Title
Zero-copy I/O processing for low-latency GPU computing
Abstract
Cyber-physical systems (CPS) aim to monitor and control complex real-world phenomena where the computational cost and real-time constraints could be a major challenge. Many-core hardware accelerators such as graphics processing units (GPUs) promise to enhancing computation, leveraging the data parallelism often found in real-world scenarios of CPS, but performance is limited by the overhead of the data transfer between the host and the device memory. For example, plasma control in the HBT-EP Tokamak device at Columbia University [11, 18] must execute the control algorithm in a few microseconds, but may take tens of microseconds to copy the data set between the host and the device memory. This paper presents a zero-copy I/O processing scheme that maps the I/O address space of the system to the virtual address space of the compute device, allowing sensors and actuators to transfer data to and from the compute device directly. Experiments using the plasma control system show a 33% reduction in computational cost, and microbenchmarks with more generic matrix operations show a 34% reduction, while in both cases, effective data throughput remains at least as good as the current best performers.
Year
DOI
Venue
2013
10.1145/2502524.2502548
Cyber-Physical Systems
Keywords
Field
DocType
low-latency gpu computing,computational cost,plasma control,o address space,cyber-physical system,plasma control system,hbt-ep tokamak device,control algorithm,effective data throughput,device memory,o processing,data transfer,authentication,virtual address space,sensors,vehicular networks,plasmas,cyber physical systems,control systems,data parallelism,real time systems,security,actuators
Address space,CUDA,Computer science,Parallel computing,Virtual address space,Input/output,Data parallelism,General-purpose computing on graphics processing units,Latency (engineering),Zero-copy
Conference
ISSN
Citations 
PageRank 
2375-8317
22
0.95
References 
Authors
13
3
Name
Order
Citations
PageRank
Shinpei Kato195162.18
Jason Aumiller2251.35
Scott Brandt3644.67