.buffer_len + self.customization.len + self.custom_len_enc.len;
// Flush any pending chunks with SIMD
self.flushPendingChunks();

// Build view over remaining data (buffer + customization + encoding)
const remaining_view = MultiSliceView.init(
self.buffer[0..self.buffer_len],
self.customization,
self.custom_len_enc.slice(),
);
const remaining_len = remaining_view.totalLen();

var final_leaves = self.num_leaves;
var leaf_start: usize = 0;

// Tree mode: initialize if not already done (lazy initialization)
if (self.final_state == null and remaining_len > 0) {
self.final_state = StateType.init(.{});

// Absorb first chunk (up to chunk_size bytes from remaining data)
const first_chunk_len = @min(chunk_size, remaining_len);
if (remaining_view.tryGetSlice(0, first_chunk_len)) |first_chunk| {
// Data is contiguous, use it directly
self.final_state.?.update(first_chunk);
} else {
// Data spans boundaries, copy to buffer
var first_chunk_buf: [chunk_size]u8 = undefined;
remaining_view.copyRange(0, first_chunk_len, first_chunk_buf[0..first_chunk_len]);
self.final_state.?.update(first_chunk_buf[0..first_chunk_len]);
}

if (remaining_with_custom_len > 0) {
// Build final leaf data with customization
var final_leaf_buffer: [chunk_size + 256]u8 = undefined; // Extra space for customization
@memcpy(final_leaf_buffer[0..self.buffer_len], self.buffer[0..self.buffer_len]);
@memcpy(final_leaf_buffer[self.buffer_len..][0..self.customization.len], self.customization);
@memcpy(final_leaf_buffer[self.buffer_len + self.customization.len ..][0..self.custom_len_enc.len], self.custom_len_enc.slice());

// Generate CV for final leaf and absorb it
var cv_buffer: [64]u8 = undefined; // Max CV size
const cv_slice = MultiSliceView.init(final_leaf_buffer[0..remaining_with_custom_len], &[_]u8{}, &[_]u8{});
Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);
// Absorb padding (8 bytes: 0x03 followed by 7 zeros)
const padding = [_]u8{ 0x03, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 };
self.final_state.?.update(&padding);

// Process remaining data as leaves
leaf_start = first_chunk_len;
}

// Process all remaining data as leaves (starting from leaf_start)
var offset = leaf_start;
while (offset < remaining_len) {
const leaf_end = @min(offset + chunk_size, remaining_len);
const leaf_size = leaf_end - offset;

var cv_buffer: [64]u8 = undefined;
if (remaining_view.tryGetSlice(offset, leaf_end)) |leaf_data| {
// Data is contiguous, use it directly
const cv_slice = MultiSliceView.init(leaf_data, &[_]u8{}, &[_]u8{});
Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);
} else {
// Data spans boundaries, copy to buffer
var leaf_buf: [chunk_size]u8 = undefined;
remaining_view.copyRange(offset, leaf_end, leaf_buf[0..leaf_size]);
const cv_slice = MultiSliceView.init(leaf_buf[0..leaf_size], &[_]u8{}, &[_]u8{});
Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);
}
self.final_state.?.update(cv_buffer[0..cv_size]);
final_leaves += 1;
offset = leaf_end;
}

// Absorb right_encode(num_leaves) and terminator
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
crypto.kt128: when using incremental hashing, use SIMD when possible#25783

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

jedisct1
merged 1 commit into

from

Nov 2, 2025
 Merged


crypto.kt128: when using incremental hashing, use SIMD when possible
#25783
Show file tree
Hide file tree
 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


1 change: 1 addition & 0 deletions
lib/std/crypto/benchmark.zig

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -30,6 +30,7 @@ const hashes = [_]Crypto{
 Crypto{ .ty = crypto.hash.sha3.Shake256, .name = "shake-256" },
 Crypto{ .ty = crypto.hash.sha3.TurboShake128(null), .name = "turboshake-128" },
 Crypto{ .ty = crypto.hash.sha3.TurboShake256(null), .name = "turboshake-256" },
 Crypto{ .ty = crypto.hash.sha3.KT128, .name = "kt128" },
 Crypto{ .ty = crypto.hash.blake2.Blake2s256, .name = "blake2s" },
 Crypto{ .ty = crypto.hash.blake2.Blake2b512, .name = "blake2b" },
 Crypto{ .ty = crypto.hash.Blake3, .name = "blake3" },
Expand Down

136 changes: 113 additions & 23 deletions
lib/std/crypto/kangarootwelve.zig

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -848,6 +848,10 @@ fn KTHash(
 final_state: ?StateType, // Running TurboSHAKE state for final node
 num_leaves: usize, // Count of leaves processed (after first chunk)

 // SIMD chunk batching
 pending_chunks: [8 * chunk_size]u8 align(cache_line_size), // Buffer for up to 8 chunks
 pending_count: usize, // Number of complete chunks in pending_chunks

 /// Initialize a KangarooTwelve hashing context.
 /// The customization string is optional and used for domain separation.
 pub fn init(options: Options) Self {
Expand All@@ -861,9 +865,48 @@ fn KTHash(
 .first_chunk = null,
 .final_state = null,
 .num_leaves = 0,
 .pending_chunks = undefined,
 .pending_count = 0,
 };
 }

 /// Flush all pending chunks using SIMD when possible
 fn flushPendingChunks(self: *Self) void {
 const cv_size = Variant.cv_size;

 // Process all pending chunks using the largest SIMD batch sizes possible
 while (self.pending_count > 0) {
 // Try SIMD batches in decreasing size order
 inline for ([_]usize{ 8, 4, 2 }) |batch_size| {
 if (optimal_vector_len >= batch_size and self.pending_count >= batch_size) {
 var leaf_cvs: [batch_size * cv_size]u8 align(cache_line_size) = undefined;
 processLeaves(Variant, batch_size, self.pending_chunks[0 .. batch_size * chunk_size], &leaf_cvs);
 self.final_state.?.update(&leaf_cvs);
 self.num_leaves += batch_size;
 self.pending_count -= batch_size;

 // Shift remaining chunks to the front
 if (self.pending_count > 0) {
 const remaining_bytes = self.pending_count * chunk_size;
 @memcpy(self.pending_chunks[0..remaining_bytes], self.pending_chunks[batch_size * chunk_size ..][0..remaining_bytes]);
 }
 break; // Continue outer loop to try next batch
 }
 }

 // If no SIMD batch was possible, process one chunk with scalar code
 if (self.pending_count > 0 and self.pending_count < 2) {
 var cv_buffer: [64]u8 = undefined;
 const cv_slice = MultiSliceView.init(self.pending_chunks[0..chunk_size], &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);
 self.final_state.?.update(cv_buffer[0..cv_size]);
 self.num_leaves += 1;
 self.pending_count -= 1;
 break; // No more chunks to process
 }
 }
 }

 /// Absorb data into the hash state.
 /// Can be called multiple times to incrementally add data.
 pub fn update(self: *Self, data: []const u8) void {
Expand DownExpand Up@@ -895,15 +938,21 @@ fn KTHash(
 const padding = [_]u8{ 0x03, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 };
 self.final_state.?.update(&padding);
 } else {
 // Subsequent chunks - process as leaf and absorb CV
 const cv_size = Variant.cv_size;
 var cv_buffer: [64]u8 = undefined; // Max CV size
 const cv_slice = MultiSliceView.init(&self.buffer, &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);

 // Absorb CV into final state immediately
 self.final_state.?.update(cv_buffer[0..cv_size]);
 self.num_leaves += 1;
 // Add chunk to pending buffer for SIMD batch processing
 @memcpy(self.pending_chunks[self.pending_count * chunk_size ..][0..chunk_size], &self.buffer);
 self.pending_count += 1;

 // Flush when we have enough chunks for optimal SIMD batch
 // Determine best batch size for this architecture
 const optimal_batch_size = comptime blk: {
 if (optimal_vector_len >= 8) break :blk 8;
 if (optimal_vector_len >= 4) break :blk 4;
 if (optimal_vector_len >= 2) break :blk 2;
 break :blk 1;
 };
 if (self.pending_count >= optimal_batch_size) {
 self.flushPendingChunks();
 }
 }
 self.buffer_len = 0;
 }
Expand DownExpand Up@@ -931,24 +980,65 @@ fn KTHash(
 return;
 }

 // Tree mode: we've already absorbed first_chunk + padding + intermediate CVs
 // Now handle remaining buffer data
 const remaining_with_custom_len = self.buffer_len + self.customization.len + self.custom_len_enc.len;
 // Flush any pending chunks with SIMD
 self.flushPendingChunks();

 // Build view over remaining data (buffer + customization + encoding)
 const remaining_view = MultiSliceView.init(
 self.buffer[0..self.buffer_len],
 self.customization,
 self.custom_len_enc.slice(),
 );
 const remaining_len = remaining_view.totalLen();

 var final_leaves = self.num_leaves;
 var leaf_start: usize = 0;

 // Tree mode: initialize if not already done (lazy initialization)
 if (self.final_state == null and remaining_len > 0) {
 self.final_state = StateType.init(.{});

 // Absorb first chunk (up to chunk_size bytes from remaining data)
 const first_chunk_len = @min(chunk_size, remaining_len);
 if (remaining_view.tryGetSlice(0, first_chunk_len)) |first_chunk| {
 // Data is contiguous, use it directly
 self.final_state.?.update(first_chunk);
 } else {
 // Data spans boundaries, copy to buffer
 var first_chunk_buf: [chunk_size]u8 = undefined;
 remaining_view.copyRange(0, first_chunk_len, first_chunk_buf[0..first_chunk_len]);
 self.final_state.?.update(first_chunk_buf[0..first_chunk_len]);
 }

 if (remaining_with_custom_len > 0) {
 // Build final leaf data with customization
 var final_leaf_buffer: [chunk_size + 256]u8 = undefined; // Extra space for customization
 @memcpy(final_leaf_buffer[0..self.buffer_len], self.buffer[0..self.buffer_len]);
 @memcpy(final_leaf_buffer[self.buffer_len..][0..self.customization.len], self.customization);
 @memcpy(final_leaf_buffer[self.buffer_len + self.customization.len ..][0..self.custom_len_enc.len], self.custom_len_enc.slice());

 // Generate CV for final leaf and absorb it
 var cv_buffer: [64]u8 = undefined; // Max CV size
 const cv_slice = MultiSliceView.init(final_leaf_buffer[0..remaining_with_custom_len], &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);
 // Absorb padding (8 bytes: 0x03 followed by 7 zeros)
 const padding = [_]u8{ 0x03, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 };
 self.final_state.?.update(&padding);

 // Process remaining data as leaves
 leaf_start = first_chunk_len;
 }

 // Process all remaining data as leaves (starting from leaf_start)
 var offset = leaf_start;
 while (offset < remaining_len) {
 const leaf_end = @min(offset + chunk_size, remaining_len);
 const leaf_size = leaf_end - offset;

 var cv_buffer: [64]u8 = undefined;
 if (remaining_view.tryGetSlice(offset, leaf_end)) |leaf_data| {
 // Data is contiguous, use it directly
 const cv_slice = MultiSliceView.init(leaf_data, &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);
 } else {
 // Data spans boundaries, copy to buffer
 var leaf_buf: [chunk_size]u8 = undefined;
 remaining_view.copyRange(offset, leaf_end, leaf_buf[0..leaf_size]);
 const cv_slice = MultiSliceView.init(leaf_buf[0..leaf_size], &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);
 }
 self.final_state.?.update(cv_buffer[0..cv_size]);
 final_leaves += 1;
 offset = leaf_end;
 }

 // Absorb right_encode(num_leaves) and terminator
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
crypto.kt128: when using incremental hashing, use SIMD when possible#25783

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

jedisct1
merged 1 commit into

from

Nov 2, 2025
 Merged


crypto.kt128: when using incremental hashing, use SIMD when possible
#25783
Show file tree
Hide file tree
 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


1 change: 1 addition & 0 deletions
lib/std/crypto/benchmark.zig

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -30,6 +30,7 @@ const hashes = [_]Crypto{
 Crypto{ .ty = crypto.hash.sha3.Shake256, .name = "shake-256" },
 Crypto{ .ty = crypto.hash.sha3.TurboShake128(null), .name = "turboshake-128" },
 Crypto{ .ty = crypto.hash.sha3.TurboShake256(null), .name = "turboshake-256" },
 Crypto{ .ty = crypto.hash.sha3.KT128, .name = "kt128" },
 Crypto{ .ty = crypto.hash.blake2.Blake2s256, .name = "blake2s" },
 Crypto{ .ty = crypto.hash.blake2.Blake2b512, .name = "blake2b" },
 Crypto{ .ty = crypto.hash.Blake3, .name = "blake3" },
Expand Down

136 changes: 113 additions & 23 deletions
lib/std/crypto/kangarootwelve.zig

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -848,6 +848,10 @@ fn KTHash(
 final_state: ?StateType, // Running TurboSHAKE state for final node
 num_leaves: usize, // Count of leaves processed (after first chunk)

 // SIMD chunk batching
 pending_chunks: [8 * chunk_size]u8 align(cache_line_size), // Buffer for up to 8 chunks
 pending_count: usize, // Number of complete chunks in pending_chunks

 /// Initialize a KangarooTwelve hashing context.
 /// The customization string is optional and used for domain separation.
 pub fn init(options: Options) Self {
Expand All@@ -861,9 +865,48 @@ fn KTHash(
 .first_chunk = null,
 .final_state = null,
 .num_leaves = 0,
 .pending_chunks = undefined,
 .pending_count = 0,
 };
 }

 /// Flush all pending chunks using SIMD when possible
 fn flushPendingChunks(self: *Self) void {
 const cv_size = Variant.cv_size;

 // Process all pending chunks using the largest SIMD batch sizes possible
 while (self.pending_count > 0) {
 // Try SIMD batches in decreasing size order
 inline for ([_]usize{ 8, 4, 2 }) |batch_size| {
 if (optimal_vector_len >= batch_size and self.pending_count >= batch_size) {
 var leaf_cvs: [batch_size * cv_size]u8 align(cache_line_size) = undefined;
 processLeaves(Variant, batch_size, self.pending_chunks[0 .. batch_size * chunk_size], &leaf_cvs);
 self.final_state.?.update(&leaf_cvs);
 self.num_leaves += batch_size;
 self.pending_count -= batch_size;

 // Shift remaining chunks to the front
 if (self.pending_count > 0) {
 const remaining_bytes = self.pending_count * chunk_size;
 @memcpy(self.pending_chunks[0..remaining_bytes], self.pending_chunks[batch_size * chunk_size ..][0..remaining_bytes]);
 }
 break; // Continue outer loop to try next batch
 }
 }

 // If no SIMD batch was possible, process one chunk with scalar code
 if (self.pending_count > 0 and self.pending_count < 2) {
 var cv_buffer: [64]u8 = undefined;
 const cv_slice = MultiSliceView.init(self.pending_chunks[0..chunk_size], &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);
 self.final_state.?.update(cv_buffer[0..cv_size]);
 self.num_leaves += 1;
 self.pending_count -= 1;
 break; // No more chunks to process
 }
 }
 }

 /// Absorb data into the hash state.
 /// Can be called multiple times to incrementally add data.
 pub fn update(self: *Self, data: []const u8) void {
Expand DownExpand Up@@ -895,15 +938,21 @@ fn KTHash(
 const padding = [_]u8{ 0x03, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 };
 self.final_state.?.update(&padding);
 } else {
 // Subsequent chunks - process as leaf and absorb CV
 const cv_size = Variant.cv_size;
 var cv_buffer: [64]u8 = undefined; // Max CV size
 const cv_slice = MultiSliceView.init(&self.buffer, &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);

 // Absorb CV into final state immediately
 self.final_state.?.update(cv_buffer[0..cv_size]);
 self.num_leaves += 1;
 // Add chunk to pending buffer for SIMD batch processing
 @memcpy(self.pending_chunks[self.pending_count * chunk_size ..][0..chunk_size], &self.buffer);
 self.pending_count += 1;

 // Flush when we have enough chunks for optimal SIMD batch
 // Determine best batch size for this architecture
 const optimal_batch_size = comptime blk: {
 if (optimal_vector_len >= 8) break :blk 8;
 if (optimal_vector_len >= 4) break :blk 4;
 if (optimal_vector_len >= 2) break :blk 2;
 break :blk 1;
 };
 if (self.pending_count >= optimal_batch_size) {
 self.flushPendingChunks();
 }
 }
 self.buffer_len = 0;
 }
Expand DownExpand Up@@ -931,24 +980,65 @@ fn KTHash(
 return;
 }

 // Tree mode: we've already absorbed first_chunk + padding + intermediate CVs
 // Now handle remaining buffer data
 const remaining_with_custom_len = self.buffer_len + self.customization.len + self.custom_len_enc.len;
 // Flush any pending chunks with SIMD
 self.flushPendingChunks();

 // Build view over remaining data (buffer + customization + encoding)
 const remaining_view = MultiSliceView.init(
 self.buffer[0..self.buffer_len],
 self.customization,
 self.custom_len_enc.slice(),
 );
 const remaining_len = remaining_view.totalLen();

 var final_leaves = self.num_leaves;
 var leaf_start: usize = 0;

 // Tree mode: initialize if not already done (lazy initialization)
 if (self.final_state == null and remaining_len > 0) {
 self.final_state = StateType.init(.{});

 // Absorb first chunk (up to chunk_size bytes from remaining data)
 const first_chunk_len = @min(chunk_size, remaining_len);
 if (remaining_view.tryGetSlice(0, first_chunk_len)) |first_chunk| {
 // Data is contiguous, use it directly
 self.final_state.?.update(first_chunk);
 } else {
 // Data spans boundaries, copy to buffer
 var first_chunk_buf: [chunk_size]u8 = undefined;
 remaining_view.copyRange(0, first_chunk_len, first_chunk_buf[0..first_chunk_len]);
 self.final_state.?.update(first_chunk_buf[0..first_chunk_len]);
 }

 if (remaining_with_custom_len > 0) {
 // Build final leaf data with customization
 var final_leaf_buffer: [chunk_size + 256]u8 = undefined; // Extra space for customization
 @memcpy(final_leaf_buffer[0..self.buffer_len], self.buffer[0..self.buffer_len]);
 @memcpy(final_leaf_buffer[self.buffer_len..][0..self.customization.len], self.customization);
 @memcpy(final_leaf_buffer[self.buffer_len + self.customization.len ..][0..self.custom_len_enc.len], self.custom_len_enc.slice());

 // Generate CV for final leaf and absorb it
 var cv_buffer: [64]u8 = undefined; // Max CV size
 const cv_slice = MultiSliceView.init(final_leaf_buffer[0..remaining_with_custom_len], &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);
 // Absorb padding (8 bytes: 0x03 followed by 7 zeros)
 const padding = [_]u8{ 0x03, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 };
 self.final_state.?.update(&padding);

 // Process remaining data as leaves
 leaf_start = first_chunk_len;
 }

 // Process all remaining data as leaves (starting from leaf_start)
 var offset = leaf_start;
 while (offset < remaining_len) {
 const leaf_end = @min(offset + chunk_size, remaining_len);
 const leaf_size = leaf_end - offset;

 var cv_buffer: [64]u8 = undefined;
 if (remaining_view.tryGetSlice(offset, leaf_end)) |leaf_data| {
 // Data is contiguous, use it directly
 const cv_slice = MultiSliceView.init(leaf_data, &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);
 } else {
 // Data spans boundaries, copy to buffer
 var leaf_buf: [chunk_size]u8 = undefined;
 remaining_view.copyRange(offset, leaf_end, leaf_buf[0..leaf_size]);
 const cv_slice = MultiSliceView.init(leaf_buf[0..leaf_size], &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);
 }
 self.final_state.?.update(cv_buffer[0..cv_size]);
 final_leaves += 1;
 offset = leaf_end;
 }

 // Absorb right_encode(num_leaves) and terminator
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
crypto.kt128: when using incremental hashing, use SIMD when possible#25783

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

jedisct1
merged 1 commit into

from

Nov 2, 2025
 Merged


crypto.kt128: when using incremental hashing, use SIMD when possible
#25783
Show file tree
Hide file tree
 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


1 change: 1 addition & 0 deletions
lib/std/crypto/benchmark.zig

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -30,6 +30,7 @@ const hashes = [_]Crypto{
 Crypto{ .ty = crypto.hash.sha3.Shake256, .name = "shake-256" },
 Crypto{ .ty = crypto.hash.sha3.TurboShake128(null), .name = "turboshake-128" },
 Crypto{ .ty = crypto.hash.sha3.TurboShake256(null), .name = "turboshake-256" },
 Crypto{ .ty = crypto.hash.sha3.KT128, .name = "kt128" },
 Crypto{ .ty = crypto.hash.blake2.Blake2s256, .name = "blake2s" },
 Crypto{ .ty = crypto.hash.blake2.Blake2b512, .name = "blake2b" },
 Crypto{ .ty = crypto.hash.Blake3, .name = "blake3" },
Expand Down

136 changes: 113 additions & 23 deletions
lib/std/crypto/kangarootwelve.zig

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -848,6 +848,10 @@ fn KTHash(
 final_state: ?StateType, // Running TurboSHAKE state for final node
 num_leaves: usize, // Count of leaves processed (after first chunk)

 // SIMD chunk batching
 pending_chunks: [8 * chunk_size]u8 align(cache_line_size), // Buffer for up to 8 chunks
 pending_count: usize, // Number of complete chunks in pending_chunks

 /// Initialize a KangarooTwelve hashing context.
 /// The customization string is optional and used for domain separation.
 pub fn init(options: Options) Self {
Expand All@@ -861,9 +865,48 @@ fn KTHash(
 .first_chunk = null,
 .final_state = null,
 .num_leaves = 0,
 .pending_chunks = undefined,
 .pending_count = 0,
 };
 }

 /// Flush all pending chunks using SIMD when possible
 fn flushPendingChunks(self: *Self) void {
 const cv_size = Variant.cv_size;

 // Process all pending chunks using the largest SIMD batch sizes possible
 while (self.pending_count > 0) {
 // Try SIMD batches in decreasing size order
 inline for ([_]usize{ 8, 4, 2 }) |batch_size| {
 if (optimal_vector_len >= batch_size and self.pending_count >= batch_size) {
 var leaf_cvs: [batch_size * cv_size]u8 align(cache_line_size) = undefined;
 processLeaves(Variant, batch_size, self.pending_chunks[0 .. batch_size * chunk_size], &leaf_cvs);
 self.final_state.?.update(&leaf_cvs);
 self.num_leaves += batch_size;
 self.pending_count -= batch_size;

 // Shift remaining chunks to the front
 if (self.pending_count > 0) {
 const remaining_bytes = self.pending_count * chunk_size;
 @memcpy(self.pending_chunks[0..remaining_bytes], self.pending_chunks[batch_size * chunk_size ..][0..remaining_bytes]);
 }
 break; // Continue outer loop to try next batch
 }
 }

 // If no SIMD batch was possible, process one chunk with scalar code
 if (self.pending_count > 0 and self.pending_count < 2) {
 var cv_buffer: [64]u8 = undefined;
 const cv_slice = MultiSliceView.init(self.pending_chunks[0..chunk_size], &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);
 self.final_state.?.update(cv_buffer[0..cv_size]);
 self.num_leaves += 1;
 self.pending_count -= 1;
 break; // No more chunks to process
 }
 }
 }

 /// Absorb data into the hash state.
 /// Can be called multiple times to incrementally add data.
 pub fn update(self: *Self, data: []const u8) void {
Expand DownExpand Up@@ -895,15 +938,21 @@ fn KTHash(
 const padding = [_]u8{ 0x03, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 };
 self.final_state.?.update(&padding);
 } else {
 // Subsequent chunks - process as leaf and absorb CV
 const cv_size = Variant.cv_size;
 var cv_buffer: [64]u8 = undefined; // Max CV size
 const cv_slice = MultiSliceView.init(&self.buffer, &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);

 // Absorb CV into final state immediately
 self.final_state.?.update(cv_buffer[0..cv_size]);
 self.num_leaves += 1;
 // Add chunk to pending buffer for SIMD batch processing
 @memcpy(self.pending_chunks[self.pending_count * chunk_size ..][0..chunk_size], &self.buffer);
 self.pending_count += 1;

 // Flush when we have enough chunks for optimal SIMD batch
 // Determine best batch size for this architecture
 const optimal_batch_size = comptime blk: {
 if (optimal_vector_len >= 8) break :blk 8;
 if (optimal_vector_len >= 4) break :blk 4;
 if (optimal_vector_len >= 2) break :blk 2;
 break :blk 1;
 };
 if (self.pending_count >= optimal_batch_size) {
 self.flushPendingChunks();
 }
 }
 self.buffer_len = 0;
 }
Expand DownExpand Up@@ -931,24 +980,65 @@ fn KTHash(
 return;
 }

 // Tree mode: we've already absorbed first_chunk + padding + intermediate CVs
 // Now handle remaining buffer data
 const remaining_with_custom_len = self.buffer_len + self.customization.len + self.custom_len_enc.len;
 // Flush any pending chunks with SIMD
 self.flushPendingChunks();

 // Build view over remaining data (buffer + customization + encoding)
 const remaining_view = MultiSliceView.init(
 self.buffer[0..self.buffer_len],
 self.customization,
 self.custom_len_enc.slice(),
 );
 const remaining_len = remaining_view.totalLen();

 var final_leaves = self.num_leaves;
 var leaf_start: usize = 0;

 // Tree mode: initialize if not already done (lazy initialization)
 if (self.final_state == null and remaining_len > 0) {
 self.final_state = StateType.init(.{});

 // Absorb first chunk (up to chunk_size bytes from remaining data)
 const first_chunk_len = @min(chunk_size, remaining_len);
 if (remaining_view.tryGetSlice(0, first_chunk_len)) |first_chunk| {
 // Data is contiguous, use it directly
 self.final_state.?.update(first_chunk);
 } else {
 // Data spans boundaries, copy to buffer
 var first_chunk_buf: [chunk_size]u8 = undefined;
 remaining_view.copyRange(0, first_chunk_len, first_chunk_buf[0..first_chunk_len]);
 self.final_state.?.update(first_chunk_buf[0..first_chunk_len]);
 }

 if (remaining_with_custom_len > 0) {
 // Build final leaf data with customization
 var final_leaf_buffer: [chunk_size + 256]u8 = undefined; // Extra space for customization
 @memcpy(final_leaf_buffer[0..self.buffer_len], self.buffer[0..self.buffer_len]);
 @memcpy(final_leaf_buffer[self.buffer_len..][0..self.customization.len], self.customization);
 @memcpy(final_leaf_buffer[self.buffer_len + self.customization.len ..][0..self.custom_len_enc.len], self.custom_len_enc.slice());

 // Generate CV for final leaf and absorb it
 var cv_buffer: [64]u8 = undefined; // Max CV size
 const cv_slice = MultiSliceView.init(final_leaf_buffer[0..remaining_with_custom_len], &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);
 // Absorb padding (8 bytes: 0x03 followed by 7 zeros)
 const padding = [_]u8{ 0x03, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 };
 self.final_state.?.update(&padding);

 // Process remaining data as leaves
 leaf_start = first_chunk_len;
 }

 // Process all remaining data as leaves (starting from leaf_start)
 var offset = leaf_start;
 while (offset < remaining_len) {
 const leaf_end = @min(offset + chunk_size, remaining_len);
 const leaf_size = leaf_end - offset;

 var cv_buffer: [64]u8 = undefined;
 if (remaining_view.tryGetSlice(offset, leaf_end)) |leaf_data| {
 // Data is contiguous, use it directly
 const cv_slice = MultiSliceView.init(leaf_data, &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);
 } else {
 // Data spans boundaries, copy to buffer
 var leaf_buf: [chunk_size]u8 = undefined;
 remaining_view.copyRange(offset, leaf_end, leaf_buf[0..leaf_size]);
 const cv_slice = MultiSliceView.init(leaf_buf[0..leaf_size], &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);
 }
 self.final_state.?.update(cv_buffer[0..cv_size]);
 final_leaves += 1;
 offset = leaf_end;
 }

 // Absorb right_encode(num_leaves) and terminator
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
crypto.kt128: when using incremental hashing, use SIMD when possible#25783

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

jedisct1
merged 1 commit into

from

Nov 2, 2025
 Merged


crypto.kt128: when using incremental hashing, use SIMD when possible
#25783
Show file tree
Hide file tree
 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


1 change: 1 addition & 0 deletions
lib/std/crypto/benchmark.zig

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -30,6 +30,7 @@ const hashes = [_]Crypto{
 Crypto{ .ty = crypto.hash.sha3.Shake256, .name = "shake-256" },
 Crypto{ .ty = crypto.hash.sha3.TurboShake128(null), .name = "turboshake-128" },
 Crypto{ .ty = crypto.hash.sha3.TurboShake256(null), .name = "turboshake-256" },
 Crypto{ .ty = crypto.hash.sha3.KT128, .name = "kt128" },
 Crypto{ .ty = crypto.hash.blake2.Blake2s256, .name = "blake2s" },
 Crypto{ .ty = crypto.hash.blake2.Blake2b512, .name = "blake2b" },
 Crypto{ .ty = crypto.hash.Blake3, .name = "blake3" },
Expand Down

136 changes: 113 additions & 23 deletions
lib/std/crypto/kangarootwelve.zig

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -848,6 +848,10 @@ fn KTHash(
 final_state: ?StateType, // Running TurboSHAKE state for final node
 num_leaves: usize, // Count of leaves processed (after first chunk)

 // SIMD chunk batching
 pending_chunks: [8 * chunk_size]u8 align(cache_line_size), // Buffer for up to 8 chunks
 pending_count: usize, // Number of complete chunks in pending_chunks

 /// Initialize a KangarooTwelve hashing context.
 /// The customization string is optional and used for domain separation.
 pub fn init(options: Options) Self {
Expand All@@ -861,9 +865,48 @@ fn KTHash(
 .first_chunk = null,
 .final_state = null,
 .num_leaves = 0,
 .pending_chunks = undefined,
 .pending_count = 0,
 };
 }

 /// Flush all pending chunks using SIMD when possible
 fn flushPendingChunks(self: *Self) void {
 const cv_size = Variant.cv_size;

 // Process all pending chunks using the largest SIMD batch sizes possible
 while (self.pending_count > 0) {
 // Try SIMD batches in decreasing size order
 inline for ([_]usize{ 8, 4, 2 }) |batch_size| {
 if (optimal_vector_len >= batch_size and self.pending_count >= batch_size) {
 var leaf_cvs: [batch_size * cv_size]u8 align(cache_line_size) = undefined;
 processLeaves(Variant, batch_size, self.pending_chunks[0 .. batch_size * chunk_size], &leaf_cvs);
 self.final_state.?.update(&leaf_cvs);
 self.num_leaves += batch_size;
 self.pending_count -= batch_size;

 // Shift remaining chunks to the front
 if (self.pending_count > 0) {
 const remaining_bytes = self.pending_count * chunk_size;
 @memcpy(self.pending_chunks[0..remaining_bytes], self.pending_chunks[batch_size * chunk_size ..][0..remaining_bytes]);
 }
 break; // Continue outer loop to try next batch
 }
 }

 // If no SIMD batch was possible, process one chunk with scalar code
 if (self.pending_count > 0 and self.pending_count < 2) {
 var cv_buffer: [64]u8 = undefined;
 const cv_slice = MultiSliceView.init(self.pending_chunks[0..chunk_size], &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);
 self.final_state.?.update(cv_buffer[0..cv_size]);
 self.num_leaves += 1;
 self.pending_count -= 1;
 break; // No more chunks to process
 }
 }
 }

 /// Absorb data into the hash state.
 /// Can be called multiple times to incrementally add data.
 pub fn update(self: *Self, data: []const u8) void {
Expand DownExpand Up@@ -895,15 +938,21 @@ fn KTHash(
 const padding = [_]u8{ 0x03, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 };
 self.final_state.?.update(&padding);
 } else {
 // Subsequent chunks - process as leaf and absorb CV
 const cv_size = Variant.cv_size;
 var cv_buffer: [64]u8 = undefined; // Max CV size
 const cv_slice = MultiSliceView.init(&self.buffer, &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);

 // Absorb CV into final state immediately
 self.final_state.?.update(cv_buffer[0..cv_size]);
 self.num_leaves += 1;
 // Add chunk to pending buffer for SIMD batch processing
 @memcpy(self.pending_chunks[self.pending_count * chunk_size ..][0..chunk_size], &self.buffer);
 self.pending_count += 1;

 // Flush when we have enough chunks for optimal SIMD batch
 // Determine best batch size for this architecture
 const optimal_batch_size = comptime blk: {
 if (optimal_vector_len >= 8) break :blk 8;
 if (optimal_vector_len >= 4) break :blk 4;
 if (optimal_vector_len >= 2) break :blk 2;
 break :blk 1;
 };
 if (self.pending_count >= optimal_batch_size) {
 self.flushPendingChunks();
 }
 }
 self.buffer_len = 0;
 }
Expand DownExpand Up@@ -931,24 +980,65 @@ fn KTHash(
 return;
 }

 // Tree mode: we've already absorbed first_chunk + padding + intermediate CVs
 // Now handle remaining buffer data
 const remaining_with_custom_len = self.buffer_len + self.customization.len + self.custom_len_enc.len;
 // Flush any pending chunks with SIMD
 self.flushPendingChunks();

 // Build view over remaining data (buffer + customization + encoding)
 const remaining_view = MultiSliceView.init(
 self.buffer[0..self.buffer_len],
 self.customization,
 self.custom_len_enc.slice(),
 );
 const remaining_len = remaining_view.totalLen();

 var final_leaves = self.num_leaves;
 var leaf_start: usize = 0;

 // Tree mode: initialize if not already done (lazy initialization)
 if (self.final_state == null and remaining_len > 0) {
 self.final_state = StateType.init(.{});

 // Absorb first chunk (up to chunk_size bytes from remaining data)
 const first_chunk_len = @min(chunk_size, remaining_len);
 if (remaining_view.tryGetSlice(0, first_chunk_len)) |first_chunk| {
 // Data is contiguous, use it directly
 self.final_state.?.update(first_chunk);
 } else {
 // Data spans boundaries, copy to buffer
 var first_chunk_buf: [chunk_size]u8 = undefined;
 remaining_view.copyRange(0, first_chunk_len, first_chunk_buf[0..first_chunk_len]);
 self.final_state.?.update(first_chunk_buf[0..first_chunk_len]);
 }

 if (remaining_with_custom_len > 0) {
 // Build final leaf data with customization
 var final_leaf_buffer: [chunk_size + 256]u8 = undefined; // Extra space for customization
 @memcpy(final_leaf_buffer[0..self.buffer_len], self.buffer[0..self.buffer_len]);
 @memcpy(final_leaf_buffer[self.buffer_len..][0..self.customization.len], self.customization);
 @memcpy(final_leaf_buffer[self.buffer_len + self.customization.len ..][0..self.custom_len_enc.len], self.custom_len_enc.slice());

 // Generate CV for final leaf and absorb it
 var cv_buffer: [64]u8 = undefined; // Max CV size
 const cv_slice = MultiSliceView.init(final_leaf_buffer[0..remaining_with_custom_len], &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);
 // Absorb padding (8 bytes: 0x03 followed by 7 zeros)
 const padding = [_]u8{ 0x03, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 };
 self.final_state.?.update(&padding);

 // Process remaining data as leaves
 leaf_start = first_chunk_len;
 }

 // Process all remaining data as leaves (starting from leaf_start)
 var offset = leaf_start;
 while (offset < remaining_len) {
 const leaf_end = @min(offset + chunk_size, remaining_len);
 const leaf_size = leaf_end - offset;

 var cv_buffer: [64]u8 = undefined;
 if (remaining_view.tryGetSlice(offset, leaf_end)) |leaf_data| {
 // Data is contiguous, use it directly
 const cv_slice = MultiSliceView.init(leaf_data, &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);
 } else {
 // Data spans boundaries, copy to buffer
 var leaf_buf: [chunk_size]u8 = undefined;
 remaining_view.copyRange(offset, leaf_end, leaf_buf[0..leaf_size]);
 const cv_slice = MultiSliceView.init(leaf_buf[0..leaf_size], &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);
 }
 self.final_state.?.update(cv_buffer[0..cv_size]);
 final_leaves += 1;
 offset = leaf_end;
 }

 // Absorb right_encode(num_leaves) and terminator
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
crypto.kt128: when using incremental hashing, use SIMD when possible#25783

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

jedisct1
merged 1 commit into

from

Nov 2, 2025
 Merged


crypto.kt128: when using incremental hashing, use SIMD when possible
#25783
Show file tree
Hide file tree
 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


1 change: 1 addition & 0 deletions
lib/std/crypto/benchmark.zig

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -30,6 +30,7 @@ const hashes = [_]Crypto{
 Crypto{ .ty = crypto.hash.sha3.Shake256, .name = "shake-256" },
 Crypto{ .ty = crypto.hash.sha3.TurboShake128(null), .name = "turboshake-128" },
 Crypto{ .ty = crypto.hash.sha3.TurboShake256(null), .name = "turboshake-256" },
 Crypto{ .ty = crypto.hash.sha3.KT128, .name = "kt128" },
 Crypto{ .ty = crypto.hash.blake2.Blake2s256, .name = "blake2s" },
 Crypto{ .ty = crypto.hash.blake2.Blake2b512, .name = "blake2b" },
 Crypto{ .ty = crypto.hash.Blake3, .name = "blake3" },
Expand Down

136 changes: 113 additions & 23 deletions
lib/std/crypto/kangarootwelve.zig

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -848,6 +848,10 @@ fn KTHash(
 final_state: ?StateType, // Running TurboSHAKE state for final node
 num_leaves: usize, // Count of leaves processed (after first chunk)

 // SIMD chunk batching
 pending_chunks: [8 * chunk_size]u8 align(cache_line_size), // Buffer for up to 8 chunks
 pending_count: usize, // Number of complete chunks in pending_chunks

 /// Initialize a KangarooTwelve hashing context.
 /// The customization string is optional and used for domain separation.
 pub fn init(options: Options) Self {
Expand All@@ -861,9 +865,48 @@ fn KTHash(
 .first_chunk = null,
 .final_state = null,
 .num_leaves = 0,
 .pending_chunks = undefined,
 .pending_count = 0,
 };
 }

 /// Flush all pending chunks using SIMD when possible
 fn flushPendingChunks(self: *Self) void {
 const cv_size = Variant.cv_size;

 // Process all pending chunks using the largest SIMD batch sizes possible
 while (self.pending_count > 0) {
 // Try SIMD batches in decreasing size order
 inline for ([_]usize{ 8, 4, 2 }) |batch_size| {
 if (optimal_vector_len >= batch_size and self.pending_count >= batch_size) {
 var leaf_cvs: [batch_size * cv_size]u8 align(cache_line_size) = undefined;
 processLeaves(Variant, batch_size, self.pending_chunks[0 .. batch_size * chunk_size], &leaf_cvs);
 self.final_state.?.update(&leaf_cvs);
 self.num_leaves += batch_size;
 self.pending_count -= batch_size;

 // Shift remaining chunks to the front
 if (self.pending_count > 0) {
 const remaining_bytes = self.pending_count * chunk_size;
 @memcpy(self.pending_chunks[0..remaining_bytes], self.pending_chunks[batch_size * chunk_size ..][0..remaining_bytes]);
 }
 break; // Continue outer loop to try next batch
 }
 }

 // If no SIMD batch was possible, process one chunk with scalar code
 if (self.pending_count > 0 and self.pending_count < 2) {
 var cv_buffer: [64]u8 = undefined;
 const cv_slice = MultiSliceView.init(self.pending_chunks[0..chunk_size], &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);
 self.final_state.?.update(cv_buffer[0..cv_size]);
 self.num_leaves += 1;
 self.pending_count -= 1;
 break; // No more chunks to process
 }
 }
 }

 /// Absorb data into the hash state.
 /// Can be called multiple times to incrementally add data.
 pub fn update(self: *Self, data: []const u8) void {
Expand DownExpand Up@@ -895,15 +938,21 @@ fn KTHash(
 const padding = [_]u8{ 0x03, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 };
 self.final_state.?.update(&padding);
 } else {
 // Subsequent chunks - process as leaf and absorb CV
 const cv_size = Variant.cv_size;
 var cv_buffer: [64]u8 = undefined; // Max CV size
 const cv_slice = MultiSliceView.init(&self.buffer, &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);

 // Absorb CV into final state immediately
 self.final_state.?.update(cv_buffer[0..cv_size]);
 self.num_leaves += 1;
 // Add chunk to pending buffer for SIMD batch processing
 @memcpy(self.pending_chunks[self.pending_count * chunk_size ..][0..chunk_size], &self.buffer);
 self.pending_count += 1;

 // Flush when we have enough chunks for optimal SIMD batch
 // Determine best batch size for this architecture
 const optimal_batch_size = comptime blk: {
 if (optimal_vector_len >= 8) break :blk 8;
 if (optimal_vector_len >= 4) break :blk 4;
 if (optimal_vector_len >= 2) break :blk 2;
 break :blk 1;
 };
 if (self.pending_count >= optimal_batch_size) {
 self.flushPendingChunks();
 }
 }
 self.buffer_len = 0;
 }
Expand DownExpand Up@@ -931,24 +980,65 @@ fn KTHash(
 return;
 }

 // Tree mode: we've already absorbed first_chunk + padding + intermediate CVs
 // Now handle remaining buffer data
 const remaining_with_custom_len = self.buffer_len + self.customization.len + self.custom_len_enc.len;
 // Flush any pending chunks with SIMD
 self.flushPendingChunks();

 // Build view over remaining data (buffer + customization + encoding)
 const remaining_view = MultiSliceView.init(
 self.buffer[0..self.buffer_len],
 self.customization,
 self.custom_len_enc.slice(),
 );
 const remaining_len = remaining_view.totalLen();

 var final_leaves = self.num_leaves;
 var leaf_start: usize = 0;

 // Tree mode: initialize if not already done (lazy initialization)
 if (self.final_state == null and remaining_len > 0) {
 self.final_state = StateType.init(.{});

 // Absorb first chunk (up to chunk_size bytes from remaining data)
 const first_chunk_len = @min(chunk_size, remaining_len);
 if (remaining_view.tryGetSlice(0, first_chunk_len)) |first_chunk| {
 // Data is contiguous, use it directly
 self.final_state.?.update(first_chunk);
 } else {
 // Data spans boundaries, copy to buffer
 var first_chunk_buf: [chunk_size]u8 = undefined;
 remaining_view.copyRange(0, first_chunk_len, first_chunk_buf[0..first_chunk_len]);
 self.final_state.?.update(first_chunk_buf[0..first_chunk_len]);
 }

 if (remaining_with_custom_len > 0) {
 // Build final leaf data with customization
 var final_leaf_buffer: [chunk_size + 256]u8 = undefined; // Extra space for customization
 @memcpy(final_leaf_buffer[0..self.buffer_len], self.buffer[0..self.buffer_len]);
 @memcpy(final_leaf_buffer[self.buffer_len..][0..self.customization.len], self.customization);
 @memcpy(final_leaf_buffer[self.buffer_len + self.customization.len ..][0..self.custom_len_enc.len], self.custom_len_enc.slice());

 // Generate CV for final leaf and absorb it
 var cv_buffer: [64]u8 = undefined; // Max CV size
 const cv_slice = MultiSliceView.init(final_leaf_buffer[0..remaining_with_custom_len], &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);
 // Absorb padding (8 bytes: 0x03 followed by 7 zeros)
 const padding = [_]u8{ 0x03, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 };
 self.final_state.?.update(&padding);

 // Process remaining data as leaves
 leaf_start = first_chunk_len;
 }

 // Process all remaining data as leaves (starting from leaf_start)
 var offset = leaf_start;
 while (offset < remaining_len) {
 const leaf_end = @min(offset + chunk_size, remaining_len);
 const leaf_size = leaf_end - offset;

 var cv_buffer: [64]u8 = undefined;
 if (remaining_view.tryGetSlice(offset, leaf_end)) |leaf_data| {
 // Data is contiguous, use it directly
 const cv_slice = MultiSliceView.init(leaf_data, &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);
 } else {
 // Data spans boundaries, copy to buffer
 var leaf_buf: [chunk_size]u8 = undefined;
 remaining_view.copyRange(offset, leaf_end, leaf_buf[0..leaf_size]);
 const cv_slice = MultiSliceView.init(leaf_buf[0..leaf_size], &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);
 }
 self.final_state.?.update(cv_buffer[0..cv_size]);
 final_leaves += 1;
 offset = leaf_end;
 }

 // Absorb right_encode(num_leaves) and terminator
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
crypto.kt128: when using incremental hashing, use SIMD when possible#25783

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

jedisct1
merged 1 commit into

from

Nov 2, 2025
 Merged


crypto.kt128: when using incremental hashing, use SIMD when possible
#25783
Show file tree
Hide file tree
 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


1 change: 1 addition & 0 deletions
lib/std/crypto/benchmark.zig

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -30,6 +30,7 @@ const hashes = [_]Crypto{
 Crypto{ .ty = crypto.hash.sha3.Shake256, .name = "shake-256" },
 Crypto{ .ty = crypto.hash.sha3.TurboShake128(null), .name = "turboshake-128" },
 Crypto{ .ty = crypto.hash.sha3.TurboShake256(null), .name = "turboshake-256" },
 Crypto{ .ty = crypto.hash.sha3.KT128, .name = "kt128" },
 Crypto{ .ty = crypto.hash.blake2.Blake2s256, .name = "blake2s" },
 Crypto{ .ty = crypto.hash.blake2.Blake2b512, .name = "blake2b" },
 Crypto{ .ty = crypto.hash.Blake3, .name = "blake3" },
Expand Down

136 changes: 113 additions & 23 deletions
lib/std/crypto/kangarootwelve.zig

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -848,6 +848,10 @@ fn KTHash(
 final_state: ?StateType, // Running TurboSHAKE state for final node
 num_leaves: usize, // Count of leaves processed (after first chunk)

 // SIMD chunk batching
 pending_chunks: [8 * chunk_size]u8 align(cache_line_size), // Buffer for up to 8 chunks
 pending_count: usize, // Number of complete chunks in pending_chunks

 /// Initialize a KangarooTwelve hashing context.
 /// The customization string is optional and used for domain separation.
 pub fn init(options: Options) Self {
Expand All@@ -861,9 +865,48 @@ fn KTHash(
 .first_chunk = null,
 .final_state = null,
 .num_leaves = 0,
 .pending_chunks = undefined,
 .pending_count = 0,
 };
 }

 /// Flush all pending chunks using SIMD when possible
 fn flushPendingChunks(self: *Self) void {
 const cv_size = Variant.cv_size;

 // Process all pending chunks using the largest SIMD batch sizes possible
 while (self.pending_count > 0) {
 // Try SIMD batches in decreasing size order
 inline for ([_]usize{ 8, 4, 2 }) |batch_size| {
 if (optimal_vector_len >= batch_size and self.pending_count >= batch_size) {
 var leaf_cvs: [batch_size * cv_size]u8 align(cache_line_size) = undefined;
 processLeaves(Variant, batch_size, self.pending_chunks[0 .. batch_size * chunk_size], &leaf_cvs);
 self.final_state.?.update(&leaf_cvs);
 self.num_leaves += batch_size;
 self.pending_count -= batch_size;

 // Shift remaining chunks to the front
 if (self.pending_count > 0) {
 const remaining_bytes = self.pending_count * chunk_size;
 @memcpy(self.pending_chunks[0..remaining_bytes], self.pending_chunks[batch_size * chunk_size ..][0..remaining_bytes]);
 }
 break; // Continue outer loop to try next batch
 }
 }

 // If no SIMD batch was possible, process one chunk with scalar code
 if (self.pending_count > 0 and self.pending_count < 2) {
 var cv_buffer: [64]u8 = undefined;
 const cv_slice = MultiSliceView.init(self.pending_chunks[0..chunk_size], &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);
 self.final_state.?.update(cv_buffer[0..cv_size]);
 self.num_leaves += 1;
 self.pending_count -= 1;
 break; // No more chunks to process
 }
 }
 }

 /// Absorb data into the hash state.
 /// Can be called multiple times to incrementally add data.
 pub fn update(self: *Self, data: []const u8) void {
Expand DownExpand Up@@ -895,15 +938,21 @@ fn KTHash(
 const padding = [_]u8{ 0x03, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 };
 self.final_state.?.update(&padding);
 } else {
 // Subsequent chunks - process as leaf and absorb CV
 const cv_size = Variant.cv_size;
 var cv_buffer: [64]u8 = undefined; // Max CV size
 const cv_slice = MultiSliceView.init(&self.buffer, &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);

 // Absorb CV into final state immediately
 self.final_state.?.update(cv_buffer[0..cv_size]);
 self.num_leaves += 1;
 // Add chunk to pending buffer for SIMD batch processing
 @memcpy(self.pending_chunks[self.pending_count * chunk_size ..][0..chunk_size], &self.buffer);
 self.pending_count += 1;

 // Flush when we have enough chunks for optimal SIMD batch
 // Determine best batch size for this architecture
 const optimal_batch_size = comptime blk: {
 if (optimal_vector_len >= 8) break :blk 8;
 if (optimal_vector_len >= 4) break :blk 4;
 if (optimal_vector_len >= 2) break :blk 2;
 break :blk 1;
 };
 if (self.pending_count >= optimal_batch_size) {
 self.flushPendingChunks();
 }
 }
 self.buffer_len = 0;
 }
Expand DownExpand Up@@ -931,24 +980,65 @@ fn KTHash(
 return;
 }

 // Tree mode: we've already absorbed first_chunk + padding + intermediate CVs
 // Now handle remaining buffer data
 const remaining_with_custom_len = self.buffer_len + self.customization.len + self.custom_len_enc.len;
 // Flush any pending chunks with SIMD
 self.flushPendingChunks();

 // Build view over remaining data (buffer + customization + encoding)
 const remaining_view = MultiSliceView.init(
 self.buffer[0..self.buffer_len],
 self.customization,
 self.custom_len_enc.slice(),
 );
 const remaining_len = remaining_view.totalLen();

 var final_leaves = self.num_leaves;
 var leaf_start: usize = 0;

 // Tree mode: initialize if not already done (lazy initialization)
 if (self.final_state == null and remaining_len > 0) {
 self.final_state = StateType.init(.{});

 // Absorb first chunk (up to chunk_size bytes from remaining data)
 const first_chunk_len = @min(chunk_size, remaining_len);
 if (remaining_view.tryGetSlice(0, first_chunk_len)) |first_chunk| {
 // Data is contiguous, use it directly
 self.final_state.?.update(first_chunk);
 } else {
 // Data spans boundaries, copy to buffer
 var first_chunk_buf: [chunk_size]u8 = undefined;
 remaining_view.copyRange(0, first_chunk_len, first_chunk_buf[0..first_chunk_len]);
 self.final_state.?.update(first_chunk_buf[0..first_chunk_len]);
 }

 if (remaining_with_custom_len > 0) {
 // Build final leaf data with customization
 var final_leaf_buffer: [chunk_size + 256]u8 = undefined; // Extra space for customization
 @memcpy(final_leaf_buffer[0..self.buffer_len], self.buffer[0..self.buffer_len]);
 @memcpy(final_leaf_buffer[self.buffer_len..][0..self.customization.len], self.customization);
 @memcpy(final_leaf_buffer[self.buffer_len + self.customization.len ..][0..self.custom_len_enc.len], self.custom_len_enc.slice());

 // Generate CV for final leaf and absorb it
 var cv_buffer: [64]u8 = undefined; // Max CV size
 const cv_slice = MultiSliceView.init(final_leaf_buffer[0..remaining_with_custom_len], &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);
 // Absorb padding (8 bytes: 0x03 followed by 7 zeros)
 const padding = [_]u8{ 0x03, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 };
 self.final_state.?.update(&padding);

 // Process remaining data as leaves
 leaf_start = first_chunk_len;
 }

 // Process all remaining data as leaves (starting from leaf_start)
 var offset = leaf_start;
 while (offset < remaining_len) {
 const leaf_end = @min(offset + chunk_size, remaining_len);
 const leaf_size = leaf_end - offset;

 var cv_buffer: [64]u8 = undefined;
 if (remaining_view.tryGetSlice(offset, leaf_end)) |leaf_data| {
 // Data is contiguous, use it directly
 const cv_slice = MultiSliceView.init(leaf_data, &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);
 } else {
 // Data spans boundaries, copy to buffer
 var leaf_buf: [chunk_size]u8 = undefined;
 remaining_view.copyRange(offset, leaf_end, leaf_buf[0..leaf_size]);
 const cv_slice = MultiSliceView.init(leaf_buf[0..leaf_size], &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);
 }
 self.final_state.?.update(cv_buffer[0..cv_size]);
 final_leaves += 1;
 offset = leaf_end;
 }

 // Absorb right_encode(num_leaves) and terminator
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
crypto.kt128: when using incremental hashing, use SIMD when possible#25783

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

jedisct1
merged 1 commit into

from

Nov 2, 2025
 Merged


crypto.kt128: when using incremental hashing, use SIMD when possible
#25783
Show file tree
Hide file tree
 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


1 change: 1 addition & 0 deletions
lib/std/crypto/benchmark.zig

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -30,6 +30,7 @@ const hashes = [_]Crypto{
 Crypto{ .ty = crypto.hash.sha3.Shake256, .name = "shake-256" },
 Crypto{ .ty = crypto.hash.sha3.TurboShake128(null), .name = "turboshake-128" },
 Crypto{ .ty = crypto.hash.sha3.TurboShake256(null), .name = "turboshake-256" },
 Crypto{ .ty = crypto.hash.sha3.KT128, .name = "kt128" },
 Crypto{ .ty = crypto.hash.blake2.Blake2s256, .name = "blake2s" },
 Crypto{ .ty = crypto.hash.blake2.Blake2b512, .name = "blake2b" },
 Crypto{ .ty = crypto.hash.Blake3, .name = "blake3" },
Expand Down

136 changes: 113 additions & 23 deletions
lib/std/crypto/kangarootwelve.zig

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -848,6 +848,10 @@ fn KTHash(
 final_state: ?StateType, // Running TurboSHAKE state for final node
 num_leaves: usize, // Count of leaves processed (after first chunk)

 // SIMD chunk batching
 pending_chunks: [8 * chunk_size]u8 align(cache_line_size), // Buffer for up to 8 chunks
 pending_count: usize, // Number of complete chunks in pending_chunks

 /// Initialize a KangarooTwelve hashing context.
 /// The customization string is optional and used for domain separation.
 pub fn init(options: Options) Self {
Expand All@@ -861,9 +865,48 @@ fn KTHash(
 .first_chunk = null,
 .final_state = null,
 .num_leaves = 0,
 .pending_chunks = undefined,
 .pending_count = 0,
 };
 }

 /// Flush all pending chunks using SIMD when possible
 fn flushPendingChunks(self: *Self) void {
 const cv_size = Variant.cv_size;

 // Process all pending chunks using the largest SIMD batch sizes possible
 while (self.pending_count > 0) {
 // Try SIMD batches in decreasing size order
 inline for ([_]usize{ 8, 4, 2 }) |batch_size| {
 if (optimal_vector_len >= batch_size and self.pending_count >= batch_size) {
 var leaf_cvs: [batch_size * cv_size]u8 align(cache_line_size) = undefined;
 processLeaves(Variant, batch_size, self.pending_chunks[0 .. batch_size * chunk_size], &leaf_cvs);
 self.final_state.?.update(&leaf_cvs);
 self.num_leaves += batch_size;
 self.pending_count -= batch_size;

 // Shift remaining chunks to the front
 if (self.pending_count > 0) {
 const remaining_bytes = self.pending_count * chunk_size;
 @memcpy(self.pending_chunks[0..remaining_bytes], self.pending_chunks[batch_size * chunk_size ..][0..remaining_bytes]);
 }
 break; // Continue outer loop to try next batch
 }
 }

 // If no SIMD batch was possible, process one chunk with scalar code
 if (self.pending_count > 0 and self.pending_count < 2) {
 var cv_buffer: [64]u8 = undefined;
 const cv_slice = MultiSliceView.init(self.pending_chunks[0..chunk_size], &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);
 self.final_state.?.update(cv_buffer[0..cv_size]);
 self.num_leaves += 1;
 self.pending_count -= 1;
 break; // No more chunks to process
 }
 }
 }

 /// Absorb data into the hash state.
 /// Can be called multiple times to incrementally add data.
 pub fn update(self: *Self, data: []const u8) void {
Expand DownExpand Up@@ -895,15 +938,21 @@ fn KTHash(
 const padding = [_]u8{ 0x03, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 };
 self.final_state.?.update(&padding);
 } else {
 // Subsequent chunks - process as leaf and absorb CV
 const cv_size = Variant.cv_size;
 var cv_buffer: [64]u8 = undefined; // Max CV size
 const cv_slice = MultiSliceView.init(&self.buffer, &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);

 // Absorb CV into final state immediately
 self.final_state.?.update(cv_buffer[0..cv_size]);
 self.num_leaves += 1;
 // Add chunk to pending buffer for SIMD batch processing
 @memcpy(self.pending_chunks[self.pending_count * chunk_size ..][0..chunk_size], &self.buffer);
 self.pending_count += 1;

 // Flush when we have enough chunks for optimal SIMD batch
 // Determine best batch size for this architecture
 const optimal_batch_size = comptime blk: {
 if (optimal_vector_len >= 8) break :blk 8;
 if (optimal_vector_len >= 4) break :blk 4;
 if (optimal_vector_len >= 2) break :blk 2;
 break :blk 1;
 };
 if (self.pending_count >= optimal_batch_size) {
 self.flushPendingChunks();
 }
 }
 self.buffer_len = 0;
 }
Expand DownExpand Up@@ -931,24 +980,65 @@ fn KTHash(
 return;
 }

 // Tree mode: we've already absorbed first_chunk + padding + intermediate CVs
 // Now handle remaining buffer data
 const remaining_with_custom_len = self.buffer_len + self.customization.len + self.custom_len_enc.len;
 // Flush any pending chunks with SIMD
 self.flushPendingChunks();

 // Build view over remaining data (buffer + customization + encoding)
 const remaining_view = MultiSliceView.init(
 self.buffer[0..self.buffer_len],
 self.customization,
 self.custom_len_enc.slice(),
 );
 const remaining_len = remaining_view.totalLen();

 var final_leaves = self.num_leaves;
 var leaf_start: usize = 0;

 // Tree mode: initialize if not already done (lazy initialization)
 if (self.final_state == null and remaining_len > 0) {
 self.final_state = StateType.init(.{});

 // Absorb first chunk (up to chunk_size bytes from remaining data)
 const first_chunk_len = @min(chunk_size, remaining_len);
 if (remaining_view.tryGetSlice(0, first_chunk_len)) |first_chunk| {
 // Data is contiguous, use it directly
 self.final_state.?.update(first_chunk);
 } else {
 // Data spans boundaries, copy to buffer
 var first_chunk_buf: [chunk_size]u8 = undefined;
 remaining_view.copyRange(0, first_chunk_len, first_chunk_buf[0..first_chunk_len]);
 self.final_state.?.update(first_chunk_buf[0..first_chunk_len]);
 }

 if (remaining_with_custom_len > 0) {
 // Build final leaf data with customization
 var final_leaf_buffer: [chunk_size + 256]u8 = undefined; // Extra space for customization
 @memcpy(final_leaf_buffer[0..self.buffer_len], self.buffer[0..self.buffer_len]);
 @memcpy(final_leaf_buffer[self.buffer_len..][0..self.customization.len], self.customization);
 @memcpy(final_leaf_buffer[self.buffer_len + self.customization.len ..][0..self.custom_len_enc.len], self.custom_len_enc.slice());

 // Generate CV for final leaf and absorb it
 var cv_buffer: [64]u8 = undefined; // Max CV size
 const cv_slice = MultiSliceView.init(final_leaf_buffer[0..remaining_with_custom_len], &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);
 // Absorb padding (8 bytes: 0x03 followed by 7 zeros)
 const padding = [_]u8{ 0x03, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 };
 self.final_state.?.update(&padding);

 // Process remaining data as leaves
 leaf_start = first_chunk_len;
 }

 // Process all remaining data as leaves (starting from leaf_start)
 var offset = leaf_start;
 while (offset < remaining_len) {
 const leaf_end = @min(offset + chunk_size, remaining_len);
 const leaf_size = leaf_end - offset;

 var cv_buffer: [64]u8 = undefined;
 if (remaining_view.tryGetSlice(offset, leaf_end)) |leaf_data| {
 // Data is contiguous, use it directly
 const cv_slice = MultiSliceView.init(leaf_data, &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);
 } else {
 // Data spans boundaries, copy to buffer
 var leaf_buf: [chunk_size]u8 = undefined;
 remaining_view.copyRange(offset, leaf_end, leaf_buf[0..leaf_size]);
 const cv_slice = MultiSliceView.init(leaf_buf[0..leaf_size], &[_]u8{}, &[_]u8{});
 Variant.turboSHAKEToBuffer(&cv_slice, 0x0B, cv_buffer[0..cv_size]);
 }
 self.final_state.?.update(cv_buffer[0..cv_size]);
 final_leaves += 1;
 offset = leaf_end;
 }

 // Absorb right_encode(num_leaves) and terminator
Expand Down