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

Sparse Matricized Tensor Times Khatri-Rao Product (spMTTKRP) is the mosttime-consuming compute kernel in sparse tensor decomposition. In this paper, weintroduce a novel algorithm to minimize the execution time of spMTTKRP acrossall modes of an input tensor on multi-core CPU platform. The proposed algorithmleverages the FLYCOO tensor format to exploit data locality in external memoryaccesses. It effectively utilizes computational resources by enabling lock-freeconcurrent processing of independent partitions of the input tensor. Theproposed partitioning ensures load balancing among CPU threads. Our dynamictensor remapping technique leads to reduced communication overhead along allthe modes. On widely used real-world tensors, our work achieves 2.12x - 9.01xspeedup in total execution time across all modes compared with thestate-of-the-art CPU implementations.

Dynasor: A Dynamic Memory Layout for Accelerating Sparse MTTKRP for Tensor Decomposition on Multi-core CPU