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

Tensor accelerators have gained popularity because they provide a cheap andefficient solution for speeding up computational-expensive tasks in DeepLearning and, more recently, in other Scientific Computing applications.However, since their features are specifically designed for tensor algebra(typically dense matrix-product), it is commonly assumed that they are notsuitable for applications with sparse data. To challenge this viewpoint, wediscuss methods and present solutions for accelerating sparse matrixmultiplication on such architectures. In particular, we present a 1-dimensionalblocking algorithm with theoretical guarantees on the density, which buildsdense blocks from arbitrary sparse matrices. Experimental results show that,even for unstructured and highly-sparse matrices, our block-based solutionwhich exploits Nvidia Tensor Cores is faster than its sparse counterpart. Weobserved significant speed-ups of up to two orders of magnitude on real-worldsparse matrices.

Blocking Techniques for Sparse Matrix Multiplication on Tensor Accelerators