HD video applications can be represented with multiple tasks consisting of tightly coupled multiple threads. Each task requires\r\nmassive computation, and their communication can be categorized as asynchronous distributed small data and large streaming\r\ndata transfers. In this paper, we propose a high performance programmable video platform that consists of four processing\r\nelement (PE) clusters. Each PE cluster runs a task in the video application with RISC cores, a hardware operating system kernel\r\n(HOSK), and task-specific accelerators. PE clusters are connected with two separate point-to-point networks: one for asynchronous\r\ndistributed controls and the other for heavy streaming data transfers among the tasks. Furthermore, we developed an application\r\nmapping framework, with which parallel executable codes can be obtained from a manually developed SystemC model of the\r\ntarget application without knowing the detailed architecture of the video platform. To show the effectivity of the platform and\r\nits mapping framework, we also present mapping results for an H.264/AVC 720p decoder/encoder and a VC-1 720p decoder with\r\n30 fps, assuming that the platform operates at 200MHz.
Loading....