Skip site navigation (1) Skip section navigation (2)

Re: spinlocks on powerpc

From: Peter Eisentraut <peter_e(at)gmx(dot)net>
To: Manabu Ori <manabu(dot)ori(at)gmail(dot)com>
Cc: Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>, Heikki Linnakangas <heikki(dot)linnakangas(at)enterprisedb(dot)com>, Tatsuo Ishii <ishii(at)postgresql(dot)org>, robertmhaas(at)gmail(dot)com, pgsql-hackers(at)postgresql(dot)org
Subject: Re: spinlocks on powerpc
Date: 2011-12-30 16:26:42
Message-ID: (view raw, whole thread or download thread mbox)
Lists: pgsql-hackers
On fre, 2011-12-30 at 14:47 +0900, Manabu Ori wrote:
> If we can decide whether to use the hint operand when we build
> postgres, I think it's better to check if we can compile and run
> a sample code with lwarx hint operand than to refer to some
> arbitrary defines, such as FOO_PPC64 or something.
But you can't be sure that the host you are running this on has the same
capability as the build system.  Packaging systems only classify
architectures on broad categories such as "i386" or "powerpc" or maybe
"powerpc64".  So a package built for "powerpc64" has to run on all
powerpc64 hosts.

Imagine you are using some Pentium instruction and run the program on a
80486.  It's the same architecture as far as kernel, package management,
etc. are concerned, but your program will break.

In response to

pgsql-hackers by date

Next:From: Andrew DunstanDate: 2011-12-30 16:43:05
Subject: Re: spinlocks on powerpc
Previous:From: Tom LaneDate: 2011-12-30 16:23:14
Subject: Re: spinlocks on powerpc

Privacy Policy | About PostgreSQL
Copyright © 1996-2017 The PostgreSQL Global Development Group