CPL - Chalmers Publication Library
| Utbildning | Forskning | Styrkeområden | Om Chalmers | In English In English Ej inloggad.

HyComp: A Hybrid Cache Compression Method for Selection of Data-Type-Specific Compression Methods

Angelos Arelakis (Institutionen för data- och informationsteknik, Datorteknik (Chalmers)) ; Fredrik Dahlgren ; Per Stenström (Institutionen för data- och informationsteknik, Datorteknik (Chalmers))
48th Annual IEEE/ACM International Symposium on Microarchitecture, MICRO 2015, Waikiki, United States, 5-9 December 2015 (1072-4451). p. 38-49. (2015)
[Konferensbidrag, refereegranskat]

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.

Nyckelord: cache compression, floating-point data, huffman coding, hybrid compression, value locality

Den här publikationen ingår i följande styrkeområden:

Läs mer om Chalmers styrkeområden  

Denna post skapades 2016-01-06. Senast ändrad 2017-06-28.
CPL Pubid: 229926


Läs direkt!

Länk till annan sajt (kan kräva inloggning)