Dynamic Task Mapping for MPSoCs

Carvalho, Ewerson; Calazans, Ney; Moraes, Fernando

doi:10.1109/mdt.2010.106

Cited by 121 publications

(22 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Several resource allocation approaches have been proposed while following different policies. Most of these approaches map communicating tasks of each application close to each other such that communication overhead and power are reduced [2], [7], [8], [9], [11], [21], [23], [31], [34]. Some of these approaches also reduce computation power of the cores by employing voltage/frequency scaling [9].…”

Section: Related Workmentioning

confidence: 99%

Bubble budgeting: throughput optimization for dynamic workloads by exploiting dark cores in many core systems

Wang

Singh

et al. 2016

2016 Tenth IEEE/ACM International Symposium on Networks-on-Chip (NOCS)

View full text Add to dashboard Cite

Abstract-All the cores of a many-core chip cannot be active at the same time, due to reasons like low CPU utilization in server systems and limited power budget in dark silicon era. These free cores (referred to as bubbles) can be placed near active cores for heat dissipation so that the active cores can run at a higher frequency level, boosting the performance of applications that run on active cores. Budgeting inactive cores (bubbles) to applications to boost performance has the following three challenges. First, the number of bubbles varies due to open workloads. Second, communication distance increases when a bubble is inserted between two communicating tasks (a task is a thread or process of a parallel application), leading to performance degradation. Third, budgeting too many bubbles as coolers to running applications leads to insufficient cores for future applications. In order to address these challenges, in this paper, a bubble budgeting scheme is proposed to budget free cores to each application so as to optimize the throughput of the whole system. Throughput of the system depends on the execution time of each application and the waiting time incurred for newly arrived applications. Essentially, the proposed algorithm determines the number and locations of bubbles to optimize the performance and waiting time of each application, followed by tasks of each application being mapped to a core region. A Rollout algorithm is used to budget power to the cores as the last step. Experiments show that our approach achieves 50% higher throughput when compared to state-of-the-art thermal-aware runtime task mapping approaches. The runtime overhead of the proposed algorithm is in the order of 1M cycles, making it an efficient runtime task management method for large-scale many-core systems.

show abstract

Section: Related Workmentioning

confidence: 99%

Bubble budgeting: throughput optimization for dynamic workloads by exploiting dark cores in many core systems

Wang

Singh

et al. 2016

2016 Tenth IEEE/ACM International Symposium on Networks-on-Chip (NOCS)

View full text Add to dashboard Cite

show abstract

“…For NoC based heterogeneous MPSoCs, Carvalho et al [27,28] proposed dynamic task mapping heuristics. The performance of mapping heuristic is observed for dynamic workloads.…”

Section: Related Workmentioning

confidence: 99%

Dynamic task mapping for Network-on-Chip based systems

Maqsood

Ali

Malik

et al. 2015

Journal of Systems Architecture

View full text Add to dashboard Cite

“…Carvalho et al [1] compare six dynamic mapping algorithms. The First Free (FF) simply selects the next compatible IP core to map a given task, thus walking sequentially through all IP cores before considering an IP core again.…”

Section: Dynamic Mapping Algorithmsmentioning

confidence: 99%

“…load of new applications) and/or performance (e.g. change the frequency operation for optimizing battery lifetime) requirements, which leads in both time-changing processor workload and communication patterns [1][3] [4]. Thus, offlinemapping techniques can be sub-optimal or inadequate in many scenarios.…”

Section: Introductionmentioning

confidence: 99%

“…the affinity of the task to a PE) must be considered at run-time. In this context, Carvalho et al [1] proposed and evaluated the performance of six mono-task mapping heuristics considering different application workloads. Some of these heuristics were extended to consider multi-tasks mapping onto the same PE, while minimizing the commutation overhead in the same NoC-based platform [2].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Comparative analysis of dynamic task mapping heuristics in heterogeneous NoC-based MPSoCs

Möller

Indrusiak

Ost

et al. 2012

2012 International Symposium on System on Chip (SoC)

View full text Add to dashboard Cite

Dynamic mapping heuristics can cope with dynamic application scenarios by allocating tasks to cores of an MPSoC during runtime. In this paper, we compare eight heuristics in terms of the response time of application tasks -that is, the time between the issuing of a task and the time when it completes executing and communicating. By taking into account the task execution, communication and waiting times, we could better evaluate the quality of the different heuristics and show that there is room for improvement when it comes to heterogeneous platforms under high utilization.

show abstract

Dynamic Task Mapping for MPSoCs

Cited by 121 publications

References 12 publications

Bubble budgeting: throughput optimization for dynamic workloads by exploiting dark cores in many core systems

Bubble budgeting: throughput optimization for dynamic workloads by exploiting dark cores in many core systems

Dynamic task mapping for Network-on-Chip based systems

Comparative analysis of dynamic task mapping heuristics in heterogeneous NoC-based MPSoCs

Contact Info

Product

Resources

About