JPL Technical Report Server

Gilgamesh: A Multithreaded Processor-In-Memory Architecture for Petaflops Computing

Show simple item record Sterling, T. L. en_US Zima, H. P. en_US 2004-09-17T07:07:54Z 2004-09-17T07:07:54Z 2002-11-16 en_US
dc.identifier.citation Supercomputing 2002 en_US
dc.identifier.citation Baltimore, MD, USA en_US
dc.identifier.clearanceno 02-1842 en_US
dc.description.abstract Processor-in-Memory (PIM) architectures avoid the von Neumann bottleneck in conventional machines by integrating high-density DRAM and CMOS logic on the same chip. Parallel systems based on this new technology are expected to provide higher scalability, adaptability, robustness, fault tolerance and lower power consumption than current MPPs or commodity clusters. In this paper we describe the design of Gilgamesh, a PIM-based massively parallel architecture, and elements of its execution model. Gilgamesh extends existing PIM capabilities by incorporating advanced mechanisms for virtualizing tasks and data and providing adaptive resource management for load balancing and latency tolerance. The Gilgamesh execution model is based on macroservers, a middleware layer which supports object-based runtime management of data and threads allowing explicit and dynamic control of locality and load balancing. The paper concludes with a discussion of related research activities and an outlook to future work. en_US
dc.format.extent 4442821 bytes
dc.format.mimetype application/pdf
dc.language.iso en_US
dc.subject.other processor-in-memory massively parallel systems PetaFlops computing resource management locality load balance en_US
dc.title Gilgamesh: A Multithreaded Processor-In-Memory Architecture for Petaflops Computing en_US

Files in this item

This item appears in the following Collection(s)

Show simple item record



My Account