English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Matrix languages, including MATLAB and Octave, are established standards forapplications in science and engineering. They provide interactive programmingenvironments that are easy to use due to their scripting languages with matrixdata types. Current implementations of matrix languages do not fully utilisehigh-performance, special-purpose chip architectures such as the IBM PowerXCellprocessor (Cell), which is currently used in the fastest computer in the world.  We present a new framework that extends Octave to harness the computationalpower of the Cell. With this framework the programmer is relieved of the burdenof introducing explicit notions of parallelism. Instead the programmer uses anew matrix data-type to execute matrix operations in parallel on thesynergistic processing elements (SPEs) of the Cell. We employ lazy evaluationsemantics for our new matrix data-type to obtain execution traces of matrixoperations. Traces are converted to data dependence graphs; operations in thedata dependence graph are lowered (split into sub-matrices), scheduled andexecuted on the SPEs. Thereby we exploit (1) data parallelism, (2) instructionlevel parallelism, (3) pipeline parallelism and (4) task parallelism of matrixlanguage programs. We conducted extensive experiments to show the validity ofour approach. Our Cell-based implementation achieves speedups of up to a factorof 12 over code run on recent Intel Core2 Quad processors.

Accelerating the Execution of Matrix Languages on the Cell Broadband Engine Architecture