Re: [eigen] Optimization advice for a specific expression
• To: eigen <eigen@xxxxxxxxxxxxxxxxxxx>
• Subject: Re: [eigen] Optimization advice for a specific expression
• From: Gael Guennebaud <gael.guennebaud@xxxxxxxxx>
• Date: Fri, 5 Feb 2016 23:07:33 +0100
• Dkim-signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:in-reply-to:references:from:date:message-id:subject:to :content-type; bh=pZQvnIXdoZHsYT7GOrXxD1cbcy+pCFwrp3XRl7H2mLY=; b=UU5cHu6hkTcX7I6e48dGp9bXOPZ7fASid2Rg7zlYFuwRSLykVt1O+2oZjwAxY6DFlH IsOzy38E9Br3P27k1aY2I++PeGCuqCK3FRBH5G72F5TRmSGIO3ejAlqjGJom+rjaPyaN 8wbowXRyRUUlDj+jRdHK44N+qEdoCujuFu8ABnvz8VM8HB4EFlcGCx7ls1Wl/g5RNk2n C1V6hKEgfARhtlMwnm3llE85n8D+dd+9v7i5elmJtzEGBP/YXKELbIq3dUWmdXEWfq4m nwpPg0svgV/S23WiiZdKQV7MOCO8AI+SCMEVdlnbRW53KmotXo3mlzOf7v0ycT3IYBpi MpWw==

I don't observe difference between 3.2 and 3.3, and gcc/clang gives similar results too. Counting the number of flops for the determinant + the two matrix products, I measure for the "naive" version, a rate of 8.8GFlops, with is pretty good for such small size computation. The theoretical peak for my computer is 10.4.

gael

On Fri, Feb 5, 2016 at 8:02 PM, Christoph Hertzberg wrote:
On 2016-02-05 17:30, Christoph Hertzberg wrote:
which is not inlined. I was able to fix that by adding lots of
EIGEN_STRONG_INLINE in src/Core/AssignEvaluator.h

@Gael, can you confirm? Or is it better to use EIGEN_ALWAYS_INLINE, here?

Sorry, it seems I was behind with pulling ...
https://bitbucket.org/eigen/eigen/commits/dc19770fa4b0/

@Alberto: Have you tried the very newest version?
http://bitbucket.org/eigen/eigen/get/default.tar..bz2

Christoph

--
Dipl. Inf., Dipl. Math. Christoph Hertzberg

Universität Bremen
FB 3 - Mathematik und Informatik
AG Robotik
Robert-Hooke-Straße 1
28359 Bremen, Germany

Zentrale: +49 421 178 45-6611

Robert-Hooke-Straße 5
28359 Bremen, Germany

Tel.:    +49 421 178 45-4021
Empfang: +49 421 178 45-6600
Fax:     +49 421 178 45-4150
E-Mail:  chtz@xxxxxxxxxxxxxxxxxxxxxxxx

Weitere Informationen: http://www.informatik.uni-bremen.de/robotik

 Mail converted by MHonArc 2.6.19+ http://listengine.tuxfamily.org/