Schedule Based Code Generation for ParallelProcessors
Dynamic model driven architecture (DMDA) is a architecture made to aid in the development of parallel computing code. This thesis is applied to an implementation of DMDA known as DMDA3 that should convert graphs of computations into efficient computation code, and it deals with the translation of Pl...
Main Author: | |
---|---|
Format: | Others |
Language: | English |
Published: |
Linnéuniversitetet, Institutionen för datavetenskap, fysik och matematik, DFM
2010
|
Subjects: | |
Online Access: | http://urn.kb.se/resolve?urn=urn:nbn:se:lnu:diva-222 |
id |
ndltd-UPSALLA1-oai-DiVA.org-lnu-222 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-UPSALLA1-oai-DiVA.org-lnu-2222018-01-13T05:16:12ZSchedule Based Code Generation for ParallelProcessorsengNygård, JohanLinnéuniversitetet, Institutionen för datavetenskap, fysik och matematik, DFM2010Parallel programmingDMDADynamic Model Driven ArchitectureJavaLOISComputer SciencesDatavetenskap (datalogi)Dynamic model driven architecture (DMDA) is a architecture made to aid in the development of parallel computing code. This thesis is applied to an implementation of DMDA known as DMDA3 that should convert graphs of computations into efficient computation code, and it deals with the translation of Platform Specific Models (PSM) into running systems. Currently DMDA3 can generate schedules of operations but not finished code. This thesis describes a DMDA3 module that turns a schedule of operations into a runable program. Code was obtained from the DMDA3 schedules by reflection and a framework was build that allowed generation of low level language code from schedules. The module is written in Java and can currently generate C and Fortran code for computational tasks. Based on runtime tests for matrix multiplication algorithms the generated code is almost as fast as handwritten code. Student thesisinfo:eu-repo/semantics/bachelorThesistexthttp://urn.kb.se/resolve?urn=urn:nbn:se:lnu:diva-222application/pdfinfo:eu-repo/semantics/openAccess |
collection |
NDLTD |
language |
English |
format |
Others
|
sources |
NDLTD |
topic |
Parallel programming DMDA Dynamic Model Driven Architecture Java LOIS Computer Sciences Datavetenskap (datalogi) |
spellingShingle |
Parallel programming DMDA Dynamic Model Driven Architecture Java LOIS Computer Sciences Datavetenskap (datalogi) Nygård, Johan Schedule Based Code Generation for ParallelProcessors |
description |
Dynamic model driven architecture (DMDA) is a architecture made to aid in the development of parallel computing code. This thesis is applied to an implementation of DMDA known as DMDA3 that should convert graphs of computations into efficient computation code, and it deals with the translation of Platform Specific Models (PSM) into running systems. Currently DMDA3 can generate schedules of operations but not finished code. This thesis describes a DMDA3 module that turns a schedule of operations into a runable program. Code was obtained from the DMDA3 schedules by reflection and a framework was build that allowed generation of low level language code from schedules. The module is written in Java and can currently generate C and Fortran code for computational tasks. Based on runtime tests for matrix multiplication algorithms the generated code is almost as fast as handwritten code. |
author |
Nygård, Johan |
author_facet |
Nygård, Johan |
author_sort |
Nygård, Johan |
title |
Schedule Based Code Generation for ParallelProcessors |
title_short |
Schedule Based Code Generation for ParallelProcessors |
title_full |
Schedule Based Code Generation for ParallelProcessors |
title_fullStr |
Schedule Based Code Generation for ParallelProcessors |
title_full_unstemmed |
Schedule Based Code Generation for ParallelProcessors |
title_sort |
schedule based code generation for parallelprocessors |
publisher |
Linnéuniversitetet, Institutionen för datavetenskap, fysik och matematik, DFM |
publishDate |
2010 |
url |
http://urn.kb.se/resolve?urn=urn:nbn:se:lnu:diva-222 |
work_keys_str_mv |
AT nygardjohan schedulebasedcodegenerationforparallelprocessors |
_version_ |
1718608997024530432 |