@InProceedings{Supelec881,
author = {Jens Gustedt and Stephane Vialle and Patrick Mercier},
title = {{Resource Centered Computing delivering high parallel performance}},
year = {2014},
booktitle = {{Heterogeneity in Computing Workshop (HCW 2014), workshop of 28th IEEE International Parallel \& Distributed Processing Symposium (IPDPS 2014)}},
pages = {11 pages},
month = {May},
address = {PHOENIX (Arizona) USA},
abstract = {Modern parallel programming requires a combination
of different paradigms, expertise and tuning, that correspond
to the different levels in today’s hierarchical architectures. To
cope with the inherent difficulty, ORWL (ordered read-write
locks)
presents a new paradigm and toolbox centered around local or
remote resources, such as data, processors or accelerators. ORWL
programmers describe their computation in terms of access to
these resources during critical sections. Exclusive or shared
access
to the resources is granted through FIFOs and with read-write
semantic. ORWL partially replaces a classical runtime and offers
a new API for resource centric parallel programming.
We successfully ran an ORWL benchmark application on different
parallel architectures (a multicore CPU cluster, a NUMA
machine, a CPU+GPU cluster). When processing large data
we achieved scalability and performance similar to a reference
code built on top of MPI+OpenMP+CUDA. The integration of
optimized kernels of scientific computing libraries (ATLAS and
cuBLAS) has been almost effortless, and we were able to increase
performance using both CPU and GPU cores on our hybrid
hierarchical cluster simultaneously. We aim to make ORWL a
new easy-to-use and efficient programming model and toolbox
for parallel developers.}
}