SIMDOM: A framework for SIMD instruction translation and offloading in heterogeneous mobile architectures
Fog and mobile edge computing is a paradigm that augments resource-scarce mobile devices with resource-rich network servers to enable ubiquitous computing. Smartphone applications rely on code offloading techniques to leverage high-performance computing opportunities available on edge and cloud serv...
Saved in:
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Published: |
Wiley
2017
|
Subjects: | |
Online Access: | http://eprints.um.edu.my/20670/ https://doi.org/10.1002/ett.3174 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.um.eprints.20670 |
---|---|
record_format |
eprints |
spelling |
my.um.eprints.206702019-03-13T01:34:43Z http://eprints.um.edu.my/20670/ SIMDOM: A framework for SIMD instruction translation and offloading in heterogeneous mobile architectures Shuja, Junaid Gani, Abdullah Ko, Kwangman So, Kyoungyoung Mustafa, Saad Madani, Sajjad A. Khan, Muhammad Khurram QA75 Electronic computers. Computer science Fog and mobile edge computing is a paradigm that augments resource-scarce mobile devices with resource-rich network servers to enable ubiquitous computing. Smartphone applications rely on code offloading techniques to leverage high-performance computing opportunities available on edge and cloud servers for compute-intensive applications. Mobile (ARM) and edge/cloud (x86) architectures are heterogeneous and necessitate dynamic binary translation for compiled code migration that increases the application execution time. The application execution time and energy consumption should be lesser on the edge/cloud server as compared with the local mobile execution for optimal offload. Multimedia-based applications contain a large set of single instruction multiple data (SIMD) instructions that are compute and resource intensive. However, dynamic binary translation techniques of SIMD instructions lose the parallelism and optimization because of inefficient vector-to-scalar translation. We present a framework for SIMD instruction translation and offloading for mobile devices (SIMDOM) in cloud and edge environments. The SIMDOM framework reduces the execution overhead of migrated vectorized multimedia application by using vector-to-vector instruction mappings. The framework maps and translates ARM SIMD intrinsic instructions to x86 SIMD intrinsic instructions such that an application programmed for the mobile platform can be executed on the cloud server without any modification. The offload decision is based on inputs from the device energy, network, and application profilers. Experiments show that SIMDOM framework provides 84.78%, 3.41%, and 79.93% energy, time, and performance efficiency, respectively, compared with local offload-disabled execution. Compared with compiled code offloading, the SIMDOM framework provides 55.99%, 57.50%, and 96.23% energy, time, and performance efficiency, respectively. Wiley 2017 Article PeerReviewed Shuja, Junaid and Gani, Abdullah and Ko, Kwangman and So, Kyoungyoung and Mustafa, Saad and Madani, Sajjad A. and Khan, Muhammad Khurram (2017) SIMDOM: A framework for SIMD instruction translation and offloading in heterogeneous mobile architectures. Transactions on Emerging Telecommunications Technologies, 29 (4). e3174. ISSN 2161-3915 https://doi.org/10.1002/ett.3174 doi:10.1002/ett.3174 |
institution |
Universiti Malaya |
building |
UM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Malaya |
content_source |
UM Research Repository |
url_provider |
http://eprints.um.edu.my/ |
topic |
QA75 Electronic computers. Computer science |
spellingShingle |
QA75 Electronic computers. Computer science Shuja, Junaid Gani, Abdullah Ko, Kwangman So, Kyoungyoung Mustafa, Saad Madani, Sajjad A. Khan, Muhammad Khurram SIMDOM: A framework for SIMD instruction translation and offloading in heterogeneous mobile architectures |
description |
Fog and mobile edge computing is a paradigm that augments resource-scarce mobile devices with resource-rich network servers to enable ubiquitous computing. Smartphone applications rely on code offloading techniques to leverage high-performance computing opportunities available on edge and cloud servers for compute-intensive applications. Mobile (ARM) and edge/cloud (x86) architectures are heterogeneous and necessitate dynamic binary translation for compiled code migration that increases the application execution time. The application execution time and energy consumption should be lesser on the edge/cloud server as compared with the local mobile execution for optimal offload. Multimedia-based applications contain a large set of single instruction multiple data (SIMD) instructions that are compute and resource intensive. However, dynamic binary translation techniques of SIMD instructions lose the parallelism and optimization because of inefficient vector-to-scalar translation. We present a framework for SIMD instruction translation and offloading for mobile devices (SIMDOM) in cloud and edge environments. The SIMDOM framework reduces the execution overhead of migrated vectorized multimedia application by using vector-to-vector instruction mappings. The framework maps and translates ARM SIMD intrinsic instructions to x86 SIMD intrinsic instructions such that an application programmed for the mobile platform can be executed on the cloud server without any modification. The offload decision is based on inputs from the device energy, network, and application profilers. Experiments show that SIMDOM framework provides 84.78%, 3.41%, and 79.93% energy, time, and performance efficiency, respectively, compared with local offload-disabled execution. Compared with compiled code offloading, the SIMDOM framework provides 55.99%, 57.50%, and 96.23% energy, time, and performance efficiency, respectively. |
format |
Article |
author |
Shuja, Junaid Gani, Abdullah Ko, Kwangman So, Kyoungyoung Mustafa, Saad Madani, Sajjad A. Khan, Muhammad Khurram |
author_facet |
Shuja, Junaid Gani, Abdullah Ko, Kwangman So, Kyoungyoung Mustafa, Saad Madani, Sajjad A. Khan, Muhammad Khurram |
author_sort |
Shuja, Junaid |
title |
SIMDOM: A framework for SIMD instruction translation and offloading in heterogeneous mobile architectures |
title_short |
SIMDOM: A framework for SIMD instruction translation and offloading in heterogeneous mobile architectures |
title_full |
SIMDOM: A framework for SIMD instruction translation and offloading in heterogeneous mobile architectures |
title_fullStr |
SIMDOM: A framework for SIMD instruction translation and offloading in heterogeneous mobile architectures |
title_full_unstemmed |
SIMDOM: A framework for SIMD instruction translation and offloading in heterogeneous mobile architectures |
title_sort |
simdom: a framework for simd instruction translation and offloading in heterogeneous mobile architectures |
publisher |
Wiley |
publishDate |
2017 |
url |
http://eprints.um.edu.my/20670/ https://doi.org/10.1002/ett.3174 |
_version_ |
1643691345751048192 |
score |
13.160551 |