[prev in list] [next in list] [prev in thread] [next in thread]
List: kde-devel
Subject: GPU Implementation of image processing algorithms
From: kunal ghosh <kunal.t2 () gmail ! com>
Date: 2010-04-17 15:52:56
Message-ID: j2m6ee952ce1004170850p30717a8az868de684a3d3ab3d () mail ! gmail ! com
[Download RAW message or body]
[Attachment #2 (multipart/alternative)]
Hi,
I am implementing the face recognition algorithm for digikam, and wanted to
use GPGPU <http://en.wikipedia.org/wiki/GPGPU> frameworks for the same. But
was not able to decide which framework to use
OpenCL<http://en.wikipedia.org/wiki/OpenCL>or
CUDA <http://en.wikipedia.org/wiki/CUDA> (C for CUDA specifically).
PS: I am willingly not including any more information about either of the
above frameworks to attract unbiased opinions.
Also, i could code part that would execute on the GPU in python , shortening
the development cycle. Good python bindings exist for either GPU programming
frameworks. Py[CUDA,OpenCL] are the bindings.
Python functions are easily callable from within C/C++ code as demonstrated
by Link 1 <http://docs.python.org/release/2.5.2/ext/callingPython.html>
Link2 <http://www.codeproject.com/KB/cpp/embedpython_1.aspx> and
Link3<http://www.linuxjournal.com/article/8497>
so, is it fine if the algorithms are implemented in python and then called
from within digikam.
all suggestions , comments welcome.
--
regards
-------
Kunal Ghosh
Dept of Computer Sc. & Engineering.
Sir MVIT
Bangalore,India
Quote:
"Ignorance is not a sin, the persistence of ignorance is"
--
"If you find a task difficult today, you'll find it difficult 10yrs later
too !"
-----
"Failing to Plan is Planning to Fail"
Blog:kunalghosh.wordpress.com
Website:www.kunalghosh.net46.net
V-card:http://tinyurl.com/86qjyk
[Attachment #5 (text/html)]
Hi,<br>I am implementing the face recognition algorithm for digikam, and wanted to \
use <a href="http://en.wikipedia.org/wiki/GPGPU">GPGPU</a> frameworks for the same. \
But<br>was not able to decide which framework to use <a \
href="http://en.wikipedia.org/wiki/OpenCL">OpenCL</a> or <a \
href="http://en.wikipedia.org/wiki/CUDA">CUDA</a> (C for CUDA specifically).<br> \
<br>PS: I am willingly not including any more information about either of the above \
frameworks to attract unbiased opinions.<br><br>Also, i could code part that would \
execute on the GPU in python , shortening the development cycle. Good python bindings \
exist for either GPU programming frameworks. Py[CUDA,OpenCL] are the bindings.<br> \
<br>Python functions are easily callable from within C/C++ code as demonstrated by <a \
href="http://docs.python.org/release/2.5.2/ext/callingPython.html">Link 1</a> <a \
href="http://www.codeproject.com/KB/cpp/embedpython_1.aspx">Link2</a> and <a \
href="http://www.linuxjournal.com/article/8497">Link3</a><br> so, is it fine if the \
algorithms are implemented in python and then called from within digikam.<br><br>all \
suggestions , comments welcome.<br><br>-- <br>regards<br>-------<br>Kunal \
Ghosh<br>Dept of Computer Sc. & Engineering.<br> Sir \
MVIT<br>Bangalore,India<br><br>Quote:<br>"Ignorance is not a sin, the \
persistence of ignorance is"<br>
--<br>"If you find a task difficult today, you'll find it difficult 10yrs \
later too !"<br>-----<br>"Failing to Plan is Planning to \
Fail"<br><br>Blog:<a href="http://kunalghosh.wordpress.com" \
target="_blank">kunalghosh.wordpress.com</a><br>
Website:<a href="http://www.kunalghosh.net46.net" \
target="_blank">www.kunalghosh.net46.net</a><br>V-card:<a \
href="http://tinyurl.com/86qjyk" \
target="_blank">http://tinyurl.com/86qjyk</a><br><br>
>> Visit http://mail.kde.org/mailman/listinfo/kde-devel#unsub to unsubscribe <<
[prev in list] [next in list] [prev in thread] [next in thread]
Configure |
About |
News |
Add a list |
Sponsored by KoreLogic