@article {826, title = {Unveiling the Performance-energy Trade-off in Iterative Linear System Solvers for Multithreaded Processors}, journal = {Concurrency and Computation: Practice and Experience}, volume = {27}, year = {2014}, month = {2014-09}, pages = {885-904}, chapter = {885}, abstract = {In this paper, we analyze the interactions occurring in the triangle performance-power-energy for the execution of a pivotal numerical algorithm, the iterative conjugate gradient (CG) method, on a diverse collection of parallel multithreaded architectures. This analysis is especially timely in a decade where the power wall has arisen as a major obstacle to build faster processors. Moreover, the CG method has recently been proposed as a complement to the LINPACK benchmark, as this iterative method is argued to be more archetypical of the performance of today{\textquoteright}s scientific and engineering applications. To gain insights about the benefits of hands-on optimizations we include runtime and energy efficiency results for both out-of-the-box usage relying exclusively on compiler optimizations, and implementations manually optimized for target architectures, that range from general-purpose and digital signal multicore processors to manycore graphics processing units, all representative of current multithreaded systems.}, keywords = {CG, CPUs, energy efficiency, GPUs, low-power architectures}, doi = {10.1002/cpe.3341}, url = {http://dx.doi.org/10.1002/cpe.3341}, author = {Jos{\'e} I. Aliaga and Hartwig Anzt and Maribel Castillo and Juan C. Fern{\'a}ndez and Germ{\'a}n Le{\'o}n and Joaqu{\'\i}n P{\'e}rez and Enrique S. Quintana-Orti} }