high performance computing on graphics processing units: hgpu.org

In recent years, modern graphics processing units have been widely adopted in high performance computing areas to solve large scale computation problems. The leading GPU manufacturers Nvidia and AMD have introduced series of products to the market. While sharing many similar design concepts, GPUs from these two manufacturers differ in several aspects on processor cores and the memory subsystem. In this work, we conduct a comprehensive study to characterize and compare the architectural features of Nvidia’s Fermi and AMD’s Cypress GPUs. We first investigate the performance and power consumptions of an AMD Cypress GPU. By employing a rigorous statistical model to analyze the execution behaviors of representative general-purpose GPU (GPGPU) applications, we conduct insightful investigations on the target GPU architecture. Our results demonstrate that the GPU execution throughput and the power dissipation are dependent on different architectural variables. Furthermore, we design a set of micro-benchmarks to study the power consumption features of different function units on the GPU. Based on those results, we derive instructive principles that can guide the design of power-efficient high performance computing systems. We then make the concentration shift to the Nvidia Fermi GPU and compare it with the product from AMD. Our results indicate that these two products have diverse advantages that are reflected in their performance for different sets of applications. In addition, we also compare the energy efficiencies of these two platforms since power/energy consumption is a major concern in the high performance computing system.