Exploring processor parallelism : estimation methods and optimization strategies

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

12 Citaten (Scopus)

Samenvatting

Former research on automatic exploration of ASIP architectures mostly focused on either the internal memory hierarchy, or the addition of complex custom operations to RISC based architectures. This paper focuses on VLIW architectures and, more specifically, on automating the selection of an application specific VLIW issue-width. An accurate and efficient issue-width estimation strongly influences all the important processor properties (e.g. processing speed, silicon area, and power consumption). We first compare different methods for estimating the required issue-width, and subsequently introduce a new force-based parallelism measure which is capable of estimating the required issue-width within 3% on average. Moreover, we show that we can quickly estimate the latency-parallelism Pareto-front of an example ECG application with less than 10% error using our issue-width estimations.
Originele taal-2Engels
TitelProceedings on the 16th IEEE Symposium on Design and Diagnostics of Electronic Circuits and Systems (DDECS'13), 8-10 April 2013, Karlovy Vary, Czech Republic
Plaats van productiePiscataway
UitgeverijInstitute of Electrical and Electronics Engineers
DOI's
StatusGepubliceerd - 2013
Evenementconference; DDECS'13; 2013-04-08; 2013-04-10 -
Duur: 8 apr 201310 apr 2013

Congres

Congresconference; DDECS'13; 2013-04-08; 2013-04-10
Periode8/04/1310/04/13
AnderDDECS'13

Vingerafdruk Duik in de onderzoeksthema's van 'Exploring processor parallelism : estimation methods and optimization strategies'. Samen vormen ze een unieke vingerafdruk.

Citeer dit