Parallel Programming

Bertil Schmidt is tenured Full Professor and Chair for Parallel and Distributed Architectures at the Johannes Gutenberg University Mainz, Germany. Prior to that he was a faculty member at Nanyang Technological University (Singapore) and at the University of New South Wales (UNSW). His research group has designed a variety of parallel algorithms and tools for Bioinformatics mainly focusing on the analysis of large-scale sequence and short read datasets. For his research work, he has received a CUDA Research Center award, a CUDA Academic Partnership award, a CUDA Professor Partnership award and the Best Paper Award at IEEE ASAP 2009. Furthermore, he serves as the champion for Bioinformatics and Computational Biology on gpucomputing.net. He is also director of the “Competence Center for HPC in the Natural Sciences” which has recently been funded by the Carl-Zeiss-Foundation. His work has been published in leading journals such as Bioinformatics, BMC Bioinformatics, IEEE Transactions on Parallel and Distributed Computing, IEEE Transactions on VLSI, BMC Genomics, Parallel Computing, and Journal of Parallel and Distributed Computing. Jorge Álvaro González Martínez, MD, PhD, FAANS, is a board-certified neurosurgeon specialized in epilepsy and functional neurosurgery and Tenure Professor in Neurological Surgery and Neurobiology at University of Pittsburgh. He serves as the Director of Epilepsy and Movement Disorders Surgery and is the co-director of the Epilepsy Center at the University of Pittsburgh Medical Center. He is the current Vice-Chair of the department of Neurological Surgery and the Stuart Niles Rowe Endowed Chair in Epilepsy Surgery. Dr. González Martínez is a world-renowned surgeon/scientist with an extensive publication record, having authored over 300 peer-reviewed articles book chapters and patents focused on epilepsy surgery and advanced brain mapping techniques for patients with medically intractable epilepsy and movement disorders. Dr. González Martínez's legacy is etched in his pioneering contributions to surgical innovation. He spearheaded the introduction of modern conceptual and surgical facets of the Stereoelectroencephalography (SEEG) methodology to the United States, heralding a paradigm shift in epilepsy surgery. By replacing antiquated techniques with state-of-the-art stereotaxic approaches, he has revolutionized surgical strategies, thereby elevating the standard of care and transforming the landscape of epilepsy surgery both domestically and abroad. His expertise spans a gamut of surgical modalities, encompassing stereotaxic anatomy applied to SEEG, SEEG-guided laser ablations, neuromodulatory interventions, and robotic-assisted surgeries, all of which underscore his commitment to excellence in patient care. Beyond the operating theater, Dr. González Martínez's scholarly pursuits traverse the realms of neuro-electrophysiology, intracranial signal processing, and behavioral neuroscience. Through synergistic amalgamation of clinical and basic science endeavors, he endeavors to forge safer and more effective treatment modalities, aimed at enhancing patient outcomes and ameliorating the burdens imposed by debilitating seizures. His research activities, rooted in the University of Pittsburgh Cortical System Lab, have received generous support from prestigious funding bodies such as the NIH and NSF, underscoring the translational impact of his endeavors on the broader scientific community. Christian Hundt has received his diploma degree in theoretical physics for the analysis of quantization maps and the associated structure of Lie groups on curved manifolds at the University of Mainz, Germany. In his current position, as a research associate at the Parallel and Distributed Architectures group, he investigates the design and parallelization of elastic subsequence alignment algorithms using CUDA-enabled accelerators. Further topics of interest involve the robust and Galilean-invariant vortex detection in wind fields (Lagrangian Coherent Structures) and the efficient analysis of spatio-temporal data. Moritz Schlarb is currently an M. Sc. student of Computer Science at Technische Universität Darmstadt, Germany. For several years, he has gained experience with the practical usage of parallel applications by working on the technical administration of the High Performance Computing Cluster at the Johannes Gutenberg University Mainz, Germany. He created and maintains the SAUCE tool which is provided for assisting the practical exercises provided in this book.

1. Introduction2. Theoretical Background3. Modern Architectures4. C++11 Multithreading5. Advanced C++11 Multithreading6. OpenMP7. Compute Unified Device Architecture8. Advance CUDA Programming9. Message Passing Interface10. Unified Parallel C++