Skip to content

⚡ Bolt: Unroll literal writing loop for performance #238

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
404Setup merged 1 commit into from
Feb 19, 2026
Merged

⚡ Bolt: Unroll literal writing loop for performance #238

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
20 changes: 20 additions & 0 deletions src/compress/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1145,6 +1145,18 @@ impl Compressor {
// We add 16 bytes margin for the last flush (8 bytes) and safety.
if bs.out_idx + 16 + (seq.litrunlen as usize * 2) < bs.output.len() {
let mut lit_remain = seq.litrunlen as usize;
while lit_remain >= 4 {
// SAFETY: We verified sufficient buffer space above.
// `write_literals_2` writes at most 30 bits and may flush 4 bytes.
// We do this twice, so max 60 bits + flush overhead.
// The loop precondition checks for space.
unsafe {
self.write_literals_2(bs, input[in_pos], input[in_pos + 1]);
self.write_literals_2(bs, input[in_pos + 2], input[in_pos + 3]);
}
in_pos += 4;
lit_remain -= 4;
}
while lit_remain >= 2 {
// SAFETY: We verified sufficient buffer space above.
// `write_literals_2` writes at most 30 bits and may flush 4 bytes.
Expand Down Expand Up @@ -1355,6 +1367,14 @@ impl Compressor {
if seq.litrunlen > 0 {
if bs.out_idx + 16 + (seq.litrunlen as usize * 2) < bs.output.len() {
let mut lit_remain = seq.litrunlen as usize;
while lit_remain >= 4 {
unsafe {
self.write_literals_2(bs, input[in_pos], input[in_pos + 1]);
self.write_literals_2(bs, input[in_pos + 2], input[in_pos + 3]);
}
in_pos += 4;
lit_remain -= 4;
}
while lit_remain >= 2 {
unsafe { self.write_literals_2(bs, input[in_pos], input[in_pos + 1]) };
in_pos += 2;
Expand Down