<div>Hi all,<br><br>I apologize to not keep you up to date to what is going
on with my project. Portavales has worked in a desk behind me and when
we go to take coffee we talk about the project. Second I didn't know we
have to discuss weekly, it was my fault. I should have read the rules.
Sorry.<br>
<br>At the first month, I studied the code and the Theora Beta
implementation. The code is completely different from Alpha and I have
to be familiarized with the code.<br></div><div>After that I started doing tests with OpenMP.<br>
<br></div><div>One first test was 40% faster, but unfortunately it did not decode the frame correctly, three quarters was green.<br><br></div><div> I have one implementation decoding the Y, Cb and Cr planes in parallel. The OpenMP implementation was about 5% faster. Not
worthless, since it does not require any great modifications. <br>
<br>I looked at Ralph's implementation and merged it to the current.
The speed up was about 10% but the code have to be modified in many
places.<br clear="all">
<br></div>Extract parallelism from the current implementation is very
difficult. Coarse grain functions are the best functions to be
parallelize to become the overhead worthwhile, but the current
implementation has one, at most two. The parts that I suggested in my
initial plan are fine grain functions, they spend a lot of cpu time but
they are called too many times. The time spent to create and synchronize
threads is greater than the speed up gains. We need functions that are
called a few times and spend many cpu time. Also data dependency should
be the lowest as possible.<br>
<br>According to the model that i did (<a href="http://lampiao.lsc.ic.unicamp.br/%7Epiga/gsoc_2008/implementation.pdf" target="_blank">http://lampiao.lsc.ic.unicamp.br/~piga/gsoc_2008/implementation.pdf</a>)
the decoding time should be reduced in 33%, but it was just 10% for pthread an 5% for openMP.<br><br>I used a video with 1440x1080. The pthread implementation has 3 threads
and the OpenMP was executed with the environment variable
OMP_NUM_THREADS=3. The results are:<br>
<br> Real(s) User(s) System(s) Speed up(%)<br>OpenMP 25.2 29.2 1.8 4<br>PThread 23.8 28.3 1.0 10<br>
Current 26.2 26.0 0.3 0<br><br>I used an Intel(R) Core(TM)2 Quad CPU with 2.4GHz and RAM of 4GB. The video has 85 seconds.<br>These
two implementations decode the Y, Cb and Cr planes in parallel, that
is why I am using OMP_NUM_THREADS=3 and the upper bound gain is 33%,
that is, let To be the time spent in decoding a video with the current
implementation. Let T1 be a video decoded with the parallel
implementation. T1 should be at most 0.66To.<div><br>
<br>I will use the
pthread implementation to try a pipelined version and see if we obtain
more gains.<br></div>These version will run the functions (c_dec_dc_unpredict_mcu_plane + oc_dec_frags_recon_mcu_plane) and<br>(oc_state_loop_filter_frag_rows
+ oc_state_borders_fill_rows) in parallel. The upper bound for the gain
is 60%, that is, let T2 be a video decoded with the pipelined
implementation. T2 should be at most 0.4To.<br>
<br>Here is the branch for the OpenMP implementation: <a href="http://svn.xiph.org/branches/theora_multithread_decode_omp/" target="_blank">http://svn.xiph.org/branches/theora_multithread_decode_omp/</a><br>Here is the branch for the PThread implementation: <a href="http://svn.xiph.org/branches/theora_multithread_decode_pthread/" target="_blank">http://svn.xiph.org/branches/theora_multithread_decode_pthread/</a><br>
<br><br><br><br><br>Again, sorry about the long time without any feedback.<br clear="all"><br>-- <br>Leonardo de Paula Rosa Piga<br>Undergraduate Computer Engineering Student <br>LSC - IC - UNICAMP<br><a href="http://lampiao.lsc.ic.unicamp.br/%7Epiga" target="_blank">http://lampiao.lsc.ic.unicamp.br/~piga</a>