Skip to content
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.

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

Use SSE2 in the x86_64 C version of decodeLatin1 #297

Closed
wants to merge 1 commit into from

Conversation

ethercrow
Copy link
Contributor

@ethercrow ethercrow commented Sep 21, 2020

Before (sorry for truncated lines):

benchmarking DecodeASCII/strict decodeLatin1
time                 28.60 ns   (28.53 ns .. 28.67
                     1.000 R²   (1.000 R² .. 1.000
mean                 28.60 ns   (28.50 ns .. 28.69
std dev              324.4 ps   (258.4 ps .. 426.7
variance introduced by outliers: 12% (moderately i

benchmarking DecodeASCII/lazy decodeLatin1
time                 39.73 ns   (39.42 ns .. 40.07
                     1.000 R²   (1.000 R² .. 1.000
mean                 39.56 ns   (39.46 ns .. 39.74
std dev              431.1 ps   (271.5 ps .. 699.6
variance introduced by outliers: 11% (moderately i

After:

benchmarking DecodeASCII/strict decodeLatin1
time                 21.71 ns   (21.67 ns .. 21.77 ns)
                     1.000 R²   (1.000 R² .. 1.000 R²)
mean                 21.70 ns   (21.67 ns .. 21.74 ns)
std dev              114.6 ps   (90.46 ps .. 150.4 ps)

benchmarking DecodeASCII/lazy decodeLatin1
time                 32.80 ns   (32.75 ns .. 32.84 ns)
                     1.000 R²   (1.000 R² .. 1.000 R²)
mean                 32.89 ns   (32.78 ns .. 33.39 ns)
std dev              660.6 ps   (137.1 ps .. 1.483 ns)
variance introduced by outliers: 29% (moderately inflated)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants