Improving power consumption and performance of error tolerant applications is the target of the design paradigm known as approximate computing. The memory subsystem is one of the units of a computational architecture where approximations can be introduced, leveraging on the resilience of an application to maintain an acceptable output quality even if its input data are subject to imprecision and errors.This paper proposes and implements the management, in the Linux kernel, of multiple approximate memory banks. Applications can then allocate approximate memory for their data structures selecting between different levels of approximation, depending on the requirements on output quality. This allows to design an architecture where approximate physical memory, instead of being composed of a unit intercepting a single point in the energy-quality tradeoff curve, can be split into multiple banks trading off levels of approximation and energy savings.We finally show a case study in the results, where we explore the allocation of different data structures of a signal processing application, depending on sensitivity to errors and desired output quality.

Quality aware approximate memory in RISC-V Linux Kernel / Stazi, G.; Mastrandrea, A.; Olivieri, M.; Menichelli, F.. - (2019), pp. 177-180. (Intervento presentato al convegno 15th Conference on Ph.D. Research in Microelectronics and Electronics, PRIME 2019 tenutosi a Lausanne, Switzerald) [10.1109/PRIME.2019.8787745].

Quality aware approximate memory in RISC-V Linux Kernel

Stazi G.
Primo
;
Mastrandrea A.
Secondo
;
Olivieri M.
Penultimo
;
Menichelli F.
Ultimo
2019

Abstract

Improving power consumption and performance of error tolerant applications is the target of the design paradigm known as approximate computing. The memory subsystem is one of the units of a computational architecture where approximations can be introduced, leveraging on the resilience of an application to maintain an acceptable output quality even if its input data are subject to imprecision and errors.This paper proposes and implements the management, in the Linux kernel, of multiple approximate memory banks. Applications can then allocate approximate memory for their data structures selecting between different levels of approximation, depending on the requirements on output quality. This allows to design an architecture where approximate physical memory, instead of being composed of a unit intercepting a single point in the energy-quality tradeoff curve, can be split into multiple banks trading off levels of approximation and energy savings.We finally show a case study in the results, where we explore the allocation of different data structures of a signal processing application, depending on sensitivity to errors and desired output quality.
2019
15th Conference on Ph.D. Research in Microelectronics and Electronics, PRIME 2019
approximate computing; energy quality tradeoff; low power
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
Quality aware approximate memory in RISC-V Linux Kernel / Stazi, G.; Mastrandrea, A.; Olivieri, M.; Menichelli, F.. - (2019), pp. 177-180. (Intervento presentato al convegno 15th Conference on Ph.D. Research in Microelectronics and Electronics, PRIME 2019 tenutosi a Lausanne, Switzerald) [10.1109/PRIME.2019.8787745].
File allegati a questo prodotto
File Dimensione Formato  
Stazi_Quality_post-print_2019.pdf

accesso aperto

Tipologia: Documento in Post-print (versione successiva alla peer review e accettata per la pubblicazione)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 109.68 kB
Formato Adobe PDF
109.68 kB Adobe PDF
Stazi_Quality-aware_2019.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.02 MB
Formato Adobe PDF
1.02 MB Adobe PDF   Contatta l'autore

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1350617
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact