Re: [eigen] Eigen 3 is extremely slow |

[ Thread Index | Date Index | More lists.tuxfamily.org/eigen Archives ]

*To*: eigen@xxxxxxxxxxxxxxxxxxx*Subject*: Re: [eigen] Eigen 3 is extremely slow*From*: Hari Sundar <hsundar@xxxxxxxxx>*Date*: Mon, 14 Mar 2011 10:00:34 -0400*Dkim-signature*: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:mime-version:in-reply-to:references:date :message-id:subject:from:to:content-type; bh=k+dW+JfSH+BnbDexSitgvoo0EUNE6MoHz6LOCVj4nNM=; b=aJOxF1lvqGFYnULrS9WGAHP777kKCMWe4VKAKnY4td1p9IOvdjusyaiYAFzfw6R4Uu S4bzH7i5gpU31BNchBByFhhcKSR2U0mYmhb10qv5noGg6erg2D2Gex+ShPIntSURky8f Ohz24+2qSEc7qtftPZxkMgyAQCxwk80pUvo2U=*Domainkey-signature*: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :content-type; b=vHjcAHPVliMD5tgQH2oitPyqksZTO1KDSaekIxv/Natk/0MqA4No//bhnwXAj9iduC B6UdzXq7pcQBjIsUumfi6Vdm/nUGyVN3gmEmRmGOuEmbsKUDoDKc4sSDEb+RorRv4ajS LDCpp8Vp747t9YDmoJlFTey3lEKhRSzk20Xrk=

I am working on creating a simple example that I can share. I'll send you both the eigen and blitz versions. (if I am able to re-create the slowdown with the simple example)

thanks,

Hari

On Mon, Mar 14, 2011 at 9:57 AM, Benoit Jacob <jacob.benoit.1@xxxxxxxxx> wrote:

2011/3/14 Hari Sundar <hsundar@xxxxxxxxx>:

> I do not have any NaN values and I have checked it for my sample dataset.As Hauke said, the only useful thing would be a compilable test case.

>

> I did some additional tests and it appears that it is not the matrix

> multiplication itself that is slow, but it appears to be some really bad

> case of cache usage.

>

> Once projected, I use the points to sample from an Array (512x512). If I do

> not use Eigen for this array (instead using a std. C array), then my

> performance is much better.

>

> I hope that is able to point you in the right direction.

Benoit

>

> I was using an ArrayXXf (also tried MatrixXf) to store the array.

>

> best,

> Hari

>

> On Mon, Mar 14, 2011 at 9:18 AM, Benoit Jacob <jacob.benoit.1@xxxxxxxxx>

> wrote:

>>

>> 2011/3/14 Gael Guennebaud <gael.guennebaud@xxxxxxxxx>:

>> > On Mon, Mar 14, 2011 at 12:48 AM, Hari Sundar <hsundar@xxxxxxxxx> wrote:

>> >> For example a simple 4x4 * 4*1 multiplication takes around 0.5msec.

>> >

>> > hm, that's indeed extremely slow... which compiler? flags?

>> >

>> > for instance here a 4x4 * 4x1 product takes less than 4e-6msec, and

>> > even in debug mode (-g2) with a very old gcc 3.4 it takes less than

>> > 0.0008 msec...

>>

>> If his matrix has NaN values, that could explain another 500x factor.

>>

>> Benoit

>>

>> >

>> > gael

>> >

>> >

>> >

>>

>>

>

>

>

> --

> +1 (215) 501 7752

> https://www.rad.upenn.edu/sbia/hsundar/

>

--

+1 (215) 501 7752

https://www.rad.upenn.edu/sbia/hsundar/

**Follow-Ups**:**Re: [eigen] Eigen 3 is extremely slow***From:*Gael Guennebaud

**References**:**[eigen] Eigen 3 is extremely slow***From:*Hari Sundar

**Re: [eigen] Eigen 3 is extremely slow***From:*Gael Guennebaud

**Re: [eigen] Eigen 3 is extremely slow***From:*Benoit Jacob

**Re: [eigen] Eigen 3 is extremely slow***From:*Hari Sundar

**Re: [eigen] Eigen 3 is extremely slow***From:*Benoit Jacob

**Messages sorted by:**[ date | thread ]- Prev by Date:
**Re: [eigen] Eigen 3 is extremely slow** - Next by Date:
**Re: [eigen] Eigen 3 is extremely slow** - Previous by thread:
**Re: [eigen] Eigen 3 is extremely slow** - Next by thread:
**Re: [eigen] Eigen 3 is extremely slow**

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