North Carolina State University
Given the extraordinary computational power of modern Graphics Processing Units (GPUs), general purpose computation on GPUs (GPGPU) has become an increasingly important platform for high performance computing. To better understand how well the GPU resource has been utilized by application developers and then to facilitate them to develop high performance GPGPU code, the authors conduct an empirical study on GPGPU programs from ten open-source projects. These projects span a wide range of disciplines and many are designed as high performance libraries. Among these projects, they found various performance 'Bugs', i.e., code segments leading to inefficient use of GPU hardware.