Scalable Heterogeneous CPU-GPU Computations for Unstructured Tetrahedral Meshes

A recent trend in modern high-performance computing environments is the introduction of powerful, energy-efficient hardware accelerators such as GPUs and Xeon Phi coprocessors. These specialized computing devices coexist with CPUs and are optimized for highly parallel applications. In regular comput...

Full description

Saved in:
Bibliographic Details
Published in:IEEE MICRO 2015-07, Vol.35 (4), p.6-15
Main Authors: Langguth, Johannes, Sourouri, Mohammed, Lines, Glenn Terje, Baden, Scott B., Xing Cai
Format: Article
Language:English
Subjects:
Central processing units
Computer peripherals
Computer programs
CPUs
emerging technologies
Energy efficiency
GPUs
Graphics processing units
Instruction sets
irregular meshes
Mathematical model
Microprocessors
multicore processors
Optimization
parallel numerical algorithms
Particle separators
Performance evaluation
performance optimization
sparse linear algebra
Three-dimensional displays
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A recent trend in modern high-performance computing environments is the introduction of powerful, energy-efficient hardware accelerators such as GPUs and Xeon Phi coprocessors. These specialized computing devices coexist with CPUs and are optimized for highly parallel applications. In regular computing-intensive applications with predictable data access patterns, these devices often far outperform CPUs and thus relegate the latter to pure control functions instead of computations. For irregular applications, however, the performance gap can be much smaller and is sometimes even reversed. Thus, maximizing the overall performance on heterogeneous systems requires making full use of all available computational resources, including both accelerators and CPUs.
ISSN:0272-1732
1937-4143
DOI:10.1109/MM.2015.70