Sciweavers

35 search results - page 4 / 7
» hpca 2008
Sort
View
HPCA
2008
IEEE
14 years 9 months ago
PEEP: Exploiting predictability of memory dependences in SMT processors
Simultaneous Multithreading (SMT) attempts to keep a dynamically scheduled processor's resources busy with work from multiple independent threads. Threads with longlatency st...
Samantika Subramaniam, Milos Prvulovic, Gabriel H....
HPCA
2008
IEEE
14 years 9 months ago
Fabric convergence implications on systems architecture
Converged fabrics that support data, storage, and cluster networking in a unified fashion are desirable for their cost and manageability advantages. Recent trends towards higher-b...
Kevin Leigh, Parthasarathy Ranganathan, Jaspal Sub...
HPCA
2008
IEEE
14 years 9 months ago
CMP network-on-chip overlaid with multi-band RF-interconnect
In this paper, we explore the use of multi-band radio frequency interconnect (or RF-I) with signal propagation at the speed of light to provide shortcuts in a many core network-on...
M. Frank Chang, Jason Cong, Adam Kaplan, Mishali N...
HPCA
2008
IEEE
14 years 9 months ago
Branch-mispredict level parallelism (BLP) for control independence
A microprocessor's performance is fundamentally limited by the rate at which it can resolve branch mispredictions. Control independence (CI) architectures look for useful con...
Kshitiz Malik, Mayank Agarwal, Sam S. Stone, Kevin...
HPCA
2008
IEEE
14 years 9 months ago
Runahead Threads to improve SMT performance
In this paper, we propose Runahead Threads (RaT) as a valuable solution for both reducing resource contention and exploiting memory-level parallelism in Simultaneous Multithreaded...
Tanausú Ramírez, Alex Pajuelo, Olive...