Accelerating Dense Linear Algebra for GPUs, Multicores and Hybrid Architectures: an Autotuned and Algorithmic Approach

Accelerating Dense Linear Algebra for GPUs, Multicores and Hybrid Architectures: an Autotuned and Algorithmic Approach

Dense linear algebra(DLA) is one of the most seven important kernels in high performance computing. The introduction of new machines from vendors provides us opportunities to optimize DLA libraries for the new machines and thus exploit their power. Unfortunately the optimization phase is not straigh...

Full description

Bibliographic Details
Main Author: Nath, Rajib Kumar
Format: Others
Published: Trace: Tennessee Research and Creative Exchange 2010
Subjects:
Optimization
GPUs
Multicore
Dense Linear Algebra
BLAS
Hybrid Architecture
Online Access:http://trace.tennessee.edu/utk_gradthes/734

Internet

http://trace.tennessee.edu/utk_gradthes/734

Similar Items