The case for reconfigurable general purpose GPU computing

General purpose graphics processing unit (GPU) computing (GPGPU) has emerged as a new paradigm for programmers to exploit massive amounts of parallelism for relatively low costs. The abundance of GPUs in desktop and mobile computing platforms makes them ideal for accelerating tasks on multiple devices. However, despite the massively parallel architecture, GPUs are limited by the applications that run on them. The generic architecture of a GPU allows it to accelerate a large variety of applications, but none of these applications are capable of exploiting the complete performance capabilities of the GPU. This underutilization results in wastage of resources and power. In this work, we propose to introduce reconfiguration to the GPU architecture in the hopes of being able to tune its architecture to maximize performance for a given application or redistribute resources so as to reduce power consumption