| | |
Summary: Low-Power Amdahl-Balanced Blades for Data
Intensive Computing
Alexander S. Szalay
Gordon Bell
H. Howie Huang
Andreas Terzis
Alainna White
Johns Hopkins University
, George Washington University
, Microsoft Research
ABSTRACT
Enterprise and scientific data sets double every year,
forcing similar growths in storage size and power con-
sumption. As a consequence, current system architec-
tures used to build data warehouses are about to hit
a power consumption wall. In this paper we propose
a novel alternative architecture comprising large num-
ber of so-called Amdahl blades that combine energy-
efficient CPUs with solid state disks to increase se-
quential read I/O throughput by an order of magnitude
|
