Improving Performance and Quality-of-Service through the Task-Parallel Model​ : Optimizations and Future Directions for OpenMP

With the failure of Dennard's scaling, which stated that shrinking transistors will be more power-efficient, computer hardware has today become very divergent. Initially the change only concerned the number of processor on a chip (multicores), but has today further escalated into complex hetero...

Full description

Bibliographic Details
Main Author: Podobas, Artur
Format: Doctoral Thesis
Language:English
Published: KTH, Programvaruteknik och Datorsystem, SCS 2015
Subjects:
Online Access:http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-175539
http://nbn-resolving.de/urn:isbn:978-91-7595-711-1
id ndltd-UPSALLA1-oai-DiVA.org-kth-175539
record_format oai_dc
collection NDLTD
language English
format Doctoral Thesis
sources NDLTD
topic Task Parallel
OpenMP
Scheduling
OmpSs
multicore
manycore
spellingShingle Task Parallel
OpenMP
Scheduling
OmpSs
multicore
manycore
Podobas, Artur
Improving Performance and Quality-of-Service through the Task-Parallel Model​ : Optimizations and Future Directions for OpenMP
description With the failure of Dennard's scaling, which stated that shrinking transistors will be more power-efficient, computer hardware has today become very divergent. Initially the change only concerned the number of processor on a chip (multicores), but has today further escalated into complex heterogeneous system with non-intuitive properties -- properties that can improve performance and power consumption but also strain the programmer expected to develop on them. Answering these challenges is the OpenMP task-parallel model -- a programming model that simplifies writing parallel software. Our focus in the thesis has been to explore performance and quality-of-service directions of the OpenMP task-parallel model, particularly by taking architectural features into account. The first question tackled is: what capabilities does existing state of the art runtime-systems have and how do they perform? We empirically evaluated the performance of several modern task-parallel runtime-systems. Performance and power-consumption was measured through the use of benchmarks and we show that the two primary causes for bottlenecks in modern runtime-systems lies in either the task management overheads or how tasks are being distributed across processors. Next, we consider quality-of-service improvements in task-parallel runtime-systems. Striving to improve execution performance, current state of the art runtime-systems seldom take dynamic architectural features such as temperature into account when deciding how work should be distributed across the processors, which can lead to overheating. We developed and evaluated two strategies for thermal-awareness in task-parallel runtime-systems. The first improves performance when the computer system is constrained by temperature while the second strategy strives to reduce temperature while meeting soft real-time objectives. We end the thesis by focusing on performance. Here we introduce our original contribution called BLYSK -- a prototype OpenMP framework created exclusively for performance research. We found that overheads in current runtime-systems can be expensive, which often lead to performance degradation. We introduce a novel way of preserving task-graphs throughout application runs: task-graphs are recorded, identified and optimized the first time an OpenMP application is executed and are later re-used in following executions, removing unnecessary overheads. Our proposed solution can nearly double the performance compared with other state of the art runtime-systems. Performance can also be improved through heterogeneity. Today, manufacturers are placing processors with different capabilities on the same chip. Because they are different, their power-consuming characteristics and performance differ. Heterogeneity adds another dimension to the multiprocessing problem: how should work be distributed across the heterogeneous processors?We evaluated the performance of existing, homogeneous scheduling algorithms and found them to be an ill-match for heterogeneous systems. We proposed a novel scheduling algorithm that dynamically adjusts itself to the heterogeneous system in order to improve performance. The thesis ends with a high-level synthesis approach to improve performance in task-parallel applications. Rather than limiting ourselves to off-the-shelf processors -- which often contains a large amount of unused logic -- our approach is to automatically generate the processors ourselves. Our method allows us to generate application-specific hardware from the OpenMP task-parallel source code. Evaluated using FPGAs, the performance of our System-on-Chips outperformed other soft-cores such as the NiosII processor and were also comparable in performance with modern state of the art processors such as the Xeon PHI and the AMD Opteron. === <p>QC 20151016</p>
author Podobas, Artur
author_facet Podobas, Artur
author_sort Podobas, Artur
title Improving Performance and Quality-of-Service through the Task-Parallel Model​ : Optimizations and Future Directions for OpenMP
title_short Improving Performance and Quality-of-Service through the Task-Parallel Model​ : Optimizations and Future Directions for OpenMP
title_full Improving Performance and Quality-of-Service through the Task-Parallel Model​ : Optimizations and Future Directions for OpenMP
title_fullStr Improving Performance and Quality-of-Service through the Task-Parallel Model​ : Optimizations and Future Directions for OpenMP
title_full_unstemmed Improving Performance and Quality-of-Service through the Task-Parallel Model​ : Optimizations and Future Directions for OpenMP
title_sort improving performance and quality-of-service through the task-parallel model​ : optimizations and future directions for openmp
publisher KTH, Programvaruteknik och Datorsystem, SCS
publishDate 2015
url http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-175539
http://nbn-resolving.de/urn:isbn:978-91-7595-711-1
work_keys_str_mv AT podobasartur improvingperformanceandqualityofservicethroughthetaskparallelmodeloptimizationsandfuturedirectionsforopenmp
_version_ 1718093610853859328
spelling ndltd-UPSALLA1-oai-DiVA.org-kth-1755392015-10-17T04:51:54ZImproving Performance and Quality-of-Service through the Task-Parallel Model​ : Optimizations and Future Directions for OpenMPengPodobas, ArturKTH, Programvaruteknik och Datorsystem, SCSStockholm2015Task ParallelOpenMPSchedulingOmpSsmulticoremanycoreWith the failure of Dennard's scaling, which stated that shrinking transistors will be more power-efficient, computer hardware has today become very divergent. Initially the change only concerned the number of processor on a chip (multicores), but has today further escalated into complex heterogeneous system with non-intuitive properties -- properties that can improve performance and power consumption but also strain the programmer expected to develop on them. Answering these challenges is the OpenMP task-parallel model -- a programming model that simplifies writing parallel software. Our focus in the thesis has been to explore performance and quality-of-service directions of the OpenMP task-parallel model, particularly by taking architectural features into account. The first question tackled is: what capabilities does existing state of the art runtime-systems have and how do they perform? We empirically evaluated the performance of several modern task-parallel runtime-systems. Performance and power-consumption was measured through the use of benchmarks and we show that the two primary causes for bottlenecks in modern runtime-systems lies in either the task management overheads or how tasks are being distributed across processors. Next, we consider quality-of-service improvements in task-parallel runtime-systems. Striving to improve execution performance, current state of the art runtime-systems seldom take dynamic architectural features such as temperature into account when deciding how work should be distributed across the processors, which can lead to overheating. We developed and evaluated two strategies for thermal-awareness in task-parallel runtime-systems. The first improves performance when the computer system is constrained by temperature while the second strategy strives to reduce temperature while meeting soft real-time objectives. We end the thesis by focusing on performance. Here we introduce our original contribution called BLYSK -- a prototype OpenMP framework created exclusively for performance research. We found that overheads in current runtime-systems can be expensive, which often lead to performance degradation. We introduce a novel way of preserving task-graphs throughout application runs: task-graphs are recorded, identified and optimized the first time an OpenMP application is executed and are later re-used in following executions, removing unnecessary overheads. Our proposed solution can nearly double the performance compared with other state of the art runtime-systems. Performance can also be improved through heterogeneity. Today, manufacturers are placing processors with different capabilities on the same chip. Because they are different, their power-consuming characteristics and performance differ. Heterogeneity adds another dimension to the multiprocessing problem: how should work be distributed across the heterogeneous processors?We evaluated the performance of existing, homogeneous scheduling algorithms and found them to be an ill-match for heterogeneous systems. We proposed a novel scheduling algorithm that dynamically adjusts itself to the heterogeneous system in order to improve performance. The thesis ends with a high-level synthesis approach to improve performance in task-parallel applications. Rather than limiting ourselves to off-the-shelf processors -- which often contains a large amount of unused logic -- our approach is to automatically generate the processors ourselves. Our method allows us to generate application-specific hardware from the OpenMP task-parallel source code. Evaluated using FPGAs, the performance of our System-on-Chips outperformed other soft-cores such as the NiosII processor and were also comparable in performance with modern state of the art processors such as the Xeon PHI and the AMD Opteron. <p>QC 20151016</p>Doctoral thesis, comprehensive summaryinfo:eu-repo/semantics/doctoralThesistexthttp://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-175539urn:isbn:978-91-7595-711-1TRITA-ICT ; 2015:13application/pdfinfo:eu-repo/semantics/openAccess