Implementation of GTS
Graph Traverse Scheduling, GTS [ALTB89], was developed as a technique suitable for parallelizing DO loops with cycles on their dependence graph, but actually, GTS is a generalization of many loop restructuring techniques. The improvements achieved with its application in front of other techniques ar...
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | SER |
| Materias: | |
| Acceso en línea: | http://hdl.handle.net/20.500.12110/paper_03029743_v817LNCS_n_p555_Barrado |
| Aporte de: |
| id |
todo:paper_03029743_v817LNCS_n_p555_Barrado |
|---|---|
| record_format |
dspace |
| spelling |
todo:paper_03029743_v817LNCS_n_p555_Barrado2023-10-03T15:19:33Z Implementation of GTS Barrado, C. Labarta, J. Borensztejn, P. Maritsas D. Theodoridis S. Halatsis C. Philokyprou G. Commision of the European Union; et al.; General Secretariat of Research and Technology; Greek Ministry of Cultural Affairs; Intracom; Ministry of Education Memory architecture Scheduling Dependence graphs ITS applications Memory hierarchy Parallel code Re-structuring techniques Restructuring compilers Scalar optimization Shared memory multiprocessor Parallel architectures Graph Traverse Scheduling, GTS [ALTB89], was developed as a technique suitable for parallelizing DO loops with cycles on their dependence graph, but actually, GTS is a generalization of many loop restructuring techniques. The improvements achieved with its application in front of other techniques are the reduction of synchronizations, the introduction of scalar optimizations and the better use of the memory hierarchy. The purpose of this work has been the implementation of this new technique for a particular existing shared-memory multiprocessor and its integration on a source-to-source restructuring compiler. We studied the limitations imposed by the architecture to the technique and modified it in order to adapt the generated parallel code to the architecture. Finally, we measured the improvements of the new scheduling comparing the execution time of some example loops obtained by the commercial parallelizer with the execution time obtained by GTS. © Springer-Verlag Berlin Heidelberg 1994. SER info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by/2.5/ar http://hdl.handle.net/20.500.12110/paper_03029743_v817LNCS_n_p555_Barrado |
| institution |
Universidad de Buenos Aires |
| institution_str |
I-28 |
| repository_str |
R-134 |
| collection |
Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) |
| topic |
Memory architecture Scheduling Dependence graphs ITS applications Memory hierarchy Parallel code Re-structuring techniques Restructuring compilers Scalar optimization Shared memory multiprocessor Parallel architectures |
| spellingShingle |
Memory architecture Scheduling Dependence graphs ITS applications Memory hierarchy Parallel code Re-structuring techniques Restructuring compilers Scalar optimization Shared memory multiprocessor Parallel architectures Barrado, C. Labarta, J. Borensztejn, P. Maritsas D. Theodoridis S. Halatsis C. Philokyprou G. Commision of the European Union; et al.; General Secretariat of Research and Technology; Greek Ministry of Cultural Affairs; Intracom; Ministry of Education Implementation of GTS |
| topic_facet |
Memory architecture Scheduling Dependence graphs ITS applications Memory hierarchy Parallel code Re-structuring techniques Restructuring compilers Scalar optimization Shared memory multiprocessor Parallel architectures |
| description |
Graph Traverse Scheduling, GTS [ALTB89], was developed as a technique suitable for parallelizing DO loops with cycles on their dependence graph, but actually, GTS is a generalization of many loop restructuring techniques. The improvements achieved with its application in front of other techniques are the reduction of synchronizations, the introduction of scalar optimizations and the better use of the memory hierarchy. The purpose of this work has been the implementation of this new technique for a particular existing shared-memory multiprocessor and its integration on a source-to-source restructuring compiler. We studied the limitations imposed by the architecture to the technique and modified it in order to adapt the generated parallel code to the architecture. Finally, we measured the improvements of the new scheduling comparing the execution time of some example loops obtained by the commercial parallelizer with the execution time obtained by GTS. © Springer-Verlag Berlin Heidelberg 1994. |
| format |
SER |
| author |
Barrado, C. Labarta, J. Borensztejn, P. Maritsas D. Theodoridis S. Halatsis C. Philokyprou G. Commision of the European Union; et al.; General Secretariat of Research and Technology; Greek Ministry of Cultural Affairs; Intracom; Ministry of Education |
| author_facet |
Barrado, C. Labarta, J. Borensztejn, P. Maritsas D. Theodoridis S. Halatsis C. Philokyprou G. Commision of the European Union; et al.; General Secretariat of Research and Technology; Greek Ministry of Cultural Affairs; Intracom; Ministry of Education |
| author_sort |
Barrado, C. |
| title |
Implementation of GTS |
| title_short |
Implementation of GTS |
| title_full |
Implementation of GTS |
| title_fullStr |
Implementation of GTS |
| title_full_unstemmed |
Implementation of GTS |
| title_sort |
implementation of gts |
| url |
http://hdl.handle.net/20.500.12110/paper_03029743_v817LNCS_n_p555_Barrado |
| work_keys_str_mv |
AT barradoc implementationofgts AT labartaj implementationofgts AT borensztejnp implementationofgts AT maritsasd implementationofgts AT theodoridiss implementationofgts AT halatsisc implementationofgts AT philokyproug implementationofgts AT commisionoftheeuropeanunionetalgeneralsecretariatofresearchandtechnologygreekministryofculturalaffairsintracomministryofeducation implementationofgts |
| _version_ |
1807320263971307520 |