An efficient scheduler of RTOS for multi/many-core system

Article history: Available online xxxx a b s t r a c t Recently there is a trend to broaden the usage of lower-power embedded media processor core to build the future high-end computing machine or the supercomputer. However the embedded solution also faces the operating system (OS) design challenge which the thread invoking overhead is higher for fine-grained scientific workload, the message passing among threads is not managed efficiently enough and the OS does not provide convenient enough service for parallel programming. This paper presents a scheduler of master-slave real-time operating system (RTOS) to manage the thread running for the distributed multi/ many-core system without shared memories. The proposed scheduler exploits the data-driven feature of scientific workloads to reduce the thread invoking overhead. And it also defines two protocols: (1) one is between the RTOS and application program, which is used to reduce the burden of parallel programming for the programmer; (2) another one is between the RTOS and networks-on-chip, which is used to manage the message passing among threads efficiently. The experimental results show that the proposed scheduler can manage the thread running with lower overhead and less storage requirement, thereby, improving the multi/many-core system performance. One of the major challenges faced by high-end computing machines or supercomputers, which are widely used in scientific computing area, is energy and power efficiency [1]. A promising way to improve the energy and power efficiency is to employ the low-power architecture developed for multi-core media processor in embedded computing [2]. In order to benefit from the rapidly improving computing power delivered by multi/many-core processors, software development plays an important role. Particularly, an efficient operating system (OS) is the key to better utilize the computing power provided by multi/many-core systems. Our study is focused on the distributed multi/many-core system without shared memory and networks-on-chip (NoC) provides the on-chip interconnection architecture for such a system. The corresponding OS shall provide service for application programs, schedule the execution resources for efficient task/thread running and manage the message passing among processors with lower overhead on the interconnection network, as shown in Fig. 1. The major challenges [3] faced by designing such type of OS include: (1) the OS shall provide efficient protocol for the application programs to facilitate parallel programming and OS task/thread scheduling or invoking; (2) if the dynamic scheduling method is applied in parallel programming , the scheduling algorithm of OS shall guarantee …