Facing the Multicore-Challenge

This survey of the impact of multicore and co-processor technologies on science as well as on large-scale interdisciplinary applications covers the state of the art in the field. It also points to a number of potentially fruitful areas for future research.

The proceedings at hand are the outcome of the conference for young sci- tists titled Facing the Multicore-Challenge held at the Heidelberger Akademie der Wissenschaften, March 17 19, 2010. The conference focused on topics - lated to the impact of multicore and coprocessor technologies in science and for large-scale applications in an interdisciplinary environment. The conference was funded by the Heidelberger Akademie der Wissenschaften and placed emphasis on the support and advancement of young scientists. The aim of the conference was to bring together leading experts as well as motivated young researchers in order to discuss, recent developments, the present status of the ?eld, and its future prospects the exchange of ideas, in a pleasant atmosphere that stimulates. It was the designated goal to address current issues including mathematical modeling, design of parallel algorithms, aspects of microprocessor architecture, parallel programming languages, c- pilers, hardware-aware computing, heterogeneous platforms, emerging archit- tures, tools, performance tuning, and requirements for large-scale applications. Thisbroadrangeofissuesisre?ectedbythepresentconferenceproceedings.The results of the presented research papers clearly show the potential of emerging technologiesintheareaofmulticoreandmanycoreprocessorsthatarepavingthe way towards personal supercomputing. However, many issues related to parallel programmingenvironments, developmentof portable and future-proof concepts, and the design of scalable and manycore-ready algorithms still need to be - dressed in future research. Some of these points are the subject of the presented papers.

State-of-the-art survey Contains 12 revised full papers and 3 invited papers Features topics related to the impact of multicore and coprocessor technologies

Klappentext

This state-of-the-art survey features topics related to the impact of multicore and coprocessor technologies in science and for large-scale applications in an interdisciplinary environment. The papers cover all issues of current research in mathematical modeling, design of parallel algorithms, aspects of microprocessor architecture, parallel programming languages, compilers, hardware-aware computing, heterogeneous platforms, emerging architectures, tools, performance tuning, and requirements for large-scale applications. The contributions presented in this volume offer a survey on the state of the art, the concepts and perspectives for future developments. They are an outcome of an inspiring conference conceived and organized by the editors within the junior scientist program of Heidelberg Academy for Sciences and Humanities titled "Facing the Multicore-Challenge", held at Heidelberg, Germany, in March 2010. The 12 revised full papers presented together with the extended abstracts of 3 invited lectures focus on combination of new aspects of multicore microprocessor technologies, parallel applications, numerical simulation, software development, and tools; thus they clearly show the potential of emerging technologies in the area of multicore and manycore processors that are paving the way towards personal supercomputing. TOC:Invited Talks.- Analyzing Massive Social Networks Using Multicore and Multithreaded Architectures.- MareIncognito: A Perspective towards Exascale.- The Natural Parallelism.- Computer Architecture and Parallel Programming.- RapidMind: Portability across Architectures and Its Limitations.- A Majority-Based Control Scheme for Way-Adaptable Caches.- Improved Scalability by Using Hardware-Aware Thread Affinities.- Thread Creation for Self-aware Parallel Systems.- Applications on Multicore.- G-Means Improved for Cell BE Environment.- Parallel 3D Multigrid Methods on the STI Cell BE Architecture.- Applying Classic Feedback Control for Enhancing the Fault-Tolerance of Parallel Pipeline Workflows on Multi-core Systems.- Lattice-Boltzmann Simulation of the Shallow-Water Equations with Fluid-Structure Interaction on Multi- and Manycore Processors.- FPGA vs. Multi-core CPUs vs. GPUs: Hands-On Experience with a Sorting Application.- GPGPU Computing.- Considering GPGPU for HPC Centers: Is it Worth the Effort?.- Real-Time Image Segmentation on a GPU.- Parallel Volume Rendering Implementation on Graphics Cards Using CUDA.

Inhalt
Invited Talks.- Analyzing Massive Social Networks Using Multicore and Multithreaded Architectures.- MareIncognito: A Perspective towards Exascale.- The Natural Parallelism.- Computer Architecture and Parallel Programming.- RapidMind: Portability across Architectures and Its Limitations.- A Majority-Based Control Scheme for Way-Adaptable Caches.- Improved Scalability by Using Hardware-Aware Thread Affinities.- Thread Creation for Self-aware Parallel Systems.- Applications on Multicore.- G-Means Improved for Cell BE Environment.- Parallel 3D Multigrid Methods on the STI Cell BE Architecture.- Applying Classic Feedback Control for Enhancing the Fault-Tolerance of Parallel Pipeline Workflows on Multi-core Systems.- Lattice-Boltzmann Simulation of the Shallow-Water Equations with Fluid-Structure Interaction on Multi- and Manycore Processors.- FPGA vs. Multi-core CPUs vs. GPUs: Hands-On Experience with a Sorting Application.- GPGPU Computing.- Considering GPGPU for HPC Centers: Is it Worth the Effort?.- Real-Time Image Segmentation on a GPU.- Parallel Volume Rendering Implementation on Graphics Cards Using CUDA.