NDLI: Neural acceleration for general-purpose approximate programs (CACM, Vol. 58, Issue. 1)

Content Provider	ACM Digital Library
Author	Ceze, Luis Esmaeilzadeh, Hadi Burger, Doug Sampson, Adrian
Abstract	As improvements in per-transistor speed and energy efficiency diminish, radical departures from conventional approaches are needed to continue improvements in the performance and energy efficiency of general-purpose processors. One such departure is approximate computing, where error in computation is acceptable and the traditional robust digital abstraction of near-perfect accuracy is relaxed. Conventional techniques in energy-efficient computing navigate a design space defined by the two dimensions of performance and energy, and traditionally trade one for the other. General-purpose approximate computing explores a third dimension---error---and trades the accuracy of computation for gains in both energy and performance. Techniques to harvest large savings from small errors have proven elusive. This paper describes a new approach that uses machine learning-based transformations to accelerate approximation-tolerant programs. The core idea is to train a learning model how an approximable region of code---code that can produce imprecise but acceptable results---behaves and replace the original code region with an efficient computation of the learned model. We use neural networks to learn code behavior and approximate it. We describe the Parrot algorithmic transformation, which leverages a simple programmer annotation ("approximable") to transform a code region from a von Neumann model to a neural model. After the learning phase, the compiler replaces the original code with an invocation of a low-power accelerator called a neural processing unit (NPU). The NPU is tightly coupled to the processor pipeline to permit profitable acceleration even when small regions of code are transformed. Offloading approximable code regions to NPUs is faster and more energy efficient than executing the original code. For a set of diverse applications, NPU acceleration provides whole-application speedup of 2.3× and energy savings of 3.0× on average with average quality loss of at most 9.6%. NPUs form a new class of accelerators and show that significant gains in both performance and efficiency are achievable when the traditional abstraction of near-perfect accuracy is relaxed in general-purpose computing.
Starting Page	105
Ending Page	115
Page Count	11
File Format	PDF
ISSN	00010782 15577317
DOI	10.1145/2589750
Journal	Communications of the ACM (CACM)
Volume Number	58
Issue Number	1
Language	English
Publisher	Association for Computing Machinery (ACM)
Publisher Date	2005-08-01
Publisher Place	New York
Access Restriction	One Nation One Subscription (ONOS)
Content Type	Text
Resource Type	Article
Subject	Computer Science Computer Science

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Big data needs approximate computing (CACM, Vol. 58, Issue. 1)

Wearables (CACM, Vol. 58, Issue. 1)

Disambiguating databases (CACM, Vol. 58, Issue. 1)

Internal access controls (CACM, Vol. 58, Issue. 1)

Interactive intent modeling (CACM, Vol. 58, Issue. 1)

Scalability techniques for practical synchronization primitives (CACM, Vol. 58, Issue. 1)

A little queue theory (CACM, Vol. 58, Issue. 1)

In search of Bayesian inference (CACM, Vol. 58, Issue. 1)

Smart transportation networks drive gains (CACM, Vol. 58, Issue. 1)

Neural acceleration for general-purpose approximate programs (CACM, Vol. 58, Issue. 1)

Similar Documents

Big data needs approximate computing (CACM, Vol. 58, Issue. 1)

Wearables (CACM, Vol. 58, Issue. 1)

Disambiguating databases (CACM, Vol. 58, Issue. 1)

Internal access controls (CACM, Vol. 58, Issue. 1)

Interactive intent modeling (CACM, Vol. 58, Issue. 1)

Scalability techniques for practical synchronization primitives (CACM, Vol. 58, Issue. 1)

A little queue theory (CACM, Vol. 58, Issue. 1)

In search of Bayesian inference (CACM, Vol. 58, Issue. 1)

Smart transportation networks drive gains (CACM, Vol. 58, Issue. 1)

Neural acceleration for general-purpose approximate programs (CACM, Vol. 58, Issue. 1)