From: | Alexander Kuzmenkov <a(dot)kuzmenkov(at)postgrespro(dot)ru> |
---|---|
To: | Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>, pgsql-hackers(at)lists(dot)postgresql(dot)org |
Subject: | Re: Performance improvements for src/port/snprintf.c |
Date: | 2018-09-07 18:53:27 |
Message-ID: | f5dd41da-911c-fd97-1b78-e0f8c0141897@postgrespro.ru |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Thread: | |
Lists: | pgsql-hackers |
I benchmarked this, using your testbed and comparing to libc sprintf
(Ubuntu GLIBC 2.27-0ubuntu3) and another implementation I know [1], all
compiled with gcc 5.4.0 with -O2. I used bigger decimals in one of the
formats, but otherwise they are the same as yours. Here is the table of
conversion time relative to libc:
format pg stb
("%2$.*3$f %1$d\n", 42, 123.456, 2) 1.03 -
("%.*g", 15, 123.456) 1.08 0.31
("%10d", 15) 0.63 0.52
("%s", "012345678900123456789001234 2.06 6.20
("%d 012345678900123456789001234567 2.03 1.81
("%1$d 0123456789001234567890012345 1.34 -
("%d %d", 845879348, 994502893) 1.97 0.59
Surprisingly, our implementation is twice faster than libc on "%10d".
Stb is faster than we are with floats, but it uses its own algorithm for
that. It is also faster with decimals, probably because it uses a
two-digit lookup table, not one-digit like we do. Unfortunately it
doesn't support dollars.
1. https://github.com/nothings/stb/blob/master/stb_sprintf.h
--
Alexander Kuzmenkov
Postgres Professional: http://www.postgrespro.com
The Russian Postgres Company
From | Date | Subject | |
---|---|---|---|
Next Message | Bruce Momjian | 2018-09-07 19:09:37 | Re: A strange GiST error message or fillfactor of GiST build |
Previous Message | Michael Paquier | 2018-09-07 18:04:33 | Re: Incorrect error handling for two-phase state files resulting in data loss |