Skip to content

Optimization for eliminating redundant memory operations #281

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

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Optimization for eliminating redundant memory operations #281

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
4 changes: 3 additions & 1 deletion csv-core/src/reader.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -666,7 +666,9 @@ impl Reader {
let mut state = self.dfa_state;
while nin < input.len() && nout < output.len() && nend < ends.len() {
let (s, has_out) = self.dfa.get_output(state, input[nin]);
self.line += (input[nin] == b'\n') as u64;
if input[nin] == b'\n'{
self.line += 1;
}
Comment on lines +669 to +671
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Do you have benchmarks backing this up? I'm a little skeptical that the cost of looking up self.line in order to increment it by zero is higher than the cost of adding a branch in the code path, at least on most modern CPUs where branches do unpleasant things to instruction pipelining.

state = s;
if has_out {
output[nout] = input[nin];
Expand Down