graphical blog 2

I just discovered, searching for the exact Chinese translation for the word “paddy field”, than nor my french=>chinese electronic dictionary (我爱法语(I love french) from Stardict) nor Wikipedia has a Chinese translation for this word. Even the Japanese that use in great part, Han Chinese characters (they call than 漢字 kanji meaning Han character, with the same writing than in old Chinese still in use in Taiwan/Hong-Kong/Macao/Singapour). But the link to Japanese is 田 (tián = field in Chinese). Something goes wrong with what feed most of Chinese and Japanese people.
In fact there are two translation :
* 稻田 dàotián, literally “rice field” (I just learned this form of rice character, there are several around this meaning)
* 水田 shuǐtián, literally “water field”, because paddy fields are often full of water.

Kyoto street after photography (reframed)
technics : acrylics

Il y a également une version en français de cet article
Most of today computer has got several core in their CPU, today I wanted to accelerate some hard computing tasks that are done in a monothread, by dispatching them on 4core computer (my atom330 64bits ultra-low voltage and low-cost deskstation has 4 core and several servers have 2 to 8 cores).

I remember the old day of funny coding with BeOS on BeBox first two-CPU personal computer. I thought it could be cool and fun to reuse those technics on today computers.

I was astonished by the lake of semaphore management on Bash and other shell. Then I written these POSIX atomic semaphore API binding to be able to use more resources in parallel. This is a quick’n'dirty coding, without comments, with commented printf, without return code testing, but working enough for simple use. It only manage named semaphores (Linux-2.6 minimum), I will try to add more functions or aggregate them in a single command later.

You can download sema4shell (sema(phore/ for) shell) here. (updated to 0.3, march, 17 2009)
You can read the included README, included example sample.sh and the sem_overview man page to understand the POSIX implementation.

Il y a également une version en français de cet article
As MyPaint(painting application), Pencil (animation application) and Sakura (light, GTK tabbed terminal) are missing on Ubuntu 9.04 (test version) and thant only this version can boot in 64 bits on my Atom 330, I’ve installed from sources these three great pieces of software. For older Ubuntu version (32 or 64bits), GetDeb contain packages for them (MyPaint and Pencil)

Deb package I generated for ubunutu-9.04-alpha6 (amd64/x86_64), Pencil is on only a binary, no package for mypaint 0.7.0:
http://popolon.online.fr/deb/jaunty-amd64/
x86 version:
http://popolon.online.fr/deb/jaunty-i386/

Mypaint:
Install dependencies:
sudo apt-get install build-essential g++ scons swig python2.6-dev libglib2.0-dev python-numpy-dev
Get MyPaint sources:
wget http://download.gna.org/mypaint/mypaint-0.6.0.tar.bz2
And compile/install it
tar xf mypaint-0.6.0.tar.bz2 && cd mypaint-0.6.0
# work with all version including
# git version
scons # (scons -j4 to compile using the 4 Atom330 cores in parallel).
sudo scons prefix=/usr install

An entry is added on menu, but there is to search manually its icon.

I just discovered in link on Mypaint site Drawpile another painting tool that allow several painters to work together by network. I don’t why for, but the stylus pressure is not managed on this tool on my computer.

Pencil:
Install dependencies
sudo apt-get install qt4-qmake libqt4-dev libming-dev
Get Pencil sources:
wget http://downloads.sourceforge.net/pencil-planner/pencil-0.4.4b-src.zip
(The SVN version actually krach).
Compile then install :
unzip -x pencil-0.4.4b-src.zip
cd pencil-0.4.4b-source/
qmake
make # (make -j4 to compile using the 4 Atom330 cores in parallel).
cp Pencil /usr/bin
Then add the menu entry by hand (or launch it using terminal) : Pencil

Sakura
sudo apt-get install cmake libgtk2.0-dev libvte-dev
cd /tmp/ wget http://www.pleyades.net/david/projects/sakura/sakura-2.3.3.tar.bz2
In /usr/local
cmake . && sudo make install
Or in /usr
cmake -DCMAKE_INSTALL_PREFIX=/usr . && sudo make install

Cet article existe également en français.
Introduction

I bought a shuttle X27D (330€) that has got a 64 bit compatible, 2 core hyper-threaded (4 core with Linux, 512K cache for each one), ultra-low voltage (8W TDP) Atom 330, the one used in the SGI molecule supercomputer concept (10,000 cores in a rack), sadly, the North bridge has a greater TDP (around 23W) than the CPU. I choose the shuttle, because of the DVI connector. Every Atom 330 motherboards has only VGA and there are problem of detection in VGA between computers and my LCD screen.

As there wasn’t any 64 bit mode Atom test, I do one using Ubuntu. Ubuntu-8.10 liveCD crash at boot on atom 330, but Ubuntu 9.04 alpha works perfectly.

I used two tests, Hardinfo, mono-thread test included in Ubuntu and Blender well known bench using multithreading (4 threads for the 4 cores was used for this test).

Test Hardinfo MONOCORE

* Zlib compression (integers). greater is better

* Fibonacci suite (integers). lower is better

MD5 sum, used for file integrity (integers). greater is better

SHA1 encryption (integers). greater is better

Blowfish encryption (integers). littler is better

There are great difference between 32 bits and other in this test.

3D raytracing (floats). littler is better

The 64 bit mode is better than 32 bit mode for floats
The 32 bit mode is better than 64 bit mode for integers

As all these test are mono-threaded, performance of the CPU should be far better if multi-threaded, as this is the case on lot of application on GNU/Linux today.

Test multicore with Blender rendering
This test uses eofw.org benchmark/

This test uses default Ubuntu or getdeb Blender, these version are not optimised for sse and so…
The atom330 has got : sse sse2 and ssse3 but no sse3 (could need patch for Hackintosh).

As Blender is perfectly multithreaded, it will use multicore. On Turion CPU, Getdeb version of Blender is used. Don’t know if Ubuntu Jaunty version is more optimized ???
Ubuntu 2.46 32bits version is faster than official Blender.org one.

I can see on the window displaying the rendering that the 1024KB cache of Turion help him gain time by compute bigger blocks of the picture. The 512KB caches of Atom330 reduce the sizes of the block and the FPU performances of the CPU is lower than the Turion. The memory management that is externalized on Atom is also a bad point for him. Anyway Atom works really better in 64 bits mode than in 32 bits modes for floating numbers computation. Next generation of Atom including memory management included in CPU this year will probably has better results.