Learn More
DARPA's Ubiquitous High-Performance Computing (UHPC) program asked researchers to develop computing systems capable of achieving energy efficiencies of 50 GOPS/Watt, assuming 2018-era fabrication technologies. This paper describes Runnemede, the research architecture developed by the Intel-led UHPC team. Runnemede is being developed through a co-design(More)
— Future many-core platforms present scalability challenges to VMMs, including the need to efficiently utilize their processor and cache resources. Focusing on platform virtualization, we address these challenges by devising new virtualization methods that not only work with, but actually exploit the many-core nature of future processors. Specifically, we(More)
— We describe and evaluate a quad 100T ethernet network interface built using an Intel IXP1200 network processor on a commonly available Radisys ENP2505 PCI board. The network interface exports a raw ethernet interface either to the host kernel or to user level for cluster computing applications. We describe the firmware architecture and internal design(More)
To my sister Susan Nadine Grizzard – A truly amazing person ACKNOWLEDGEMENTS Most importantly, I would like to deeply thank my advisor Dr. Henry Owen for his unparalleled brilliance and excellent guidance. His continuous encouragement and unwavering support have been of tremendous value to me. I would also like to thank my committee members Dr. Their(More)
New applications like remote surveillance and online environmental or traffic monitoring are making it increasingly important to provide flexible and protected access to remote video sensor devices. Current systems use application-level codes like web-based solutions to provide such access. This requires adherence to user-level APIs provided by such(More)
Virtualizing I/O subsystems and peripheral devices is an integral part of system virtualization. This paper advocates the notion of self-virtualized I/O (S-VIO). Specifically, it proposes a hypervisor-level abstraction that permits guest virtual machines to efficiently exploit the multi-core nature of future machines when interacting with virtualized I/O.(More)
The virtualization of I/O devices is an integral part of system virtualization. This includes both virtualizing the physical devices and managing them across multiple guest virtual machines (VMs) or domains running on top of a virtual machine monitor (VMM) or hypervisor (HV). This paper presents the notion of self-virtualizing devices, where for higher end,(More)
The Open Community Runtime (OCR) is a new runtime system designed to meet the needs of extreme-scale computing. While there is growing support for the idea that future execution models will be based on dynamic tasks, there is little agreement on what else should be included. OCR minimally adds events for synchronization and relocatable data-blocks for data(More)
Date Approved by Chairman Dedication To Karen, Mum, Dad and Midnight iii Acknowledgments I'd like to thank my advisor, Karsten Schwan, for providing me with support, advice and the freedom to pursue exciting and challenging work. I'd also like to acknowledge my committee members, most of whom I've had the pleasure of working with at some point during my(More)