Cognitive Correlative Encoding for Genome Sequence Matching in Hyperdimensional System

Pattern matching is one of the key algorithms in identifying and analyzing genomic data. In this paper, we propose HYPERS, a novel framework supporting highly efficient and parallel pattern matching based on HyperDimensional computing (HDC). HYPERS transforms inherent sequential processes of pattern...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2021 58th ACM/IEEE Design Automation Conference (DAC) s. 781 - 786
Hlavní autoři: Poduval, Prathyush, Zou, Zhuowen, Yin, Xunzhao, Sadredini, Elaheh, Imani, Mohsen
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 05.12.2021
Témata:
Genomics
Graphics processing units
Hardware
Libraries
Software
Transforms
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Pattern matching is one of the key algorithms in identifying and analyzing genomic data. In this paper, we propose HYPERS, a novel framework supporting highly efficient and parallel pattern matching based on HyperDimensional computing (HDC). HYPERS transforms inherent sequential processes of pattern matching to highly-parallelizable computation tasks using HDC. HYPERS exploits HDC memorization to encode and represent the genome sequences using high-dimensional vectors. Then, it combines the genome sequences to generate an HDC reference library. During the matching, HYPERS performs alignment by exact or approximate similarity check of an encoded query with the HDC reference library. HYPERS functionality is supported by theoretical proof, verified by software implementation, and extensively tested on the existing hardware platform. Our evaluation on FPGA shows that HYPERS provides, on average, 17.5\times speedup and 39.4\times energy efficiency as compared to the state-of-the-art pattern matching tools running on GTX 1080 GPU.
DOI:10.1109/DAC18074.2021.9586253