High Performance Computing for Computational Science VECPAR 2014 1st Edition by Michel Daydé,Kengo Nakajima,Osni Marques 9783319173535 3319173537

1. Algorithms for GPU and Manycores

A Communication Optimization Scheme for Basis Computation of Krylov Subspace Methods on Multi-GPUs

Mixed-Precision Orthogonalization Scheme and Adaptive Step Size for Improving the Stability and Performance of CA-GMRES on GPUs

Heterogenous Acceleration for Linear Algebra in Multi-coprocessor Environments

A Study of SpMV Implementation Using MPI and OpenMP on Intel Many-Core Architecture

SIMD Implementation of a Multiplicative Schwarz Smoother for a Multigrid Poisson Solver on an Intel Xeon Phi Coprocessor

Performance Optimization of the 3D FDM Simulation of Seismic Wave Propagation on the Intel Xeon Phi Coprocessor Using the ppOpen-APPL/FDM Library

2. Large-Scale Applications

Machine-Learning-Based Load Balancing for Community Ice Code Component in CESM

Domain Decomposition for Heterojunction Problems in Semiconductors

A Hybrid Approach for Parallel Transistor-Level Full-Chip Circuit Simulation

3. Numerical Algorithms

Self-adaptive Multiprecision Preconditioners on Multicore and Manycore Architectures

Fault Tolerance in an Inner-Outer Solver: A GVR-Enabled Case Study

4. Direct/Hybrid Methods for Solving Sparse Matrices

Using Random Butterfly Transformations to Avoid Pivoting in Sparse Direct Methods

Hybrid Sparse Linear Solutions with Substituted Factorization

Modeling 1D Distributed-Memory Dense Kernels for an Asynchronous Multifrontal Sparse Solver

5. Performance Tuning

Performance Characteristics of HYDRA – A Multi-physics Simulation Code from LLNL

Accelerating Computation of Eigenvectors in the Dense Nonsymmetric Eigenvalue Problem

Low Byte/Flop Implementation of Iterative Solver for Sparse Matrices Derived from Stencil Computations

6. The Ninth International Workshop on Automatic Performance Tuning

Environment-Sensitive Performance Tuning for Distributed Service Orchestration

Historic Learning Approach for Auto-tuning OpenACC Accelerated Scientific Applications

Capturing the Expert: Generating Fast Matrix-Multiply Kernels with Spiral

A Study on the Influence of Caching: Sequences of Dense Linear Algebra Kernels

Toward Restarting Strategies Tuning for a Krylov Eigenvalue Solver

Performance Analysis of the Householder-Type Parallel Tall-Skinny QR Factorizations Toward Automatic Algorithm Selection

Automatic Parameter Tuning of Three-Dimensional Tiled FDTD Kernel

Automatic Parameter Tuning of Hierarchical Incremental Checkpointing