Graph partitioning applied to DAG scheduling to reduce NUMA effects
Uloženo v:
| Název: | Graph partitioning applied to DAG scheduling to reduce NUMA effects |
|---|---|
| Autoři: | Sánchez Barrera, Isaac, Casas, Marc, Moretó Planas, Miquel, Ayguadé Parra, Eduard, Labarta Mancho, Jesús José, Valero Cortés, Mateo |
| Přispěvatelé: | Universitat Politècnica de Catalunya. Departament d'Arquitectura de Computadors, Barcelona Supercomputing Center, Universitat Politècnica de Catalunya. CAP - Grup de Computació d'Altes Prestacions |
| Informace o vydavateli: | Association for Computing Machinery (ACM) |
| Rok vydání: | 2018 |
| Sbírka: | Universitat Politècnica de Catalunya, BarcelonaTech: UPCommons - Global access to UPC knowledge |
| Témata: | Àrees temàtiques de la UPC::Informàtica::Sistemes d'informació::Emmagatzematge i recuperació de la informació, Memory management (Computer science), Shared memory, Scheduling, Task-based programming model, NUMA, graph partitioning, Gestió de memòria (Informàtica) |
| Popis: | The complexity of shared memory systems is becoming more relevant as the number of memory domains increases, with different access latencies and bandwidth rates depending on the proximity between the cores and the devices containing the data. In this context, techniques to manage and mitigate non-uniform memory access (NUMA) effects consist in migrating threads, memory pages or both and are typically applied by the system software. We propose techniques at the runtime system level to reduce NUMA effects on parallel applications. We leverage runtime system metadata in terms of a task dependency graph. Our approach, based on graph partitioning methods, is able to provide parallel performance improvements of 1.12X on average with respect to the state-of-the-art. ; This work has been partially supported by the RoMoL ERC Advanced Grant (GA 321253), the European HiPEAC Network of Excellence and the Spanish Government (contract TIN2015-65316-P). I. Sánchez Barrera has been supported by the Spanish Government under Formación del Profesorado Universitario fellowship number FPU15/03612. ; Peer Reviewed ; Postprint (published version) |
| Druh dokumentu: | conference object |
| Popis souboru: | 2 p.; application/pdf |
| Jazyk: | English |
| Relation: | https://dl.acm.org/citation.cfm?doid=3178487.3178535; info:eu-repo/grantAgreement/MINECO//TIN2015-65316-P/ES/COMPUTACION DE ALTAS PRESTACIONES VII/; info:eu-repo/grantAgreement/EC/FP7/321253/EU/Riding on Moore's Law/ROMOL; https://hdl.handle.net/2117/117284 |
| DOI: | 10.1145/3178487.3178535 |
| Dostupnost: | https://hdl.handle.net/2117/117284 https://doi.org/10.1145/3178487.3178535 |
| Rights: | Open Access |
| Přístupové číslo: | edsbas.F599DB33 |
| Databáze: | BASE |
Nájsť tento článok vo Web of Science | Abstrakt: | The complexity of shared memory systems is becoming more relevant as the number of memory domains increases, with different access latencies and bandwidth rates depending on the proximity between the cores and the devices containing the data. In this context, techniques to manage and mitigate non-uniform memory access (NUMA) effects consist in migrating threads, memory pages or both and are typically applied by the system software. We propose techniques at the runtime system level to reduce NUMA effects on parallel applications. We leverage runtime system metadata in terms of a task dependency graph. Our approach, based on graph partitioning methods, is able to provide parallel performance improvements of 1.12X on average with respect to the state-of-the-art. ; This work has been partially supported by the RoMoL ERC Advanced Grant (GA 321253), the European HiPEAC Network of Excellence and the Spanish Government (contract TIN2015-65316-P). I. Sánchez Barrera has been supported by the Spanish Government under Formación del Profesorado Universitario fellowship number FPU15/03612. ; Peer Reviewed ; Postprint (published version) |
|---|---|
| DOI: | 10.1145/3178487.3178535 |