crypto - threaded K12: separate context computation from thread spawning#25793

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 2 commits into from
Nov 3, 2025
Merged

crypto - threaded K12: separate context computation from thread spawning #25793

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
06cfea7
threaded K12: separate context computation from thread spawning
jedisct1 Nov 3, 2025
1fb0c58
kt128: unroll the permutation rounds only twice
jedisct1 Nov 3, 2025
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
189 changes: 100 additions & 89 deletions lib/std/crypto/kangarootwelve.zig
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -230,58 +230,61 @@ fn keccakP1600timesN(comptime N: usize, states: *[5][5]@Vector(N, u64)) void {
break :blk offsets;
};

inline for (RC) |rc| {
// θ (theta)
var C: [5]@Vector(N, u64) = undefined;
inline for (0..5) |x| {
C[x] = states[x][0] ^ states[x][1] ^ states[x][2] ^ states[x][3] ^ states[x][4];
}
var round: usize = 0;
while (round < 12) : (round += 2) {
inline for (0..2) |i| {
// θ (theta)
var C: [5]@Vector(N, u64) = undefined;
inline for (0..5) |x| {
C[x] = states[x][0] ^ states[x][1] ^ states[x][2] ^ states[x][3] ^ states[x][4];
}

var D: [5]@Vector(N, u64) = undefined;
inline for (0..5) |x| {
D[x] = C[(x + 4) % 5] ^ rol64Vec(N, C[(x + 1) % 5], 1);
}
var D: [5]@Vector(N, u64) = undefined;
inline for (0..5) |x| {
D[x] = C[(x + 4) % 5] ^ rol64Vec(N, C[(x + 1) % 5], 1);
}

// Apply D to all lanes
inline for (0..5) |x| {
states[x][0] ^= D[x];
states[x][1] ^= D[x];
states[x][2] ^= D[x];
states[x][3] ^= D[x];
states[x][4] ^= D[x];
}
// Apply D to all lanes
inline for (0..5) |x| {
states[x][0] ^= D[x];
states[x][1] ^= D[x];
states[x][2] ^= D[x];
states[x][3] ^= D[x];
states[x][4] ^= D[x];
}

// ρ (rho) and π (pi) - optimized with pre-computed offsets
var current = states[1][0];
var px: usize = 1;
var py: usize = 0;
inline for (rho_offsets) |rot| {
const next_y = (2 * px + 3 * py) % 5;
const next = states[py][next_y];
states[py][next_y] = rol64Vec(N, current, rot);
current = next;
px = py;
py = next_y;
}
// ρ (rho) and π (pi) - optimized with pre-computed offsets
var current = states[1][0];
var px: usize = 1;
var py: usize = 0;
inline for (rho_offsets) |rot| {
const next_y = (2 * px + 3 * py) % 5;
const next = states[py][next_y];
states[py][next_y] = rol64Vec(N, current, rot);
current = next;
px = py;
py = next_y;
}

// χ (chi) - optimized with better register usage
inline for (0..5) |y| {
const t0 = states[0][y];
const t1 = states[1][y];
const t2 = states[2][y];
const t3 = states[3][y];
const t4 = states[4][y];

states[0][y] = t0 ^ (~t1 & t2);
states[1][y] = t1 ^ (~t2 & t3);
states[2][y] = t2 ^ (~t3 & t4);
states[3][y] = t3 ^ (~t4 & t0);
states[4][y] = t4 ^ (~t0 & t1);
}
// χ (chi) - optimized with better register usage
inline for (0..5) |y| {
const t0 = states[0][y];
const t1 = states[1][y];
const t2 = states[2][y];
const t3 = states[3][y];
const t4 = states[4][y];

states[0][y] = t0 ^ (~t1 & t2);
states[1][y] = t1 ^ (~t2 & t3);
states[2][y] = t2 ^ (~t3 & t4);
states[3][y] = t3 ^ (~t4 & t0);
states[4][y] = t4 ^ (~t0 & t1);
}

// ι (iota)
const rc_splat: @Vector(N, u64) = @splat(rc);
states[0][0] ^= rc_splat;
// ι (iota)
const rc_splat: @Vector(N, u64) = @splat(RC[round + i]);
states[0][0] ^= rc_splat;
}
}
}

Expand DownExpand Up@@ -323,46 +326,49 @@ fn keccakP(state: *[200]u8) void {
}

// Apply 12 rounds
inline for (RC) |rc| {
// θ
var C: [5]u64 = undefined;
inline for (0..5) |x| {
C[x] = lanes[x][0] ^ lanes[x][1] ^ lanes[x][2] ^ lanes[x][3] ^ lanes[x][4];
}
var D: [5]u64 = undefined;
inline for (0..5) |x| {
D[x] = C[(x + 4) % 5] ^ std.math.rotl(u64, C[(x + 1) % 5], 1);
}
inline for (0..5) |x| {
inline for (0..5) |y| {
lanes[x][y] ^= D[x];
var round: usize = 0;
while (round < 12) : (round += 2) {
inline for (0..2) |i| {
// θ
var C: [5]u64 = undefined;
inline for (0..5) |x| {
C[x] = lanes[x][0] ^ lanes[x][1] ^ lanes[x][2] ^ lanes[x][3] ^ lanes[x][4];
}
var D: [5]u64 = undefined;
inline for (0..5) |x| {
D[x] = C[(x + 4) % 5] ^ std.math.rotl(u64, C[(x + 1) % 5], 1);
}
inline for (0..5) |x| {
inline for (0..5) |y| {
lanes[x][y] ^= D[x];
}
}
}

// ρ and π
var current = lanes[1][0];
var px: usize = 1;
var py: usize = 0;
inline for (0..24) |t| {
const temp = lanes[py][(2 * px + 3 * py) % 5];
const rot_amount = ((t + 1) * (t + 2) / 2) % 64;
lanes[py][(2 * px + 3 * py) % 5] = std.math.rotl(u64, current, @as(u6, @intCast(rot_amount)));
current = temp;
const temp_x = py;
py = (2 * px + 3 * py) % 5;
px = temp_x;
}
// ρ and π
var current = lanes[1][0];
var px: usize = 1;
var py: usize = 0;
inline for (0..24) |t| {
const temp = lanes[py][(2 * px + 3 * py) % 5];
const rot_amount = ((t + 1) * (t + 2) / 2) % 64;
lanes[py][(2 * px + 3 * py) % 5] = std.math.rotl(u64, current, @as(u6, @intCast(rot_amount)));
current = temp;
const temp_x = py;
py = (2 * px + 3 * py) % 5;
px = temp_x;
}

// χ
inline for (0..5) |y| {
const T = [5]u64{ lanes[0][y], lanes[1][y], lanes[2][y], lanes[3][y], lanes[4][y] };
inline for (0..5) |x| {
lanes[x][y] = T[x] ^ (~T[(x + 1) % 5] & T[(x + 2) % 5]);
// χ
inline for (0..5) |y| {
const T = [5]u64{ lanes[0][y], lanes[1][y], lanes[2][y], lanes[3][y], lanes[4][y] };
inline for (0..5) |x| {
lanes[x][y] = T[x] ^ (~T[(x + 1) % 5] & T[(x + 2) % 5]);
}
}
}

// ι
lanes[0][0] ^= rc;
// ι
lanes[0][0] ^= RC[round + i];
}
}

// Store lanes back to state
Expand DownExpand Up@@ -759,32 +765,37 @@ fn ktMultiThreaded(
const all_scratch = try allocator.alloc(u8, thread_count * scratch_size);
defer allocator.free(all_scratch);

var group: Io.Group = .init;
const contexts = try allocator.alloc(LeafBatchContext, thread_count);
defer allocator.free(contexts);

var leaves_assigned: usize = 0;
var thread_idx: usize = 0;
var context_count: usize = 0;

while (leaves_assigned < total_leaves) {
const batch_count = @min(leaves_per_thread, total_leaves - leaves_assigned);
const batch_start = chunk_size + leaves_assigned * chunk_size;
const cvs_offset = leaves_assigned * cv_size;

const ctx = LeafBatchContext{
contexts[context_count] = LeafBatchContext{
.output_cvs = cvs[cvs_offset .. cvs_offset + batch_count * cv_size],
.batch_start = batch_start,
.batch_count = batch_count,
.view = view,
.scratch_buffer = all_scratch[thread_idx * scratch_size .. (thread_idx + 1) * scratch_size],
.scratch_buffer = all_scratch[context_count * scratch_size .. (context_count + 1) * scratch_size],
.total_len = total_len,
};

leaves_assigned += batch_count;
context_count += 1;
}

var group: Io.Group = .init;
for (contexts[0..context_count]) |ctx| {
group.async(io, struct {
fn process(c: LeafBatchContext) void {
processLeafBatch(Variant, c);
}
}.process, .{ctx});

leaves_assigned += batch_count;
thread_idx += 1;
}

// Wait for all threads to complete
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 - threaded K12: separate context computation from thread spawning#25793

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 2 commits into

from

Nov 3, 2025
 Merged


crypto - threaded K12: separate context computation from thread spawning
#25793
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
06cfea7

threaded K12: separate context computation from thread spawning


jedisct1 Nov 3, 2025
1fb0c58

kt128: unroll the permutation rounds only twice


jedisct1 Nov 3, 2025

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


189 changes: 100 additions & 89 deletions
lib/std/crypto/kangarootwelve.zig

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -230,58 +230,61 @@ fn keccakP1600timesN(comptime N: usize, states: *[5][5]@Vector(N, u64)) void {
 break :blk offsets;
 };

 inline for (RC) |rc| {
 // θ (theta)
 var C: [5]@Vector(N, u64) = undefined;
 inline for (0..5) |x| {
 C[x] = states[x][0] ^ states[x][1] ^ states[x][2] ^ states[x][3] ^ states[x][4];
 }
 var round: usize = 0;
 while (round < 12) : (round += 2) {
 inline for (0..2) |i| {
 // θ (theta)
 var C: [5]@Vector(N, u64) = undefined;
 inline for (0..5) |x| {
 C[x] = states[x][0] ^ states[x][1] ^ states[x][2] ^ states[x][3] ^ states[x][4];
 }

 var D: [5]@Vector(N, u64) = undefined;
 inline for (0..5) |x| {
 D[x] = C[(x + 4) % 5] ^ rol64Vec(N, C[(x + 1) % 5], 1);
 }
var D: [5]@Vector(N, u64) = undefined;
inline for (0..5) |x| {
D[x] = C[(x + 4) % 5] ^ rol64Vec(N, C[(x + 1) % 5], 1);
}

 // Apply D to all lanes
 inline for (0..5) |x| {
 states[x][0] ^= D[x];
 states[x][1] ^= D[x];
 states[x][2] ^= D[x];
 states[x][3] ^= D[x];
 states[x][4] ^= D[x];
 }
// Apply D to all lanes
inline for (0..5) |x| {
states[x][0] ^= D[x];
states[x][1] ^= D[x];
states[x][2] ^= D[x];
states[x][3] ^= D[x];
states[x][4] ^= D[x];
}

 // ρ (rho) and π (pi) - optimized with pre-computed offsets
 var current = states[1][0];
 var px: usize = 1;
 var py: usize = 0;
 inline for (rho_offsets) |rot| {
 const next_y = (2 * px + 3 * py) % 5;
 const next = states[py][next_y];
 states[py][next_y] = rol64Vec(N, current, rot);
 current = next;
 px = py;
 py = next_y;
 }
// ρ (rho) and π (pi) - optimized with pre-computed offsets
var current = states[1][0];
var px: usize = 1;
var py: usize = 0;
inline for (rho_offsets) |rot| {
const next_y = (2 * px + 3 * py) % 5;
const next = states[py][next_y];
states[py][next_y] = rol64Vec(N, current, rot);
current = next;
px = py;
py = next_y;
}

 // χ (chi) - optimized with better register usage
 inline for (0..5) |y| {
 const t0 = states[0][y];
 const t1 = states[1][y];
 const t2 = states[2][y];
 const t3 = states[3][y];
 const t4 = states[4][y];

 states[0][y] = t0 ^ (~t1 & t2);
 states[1][y] = t1 ^ (~t2 & t3);
 states[2][y] = t2 ^ (~t3 & t4);
 states[3][y] = t3 ^ (~t4 & t0);
 states[4][y] = t4 ^ (~t0 & t1);
 }
// χ (chi) - optimized with better register usage
inline for (0..5) |y| {
const t0 = states[0][y];
const t1 = states[1][y];
const t2 = states[2][y];
const t3 = states[3][y];
const t4 = states[4][y];

states[0][y] = t0 ^ (~t1 & t2);
states[1][y] = t1 ^ (~t2 & t3);
states[2][y] = t2 ^ (~t3 & t4);
states[3][y] = t3 ^ (~t4 & t0);
states[4][y] = t4 ^ (~t0 & t1);
}

 // ι (iota)
 const rc_splat: @Vector(N, u64) = @splat(rc);
 states[0][0] ^= rc_splat;
 // ι (iota)
 const rc_splat: @Vector(N, u64) = @splat(RC[round + i]);
 states[0][0] ^= rc_splat;
 }
 }
}

Expand DownExpand Up@@ -323,46 +326,49 @@ fn keccakP(state: *[200]u8) void {
 }

 // Apply 12 rounds
 inline for (RC) |rc| {
 // θ
 var C: [5]u64 = undefined;
 inline for (0..5) |x| {
 C[x] = lanes[x][0] ^ lanes[x][1] ^ lanes[x][2] ^ lanes[x][3] ^ lanes[x][4];
 }
 var D: [5]u64 = undefined;
 inline for (0..5) |x| {
 D[x] = C[(x + 4) % 5] ^ std.math.rotl(u64, C[(x + 1) % 5], 1);
 }
 inline for (0..5) |x| {
 inline for (0..5) |y| {
 lanes[x][y] ^= D[x];
 var round: usize = 0;
 while (round < 12) : (round += 2) {
 inline for (0..2) |i| {
 // θ
 var C: [5]u64 = undefined;
 inline for (0..5) |x| {
 C[x] = lanes[x][0] ^ lanes[x][1] ^ lanes[x][2] ^ lanes[x][3] ^ lanes[x][4];
 }
 var D: [5]u64 = undefined;
 inline for (0..5) |x| {
 D[x] = C[(x + 4) % 5] ^ std.math.rotl(u64, C[(x + 1) % 5], 1);
 }
 inline for (0..5) |x| {
 inline for (0..5) |y| {
 lanes[x][y] ^= D[x];
 }
 }
 }

 // ρ and π
 var current = lanes[1][0];
 var px: usize = 1;
 var py: usize = 0;
 inline for (0..24) |t| {
 const temp = lanes[py][(2 * px + 3 * py) % 5];
 const rot_amount = ((t + 1) * (t + 2) / 2) % 64;
 lanes[py][(2 * px + 3 * py) % 5] = std.math.rotl(u64, current, @as(u6, @intCast(rot_amount)));
 current = temp;
 const temp_x = py;
 py = (2 * px + 3 * py) % 5;
 px = temp_x;
 }
// ρ and π
var current = lanes[1][0];
var px: usize = 1;
var py: usize = 0;
inline for (0..24) |t| {
const temp = lanes[py][(2 * px + 3 * py) % 5];
const rot_amount = ((t + 1) * (t + 2) / 2) % 64;
lanes[py][(2 * px + 3 * py) % 5] = std.math.rotl(u64, current, @as(u6, @intCast(rot_amount)));
current = temp;
const temp_x = py;
py = (2 * px + 3 * py) % 5;
px = temp_x;
}

 // χ
 inline for (0..5) |y| {
 const T = [5]u64{ lanes[0][y], lanes[1][y], lanes[2][y], lanes[3][y], lanes[4][y] };
 inline for (0..5) |x| {
 lanes[x][y] = T[x] ^ (~T[(x + 1) % 5] & T[(x + 2) % 5]);
 // χ
 inline for (0..5) |y| {
 const T = [5]u64{ lanes[0][y], lanes[1][y], lanes[2][y], lanes[3][y], lanes[4][y] };
 inline for (0..5) |x| {
 lanes[x][y] = T[x] ^ (~T[(x + 1) % 5] & T[(x + 2) % 5]);
 }
 }
 }

 // ι
 lanes[0][0] ^= rc;
 // ι
 lanes[0][0] ^= RC[round + i];
 }
 }

 // Store lanes back to state
Expand DownExpand Up@@ -759,32 +765,37 @@ fn ktMultiThreaded(
 const all_scratch = try allocator.alloc(u8, thread_count * scratch_size);
 defer allocator.free(all_scratch);

 var group: Io.Group = .init;
 const contexts = try allocator.alloc(LeafBatchContext, thread_count);
 defer allocator.free(contexts);

 var leaves_assigned: usize = 0;
 var thread_idx: usize = 0;
 var context_count: usize = 0;

 while (leaves_assigned < total_leaves) {
 const batch_count = @min(leaves_per_thread, total_leaves - leaves_assigned);
 const batch_start = chunk_size + leaves_assigned * chunk_size;
 const cvs_offset = leaves_assigned * cv_size;

const ctx = LeafBatchContext{
contexts[context_count] = LeafBatchContext{
 .output_cvs = cvs[cvs_offset .. cvs_offset + batch_count * cv_size],
 .batch_start = batch_start,
 .batch_count = batch_count,
 .view = view,
 .scratch_buffer = all_scratch[thread_idx * scratch_size .. (thread_idx + 1) * scratch_size],
 .scratch_buffer = all_scratch[context_count * scratch_size .. (context_count + 1) * scratch_size],
 .total_len = total_len,
 };

 leaves_assigned += batch_count;
 context_count += 1;
 }

 var group: Io.Group = .init;
 for (contexts[0..context_count]) |ctx| {
 group.async(io, struct {
 fn process(c: LeafBatchContext) void {
 processLeafBatch(Variant, c);
 }
 }.process, .{ctx});

 leaves_assigned += batch_count;
 thread_idx += 1;
 }

 // Wait for all threads to complete
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 - threaded K12: separate context computation from thread spawning#25793

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 2 commits into

from

Nov 3, 2025
 Merged


crypto - threaded K12: separate context computation from thread spawning
#25793
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
06cfea7

threaded K12: separate context computation from thread spawning


jedisct1 Nov 3, 2025
1fb0c58

kt128: unroll the permutation rounds only twice


jedisct1 Nov 3, 2025

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


189 changes: 100 additions & 89 deletions
lib/std/crypto/kangarootwelve.zig

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -230,58 +230,61 @@ fn keccakP1600timesN(comptime N: usize, states: *[5][5]@Vector(N, u64)) void {
 break :blk offsets;
 };

 inline for (RC) |rc| {
 // θ (theta)
 var C: [5]@Vector(N, u64) = undefined;
 inline for (0..5) |x| {
 C[x] = states[x][0] ^ states[x][1] ^ states[x][2] ^ states[x][3] ^ states[x][4];
 }
 var round: usize = 0;
 while (round < 12) : (round += 2) {
 inline for (0..2) |i| {
 // θ (theta)
 var C: [5]@Vector(N, u64) = undefined;
 inline for (0..5) |x| {
 C[x] = states[x][0] ^ states[x][1] ^ states[x][2] ^ states[x][3] ^ states[x][4];
 }

 var D: [5]@Vector(N, u64) = undefined;
 inline for (0..5) |x| {
 D[x] = C[(x + 4) % 5] ^ rol64Vec(N, C[(x + 1) % 5], 1);
 }
var D: [5]@Vector(N, u64) = undefined;
inline for (0..5) |x| {
D[x] = C[(x + 4) % 5] ^ rol64Vec(N, C[(x + 1) % 5], 1);
}

 // Apply D to all lanes
 inline for (0..5) |x| {
 states[x][0] ^= D[x];
 states[x][1] ^= D[x];
 states[x][2] ^= D[x];
 states[x][3] ^= D[x];
 states[x][4] ^= D[x];
 }
// Apply D to all lanes
inline for (0..5) |x| {
states[x][0] ^= D[x];
states[x][1] ^= D[x];
states[x][2] ^= D[x];
states[x][3] ^= D[x];
states[x][4] ^= D[x];
}

 // ρ (rho) and π (pi) - optimized with pre-computed offsets
 var current = states[1][0];
 var px: usize = 1;
 var py: usize = 0;
 inline for (rho_offsets) |rot| {
 const next_y = (2 * px + 3 * py) % 5;
 const next = states[py][next_y];
 states[py][next_y] = rol64Vec(N, current, rot);
 current = next;
 px = py;
 py = next_y;
 }
// ρ (rho) and π (pi) - optimized with pre-computed offsets
var current = states[1][0];
var px: usize = 1;
var py: usize = 0;
inline for (rho_offsets) |rot| {
const next_y = (2 * px + 3 * py) % 5;
const next = states[py][next_y];
states[py][next_y] = rol64Vec(N, current, rot);
current = next;
px = py;
py = next_y;
}

 // χ (chi) - optimized with better register usage
 inline for (0..5) |y| {
 const t0 = states[0][y];
 const t1 = states[1][y];
 const t2 = states[2][y];
 const t3 = states[3][y];
 const t4 = states[4][y];

 states[0][y] = t0 ^ (~t1 & t2);
 states[1][y] = t1 ^ (~t2 & t3);
 states[2][y] = t2 ^ (~t3 & t4);
 states[3][y] = t3 ^ (~t4 & t0);
 states[4][y] = t4 ^ (~t0 & t1);
 }
// χ (chi) - optimized with better register usage
inline for (0..5) |y| {
const t0 = states[0][y];
const t1 = states[1][y];
const t2 = states[2][y];
const t3 = states[3][y];
const t4 = states[4][y];

states[0][y] = t0 ^ (~t1 & t2);
states[1][y] = t1 ^ (~t2 & t3);
states[2][y] = t2 ^ (~t3 & t4);
states[3][y] = t3 ^ (~t4 & t0);
states[4][y] = t4 ^ (~t0 & t1);
}

 // ι (iota)
 const rc_splat: @Vector(N, u64) = @splat(rc);
 states[0][0] ^= rc_splat;
 // ι (iota)
 const rc_splat: @Vector(N, u64) = @splat(RC[round + i]);
 states[0][0] ^= rc_splat;
 }
 }
}

Expand DownExpand Up@@ -323,46 +326,49 @@ fn keccakP(state: *[200]u8) void {
 }

 // Apply 12 rounds
 inline for (RC) |rc| {
 // θ
 var C: [5]u64 = undefined;
 inline for (0..5) |x| {
 C[x] = lanes[x][0] ^ lanes[x][1] ^ lanes[x][2] ^ lanes[x][3] ^ lanes[x][4];
 }
 var D: [5]u64 = undefined;
 inline for (0..5) |x| {
 D[x] = C[(x + 4) % 5] ^ std.math.rotl(u64, C[(x + 1) % 5], 1);
 }
 inline for (0..5) |x| {
 inline for (0..5) |y| {
 lanes[x][y] ^= D[x];
 var round: usize = 0;
 while (round < 12) : (round += 2) {
 inline for (0..2) |i| {
 // θ
 var C: [5]u64 = undefined;
 inline for (0..5) |x| {
 C[x] = lanes[x][0] ^ lanes[x][1] ^ lanes[x][2] ^ lanes[x][3] ^ lanes[x][4];
 }
 var D: [5]u64 = undefined;
 inline for (0..5) |x| {
 D[x] = C[(x + 4) % 5] ^ std.math.rotl(u64, C[(x + 1) % 5], 1);
 }
 inline for (0..5) |x| {
 inline for (0..5) |y| {
 lanes[x][y] ^= D[x];
 }
 }
 }

 // ρ and π
 var current = lanes[1][0];
 var px: usize = 1;
 var py: usize = 0;
 inline for (0..24) |t| {
 const temp = lanes[py][(2 * px + 3 * py) % 5];
 const rot_amount = ((t + 1) * (t + 2) / 2) % 64;
 lanes[py][(2 * px + 3 * py) % 5] = std.math.rotl(u64, current, @as(u6, @intCast(rot_amount)));
 current = temp;
 const temp_x = py;
 py = (2 * px + 3 * py) % 5;
 px = temp_x;
 }
// ρ and π
var current = lanes[1][0];
var px: usize = 1;
var py: usize = 0;
inline for (0..24) |t| {
const temp = lanes[py][(2 * px + 3 * py) % 5];
const rot_amount = ((t + 1) * (t + 2) / 2) % 64;
lanes[py][(2 * px + 3 * py) % 5] = std.math.rotl(u64, current, @as(u6, @intCast(rot_amount)));
current = temp;
const temp_x = py;
py = (2 * px + 3 * py) % 5;
px = temp_x;
}

 // χ
 inline for (0..5) |y| {
 const T = [5]u64{ lanes[0][y], lanes[1][y], lanes[2][y], lanes[3][y], lanes[4][y] };
 inline for (0..5) |x| {
 lanes[x][y] = T[x] ^ (~T[(x + 1) % 5] & T[(x + 2) % 5]);
 // χ
 inline for (0..5) |y| {
 const T = [5]u64{ lanes[0][y], lanes[1][y], lanes[2][y], lanes[3][y], lanes[4][y] };
 inline for (0..5) |x| {
 lanes[x][y] = T[x] ^ (~T[(x + 1) % 5] & T[(x + 2) % 5]);
 }
 }
 }

 // ι
 lanes[0][0] ^= rc;
 // ι
 lanes[0][0] ^= RC[round + i];
 }
 }

 // Store lanes back to state
Expand DownExpand Up@@ -759,32 +765,37 @@ fn ktMultiThreaded(
 const all_scratch = try allocator.alloc(u8, thread_count * scratch_size);
 defer allocator.free(all_scratch);

 var group: Io.Group = .init;
 const contexts = try allocator.alloc(LeafBatchContext, thread_count);
 defer allocator.free(contexts);

 var leaves_assigned: usize = 0;
 var thread_idx: usize = 0;
 var context_count: usize = 0;

 while (leaves_assigned < total_leaves) {
 const batch_count = @min(leaves_per_thread, total_leaves - leaves_assigned);
 const batch_start = chunk_size + leaves_assigned * chunk_size;
 const cvs_offset = leaves_assigned * cv_size;

const ctx = LeafBatchContext{
contexts[context_count] = LeafBatchContext{
 .output_cvs = cvs[cvs_offset .. cvs_offset + batch_count * cv_size],
 .batch_start = batch_start,
 .batch_count = batch_count,
 .view = view,
 .scratch_buffer = all_scratch[thread_idx * scratch_size .. (thread_idx + 1) * scratch_size],
 .scratch_buffer = all_scratch[context_count * scratch_size .. (context_count + 1) * scratch_size],
 .total_len = total_len,
 };

 leaves_assigned += batch_count;
 context_count += 1;
 }

 var group: Io.Group = .init;
 for (contexts[0..context_count]) |ctx| {
 group.async(io, struct {
 fn process(c: LeafBatchContext) void {
 processLeafBatch(Variant, c);
 }
 }.process, .{ctx});

 leaves_assigned += batch_count;
 thread_idx += 1;
 }

 // Wait for all threads to complete
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 - threaded K12: separate context computation from thread spawning#25793

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 2 commits into

from

Nov 3, 2025
 Merged


crypto - threaded K12: separate context computation from thread spawning
#25793
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
06cfea7

threaded K12: separate context computation from thread spawning


jedisct1 Nov 3, 2025
1fb0c58

kt128: unroll the permutation rounds only twice


jedisct1 Nov 3, 2025

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


189 changes: 100 additions & 89 deletions
lib/std/crypto/kangarootwelve.zig

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -230,58 +230,61 @@ fn keccakP1600timesN(comptime N: usize, states: *[5][5]@Vector(N, u64)) void {
 break :blk offsets;
 };

 inline for (RC) |rc| {
 // θ (theta)
 var C: [5]@Vector(N, u64) = undefined;
 inline for (0..5) |x| {
 C[x] = states[x][0] ^ states[x][1] ^ states[x][2] ^ states[x][3] ^ states[x][4];
 }
 var round: usize = 0;
 while (round < 12) : (round += 2) {
 inline for (0..2) |i| {
 // θ (theta)
 var C: [5]@Vector(N, u64) = undefined;
 inline for (0..5) |x| {
 C[x] = states[x][0] ^ states[x][1] ^ states[x][2] ^ states[x][3] ^ states[x][4];
 }

 var D: [5]@Vector(N, u64) = undefined;
 inline for (0..5) |x| {
 D[x] = C[(x + 4) % 5] ^ rol64Vec(N, C[(x + 1) % 5], 1);
 }
var D: [5]@Vector(N, u64) = undefined;
inline for (0..5) |x| {
D[x] = C[(x + 4) % 5] ^ rol64Vec(N, C[(x + 1) % 5], 1);
}

 // Apply D to all lanes
 inline for (0..5) |x| {
 states[x][0] ^= D[x];
 states[x][1] ^= D[x];
 states[x][2] ^= D[x];
 states[x][3] ^= D[x];
 states[x][4] ^= D[x];
 }
// Apply D to all lanes
inline for (0..5) |x| {
states[x][0] ^= D[x];
states[x][1] ^= D[x];
states[x][2] ^= D[x];
states[x][3] ^= D[x];
states[x][4] ^= D[x];
}

 // ρ (rho) and π (pi) - optimized with pre-computed offsets
 var current = states[1][0];
 var px: usize = 1;
 var py: usize = 0;
 inline for (rho_offsets) |rot| {
 const next_y = (2 * px + 3 * py) % 5;
 const next = states[py][next_y];
 states[py][next_y] = rol64Vec(N, current, rot);
 current = next;
 px = py;
 py = next_y;
 }
// ρ (rho) and π (pi) - optimized with pre-computed offsets
var current = states[1][0];
var px: usize = 1;
var py: usize = 0;
inline for (rho_offsets) |rot| {
const next_y = (2 * px + 3 * py) % 5;
const next = states[py][next_y];
states[py][next_y] = rol64Vec(N, current, rot);
current = next;
px = py;
py = next_y;
}

 // χ (chi) - optimized with better register usage
 inline for (0..5) |y| {
 const t0 = states[0][y];
 const t1 = states[1][y];
 const t2 = states[2][y];
 const t3 = states[3][y];
 const t4 = states[4][y];

 states[0][y] = t0 ^ (~t1 & t2);
 states[1][y] = t1 ^ (~t2 & t3);
 states[2][y] = t2 ^ (~t3 & t4);
 states[3][y] = t3 ^ (~t4 & t0);
 states[4][y] = t4 ^ (~t0 & t1);
 }
// χ (chi) - optimized with better register usage
inline for (0..5) |y| {
const t0 = states[0][y];
const t1 = states[1][y];
const t2 = states[2][y];
const t3 = states[3][y];
const t4 = states[4][y];

states[0][y] = t0 ^ (~t1 & t2);
states[1][y] = t1 ^ (~t2 & t3);
states[2][y] = t2 ^ (~t3 & t4);
states[3][y] = t3 ^ (~t4 & t0);
states[4][y] = t4 ^ (~t0 & t1);
}

 // ι (iota)
 const rc_splat: @Vector(N, u64) = @splat(rc);
 states[0][0] ^= rc_splat;
 // ι (iota)
 const rc_splat: @Vector(N, u64) = @splat(RC[round + i]);
 states[0][0] ^= rc_splat;
 }
 }
}

Expand DownExpand Up@@ -323,46 +326,49 @@ fn keccakP(state: *[200]u8) void {
 }

 // Apply 12 rounds
 inline for (RC) |rc| {
 // θ
 var C: [5]u64 = undefined;
 inline for (0..5) |x| {
 C[x] = lanes[x][0] ^ lanes[x][1] ^ lanes[x][2] ^ lanes[x][3] ^ lanes[x][4];
 }
 var D: [5]u64 = undefined;
 inline for (0..5) |x| {
 D[x] = C[(x + 4) % 5] ^ std.math.rotl(u64, C[(x + 1) % 5], 1);
 }
 inline for (0..5) |x| {
 inline for (0..5) |y| {
 lanes[x][y] ^= D[x];
 var round: usize = 0;
 while (round < 12) : (round += 2) {
 inline for (0..2) |i| {
 // θ
 var C: [5]u64 = undefined;
 inline for (0..5) |x| {
 C[x] = lanes[x][0] ^ lanes[x][1] ^ lanes[x][2] ^ lanes[x][3] ^ lanes[x][4];
 }
 var D: [5]u64 = undefined;
 inline for (0..5) |x| {
 D[x] = C[(x + 4) % 5] ^ std.math.rotl(u64, C[(x + 1) % 5], 1);
 }
 inline for (0..5) |x| {
 inline for (0..5) |y| {
 lanes[x][y] ^= D[x];
 }
 }
 }

 // ρ and π
 var current = lanes[1][0];
 var px: usize = 1;
 var py: usize = 0;
 inline for (0..24) |t| {
 const temp = lanes[py][(2 * px + 3 * py) % 5];
 const rot_amount = ((t + 1) * (t + 2) / 2) % 64;
 lanes[py][(2 * px + 3 * py) % 5] = std.math.rotl(u64, current, @as(u6, @intCast(rot_amount)));
 current = temp;
 const temp_x = py;
 py = (2 * px + 3 * py) % 5;
 px = temp_x;
 }
// ρ and π
var current = lanes[1][0];
var px: usize = 1;
var py: usize = 0;
inline for (0..24) |t| {
const temp = lanes[py][(2 * px + 3 * py) % 5];
const rot_amount = ((t + 1) * (t + 2) / 2) % 64;
lanes[py][(2 * px + 3 * py) % 5] = std.math.rotl(u64, current, @as(u6, @intCast(rot_amount)));
current = temp;
const temp_x = py;
py = (2 * px + 3 * py) % 5;
px = temp_x;
}

 // χ
 inline for (0..5) |y| {
 const T = [5]u64{ lanes[0][y], lanes[1][y], lanes[2][y], lanes[3][y], lanes[4][y] };
 inline for (0..5) |x| {
 lanes[x][y] = T[x] ^ (~T[(x + 1) % 5] & T[(x + 2) % 5]);
 // χ
 inline for (0..5) |y| {
 const T = [5]u64{ lanes[0][y], lanes[1][y], lanes[2][y], lanes[3][y], lanes[4][y] };
 inline for (0..5) |x| {
 lanes[x][y] = T[x] ^ (~T[(x + 1) % 5] & T[(x + 2) % 5]);
 }
 }
 }

 // ι
 lanes[0][0] ^= rc;
 // ι
 lanes[0][0] ^= RC[round + i];
 }
 }

 // Store lanes back to state
Expand DownExpand Up@@ -759,32 +765,37 @@ fn ktMultiThreaded(
 const all_scratch = try allocator.alloc(u8, thread_count * scratch_size);
 defer allocator.free(all_scratch);

 var group: Io.Group = .init;
 const contexts = try allocator.alloc(LeafBatchContext, thread_count);
 defer allocator.free(contexts);

 var leaves_assigned: usize = 0;
 var thread_idx: usize = 0;
 var context_count: usize = 0;

 while (leaves_assigned < total_leaves) {
 const batch_count = @min(leaves_per_thread, total_leaves - leaves_assigned);
 const batch_start = chunk_size + leaves_assigned * chunk_size;
 const cvs_offset = leaves_assigned * cv_size;

const ctx = LeafBatchContext{
contexts[context_count] = LeafBatchContext{
 .output_cvs = cvs[cvs_offset .. cvs_offset + batch_count * cv_size],
 .batch_start = batch_start,
 .batch_count = batch_count,
 .view = view,
 .scratch_buffer = all_scratch[thread_idx * scratch_size .. (thread_idx + 1) * scratch_size],
 .scratch_buffer = all_scratch[context_count * scratch_size .. (context_count + 1) * scratch_size],
 .total_len = total_len,
 };

 leaves_assigned += batch_count;
 context_count += 1;
 }

 var group: Io.Group = .init;
 for (contexts[0..context_count]) |ctx| {
 group.async(io, struct {
 fn process(c: LeafBatchContext) void {
 processLeafBatch(Variant, c);
 }
 }.process, .{ctx});

 leaves_assigned += batch_count;
 thread_idx += 1;
 }

 // Wait for all threads to complete
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 - threaded K12: separate context computation from thread spawning#25793

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 2 commits into

from

Nov 3, 2025
 Merged


crypto - threaded K12: separate context computation from thread spawning
#25793
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
06cfea7

threaded K12: separate context computation from thread spawning


jedisct1 Nov 3, 2025
1fb0c58

kt128: unroll the permutation rounds only twice


jedisct1 Nov 3, 2025

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


189 changes: 100 additions & 89 deletions
lib/std/crypto/kangarootwelve.zig

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -230,58 +230,61 @@ fn keccakP1600timesN(comptime N: usize, states: *[5][5]@Vector(N, u64)) void {
 break :blk offsets;
 };

 inline for (RC) |rc| {
 // θ (theta)
 var C: [5]@Vector(N, u64) = undefined;
 inline for (0..5) |x| {
 C[x] = states[x][0] ^ states[x][1] ^ states[x][2] ^ states[x][3] ^ states[x][4];
 }
 var round: usize = 0;
 while (round < 12) : (round += 2) {
 inline for (0..2) |i| {
 // θ (theta)
 var C: [5]@Vector(N, u64) = undefined;
 inline for (0..5) |x| {
 C[x] = states[x][0] ^ states[x][1] ^ states[x][2] ^ states[x][3] ^ states[x][4];
 }

 var D: [5]@Vector(N, u64) = undefined;
 inline for (0..5) |x| {
 D[x] = C[(x + 4) % 5] ^ rol64Vec(N, C[(x + 1) % 5], 1);
 }
var D: [5]@Vector(N, u64) = undefined;
inline for (0..5) |x| {
D[x] = C[(x + 4) % 5] ^ rol64Vec(N, C[(x + 1) % 5], 1);
}

 // Apply D to all lanes
 inline for (0..5) |x| {
 states[x][0] ^= D[x];
 states[x][1] ^= D[x];
 states[x][2] ^= D[x];
 states[x][3] ^= D[x];
 states[x][4] ^= D[x];
 }
// Apply D to all lanes
inline for (0..5) |x| {
states[x][0] ^= D[x];
states[x][1] ^= D[x];
states[x][2] ^= D[x];
states[x][3] ^= D[x];
states[x][4] ^= D[x];
}

 // ρ (rho) and π (pi) - optimized with pre-computed offsets
 var current = states[1][0];
 var px: usize = 1;
 var py: usize = 0;
 inline for (rho_offsets) |rot| {
 const next_y = (2 * px + 3 * py) % 5;
 const next = states[py][next_y];
 states[py][next_y] = rol64Vec(N, current, rot);
 current = next;
 px = py;
 py = next_y;
 }
// ρ (rho) and π (pi) - optimized with pre-computed offsets
var current = states[1][0];
var px: usize = 1;
var py: usize = 0;
inline for (rho_offsets) |rot| {
const next_y = (2 * px + 3 * py) % 5;
const next = states[py][next_y];
states[py][next_y] = rol64Vec(N, current, rot);
current = next;
px = py;
py = next_y;
}

 // χ (chi) - optimized with better register usage
 inline for (0..5) |y| {
 const t0 = states[0][y];
 const t1 = states[1][y];
 const t2 = states[2][y];
 const t3 = states[3][y];
 const t4 = states[4][y];

 states[0][y] = t0 ^ (~t1 & t2);
 states[1][y] = t1 ^ (~t2 & t3);
 states[2][y] = t2 ^ (~t3 & t4);
 states[3][y] = t3 ^ (~t4 & t0);
 states[4][y] = t4 ^ (~t0 & t1);
 }
// χ (chi) - optimized with better register usage
inline for (0..5) |y| {
const t0 = states[0][y];
const t1 = states[1][y];
const t2 = states[2][y];
const t3 = states[3][y];
const t4 = states[4][y];

states[0][y] = t0 ^ (~t1 & t2);
states[1][y] = t1 ^ (~t2 & t3);
states[2][y] = t2 ^ (~t3 & t4);
states[3][y] = t3 ^ (~t4 & t0);
states[4][y] = t4 ^ (~t0 & t1);
}

 // ι (iota)
 const rc_splat: @Vector(N, u64) = @splat(rc);
 states[0][0] ^= rc_splat;
 // ι (iota)
 const rc_splat: @Vector(N, u64) = @splat(RC[round + i]);
 states[0][0] ^= rc_splat;
 }
 }
}

Expand DownExpand Up@@ -323,46 +326,49 @@ fn keccakP(state: *[200]u8) void {
 }

 // Apply 12 rounds
 inline for (RC) |rc| {
 // θ
 var C: [5]u64 = undefined;
 inline for (0..5) |x| {
 C[x] = lanes[x][0] ^ lanes[x][1] ^ lanes[x][2] ^ lanes[x][3] ^ lanes[x][4];
 }
 var D: [5]u64 = undefined;
 inline for (0..5) |x| {
 D[x] = C[(x + 4) % 5] ^ std.math.rotl(u64, C[(x + 1) % 5], 1);
 }
 inline for (0..5) |x| {
 inline for (0..5) |y| {
 lanes[x][y] ^= D[x];
 var round: usize = 0;
 while (round < 12) : (round += 2) {
 inline for (0..2) |i| {
 // θ
 var C: [5]u64 = undefined;
 inline for (0..5) |x| {
 C[x] = lanes[x][0] ^ lanes[x][1] ^ lanes[x][2] ^ lanes[x][3] ^ lanes[x][4];
 }
 var D: [5]u64 = undefined;
 inline for (0..5) |x| {
 D[x] = C[(x + 4) % 5] ^ std.math.rotl(u64, C[(x + 1) % 5], 1);
 }
 inline for (0..5) |x| {
 inline for (0..5) |y| {
 lanes[x][y] ^= D[x];
 }
 }
 }

 // ρ and π
 var current = lanes[1][0];
 var px: usize = 1;
 var py: usize = 0;
 inline for (0..24) |t| {
 const temp = lanes[py][(2 * px + 3 * py) % 5];
 const rot_amount = ((t + 1) * (t + 2) / 2) % 64;
 lanes[py][(2 * px + 3 * py) % 5] = std.math.rotl(u64, current, @as(u6, @intCast(rot_amount)));
 current = temp;
 const temp_x = py;
 py = (2 * px + 3 * py) % 5;
 px = temp_x;
 }
// ρ and π
var current = lanes[1][0];
var px: usize = 1;
var py: usize = 0;
inline for (0..24) |t| {
const temp = lanes[py][(2 * px + 3 * py) % 5];
const rot_amount = ((t + 1) * (t + 2) / 2) % 64;
lanes[py][(2 * px + 3 * py) % 5] = std.math.rotl(u64, current, @as(u6, @intCast(rot_amount)));
current = temp;
const temp_x = py;
py = (2 * px + 3 * py) % 5;
px = temp_x;
}

 // χ
 inline for (0..5) |y| {
 const T = [5]u64{ lanes[0][y], lanes[1][y], lanes[2][y], lanes[3][y], lanes[4][y] };
 inline for (0..5) |x| {
 lanes[x][y] = T[x] ^ (~T[(x + 1) % 5] & T[(x + 2) % 5]);
 // χ
 inline for (0..5) |y| {
 const T = [5]u64{ lanes[0][y], lanes[1][y], lanes[2][y], lanes[3][y], lanes[4][y] };
 inline for (0..5) |x| {
 lanes[x][y] = T[x] ^ (~T[(x + 1) % 5] & T[(x + 2) % 5]);
 }
 }
 }

 // ι
 lanes[0][0] ^= rc;
 // ι
 lanes[0][0] ^= RC[round + i];
 }
 }

 // Store lanes back to state
Expand DownExpand Up@@ -759,32 +765,37 @@ fn ktMultiThreaded(
 const all_scratch = try allocator.alloc(u8, thread_count * scratch_size);
 defer allocator.free(all_scratch);

 var group: Io.Group = .init;
 const contexts = try allocator.alloc(LeafBatchContext, thread_count);
 defer allocator.free(contexts);

 var leaves_assigned: usize = 0;
 var thread_idx: usize = 0;
 var context_count: usize = 0;

 while (leaves_assigned < total_leaves) {
 const batch_count = @min(leaves_per_thread, total_leaves - leaves_assigned);
 const batch_start = chunk_size + leaves_assigned * chunk_size;
 const cvs_offset = leaves_assigned * cv_size;

const ctx = LeafBatchContext{
contexts[context_count] = LeafBatchContext{
 .output_cvs = cvs[cvs_offset .. cvs_offset + batch_count * cv_size],
 .batch_start = batch_start,
 .batch_count = batch_count,
 .view = view,
 .scratch_buffer = all_scratch[thread_idx * scratch_size .. (thread_idx + 1) * scratch_size],
 .scratch_buffer = all_scratch[context_count * scratch_size .. (context_count + 1) * scratch_size],
 .total_len = total_len,
 };

 leaves_assigned += batch_count;
 context_count += 1;
 }

 var group: Io.Group = .init;
 for (contexts[0..context_count]) |ctx| {
 group.async(io, struct {
 fn process(c: LeafBatchContext) void {
 processLeafBatch(Variant, c);
 }
 }.process, .{ctx});

 leaves_assigned += batch_count;
 thread_idx += 1;
 }

 // Wait for all threads to complete
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 - threaded K12: separate context computation from thread spawning#25793

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 2 commits into

from

Nov 3, 2025
 Merged


crypto - threaded K12: separate context computation from thread spawning
#25793
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
06cfea7

threaded K12: separate context computation from thread spawning


jedisct1 Nov 3, 2025
1fb0c58

kt128: unroll the permutation rounds only twice


jedisct1 Nov 3, 2025

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


189 changes: 100 additions & 89 deletions
lib/std/crypto/kangarootwelve.zig

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -230,58 +230,61 @@ fn keccakP1600timesN(comptime N: usize, states: *[5][5]@Vector(N, u64)) void {
 break :blk offsets;
 };

 inline for (RC) |rc| {
 // θ (theta)
 var C: [5]@Vector(N, u64) = undefined;
 inline for (0..5) |x| {
 C[x] = states[x][0] ^ states[x][1] ^ states[x][2] ^ states[x][3] ^ states[x][4];
 }
 var round: usize = 0;
 while (round < 12) : (round += 2) {
 inline for (0..2) |i| {
 // θ (theta)
 var C: [5]@Vector(N, u64) = undefined;
 inline for (0..5) |x| {
 C[x] = states[x][0] ^ states[x][1] ^ states[x][2] ^ states[x][3] ^ states[x][4];
 }

 var D: [5]@Vector(N, u64) = undefined;
 inline for (0..5) |x| {
 D[x] = C[(x + 4) % 5] ^ rol64Vec(N, C[(x + 1) % 5], 1);
 }
var D: [5]@Vector(N, u64) = undefined;
inline for (0..5) |x| {
D[x] = C[(x + 4) % 5] ^ rol64Vec(N, C[(x + 1) % 5], 1);
}

 // Apply D to all lanes
 inline for (0..5) |x| {
 states[x][0] ^= D[x];
 states[x][1] ^= D[x];
 states[x][2] ^= D[x];
 states[x][3] ^= D[x];
 states[x][4] ^= D[x];
 }
// Apply D to all lanes
inline for (0..5) |x| {
states[x][0] ^= D[x];
states[x][1] ^= D[x];
states[x][2] ^= D[x];
states[x][3] ^= D[x];
states[x][4] ^= D[x];
}

 // ρ (rho) and π (pi) - optimized with pre-computed offsets
 var current = states[1][0];
 var px: usize = 1;
 var py: usize = 0;
 inline for (rho_offsets) |rot| {
 const next_y = (2 * px + 3 * py) % 5;
 const next = states[py][next_y];
 states[py][next_y] = rol64Vec(N, current, rot);
 current = next;
 px = py;
 py = next_y;
 }
// ρ (rho) and π (pi) - optimized with pre-computed offsets
var current = states[1][0];
var px: usize = 1;
var py: usize = 0;
inline for (rho_offsets) |rot| {
const next_y = (2 * px + 3 * py) % 5;
const next = states[py][next_y];
states[py][next_y] = rol64Vec(N, current, rot);
current = next;
px = py;
py = next_y;
}

 // χ (chi) - optimized with better register usage
 inline for (0..5) |y| {
 const t0 = states[0][y];
 const t1 = states[1][y];
 const t2 = states[2][y];
 const t3 = states[3][y];
 const t4 = states[4][y];

 states[0][y] = t0 ^ (~t1 & t2);
 states[1][y] = t1 ^ (~t2 & t3);
 states[2][y] = t2 ^ (~t3 & t4);
 states[3][y] = t3 ^ (~t4 & t0);
 states[4][y] = t4 ^ (~t0 & t1);
 }
// χ (chi) - optimized with better register usage
inline for (0..5) |y| {
const t0 = states[0][y];
const t1 = states[1][y];
const t2 = states[2][y];
const t3 = states[3][y];
const t4 = states[4][y];

states[0][y] = t0 ^ (~t1 & t2);
states[1][y] = t1 ^ (~t2 & t3);
states[2][y] = t2 ^ (~t3 & t4);
states[3][y] = t3 ^ (~t4 & t0);
states[4][y] = t4 ^ (~t0 & t1);
}

 // ι (iota)
 const rc_splat: @Vector(N, u64) = @splat(rc);
 states[0][0] ^= rc_splat;
 // ι (iota)
 const rc_splat: @Vector(N, u64) = @splat(RC[round + i]);
 states[0][0] ^= rc_splat;
 }
 }
}

Expand DownExpand Up@@ -323,46 +326,49 @@ fn keccakP(state: *[200]u8) void {
 }

 // Apply 12 rounds
 inline for (RC) |rc| {
 // θ
 var C: [5]u64 = undefined;
 inline for (0..5) |x| {
 C[x] = lanes[x][0] ^ lanes[x][1] ^ lanes[x][2] ^ lanes[x][3] ^ lanes[x][4];
 }
 var D: [5]u64 = undefined;
 inline for (0..5) |x| {
 D[x] = C[(x + 4) % 5] ^ std.math.rotl(u64, C[(x + 1) % 5], 1);
 }
 inline for (0..5) |x| {
 inline for (0..5) |y| {
 lanes[x][y] ^= D[x];
 var round: usize = 0;
 while (round < 12) : (round += 2) {
 inline for (0..2) |i| {
 // θ
 var C: [5]u64 = undefined;
 inline for (0..5) |x| {
 C[x] = lanes[x][0] ^ lanes[x][1] ^ lanes[x][2] ^ lanes[x][3] ^ lanes[x][4];
 }
 var D: [5]u64 = undefined;
 inline for (0..5) |x| {
 D[x] = C[(x + 4) % 5] ^ std.math.rotl(u64, C[(x + 1) % 5], 1);
 }
 inline for (0..5) |x| {
 inline for (0..5) |y| {
 lanes[x][y] ^= D[x];
 }
 }
 }

 // ρ and π
 var current = lanes[1][0];
 var px: usize = 1;
 var py: usize = 0;
 inline for (0..24) |t| {
 const temp = lanes[py][(2 * px + 3 * py) % 5];
 const rot_amount = ((t + 1) * (t + 2) / 2) % 64;
 lanes[py][(2 * px + 3 * py) % 5] = std.math.rotl(u64, current, @as(u6, @intCast(rot_amount)));
 current = temp;
 const temp_x = py;
 py = (2 * px + 3 * py) % 5;
 px = temp_x;
 }
// ρ and π
var current = lanes[1][0];
var px: usize = 1;
var py: usize = 0;
inline for (0..24) |t| {
const temp = lanes[py][(2 * px + 3 * py) % 5];
const rot_amount = ((t + 1) * (t + 2) / 2) % 64;
lanes[py][(2 * px + 3 * py) % 5] = std.math.rotl(u64, current, @as(u6, @intCast(rot_amount)));
current = temp;
const temp_x = py;
py = (2 * px + 3 * py) % 5;
px = temp_x;
}

 // χ
 inline for (0..5) |y| {
 const T = [5]u64{ lanes[0][y], lanes[1][y], lanes[2][y], lanes[3][y], lanes[4][y] };
 inline for (0..5) |x| {
 lanes[x][y] = T[x] ^ (~T[(x + 1) % 5] & T[(x + 2) % 5]);
 // χ
 inline for (0..5) |y| {
 const T = [5]u64{ lanes[0][y], lanes[1][y], lanes[2][y], lanes[3][y], lanes[4][y] };
 inline for (0..5) |x| {
 lanes[x][y] = T[x] ^ (~T[(x + 1) % 5] & T[(x + 2) % 5]);
 }
 }
 }

 // ι
 lanes[0][0] ^= rc;
 // ι
 lanes[0][0] ^= RC[round + i];
 }
 }

 // Store lanes back to state
Expand DownExpand Up@@ -759,32 +765,37 @@ fn ktMultiThreaded(
 const all_scratch = try allocator.alloc(u8, thread_count * scratch_size);
 defer allocator.free(all_scratch);

 var group: Io.Group = .init;
 const contexts = try allocator.alloc(LeafBatchContext, thread_count);
 defer allocator.free(contexts);

 var leaves_assigned: usize = 0;
 var thread_idx: usize = 0;
 var context_count: usize = 0;

 while (leaves_assigned < total_leaves) {
 const batch_count = @min(leaves_per_thread, total_leaves - leaves_assigned);
 const batch_start = chunk_size + leaves_assigned * chunk_size;
 const cvs_offset = leaves_assigned * cv_size;

const ctx = LeafBatchContext{
contexts[context_count] = LeafBatchContext{
 .output_cvs = cvs[cvs_offset .. cvs_offset + batch_count * cv_size],
 .batch_start = batch_start,
 .batch_count = batch_count,
 .view = view,
 .scratch_buffer = all_scratch[thread_idx * scratch_size .. (thread_idx + 1) * scratch_size],
 .scratch_buffer = all_scratch[context_count * scratch_size .. (context_count + 1) * scratch_size],
 .total_len = total_len,
 };

 leaves_assigned += batch_count;
 context_count += 1;
 }

 var group: Io.Group = .init;
 for (contexts[0..context_count]) |ctx| {
 group.async(io, struct {
 fn process(c: LeafBatchContext) void {
 processLeafBatch(Variant, c);
 }
 }.process, .{ctx});

 leaves_assigned += batch_count;
 thread_idx += 1;
 }

 // Wait for all threads to complete
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 - threaded K12: separate context computation from thread spawning#25793

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 2 commits into

from

Nov 3, 2025
 Merged


crypto - threaded K12: separate context computation from thread spawning
#25793
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
06cfea7

threaded K12: separate context computation from thread spawning


jedisct1 Nov 3, 2025
1fb0c58

kt128: unroll the permutation rounds only twice


jedisct1 Nov 3, 2025

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


189 changes: 100 additions & 89 deletions
lib/std/crypto/kangarootwelve.zig

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -230,58 +230,61 @@ fn keccakP1600timesN(comptime N: usize, states: *[5][5]@Vector(N, u64)) void {
 break :blk offsets;
 };

 inline for (RC) |rc| {
 // θ (theta)
 var C: [5]@Vector(N, u64) = undefined;
 inline for (0..5) |x| {
 C[x] = states[x][0] ^ states[x][1] ^ states[x][2] ^ states[x][3] ^ states[x][4];
 }
 var round: usize = 0;
 while (round < 12) : (round += 2) {
 inline for (0..2) |i| {
 // θ (theta)
 var C: [5]@Vector(N, u64) = undefined;
 inline for (0..5) |x| {
 C[x] = states[x][0] ^ states[x][1] ^ states[x][2] ^ states[x][3] ^ states[x][4];
 }

 var D: [5]@Vector(N, u64) = undefined;
 inline for (0..5) |x| {
 D[x] = C[(x + 4) % 5] ^ rol64Vec(N, C[(x + 1) % 5], 1);
 }
var D: [5]@Vector(N, u64) = undefined;
inline for (0..5) |x| {
D[x] = C[(x + 4) % 5] ^ rol64Vec(N, C[(x + 1) % 5], 1);
}

 // Apply D to all lanes
 inline for (0..5) |x| {
 states[x][0] ^= D[x];
 states[x][1] ^= D[x];
 states[x][2] ^= D[x];
 states[x][3] ^= D[x];
 states[x][4] ^= D[x];
 }
// Apply D to all lanes
inline for (0..5) |x| {
states[x][0] ^= D[x];
states[x][1] ^= D[x];
states[x][2] ^= D[x];
states[x][3] ^= D[x];
states[x][4] ^= D[x];
}

 // ρ (rho) and π (pi) - optimized with pre-computed offsets
 var current = states[1][0];
 var px: usize = 1;
 var py: usize = 0;
 inline for (rho_offsets) |rot| {
 const next_y = (2 * px + 3 * py) % 5;
 const next = states[py][next_y];
 states[py][next_y] = rol64Vec(N, current, rot);
 current = next;
 px = py;
 py = next_y;
 }
// ρ (rho) and π (pi) - optimized with pre-computed offsets
var current = states[1][0];
var px: usize = 1;
var py: usize = 0;
inline for (rho_offsets) |rot| {
const next_y = (2 * px + 3 * py) % 5;
const next = states[py][next_y];
states[py][next_y] = rol64Vec(N, current, rot);
current = next;
px = py;
py = next_y;
}

 // χ (chi) - optimized with better register usage
 inline for (0..5) |y| {
 const t0 = states[0][y];
 const t1 = states[1][y];
 const t2 = states[2][y];
 const t3 = states[3][y];
 const t4 = states[4][y];

 states[0][y] = t0 ^ (~t1 & t2);
 states[1][y] = t1 ^ (~t2 & t3);
 states[2][y] = t2 ^ (~t3 & t4);
 states[3][y] = t3 ^ (~t4 & t0);
 states[4][y] = t4 ^ (~t0 & t1);
 }
// χ (chi) - optimized with better register usage
inline for (0..5) |y| {
const t0 = states[0][y];
const t1 = states[1][y];
const t2 = states[2][y];
const t3 = states[3][y];
const t4 = states[4][y];

states[0][y] = t0 ^ (~t1 & t2);
states[1][y] = t1 ^ (~t2 & t3);
states[2][y] = t2 ^ (~t3 & t4);
states[3][y] = t3 ^ (~t4 & t0);
states[4][y] = t4 ^ (~t0 & t1);
}

 // ι (iota)
 const rc_splat: @Vector(N, u64) = @splat(rc);
 states[0][0] ^= rc_splat;
 // ι (iota)
 const rc_splat: @Vector(N, u64) = @splat(RC[round + i]);
 states[0][0] ^= rc_splat;
 }
 }
}

Expand DownExpand Up@@ -323,46 +326,49 @@ fn keccakP(state: *[200]u8) void {
 }

 // Apply 12 rounds
 inline for (RC) |rc| {
 // θ
 var C: [5]u64 = undefined;
 inline for (0..5) |x| {
 C[x] = lanes[x][0] ^ lanes[x][1] ^ lanes[x][2] ^ lanes[x][3] ^ lanes[x][4];
 }
 var D: [5]u64 = undefined;
 inline for (0..5) |x| {
 D[x] = C[(x + 4) % 5] ^ std.math.rotl(u64, C[(x + 1) % 5], 1);
 }
 inline for (0..5) |x| {
 inline for (0..5) |y| {
 lanes[x][y] ^= D[x];
 var round: usize = 0;
 while (round < 12) : (round += 2) {
 inline for (0..2) |i| {
 // θ
 var C: [5]u64 = undefined;
 inline for (0..5) |x| {
 C[x] = lanes[x][0] ^ lanes[x][1] ^ lanes[x][2] ^ lanes[x][3] ^ lanes[x][4];
 }
 var D: [5]u64 = undefined;
 inline for (0..5) |x| {
 D[x] = C[(x + 4) % 5] ^ std.math.rotl(u64, C[(x + 1) % 5], 1);
 }
 inline for (0..5) |x| {
 inline for (0..5) |y| {
 lanes[x][y] ^= D[x];
 }
 }
 }

 // ρ and π
 var current = lanes[1][0];
 var px: usize = 1;
 var py: usize = 0;
 inline for (0..24) |t| {
 const temp = lanes[py][(2 * px + 3 * py) % 5];
 const rot_amount = ((t + 1) * (t + 2) / 2) % 64;
 lanes[py][(2 * px + 3 * py) % 5] = std.math.rotl(u64, current, @as(u6, @intCast(rot_amount)));
 current = temp;
 const temp_x = py;
 py = (2 * px + 3 * py) % 5;
 px = temp_x;
 }
// ρ and π
var current = lanes[1][0];
var px: usize = 1;
var py: usize = 0;
inline for (0..24) |t| {
const temp = lanes[py][(2 * px + 3 * py) % 5];
const rot_amount = ((t + 1) * (t + 2) / 2) % 64;
lanes[py][(2 * px + 3 * py) % 5] = std.math.rotl(u64, current, @as(u6, @intCast(rot_amount)));
current = temp;
const temp_x = py;
py = (2 * px + 3 * py) % 5;
px = temp_x;
}

 // χ
 inline for (0..5) |y| {
 const T = [5]u64{ lanes[0][y], lanes[1][y], lanes[2][y], lanes[3][y], lanes[4][y] };
 inline for (0..5) |x| {
 lanes[x][y] = T[x] ^ (~T[(x + 1) % 5] & T[(x + 2) % 5]);
 // χ
 inline for (0..5) |y| {
 const T = [5]u64{ lanes[0][y], lanes[1][y], lanes[2][y], lanes[3][y], lanes[4][y] };
 inline for (0..5) |x| {
 lanes[x][y] = T[x] ^ (~T[(x + 1) % 5] & T[(x + 2) % 5]);
 }
 }
 }

 // ι
 lanes[0][0] ^= rc;
 // ι
 lanes[0][0] ^= RC[round + i];
 }
 }

 // Store lanes back to state
Expand DownExpand Up@@ -759,32 +765,37 @@ fn ktMultiThreaded(
 const all_scratch = try allocator.alloc(u8, thread_count * scratch_size);
 defer allocator.free(all_scratch);

 var group: Io.Group = .init;
 const contexts = try allocator.alloc(LeafBatchContext, thread_count);
 defer allocator.free(contexts);

 var leaves_assigned: usize = 0;
 var thread_idx: usize = 0;
 var context_count: usize = 0;

 while (leaves_assigned < total_leaves) {
 const batch_count = @min(leaves_per_thread, total_leaves - leaves_assigned);
 const batch_start = chunk_size + leaves_assigned * chunk_size;
 const cvs_offset = leaves_assigned * cv_size;

const ctx = LeafBatchContext{
contexts[context_count] = LeafBatchContext{
 .output_cvs = cvs[cvs_offset .. cvs_offset + batch_count * cv_size],
 .batch_start = batch_start,
 .batch_count = batch_count,
 .view = view,
 .scratch_buffer = all_scratch[thread_idx * scratch_size .. (thread_idx + 1) * scratch_size],
 .scratch_buffer = all_scratch[context_count * scratch_size .. (context_count + 1) * scratch_size],
 .total_len = total_len,
 };

 leaves_assigned += batch_count;
 context_count += 1;
 }

 var group: Io.Group = .init;
 for (contexts[0..context_count]) |ctx| {
 group.async(io, struct {
 fn process(c: LeafBatchContext) void {
 processLeafBatch(Variant, c);
 }
 }.process, .{ctx});

 leaves_assigned += batch_count;
 thread_idx += 1;
 }

 // Wait for all threads to complete
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 - threaded K12: separate context computation from thread spawning#25793

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 2 commits into

from

Nov 3, 2025
 Merged


crypto - threaded K12: separate context computation from thread spawning
#25793
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
06cfea7

threaded K12: separate context computation from thread spawning


jedisct1 Nov 3, 2025
1fb0c58

kt128: unroll the permutation rounds only twice


jedisct1 Nov 3, 2025

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


189 changes: 100 additions & 89 deletions
lib/std/crypto/kangarootwelve.zig

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -230,58 +230,61 @@ fn keccakP1600timesN(comptime N: usize, states: *[5][5]@Vector(N, u64)) void {
 break :blk offsets;
 };

 inline for (RC) |rc| {
 // θ (theta)
 var C: [5]@Vector(N, u64) = undefined;
 inline for (0..5) |x| {
 C[x] = states[x][0] ^ states[x][1] ^ states[x][2] ^ states[x][3] ^ states[x][4];
 }
 var round: usize = 0;
 while (round < 12) : (round += 2) {
 inline for (0..2) |i| {
 // θ (theta)
 var C: [5]@Vector(N, u64) = undefined;
 inline for (0..5) |x| {
 C[x] = states[x][0] ^ states[x][1] ^ states[x][2] ^ states[x][3] ^ states[x][4];
 }

 var D: [5]@Vector(N, u64) = undefined;
 inline for (0..5) |x| {
 D[x] = C[(x + 4) % 5] ^ rol64Vec(N, C[(x + 1) % 5], 1);
 }
var D: [5]@Vector(N, u64) = undefined;
inline for (0..5) |x| {
D[x] = C[(x + 4) % 5] ^ rol64Vec(N, C[(x + 1) % 5], 1);
}

 // Apply D to all lanes
 inline for (0..5) |x| {
 states[x][0] ^= D[x];
 states[x][1] ^= D[x];
 states[x][2] ^= D[x];
 states[x][3] ^= D[x];
 states[x][4] ^= D[x];
 }
// Apply D to all lanes
inline for (0..5) |x| {
states[x][0] ^= D[x];
states[x][1] ^= D[x];
states[x][2] ^= D[x];
states[x][3] ^= D[x];
states[x][4] ^= D[x];
}

 // ρ (rho) and π (pi) - optimized with pre-computed offsets
 var current = states[1][0];
 var px: usize = 1;
 var py: usize = 0;
 inline for (rho_offsets) |rot| {
 const next_y = (2 * px + 3 * py) % 5;
 const next = states[py][next_y];
 states[py][next_y] = rol64Vec(N, current, rot);
 current = next;
 px = py;
 py = next_y;
 }
// ρ (rho) and π (pi) - optimized with pre-computed offsets
var current = states[1][0];
var px: usize = 1;
var py: usize = 0;
inline for (rho_offsets) |rot| {
const next_y = (2 * px + 3 * py) % 5;
const next = states[py][next_y];
states[py][next_y] = rol64Vec(N, current, rot);
current = next;
px = py;
py = next_y;
}

 // χ (chi) - optimized with better register usage
 inline for (0..5) |y| {
 const t0 = states[0][y];
 const t1 = states[1][y];
 const t2 = states[2][y];
 const t3 = states[3][y];
 const t4 = states[4][y];

 states[0][y] = t0 ^ (~t1 & t2);
 states[1][y] = t1 ^ (~t2 & t3);
 states[2][y] = t2 ^ (~t3 & t4);
 states[3][y] = t3 ^ (~t4 & t0);
 states[4][y] = t4 ^ (~t0 & t1);
 }
// χ (chi) - optimized with better register usage
inline for (0..5) |y| {
const t0 = states[0][y];
const t1 = states[1][y];
const t2 = states[2][y];
const t3 = states[3][y];
const t4 = states[4][y];

states[0][y] = t0 ^ (~t1 & t2);
states[1][y] = t1 ^ (~t2 & t3);
states[2][y] = t2 ^ (~t3 & t4);
states[3][y] = t3 ^ (~t4 & t0);
states[4][y] = t4 ^ (~t0 & t1);
}

 // ι (iota)
 const rc_splat: @Vector(N, u64) = @splat(rc);
 states[0][0] ^= rc_splat;
 // ι (iota)
 const rc_splat: @Vector(N, u64) = @splat(RC[round + i]);
 states[0][0] ^= rc_splat;
 }
 }
}

Expand DownExpand Up@@ -323,46 +326,49 @@ fn keccakP(state: *[200]u8) void {
 }

 // Apply 12 rounds
 inline for (RC) |rc| {
 // θ
 var C: [5]u64 = undefined;
 inline for (0..5) |x| {
 C[x] = lanes[x][0] ^ lanes[x][1] ^ lanes[x][2] ^ lanes[x][3] ^ lanes[x][4];
 }
 var D: [5]u64 = undefined;
 inline for (0..5) |x| {
 D[x] = C[(x + 4) % 5] ^ std.math.rotl(u64, C[(x + 1) % 5], 1);
 }
 inline for (0..5) |x| {
 inline for (0..5) |y| {
 lanes[x][y] ^= D[x];
 var round: usize = 0;
 while (round < 12) : (round += 2) {
 inline for (0..2) |i| {
 // θ
 var C: [5]u64 = undefined;
 inline for (0..5) |x| {
 C[x] = lanes[x][0] ^ lanes[x][1] ^ lanes[x][2] ^ lanes[x][3] ^ lanes[x][4];
 }
 var D: [5]u64 = undefined;
 inline for (0..5) |x| {
 D[x] = C[(x + 4) % 5] ^ std.math.rotl(u64, C[(x + 1) % 5], 1);
 }
 inline for (0..5) |x| {
 inline for (0..5) |y| {
 lanes[x][y] ^= D[x];
 }
 }
 }

 // ρ and π
 var current = lanes[1][0];
 var px: usize = 1;
 var py: usize = 0;
 inline for (0..24) |t| {
 const temp = lanes[py][(2 * px + 3 * py) % 5];
 const rot_amount = ((t + 1) * (t + 2) / 2) % 64;
 lanes[py][(2 * px + 3 * py) % 5] = std.math.rotl(u64, current, @as(u6, @intCast(rot_amount)));
 current = temp;
 const temp_x = py;
 py = (2 * px + 3 * py) % 5;
 px = temp_x;
 }
// ρ and π
var current = lanes[1][0];
var px: usize = 1;
var py: usize = 0;
inline for (0..24) |t| {
const temp = lanes[py][(2 * px + 3 * py) % 5];
const rot_amount = ((t + 1) * (t + 2) / 2) % 64;
lanes[py][(2 * px + 3 * py) % 5] = std.math.rotl(u64, current, @as(u6, @intCast(rot_amount)));
current = temp;
const temp_x = py;
py = (2 * px + 3 * py) % 5;
px = temp_x;
}

 // χ
 inline for (0..5) |y| {
 const T = [5]u64{ lanes[0][y], lanes[1][y], lanes[2][y], lanes[3][y], lanes[4][y] };
 inline for (0..5) |x| {
 lanes[x][y] = T[x] ^ (~T[(x + 1) % 5] & T[(x + 2) % 5]);
 // χ
 inline for (0..5) |y| {
 const T = [5]u64{ lanes[0][y], lanes[1][y], lanes[2][y], lanes[3][y], lanes[4][y] };
 inline for (0..5) |x| {
 lanes[x][y] = T[x] ^ (~T[(x + 1) % 5] & T[(x + 2) % 5]);
 }
 }
 }

 // ι
 lanes[0][0] ^= rc;
 // ι
 lanes[0][0] ^= RC[round + i];
 }
 }

 // Store lanes back to state
Expand DownExpand Up@@ -759,32 +765,37 @@ fn ktMultiThreaded(
 const all_scratch = try allocator.alloc(u8, thread_count * scratch_size);
 defer allocator.free(all_scratch);

 var group: Io.Group = .init;
 const contexts = try allocator.alloc(LeafBatchContext, thread_count);
 defer allocator.free(contexts);

 var leaves_assigned: usize = 0;
 var thread_idx: usize = 0;
 var context_count: usize = 0;

 while (leaves_assigned < total_leaves) {
 const batch_count = @min(leaves_per_thread, total_leaves - leaves_assigned);
 const batch_start = chunk_size + leaves_assigned * chunk_size;
 const cvs_offset = leaves_assigned * cv_size;

const ctx = LeafBatchContext{
contexts[context_count] = LeafBatchContext{
 .output_cvs = cvs[cvs_offset .. cvs_offset + batch_count * cv_size],
 .batch_start = batch_start,
 .batch_count = batch_count,
 .view = view,
 .scratch_buffer = all_scratch[thread_idx * scratch_size .. (thread_idx + 1) * scratch_size],
 .scratch_buffer = all_scratch[context_count * scratch_size .. (context_count + 1) * scratch_size],
 .total_len = total_len,
 };

 leaves_assigned += batch_count;
 context_count += 1;
 }

 var group: Io.Group = .init;
 for (contexts[0..context_count]) |ctx| {
 group.async(io, struct {
 fn process(c: LeafBatchContext) void {
 processLeafBatch(Variant, c);
 }
 }.process, .{ctx});

 leaves_assigned += batch_count;
 thread_idx += 1;
 }

 // Wait for all threads to complete
Expand Down