Improving Stream Buffer Management of Stream-Based Computing Platform on GPU

GPU-based computing has become one of the popular high performance computing fields. The field is called GPGPU. This paper presents design and implementation of a uniform GPGPU application that is optimized for both the legacy and the recent GPU architectures. As a typical example of such the GPGPU application, this paper will discuss the uniform implementation of the Caravela platform, with focusing on the method of handling stream buffers. Two methods for handling streams have been proposed and implemented. To verify the effectiveness of the proposed methods, evaluation has been done using applications.