Sciweavers

1075 search results - page 146 / 215
» Parallel Programming with Transactional Memory
Sort
View
ISORC
2005
IEEE
15 years 8 months ago
Object-Reuse for More Predictable Real-Time Java Behavior
One of the problems with Java for real-time systems is the unpredictable behavior of garbage collection (GC). GC introduces unexpected load and causes undesirable delays for real-...
Jameela Al-Jaroodi, Nader Mohamed
122
Voted
ISCA
1998
IEEE
135views Hardware» more  ISCA 1998»
15 years 6 months ago
Branch Prediction Based on Universal Data Compression Algorithms
Data compression and prediction are closely related. Thus prediction methods based on data compression algorithms have been suggested for the branch prediction problem. In this wo...
Eitan Federovsky, Meir Feder, Shlomo Weiss
ASPLOS
1992
ACM
15 years 6 months ago
Access Normalization: Loop Restructuring for NUMA Compilers
: In scalable parallel machines, processors can make local memory accesses much faster than they can make remote memory accesses. In addition, when a number of remote accesses must...
Wei Li, Keshav Pingali
129
Voted
DSD
2010
IEEE
161views Hardware» more  DSD 2010»
15 years 2 months ago
Design of Trace-Based Split Array Caches for Embedded Applications
—Since many embedded systems execute a predefined set of programs, tuning system components to application programs and data is the approach chosen by many design techniques to o...
Alice M. Tokarnia, Marina Tachibana
IJHPCA
2007
114views more  IJHPCA 2007»
15 years 2 months ago
An Approach To Data Distributions in Chapel
A key characteristic of today’s high performance computing systems is a physically distributed memory, which makes the efficient management of locality essential for taking adv...
R. E. Diaconescu, Hans P. Zima