Heterogeneous Multi-core Architectures for High Performance Computing

This thesis deals with heterogeneous architectures in standard workstations. Heterogeneous architectures represent an appealing alternative to traditional supercomputers because they are based on commodity components fabricated in large quantities. Hence their price-performance ratio is unparalleled in the world of high performance computing (HPC). In particular, different aspects related to the performance and consumption of heterogeneous architectures have been explored. The thesis initially focuses on an efficient implementation of a parallel application, where the execution time is dominated by an high number of floating point instructions. Then the thesis touches the central problem of efficient management of power peaks in heterogeneous computing systems. Finally it discusses a memory-bounded problem, where the execution time is dominated by the memory latency. Specifically, the following main contributions have been carried out: A novel framework for the design and analysis of solar field for Central Receiver Systems (CRS) has been developed. The implementation based on desktop workstation equipped with multiple Graphics Processing Units (GPUs) is motivated by the need to have an accurate and fast simulation environment for studying mirror imperfection and non-planar geometries. Secondly, a power-aware scheduling algorithm on heterogeneous CPU-GPU architectures, based on an efficient distribution of the computing workload to the resources, has been realized. The scheduler manages the resources of several computing nodes with a view to reducing the peak power. The two main contributions of this work follow: the approach reduces the supply cost due to high peak power whilst having negligible impact on the parallelism of computational nodes. from another point of view the developed model allows designer to increase the number of cores without increasing the capacity of the power supply unit. Finally, an implementation for efficient graph exploration on reconfigurable architectures is presented. The purpose is to accelerate graph exploration, reducing the number of random memory accesses.

Improving the cosmic distance ladder. Distance and structure of the Large Magellanic Cloud

The Large Magellanic Cloud (LMC) is widely considered as the first step of the cosmological distance ladder, since it contains many different distance indicators. An accurate determination of the distance to the LMC allows one to calibrate these distance indicators that are then used to measure the distance to far objects. The main goal of this thesis is to study the distance and structure of the LMC, as traced by different distance indicators. For these purposes three types of distance indicators were chosen: Classical Cepheids,``hot'' eclipsing binaries and RR Lyrae stars. These objects belong to different stellar populations tracing, in turn, different sub-structures of the LMC. The RR Lyrae stars (age >10 Gyr) are distributed smoothly and likely trace the halo of the LMC. Classical Cepheids are young objects (age 50-200 Myr), mainly located in the bar and spiral arm of the galaxy, while ``hot'' eclipsing binaries mainly trace the star forming regions of the LMC. Furthermore, we have chosen these distance indicators for our study, since the calibration of their zero-points is based on fundamental geometric methods. The ESA cornerstone mission Gaia, launched on 19 December 2013, will measure trigonometric parallaxes for one billion stars with an accuracy of 20 micro-arcsec at V=15 mag, and 200 micro-arcsec at V=20 mag, thus will allow us to calibrate the zero-points of Classical Cepheids, eclipsing binaries and RR Lyrae stars with an unprecedented precision.