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

Basecalling, an essential step in many genome analysis studies, relies onlarge Deep Neural Networks (DNNs) to achieve high accuracy. Unfortunately,these DNNs are computationally slow and inefficient, leading to considerabledelays and resource constraints in the sequence analysis process. AComputation-In-Memory (CIM) architecture using memristors can significantlyaccelerate the performance of DNNs. However, inherent device non-idealities andarchitectural limitations of such designs can greatly degrade the basecallingaccuracy, which is critical for accurate genome analysis. To facilitate theadoption of memristor-based CIM designs for basecalling, it is important to (1)conduct a comprehensive analysis of potential CIM architectures and (2) developeffective strategies for mitigating the possible adverse effects of inherentdevice non-idealities and architectural limitations.  This paper proposes Swordfish, a novel hardware/software co-design frameworkthat can effectively address the two aforementioned issues. Swordfishincorporates seven circuit and device restrictions or non-idealities fromcharacterized real memristor-based chips. Swordfish leverages varioushardware/software co-design solutions to mitigate the basecalling accuracy lossdue to such non-idealities. To demonstrate the effectiveness of Swordfish, wetake Bonito, the state-of-the-art (i.e., accurate and fast), open-sourcebasecaller as a case study. Our experimental results using Sword-fish show thata CIM architecture can realistically accelerate Bonito for a wide range of realdatasets by an average of 25.7x, with an accuracy loss of 6.01%.

Swordfish: A Framework for Evaluating Deep Neural Network-based Basecalling using Computation-In-Memory with Non-Ideal Memristors