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

Faced with saturation of Moore's law and increasing dimension of data, systemdesigners have increasingly resorted to parallel and distributed computing.However, distributed computing is often bottle necked by a small fraction ofslow processors called "stragglers" that reduce the speed of computationbecause the fusion node has to wait for all processors to finish. To combat theeffect of stragglers, recent literature introduces redundancy in computationsacross processors, e.g.,~using repetition-based strategies or erasure codes.The fusion node can exploit this redundancy by completing the computation usingoutputs from only a subset of the processors, ignoring the stragglers. In thispaper, we propose a novel technique -- that we call "Short-Dot" -- to introduceredundant computations in a coding theory inspired fashion, for computinglinear transforms of long vectors. Instead of computing long dot products asrequired in the original linear transform, we construct a larger number ofredundant and short dot products that can be computed faster and moreefficiently at individual processors. In reference to comparable schemes thatintroduce redundancy to tackle stragglers, Short-Dot reduces the cost ofcomputation, storage and communication since shorter portions are stored andcomputed at each processor, and also shorter portions of the input iscommunicated to each processor. We demonstrate through probabilistic analysisas well as experiments that Short-Dot offers significant speed-up compared toexisting techniques. We also derive trade-offs between the length of thedot-products and the resilience to stragglers (number of processors to waitfor), for any such strategy and compare it to that achieved by our strategy.

"Short-Dot": Computing Large Linear Transforms Distributedly Using Coded Short Dot Products