HyComp: A Hybrid Cache Compression Method for Selection of Data-Type-Specific Compression Methods
Paper in proceeding, 2015

Proposed cache compression schemes make design-time assumptions on value locality to reduce decompression latency. For example, some schemes assume that common values are spatially close whereas other schemes assume that null blocks are common. Most schemes, however, assume that value locality is best exploited by fixed-size data types (e.g., 32-bit integers). This assumption falls short when other data types, such as floating-point numbers, are common. This paper makes two contributions. First, HyComp - a hybrid cache compression scheme - selects the best-performing compression scheme, based on heuristics that predict data types. Data types considered are pointers, integers, floating-point numbers and the special (and trivial) case of null blocks. Second, this paper contributes with a compression method that exploits value locality in data types with predefined semantic value fields, e.g., as in the exponent and the mantissa in floating-point numbers. We show that HyComp, augmented with the proposed floating-point-number compression method, offers superior performance in comparison with prior art.

value locality

cache compression

floating-point data

hybrid compression

huffman coding

Author

Angelos Arelakis

Chalmers, Computer Science and Engineering (Chalmers), Computer Engineering (Chalmers)

Fredrik Dahlgren

Ericsson

Chalmers, Computer Science and Engineering (Chalmers), Computer Engineering (Chalmers)

Per Stenström

Chalmers, Computer Science and Engineering (Chalmers), Computer Engineering (Chalmers)

48th Annual IEEE/ACM International Symposium on Microarchitecture, MICRO 2015, Waikiki, United States, 5-9 December 2015

1072-4451 (ISSN)

38-49
978-1-4503-4034-2 (ISBN)

Areas of Advance

Information and Communication Technology

Subject Categories

Computer and Information Science

Electrical Engineering, Electronic Engineering, Information Engineering

DOI

10.1145/2830772.2830823

ISBN

978-1-4503-4034-2

More information

Latest update

11/23/2018