Publications

Results 51–75 of 119
Skip to search filters

Demonstrating improved application performance using dynamic monitoring and task mapping

2014 IEEE International Conference on Cluster Computing, CLUSTER 2014

Brandt, James M.; Devine, Karen D.; Gentile, Ann C.; Pedretti, Kevin P.

This work demonstrates the integration of monitoring, analysis, and feedback to perform application-to-resource mapping that adapts to both static architecture features and dynamic resource state. In particular, we present a framework for mapping MPI tasks to compute resources based on run-time analysis of system-wide network data, architecture-specific routing algorithms, and application communication patterns. We address several challenges. Within each node, we collect local utilization data. We consolidate that information to form a global view of system performance, accounting for system-wide factors including competing applications. We provide an interface for applications to query the global information. Then we exploit the system information to change the mapping of tasks to nodes so that system bottlenecks are avoided. We demonstrate the benefit of this monitoring and feedback by remapping MPI tasks based on route-length, bandwidth, and credit-stalls metrics for a parallel sparse matrix-vector multiplication kernel. In the best case, remapping based on dynamic network information in a congested environment recovered 48.9% of the time lost to congestion, reducing matrix-vector multiplication time by 7.8%. Our experiments focus on the Cray XE/XK platform, but the integration concepts are generally applicable to any platform for which applicable metrics and route knowledge can be obtained.

More Details
TYPE Conference Poster YEAR 2014
ScopusOSTIDOI

Using architecture information and real-time resource state to reduce power consumption and communication costs in parallel applications

Brandt, James M.; Devine, Karen D.; Gentile, Ann C.; Leung, Vitus J.; Olivier, Stephen L.; Pedretti, Kevin P.; Rajamanickam, Sivasankaran R.; Bunde, David P.; Deveci, Mehmet D.; Catalyurek, Umit V.

As computer systems grow in both size and complexity, the need for applications and run-time systems to adjust to their dynamic environment also grows. The goal of the RAAMP LDRD was to combine static architecture information and real-time system state with algorithms to conserve power, reduce communication costs, and avoid network contention. We devel- oped new data collection and aggregation tools to extract static hardware information (e.g., node/core hierarchy, network routing) as well as real-time performance data (e.g., CPU uti- lization, power consumption, memory bandwidth saturation, percentage of used bandwidth, number of network stalls). We created application interfaces that allowed this data to be used easily by algorithms. Finally, we demonstrated the benefit of integrating system and application information for two use cases. The first used real-time power consumption and memory bandwidth saturation data to throttle concurrency to save power without increasing application execution time. The second used static or real-time network traffic information to reduce or avoid network congestion by remapping MPI tasks to allocated processors. Results from our work are summarized in this report; more details are available in our publications [2, 6, 14, 16, 22, 29, 38, 44, 51, 54].

More Details
TYPE SAND Report YEAR 2014
OSTIDOI

Exploiting geometric partitioning in task mapping for parallel computers

Proceedings of the International Parallel and Distributed Processing Symposium, IPDPS

Deveci, Mehmet; Rajamanickam, Sivasankaran R.; Leung, Vitus J.; Pedretti, Kevin P.; Olivier, Stephen L.; Bunde, David P.; Catalyurek, Umit V.; Devine, Karen D.

We present a new method for mapping applications' MPI tasks to cores of a parallel computer such that communication and execution time are reduced. We consider the case of sparse node allocation within a parallel machine, where the nodes assigned to a job are not necessarily located within a contiguous block nor within close proximity to each other in the network. The goal is to assign tasks to cores so that interdependent tasks are performed by 'nearby' cores, thus lowering the distance messages must travel, the amount of congestion in the network, and the overall cost of communication. Our new method applies a geometric partitioning algorithm to both the tasks and the processors, and assigns task parts to the corresponding processor parts. We show that, for the structured finite difference mini-app Mini Ghost, our mapping method reduced execution time 34% on average on 65,536 cores of a Cray XE6. In a molecular dynamics mini-app, Mini MD, our mapping method reduced communication time by 26% on average on 6144 cores. We also compare our mapping with graph-based mappings from the LibTopoMap library and show that our mappings reduced the communication time on average by 15% in MiniGhost and 10% in MiniMD. © 2014 IEEE.

More Details
TYPE Conference YEAR 2014
ScopusOSTI
Results 51–75 of 119
Results 51–75 of 119