IEEE Computer Architecture Letters

IEEE Computer Architecture Letters (CAL) is a semi-annual forum for fast publication of new, high-quality ideas in the form of short, critically refereed, technical papers. Submissions are welcomed on any topic in computer architecture.


From the July-December 2014 issue

On Optimal Kernel Size for Integrated CPU-GPUs — A Case Study

By Vivek S. Nandakumar and Malgorzata Marek-Sadowska

Featured article thumbnail imageIntegrated CPU-GPU architectures with a fully addressable shared memory completely eliminate any CPU-GPU data transfer overhead. Since such architectures are relatively new, it is unclear what level of interaction between the CPU and GPU attains the best energy efficiency. Too coarse grained or larger kernels with fairly low CPU — GPU interaction could cause poor utilization of the shared resources while too fine grained kernels could cause frequent interrupts of GPU computation and performance degradation. Also larger kernels require larger shared resources causing increase in area and parasitics which affect the latency sensitive CPU cores. In this paper, we show the effect of granularity on the overall system's energy efficiency using a synthetic workload. We describe how our framework models a truly unified shared memory in integrated architectures with frequent CPU — GPU communication.

download PDF View the PDF of this article      csdl View this issue in the digital library


Editorials and Announcements

Editorials


Reviewers List


Annual Index


Access recently published CAL articles

RSS Subscribe to the RSS feed of latest CAL content added to the digital library.


Mail Sign up for the Transactions Connection newsletter.


CAL Flyer thumbnail

Download the IEEE Computer Architecture Letters flyer (PDF)