Publications
Detailed Information
A Specialized Architecture for Object Serialization with Applications to Big Data Analytics
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jang, Jaeyoung | - |
dc.contributor.author | Jung, Sung Jun | - |
dc.contributor.author | Jeong, Sunmin | - |
dc.contributor.author | Heo, Jun | - |
dc.contributor.author | Shin, Hoon | - |
dc.contributor.author | Ham, Tae Jun | - |
dc.contributor.author | Lee, Jae Wook | - |
dc.date.accessioned | 2022-10-20T00:23:58Z | - |
dc.date.available | 2022-10-20T00:23:58Z | - |
dc.date.created | 2022-06-07 | - |
dc.date.issued | 2020-05 | - |
dc.identifier.citation | Conference Proceedings - Annual International Symposium on Computer Architecture, ISCA, Vol.2020-May, pp.322-334 | - |
dc.identifier.issn | 1063-6897 | - |
dc.identifier.uri | https://hdl.handle.net/10371/186540 | - |
dc.description.abstract | © 2020 IEEE.Object serialization and deserialization (S/D) is an essential feature for efficient communication between distributed computing nodes with potentially non-uniform execution environments. S/D operations are widely used in big data analytics frameworks for remote procedure calls and massive data transfers like shuffles. However, frequent S/D operations incur significant performance and energy overheads as they must traverse and process a large object graph. Prior approaches improve S/D throughput by effectively hiding disk or network I/O latency with computation, increasing compression ratio, and/or application-specific customization. However, inherent dependencies in the existing (de)serialization formats and algorithms eventually become the major performance bottleneck. Thus, we propose Cereal, a specialized hardware accelerator for memory object serialization. By co-designing the serialization format with hardware architecture, Cereal effectively utilizes abundant parallelism in the S/D process to deliver high throughput. Cereal also employs an efficient object packing scheme to compress metadata such as object reference offsets and a space-efficient bitmap representation for the object layout. Our evaluation of Cereal using both a cycle-level simulator and synthesizable Chisel RTL demonstrates that Cereal delivers 43.4× higher average S/D throughput than 88 other S/D libraries on Java Serialization Benchmark Suite. For six Spark applications Cereal achieves 7.97× and 4.81× speedups on average for S/D operations over Java built-in serializer and Kryo, respectively, while saving S/D energy by 227.75× and 136.28×. | - |
dc.language | 영어 | - |
dc.publisher | IEEE | - |
dc.title | A Specialized Architecture for Object Serialization with Applications to Big Data Analytics | - |
dc.type | Article | - |
dc.identifier.doi | 10.1109/ISCA45697.2020.00036 | - |
dc.citation.journaltitle | Conference Proceedings - Annual International Symposium on Computer Architecture, ISCA | - |
dc.identifier.wosid | 000617734800025 | - |
dc.identifier.scopusid | 2-s2.0-85091993304 | - |
dc.citation.endpage | 334 | - |
dc.citation.startpage | 322 | - |
dc.citation.volume | 2020-May | - |
dc.description.isOpenAccess | N | - |
dc.contributor.affiliatedAuthor | Lee, Jae Wook | - |
dc.type.docType | Conference Paper | - |
dc.description.journalClass | 1 | - |
- Appears in Collections:
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.