An Advanced Compiler Designed for a VLIW DSP for Sensors-Based Systems

The VLIW architecture can be exploited to greatly enhance instruction level parallelism, thus it can provide computation power and energy efficiency advantages, which satisfies the requirements of future sensor-based systems. However, as VLIW codes are mainly compiled statically, the performance of...

Full description

Bibliographic Details
Main Authors: Hu He, Xu Yang
Format: Article
Language:English
Published: MDPI AG 2012-04-01
Series:Sensors
Subjects:
Online Access:http://www.mdpi.com/1424-8220/12/4/4466/
_version_ 1828348665939361792
author Hu He
Xu Yang
author_facet Hu He
Xu Yang
author_sort Hu He
collection DOAJ
description The VLIW architecture can be exploited to greatly enhance instruction level parallelism, thus it can provide computation power and energy efficiency advantages, which satisfies the requirements of future sensor-based systems. However, as VLIW codes are mainly compiled statically, the performance of a VLIW processor is dominated by the behavior of its compiler. In this paper, we present an advanced compiler designed for a VLIW DSP named Magnolia, which will be used in sensor-based systems. This compiler is based on the Open64 compiler. We have implemented several advanced optimization techniques in the compiler, and fulfilled the O3 level optimization. Benchmarks from the DSPstone test suite are used to verify the compiler. Results show that the code generated by our compiler can make the performance of Magnolia match that of the current state-of-the-art DSP processors.
first_indexed 2024-04-14T00:57:44Z
format Article
id doaj.art-b380a8e26b9c46bd9e0b90172f1497e2
institution Directory Open Access Journal
issn 1424-8220
language English
last_indexed 2024-04-14T00:57:44Z
publishDate 2012-04-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj.art-b380a8e26b9c46bd9e0b90172f1497e22022-12-22T02:21:32ZengMDPI AGSensors1424-82202012-04-011244466447810.3390/s120404466An Advanced Compiler Designed for a VLIW DSP for Sensors-Based SystemsHu HeXu YangThe VLIW architecture can be exploited to greatly enhance instruction level parallelism, thus it can provide computation power and energy efficiency advantages, which satisfies the requirements of future sensor-based systems. However, as VLIW codes are mainly compiled statically, the performance of a VLIW processor is dominated by the behavior of its compiler. In this paper, we present an advanced compiler designed for a VLIW DSP named Magnolia, which will be used in sensor-based systems. This compiler is based on the Open64 compiler. We have implemented several advanced optimization techniques in the compiler, and fulfilled the O3 level optimization. Benchmarks from the DSPstone test suite are used to verify the compiler. Results show that the code generated by our compiler can make the performance of Magnolia match that of the current state-of-the-art DSP processors.http://www.mdpi.com/1424-8220/12/4/4466/compilersoptimizationVLIW DSPsensor-based systems
spellingShingle Hu He
Xu Yang
An Advanced Compiler Designed for a VLIW DSP for Sensors-Based Systems
Sensors
compilers
optimization
VLIW DSP
sensor-based systems
title An Advanced Compiler Designed for a VLIW DSP for Sensors-Based Systems
title_full An Advanced Compiler Designed for a VLIW DSP for Sensors-Based Systems
title_fullStr An Advanced Compiler Designed for a VLIW DSP for Sensors-Based Systems
title_full_unstemmed An Advanced Compiler Designed for a VLIW DSP for Sensors-Based Systems
title_short An Advanced Compiler Designed for a VLIW DSP for Sensors-Based Systems
title_sort advanced compiler designed for a vliw dsp for sensors based systems
topic compilers
optimization
VLIW DSP
sensor-based systems
url http://www.mdpi.com/1424-8220/12/4/4466/
work_keys_str_mv AT huhe anadvancedcompilerdesignedforavliwdspforsensorsbasedsystems
AT xuyang anadvancedcompilerdesignedforavliwdspforsensorsbasedsystems
AT huhe advancedcompilerdesignedforavliwdspforsensorsbasedsystems
AT xuyang advancedcompilerdesignedforavliwdspforsensorsbasedsystems