Commit graph

10 commits

Author SHA1 Message Date
Kovid Goyal
e62ec6d540
Throughput improvements when processing large blocks of text
Mostly comes from detecting the case of runs of ASCII printable
characters and using a special fast path for them. Improves benchmarks
as per benchmark.py by 15-30% for text heavy workloads
2026-08-16 17:47:56 +05:30
Kovid Goyal
69025901b3
Dont hardcode /tmp 2026-08-16 17:01:27 +05:30
Kovid Goyal
9ba59a16c1
More benchmark script improvements 2026-08-16 11:59:42 +05:30
Kovid Goyal
f5ae245f65
Switch to perf for profiling from gperftools 2026-08-16 11:24:41 +05:30
Kovid Goyal
a432ef3774
Allow controlling exactly what is benachmarked by benchmark.py 2026-08-16 10:41:30 +05:30
Kovid Goyal
896fc0c36a
Improve benchmark script
It now benchmarks the I/O thread as well for results much closer to what
you get when running in real kitty
2026-08-12 15:37:22 +05:30
Kovid Goyal
7f0b072f0d
autoformat 2026-08-05 05:32:56 +05:30
Kovid Goyal
62580c855b
Make mypy 1.16 happy 2025-05-30 10:06:38 +05:30
Kovid Goyal
a855bcf9dc
... 2024-11-28 22:37:20 +05:30
Kovid Goyal
bacfb436e9
Code to run the benchmark kitten headlessly 2024-11-04 09:10:08 +05:30