2015 · 30 citations · 34 references
EngineeringComputer EngineeringElectrical EngineeringInterconnection NetworksPhotonicsSystem-on-chip DesignCachingGraphics Processing UnitsInterconnect ArchitectureMemory Hierarchy DesignNetwork-on-chip DesignSilicon PhotonicsBandwidthCache DesignCache Hierarchy DesignMany-core ArchitectureMemory BandwidthNetwork-on-chipNetwork-on-chip ArchitecturesScalability
Silicon-photonic link technology promises to satisfy the growing need for high bandwidth, low-latency and energy-efficient network-on-chip (NoC) architectures. While silicon-photonic NoC designs have been extensively studied for future many-core systems, their use in massively-threaded GPUs has received little attention to date. In this paper, we first analyze an electrical NoC which connects different cache levels (L1 to L2) in a contemporary GPU memory hierarchy. Evaluating workloads from the AMD SDK run on the Multi2sim GPU simulator finds that, apart from limits in memory bandwidth, an electrical NoC can significantly hamper performance and impede scalability, especially as the number of compute units grows in future GPU systems.
34
Analyzing CUDA workloads using a detailed GPU simulator
Ali Bakhoda, George L. Yuan, Wilson Wai Lun Fung et al. · 2009 · 1.7K citations
NVIDIA Tesla: A Unified Graphics and Computing Architecture
Erik Lindholm, John Nickolls, Stuart F. Oberman et al. · IEEE Micro · 2008 · 1.3K citations
William J. Dally · IEEE Transactions on Parallel and Distributed Systems · 1992 · 1.2K citations
Willaim J. Dally · 2002 · 778 citations
On-Chip Interconnection Architecture of the Tile Processor
David Wentzlaff, Patrick Griffin, Henry Hoffmann et al. · IEEE Micro · 2007 · 682 citations