Tezin Türü: Yüksek Lisans
Tezin Yürütüldüğü Kurum: Orta Doğu Teknik Üniversitesi, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü, Türkiye
Tezin Onay Tarihi: 2014
Tezin Dili: İngilizce
Öğrenci: Ahmet Umut Gülkök
Danışman: VEYSİ İŞLER
Özet:Temporal coherence is very important for various computational motion picture applications. Animation rendering and video encoding are good examples of these applications. This study proposes an optimization technique using temporal coherence for distributed animation rendering environments so called “Render Farms”. The proposed approach consists of separate procedures for reducing the network communication cost and providing dynamic computational load balancing between render farm worker computers. The network communication cost between the render farm controller and the workers is reduced by compressing the output images with the H.264 video codec which provides significant compression as the coherence between the adjacent frames increases. In addition, computational load balancing is achieved by a cost prediction method based also on temporal coherence. However, these two methods work best with different task distribution schemes. Therefore, these two optimizations are combined with a new task distribution algorithm considering the tradeoffs.