In recent years, a variety of concerns in power and thermal issues, instruction-level parallelism (ILP) limits, and design complexity, among others have driven a shift in focus away from uniprocessor systems to chip multiprocessor (CMP) designs, or more popularly known as multicores or manycores. Multicores alleviate many of these uniprocessor scaling barriers, by providing the potential for throughput and performance gains with an increasing number of on-chip processor cores. Ideally, designers would like to extract performance and throughput gains proportional to the increase in cores at each technology generation. Unfortunately, a major challenge, the programming wall, needs to be addressed before such a goal can be achieved. It is the obstacle for programmers to efficiently parallelize their applications to exploit multicores and manycores. The goal of the Center for Manycore Programming at Seoul National University is to overcome the multicore/manycore programming wall by means of compilers and programming tools, runtime systems, and architectures. The center is funded by the Creative Research Initiative program of the Korean Ministry of Science and ICT.
The Multicore Computing Research Laboratory is a research group in the Department of Computer Science and Engineering and is the core of the Center for Manycore Programming. The group is dedicated to exploring technologies for high-performance multicore computing systems and embedded systems. In general, our research focuses on compiler, architecture, and operating system techniques at various levels taking a pragmatic approach.
Our most recent research focuses on the following: