Title :
Hardware Technologies for High-Performance Data-Intensive Computing
Author :
Gokhale, Maya ; Cohen, Jonathan ; Yoo, Andy ; Miller, W. Marcus ; Jacob, Arpith ; Ulmer, Craig ; Pearce, Roger
Author_Institution :
Lawrence Livermore Nat. Lab., Livermore
fDate :
4/1/2008 12:00:00 AM
Abstract :
Data-intensive problems challenge conventional computing architectures with demanding CPU, memory, and I/O requirements. Experiments with three benchmarks suggest that emerging hardware technologies can significantly boost performance of a wide range of applications by increasing compute cycles and bandwidth and reducing latency.
Keywords :
computer architecture; CPU requirements; I/O requirements; benchmarks; computing architectures; hardware technologies; high-performance data-intensive computing; memory requirements; Application software; Bandwidth; Computer architecture; Computer displays; Coprocessors; Delay; Field programmable gate arrays; Graphics; Hardware; Universal Serial Bus; FPGAs; GPUs; computer systems; data management; data science; data-intensive computing; image resampling; language analysis; semantic graphs; solid-state storage;
DOI :
10.1109/MC.2008.125
