Advanced software technologies for post-Peta scale computing :
نام عام مواد
[Book]
ساير اطلاعات عنواني
the Japanese post-Peta CREST research project /
نام نخستين پديدآور
Mitsuhia Sato, editor.
وضعیت نشر و پخش و غیره
محل نشرو پخش و غیره
Singapore :
نام ناشر، پخش کننده و غيره
Springer,
تاریخ نشرو بخش و غیره
[2019]
مشخصات ظاهری
نام خاص و کميت اثر
1 online resource
یادداشتهای مربوط به مندرجات
متن يادداشت
Intro; Preface; Contents; 1 JST CREST Post-petascale Software Project Bridging to Exascale Computing; 1.1 Trends of High-Performance Computing; 1.2 Outline of JST CREST Post-petascale Software Project; 1.3 Research Topics of the Project; 1.4 Results and Achievements; 2 ppOpen-HPC/pK-Open-HPC: Application Development Framework with Automatic Tuning (AT); 2.1 Overview of ppOpen-HPC; 2.2 Development of pK-Open-FVM; 2.2.1 Application to Vlasov-Poisson Simulation; 2.2.2 AMR Particle Simulation for the Development of Reactive Plasma Deposition Equipment
متن يادداشت
2.2.3 Application to Particle-Based Sugarscape Model2.3 Robust and Massively Parallelized Preconditioner for Quantum Systems; 2.3.1 Objective; 2.3.2 Regularizations for Robustness; 2.3.2.1 Blocking Technique; 2.3.2.2 Diagonal Shifting; 2.3.2.3 Numerical Evaluation; 2.3.3 Hierarchical Parallelization of Multicoloring Algorithms for Massive Parallelism; 2.3.3.1 Parallelization of the ILU Preconditioner with Multicoloring; 2.3.3.2 Hierarchical Parallelization; 2.3.3.3 Numerical Evaluation; 2.3.4 Publication of Deliverable; 2.4 Automatic Tuning (AT) in ppOpen-HPC and pK-Open-HPC
متن يادداشت
2.4.1 Functions of ppOpen-AT2.4.2 Target Users; 2.4.3 Performance Evaluation; 2.5 Development of a Multi-physics Coupler ppOpen-MATH/MP; 2.5.1 Background; 2.5.2 NICAM-COCO Coupling; 2.5.3 Coupling Results; 2.5.4 NICAM-COCO and I/O Component; 2.6 Efficient Structures of H-Matrices on Distributed Memory Computer Systems; 2.7 Summary; References; 3 Scalable Eigen-Analysis Engine for Large-Scale Eigenvalue Problems; 3.1 Introduction; 3.2 Sparse Eigen-Super Computing Engine; 3.2.1 Complex Moment-Based Eigensolvers; 3.2.1.1 Basic Concepts; 3.2.1.2 Theoretical Aspect
متن يادداشت
3.2.1.3 Extension to Nonlinear Eigenvalue Problems3.2.2 Distributed Parallel Sparse Eigensolver Package z-Pares; 3.2.2.1 Introduction; 3.2.2.2 Features; 3.2.2.3 Dependences; 3.2.2.4 Basic Concepts of z-Pares; 3.2.2.5 Two-Level MPI Parallelism; 3.2.2.6 zpares_prm Derived Type; 3.2.2.7 Reverse Communication Interface; 3.2.2.8 Efficient Implementations for Specific Problems; 3.3 EigenExa: Development of a Dense Solver; 3.3.1 Introduction; 3.3.2 Brief History of the Dense Solver Project; 3.3.3 Our Approaches in Parallel Algorithm; 3.3.3.1 Householder Band Reduction
متن يادداشت
3.3.3.2 Divide and Conquer for a Banded Matrix3.3.3.3 Back Transformation; 3.3.4 Performance; 3.3.4.1 Performance on the K Computer; 3.3.4.2 Ultra-Scale Benchmark; 3.3.5 Related Sub-projects; 3.3.5.1 CholeskyQR2; 3.3.5.2 Performance Modeling; 3.3.5.3 High-Precision Calculation; 3.4 Conclusion; References; 4 System Software for Many-Core and Multi-core Architecture; 4.1 Overview and Background; 4.2 OS Technologies for Heterogeneous Architecture; 4.2.1 Partitioned Virtual Address Space; 4.2.2 Heterogeneous Extension of PVAS; 4.3 Lightweight Thread; 4.4 Scalable I/O; 4.5 Fault Mitigation
بدون عنوان
0
بدون عنوان
8
بدون عنوان
8
بدون عنوان
8
بدون عنوان
8
یادداشتهای مربوط به خلاصه یا چکیده
متن يادداشت
Covering research topics from system software such as programming languages, compilers, runtime systems, operating systems, communication middleware, and large-scale file systems, as well as application development support software and big-data processing software, this book presents cutting-edge software technologies for extreme scale computing. The findings presented here will provide researchers in these fields with important insights for the further development of exascale computing technologies. This book grew out of the post-peta CREST research project funded by the Japan Science and Technology Agency, the goal of which was to establish software technologies for exploring extreme performance computing beyond petascale computing. The respective were contributed by 14 research teams involved in the project. In addition to advanced technologies for large-scale numerical computation, the project addressed the technologies required for big data and graph processing, the complexity of memory hierarchy, and the power problem. Mapping the direction of future high-performance computing was also a central priority.
یادداشتهای مربوط به سفارشات
منبع سفارش / آدرس اشتراک
Springer Nature
شماره انبار
com.springer.onix.9789811319242
ویراست دیگر از اثر در قالب دیگر رسانه
عنوان
Advanced Software Technologies for Post-Peta Scale Computing : The Japanese Post-Peta CREST Research Project.