Horton

Re: Auto-vectorization speeds up multiplication of large-precision numerics

Tom Lane <tgl@sss.pgh.pa.us>

View thread View on postgr.es
From: Tom Lane <tgl@sss.pgh.pa.us>
To: Amit Khandekar <amitdkhan.pg@gmail.com>
Cc: Peter Eisentraut <peter.eisentraut@2ndquadrant.com>, PostgreSQL Hackers <pgsql-hackers@lists.postgresql.org>
Date: 2020-09-08T13:49:51Z
Lists: pgsql-hackers 
Amit Khandekar <amitdkhan.pg@gmail.com> writes:
> Thanks. I must admit it did not occur to me that I could have very
> well installed clang on my linux machine and tried compiling this
> file, or tested with some older gcc versions. I think I was using gcc
> 8. Do you know what was the gcc compiler version that gave these
> warnings ?

Per the buildfarm's configure logs, prairiedog is using

configure: using compiler=powerpc-apple-darwin8-gcc-4.0.1 (GCC) 4.0.1 (Apple Computer, Inc. build 5341)

IIRC, locust has a newer build number but it's the same underlying gcc
version.

			regards, tom lane

Commits

  1. Use plain memset() in numeric.c, not MemSet and friends.

  2. Frob numeric.c loop so that clang will auto-vectorize it too.

  3. Apply auto-vectorization to the inner loop of numeric multiplication.

  4. Split Makefile symbol CFLAGS_VECTOR into two symbols.