Sciweavers

ICS
1999
Tsinghua U.
14 years 4 months ago
Low-level router design and its impact on supercomputer system performance
Supercomputer performance is highly dependent on its interconnection subsystem design. In this paper we study how di erent architectural approaches for router design impact into s...
Valentin Puente, José A. Gregorio, Cruz Izu...
ICS
1999
Tsinghua U.
14 years 4 months ago
Responsiveness without interrupts
Dejan Perkovic, Peter J. Keleher
ICS
1999
Tsinghua U.
14 years 4 months ago
Improving the performance of speculatively parallel applications on the Hydra CMP
Hydra is a chip multiprocessor (CMP) with integrated support for thread-level speculation. Thread-level speculation provides a way to parallelize sequential programs without the n...
Kunle Olukotun, Lance Hammond, Mark Willey
ICS
1999
Tsinghua U.
14 years 4 months ago
Improving the performance of bristled CC-NUMA systems using virtual channels and adaptivity
Current high-end parallel systems achieve low-latency, highbandwidth network communication through the use of aggressive design techniques and expensive mechanical and electrical ...
José F. Martínez, Josep Torrellas, J...
ICS
1999
Tsinghua U.
14 years 4 months ago
Clustered speculative multithreaded processors
In this paper we present a processor microarchitecture that can simultaneously execute multiple threads and has a clustered design for scalability purposes. A main feature of the ...
Pedro Marcuello, Antonio González
ICS
1999
Tsinghua U.
14 years 4 months ago
High-level semantic optimization of numerical codes
This paper presents a mathematical framework to exploit the semantic properties of matrix operations in loop-based numerical codes. The heart of this framework is an algebraic lan...
Vijay Menon, Keshav Pingali
ICS
1999
Tsinghua U.
14 years 4 months ago
Improving memory hierarchy performance for irregular applications
The performance of irregular applications on modern computer systems is hurt by the wide gap between CPU and memory speeds because these applications typically underutilize multi-...
John M. Mellor-Crummey, David B. Whalley, Ken Kenn...
ICS
1999
Tsinghua U.
14 years 4 months ago
Application scaling under shared virtual memory on a cluster of SMPs
In this paper we examine how application performance scales on a state-of-the-art shared virtual memory (SVM) system on a cluster with 64 processors, comprising 4-way SMPs connect...
Dongming Jiang, Brian O'Kelley, Xiang Yu, Sanjeev ...
ICS
1999
Tsinghua U.
14 years 4 months ago
An experimental evaluation of tiling and shackling for memory hierarchy management
On modern computers, the performance of programs is often limited by memory latency rather than by processor cycle time. To reduce the impact of memory latency, the restructuring ...
Induprakas Kodukula, Keshav Pingali, Robert Cox, D...
ICS
1999
Tsinghua U.
14 years 4 months ago
Symmetry and performance in consistency protocols
A consistency protocol can be termed symmetric if all processors are treated identically when they access common resources. By contrast, asymmetric protocols usually assign a home...
Peter J. Keleher