Filters








30,041 Hits in 2.6 sec

Iterative compilation on mobile devices [article]

Paschalis Mpeis, Pavlos Petoumenos, Hugh Leather
2016 arXiv   pre-print
In this paper we present an iterative compiler which employs a novel capture and replay technique in order to collect real user input and use it later to evaluate different transformations offline.  ...  While tuning strategies for desktop and server applications have a long history, it is difficult to adapt them for use on mobile phones.  ...  Our iterative compiler runs on the device itself and uses the Clang driver [10] , version 3.6.1.  ... 
arXiv:1511.02603v4 fatcat:b6xbzindujddti2amqbz5edsou

A pervasive Internet approach to fine-grain power-aware computing

A. Abukmail, A.S. Helal
2006 International Symposium on Applications and the Internet (SAINT'06)  
code locally on the mobile device or remotely to the server based on power efficiency.  ...  We present a novel approach to conserve power in networked mobile devices.  ...  Chris Healy of Furman University for providing us with the software package that we used as a basis to calculate the number of loop iterations (vpcc compiler). References  ... 
doi:10.1109/saint.2006.5 dblp:conf/saint/AbukmailH06 fatcat:orvp7mxnq5gcbfxixlyxc7h7gu

OpenCL-Based Mobile GPGPU Benchmarking

Rotem Aviv, Guohui Wang
2016 Proceedings of the 4th International Workshop on OpenCL - IWOCL '16  
Benchmarking general-purpose computing on graphics processing unit (GPGPU) aims to profile and compare performance across different devices.  ...  This can be challenging in mobile devices due to lack of underlying hardware details and limited profiling capabilities in some platforms.  ...  INTRODUCTION As image processing, computer vision and multimedia applications became more popular on mobile devices during the past several years, general-purpose computing on graphics processing units  ... 
doi:10.1145/2909437.2909441 dblp:conf/iwocl/AvivW16 fatcat:gyxvjhsvmfayxap2vqhf5metuu

A Near-Zero Run-Time Energy Overhead within a Computation Outsourcing Framework for Energy Management in Mobile Devices

A. Abukmail, A.S. Helal
2008 Fifth International Conference on Information Technology: New Generations (itng 2008)  
As computation outsourcing is a methodology for saving energy on mobile devices, the amount of overhead incurred must be kept to a minimum.  ...  As a result of producing this client/server version, certain runtime support has to take place on both the machine executing the client (the mobile device) as the machine executing the server.  ...  the mobile device.  ... 
doi:10.1109/itng.2008.81 dblp:conf/itng/AbukmailH08 fatcat:kenvvk33y5eydo7bjdopyv337q

A programming language for ad-hoc networks of mobile devices

Yang Ni, Ulrich Kremer, Liviu Iftode
2004 Proceedings of the 7th workshop on Workshop on languages, compilers, and run-time support for scalable systems - LCR '04  
Spatial Views (SV) is a language that provides high-level abstractions for applications executing on volatile networks of embedded systems and mobile devices.  ...  The programming model relies on the compiler to translate high level SV programs into low level programs that use light-weight execution migration and property based routing.  ...  INTRODUCTION Ad-hoc networks of embedded systems and mobile devices devices connected through an ad-hoc network are emerging as an important new computing platform.  ... 
doi:10.1145/1066650.1066662 fatcat:xculo3e7frbrtdfw6sxk52rx24

CPrune: Compiler-Informed Model Pruning for Efficient Target-Aware DNN Execution [article]

Taeho Kim, Yongin Kwon, Jemin Lee, Taeho Kim, Sangtae Ha
2022 arXiv   pre-print
Due to the resource constraints of mobile devices, researchers have focused on either making a lightweight deep neural network (DNN) model using model pruning or generating an efficient code using compiler  ...  Mobile devices run deep learning models for various purposes, such as image classification and speech recognition.  ...  a mobile device.  ... 
arXiv:2207.01260v2 fatcat:och5wqfjzfc6jkavluemtdxm64

RT3D: Achieving Real-Time Execution of 3D Convolutional Neural Networks on Mobile Devices [article]

Wei Niu, Mengshu Sun, Zhengang Li, Jou-An Chen, Jiexiong Guan, Xipeng Shen, Yanzhi Wang, Sijia Liu, Xue Lin, Bin Ren
2021 arXiv   pre-print
The reason is more complex model structure and higher model dimensionality overwhelm the available computation/storage resources on mobile devices.  ...  Mobile devices are becoming an important carrier for deep learning tasks, as they are being equipped with powerful, high-end mobile CPUs and GPUs.  ...  acceleration frameworks on mobile devices.  ... 
arXiv:2007.09835v2 fatcat:qsyhrk6hhvcjfc2tcxyxoqupya

Performance optimizations in an LLVM-based cloud application store

Viktor Ivanikov, Shamil Kurmangaleev, Andrey Belevantsev, Arutyun Avetisyan
2013 Ninth International Conference on Computer Science and Information Technologies Revised Selected Papers  
This paper describes the two-stage compilation system based on LLVM compiler infrastructure and the performance optimizations made possible by this deployment technique.  ...  LLVM BITCODE APPLICATION SERVER When using two-stage compilation workflow for mobile devices, one must be careful to select the proper optimizations to be executed on the target device, as it is usually  ...  When testing our two-stage compilation approach on the target mobile ARM-based devices, we have implemented three variants of optimization levels like below: • Minimal: no optimization (level zero) for  ... 
doi:10.1109/csitechnol.2013.6710362 fatcat:ofy53qxqrvh4phdhykasns27xm

A Privacy-Preserving-Oriented DNN Pruning and Mobile Acceleration Framework [article]

Yifan Gong, Zheng Zhan, Zhengang Li, Wei Niu, Xiaolong Ma, Wenhao Wang, Bin Ren, Caiwen Ding, Xue Lin, Xiaolin Xu, Yanzhi Wang
2020 arXiv   pre-print
In addition, corresponding optimizations at the compiler level are leveraged for inference accelerations on devices.  ...  Weight pruning of deep neural networks (DNNs) has been proposed to satisfy the limited storage and computing capability of mobile edge devices.  ...  Algorithm-Level Framework Compiler-Level Framework After pattern-based pruning, we rely on a compiler-based acceleration framework to achieve real-time DNN executions on resourcerestricted mobile devices  ... 
arXiv:2003.06513v2 fatcat:yl7ale6mfjb43dmlx6bdwn2le4

Programming ad-hoc networks of mobile and resource-constrained devices

Yang Ni, Ulrich Kremer, Adrian Stere, Liviu Iftode
2005 Proceedings of the 2005 ACM SIGPLAN conference on Programming language design and implementation - PLDI '05  
Ad-hoc networks of mobile devices such as smart phones and PDAs represent a new and exciting distributed system architecture.  ...  This paper discusses SpatialViews, a high-level language designed for programming mobile devices connected through a wireless ad-hoc network.  ...  Based on the selected iteration approach, the compiler generates code that extends classes in the appropriate library.  ... 
doi:10.1145/1065010.1065040 dblp:conf/pldi/NiKSI05 fatcat:kml5rinuwjg4dcf4me4nfboejq

Programming ad-hoc networks of mobile and resource-constrained devices

Yang Ni, Ulrich Kremer, Adrian Stere, Liviu Iftode
2005 SIGPLAN notices  
Ad-hoc networks of mobile devices such as smart phones and PDAs represent a new and exciting distributed system architecture.  ...  This paper discusses SpatialViews, a high-level language designed for programming mobile devices connected through a wireless ad-hoc network.  ...  Based on the selected iteration approach, the compiler generates code that extends classes in the appropriate library.  ... 
doi:10.1145/1064978.1065040 fatcat:vwdfoai6qbbuxgxfoheu5s5keq

RT3D: Achieving Real-Time Execution of 3D Convolutional Neural Networks on Mobile Devices

Wei Niu, Mengshu Sun, Zhengang Li, Jou-An Chen, Jiexiong Guan, Xipeng Shen, Yanzhi Wang, Sijia Liu, Xue Lin, Bin Ren
2021 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
The reason is more complex model structure and higher model dimensionality overwhelm the available computation/storage resources on mobile devices.  ...  Mobile devices are becoming an important carrier for deep learning tasks, as they are being equipped with powerful, high-end mobile CPUs and GPUs.  ...  ) are representative compiler-assisted deep learning acceleration frameworks on mobile devices.  ... 
doi:10.1609/aaai.v35i10.17108 fatcat:khv2ne6xr5favkhugazo2zzvjy

One DBMS for all

Tobias Mühlbauer, Wolf Rödiger, Robert Seilbeck, Angelika Reiser, Alfons Kemper, Thomas Neumann
2014 Proceedings of the 2014 ACM SIGMOD international conference on Management of data - SIGMOD '14  
The e cient compilation of transactions and queries into ecient machine code allows for high performance, independent of the target platform.  ...  It is the goal of this demonstration to showcase the same HyPer codebase running on (a) a wimpy ARM-based smartphone system and (b) a brawny x86-64-based server system.  ...  Nonetheless, the need for high-performance database systems on mobile devices is growing.  ... 
doi:10.1145/2588555.2594527 dblp:conf/sigmod/MuhlbauerRSRK014 fatcat:3zdhul3jknhylfhvykxhhyuk7e

NPAS: A Compiler-aware Framework of Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration [article]

Zhengang Li, Geng Yuan, Wei Niu, Pu Zhao, Yanyu Li, Yuxuan Cai, Xuan Shen, Zheng Zhan, Zhenglun Kong, Qing Jin, Zhiyu Chen, Sijia Liu (+4 others)
2021 arXiv   pre-print
With the increasing demand to efficiently deploy DNNs on mobile edge devices, it becomes much more important to reduce unnecessary computation and increase the execution speed.  ...  must-do for mobile acceleration.  ...  on mobile devices (mobile CPU and GPU).  ... 
arXiv:2012.00596v3 fatcat:zinvvpwb5fb2zmqsyifdrfhwga

Towards Real-Time DNN Inference on Mobile Platforms with Model Pruning and Compiler Optimization [article]

Wei Niu, Pu Zhao, Zheng Zhan, Xue Lin, Yanzhi Wang, Bin Ren
2020 arXiv   pre-print
To address this problem, we propose a set of hardware-friendly structured model pruning and compiler optimization techniques to accelerate DNN executions on mobile devices.  ...  High-end mobile platforms rapidly serve as primary computing devices for a wide range of Deep Neural Network (DNN) applications.  ...  ., 2017] , it is quite challenging to achieve real-time DNN executions on mobile devices.  ... 
arXiv:2004.11250v1 fatcat:lcll73pmjraalfz3a5qklpm4ty
« Previous Showing results 1 — 15 out of 30,041 results