EECS Publication
MAGMA version 0.2 Users' Guide
S. Tomov and R. Nath and P. Du and J. Dongarra
The goal of the Matrix Algebra on GPU and Multicore Architectures (MAGMA) project is to create a new generation of linear algebra libraries that achieve the fastest possible time to an accurate solution on hybrid/heterogeneous architectures, starting with current multi-core+multiGPU systems. To address the complex challenges stemming from these systems' heterogeneity, massive parallelism, and gap in compute power vs CPU-GPU communication speeds, MAGMA's research is based on the idea that optimal software solutions will themselves have to hybridize, combining the strengths of different algorithms within a single framework. Building on this idea, the goal is to design linear algebra algorithms and frameworks for hybrid multi-core and multiGPU systems that can enable applications to fully exploit the power that each of the hybrid components offers. Designed to be similar to LAPACK in functionality, data storage, and interface, the MAGMA library will allow scientists to effortlessly port their LAPACK relying software components and to take advantage of the new hybrid architectures.
Published 2009-11-20 05:00:00 as ut-eecs-09-000 (ID:597)