|
From: | Julien Bect |
Subject: | Re: For loop benchmarks between Octave versions |
Date: | Tue, 17 Jun 2014 18:00:05 +0200 |
User-agent: | Mozilla/5.0 (X11; Linux i686; rv:24.0) Gecko/20100101 Thunderbird/24.2.0 |
Le 17/06/2014 17:41, John W. Eaton a écrit :
On 06/17/2014 11:11 AM, Julien Bect wrote:The runtime dropped to 2.16 when I added inline.Consistently?
Well, as far as I can tell from the small number of tests that I did : yes, consistently.
Could you look at the generated assembly code and see whether the "inline" keyword is really needed to get this trivial function to be inlined?
I'm afraid that's beyond my skills.
What compiler optimization flags are you using?
I use gcc 4.7.3 i686-linux-gnu on Ubuntu 13.04 I have configured with --enable-jit --disable-doc and didn't change any other option.
[Prev in Thread] | Current Thread | [Next in Thread] |