Information Technology Reference
In-Depth Information
Tabl e 1.
Speedup over 3D-wavefront
Video
4-proc. 8-proc. 16-proc. 32-proc. 64-proc.
bus
1.12
1.08
1.08
0.9
1.05
crowdrun
1.52
1.57
1.68
1.43
1.72
duckstakeoff
1.78
1.98
2.31
2.11
2.94
intotree
1.31
1.24
1.19
0.95
1.43
night
1.25
1.24
1.31
1.039
1.105
oldtowncross 1.26
1.16
1.10
0.26
0.93
parkjoy
1.79
1.76
1.87
1.64
2.10
parkrun
1.39
1.26
1.33
1.08
1.12
shields
1.07
1.19
1.27
0.95
0.93
shuttlestart
1.12
1.06
0.94
0.72
0.68
stockholm
1.26
1.25
1.29
0.99
0.90
Maximum
1.79
1.98
2.31
2.11
2.94
Minimum
1.07
1.06
0.94
0.26
0.68
Average
1.35
1.23
1.39
1.10
1.35
6Con lu on
In this paper, we present an ecient method for cache aware scheduling to
improve the speedup of a H.264 decode algorithm in a multi-processor setting.
We believe that a cache-oblivious strategy can benefit tremendously using the
proposed modifications. We are currently addressing ways to extend similar ideas
to the other compression standards.
References
1. Richardson, I.E.: The H. 264 advanced video compression standard. Wiley (2011)
2. Azevedo, A., Juurlink, B., Meenderinck, C., Terechko, A., Hoogerbrugge, J., Alvarez,
M., Ramirez, A., Valero, M.: A highly scalable parallel implementation of H.264.
In: Stenstrom, P. (ed.) Transactions on HiPEAC IV. LNCS, vol. 6760, pp. 111-134.
Springer, Heidelberg (2011)
3. Juurlink, B., et al.: Scalable Parallel Programming Applied to H.264/AVC Decoding.
Springer (2012) ISBN: 978-1-4614-2229-7
4. H.264/AVC JM software,
http://iphome.hhi.de/suehring/tml/
5. Guan, N., et al.: Cache-aware scheduling and analysis for multicores. In: Proceedings
of EMSOFT 2009, pp. 245-254 (2009)
6. Wiegand, T., et al.: Overview of the H. 264/AVC video coding standard. IEEE
Transactions on Circuits and Systems for Video Technology 13(7), 560-576 (2003)
