We introduce a taxonomic study of parallel programming models
on High-Performance architectures. We review the parallel
architectures(shared and distributed memory), and then the
development of the architectures through the emergence of the
heter
ogeneous and hybrid parallel architectures.
We review important parallel programming model as the
Partitioned Global Address Space (PGAS) model, as model for
distributed memory architectures and the Data Flow model as
model to heterogeneous and hybrid parallel programming. Finally
we present several scenarios for the use of this taxonomic study.
Recent technological advances have greatly improved the performance and features
of computers and mobile systems. This improvements leads to increase in power
consumption which makes the task of managing their power consumption necessary. The
proc
essor considered as one of the most power consuming elements in the system so, this
research aims to develop a new method for power management in multicore architecture
which support most of the modern electronics. Power management techniques is an
important field in multicore studies because it must balance between the demanding needs
for higher performance/throughput and the impact of aggressive power consumption and
negative thermal effects. Many techniques have been proposed in this research like
(Dynamic Voltage and Frequency Scaling (DVFS), Asymmetric cores, Thread motion,
variable size cores, core fusion) then after we summarized comparing table which clarifies
the pros and cons of these techniques, we proposed a new technique for power
management in multi-core processors implements the best of these techniques .