On 10/26/2021 6:39 PM, Tom Lane wrote:
Japin Li writes:
Why do we need likely() for base=10, however, base=16 and base=8 don't need?
Yeah, I was a little unconvinced about that too. I concur with writing
it as an if/else chain instead of a switch, but I'm not sure that likely()
adds anything
[PATCH v2] src/port/snprintf.c: Optimize the common base=10 case in fmtint
fmtint() turns an integer into a string for a given base, and to do this
it does a divide/modulo operation iteratively.
The only possible base values are 8, 10 and 16
On just about any CPU, divides are a pretty expensive
On 10/26/2021 10:51 AM, Tom Lane wrote:
Mark Dilger writes:
It appears fmtint only has three options for base, being 10, 16, and 8. Have you
profiled with either of the others special cased as well? I don't see much use in
optimizing for octal, but hexadecimal is used quite a bit in wal wit
src/port/snprintf.c: Optimize the common base=10 case in fmtint
fmtint() turns an integer into a string for a given base, and to do this
it does a divide/modulo operation iteratively.
On just about any CPU, divides are a pretty expensive operation, generally
10x to 20x or more expensive than add
