DocumentCode :
2981053
Title :
Hardware-aware Thread Scheduling: The Case of Asymmetric Multicore Processors
Author :
Peternier, Achille ; Ansaloni, Danilo ; Bonetta, D. ; Pautasso, Cesare ; Binder, Walter
Author_Institution :
Univ. of Lugano (USI), Lugano, Switzerland
fYear :
2012
fDate :
17-19 Dec. 2012
Firstpage :
400
Lastpage :
407
Abstract :
Modern processor architectures are increasingly complex and heterogeneous, often requiring solutions tailored to the specific characteristics of each processor model. In this paper we address this problem by targeting the AMD Bulldozer processor as case study for specific hardware-oriented performance optimizations. The Bulldozer architecture features an asymmetric simultaneous multithreading implementation with shared floating point units (FPUs) and per-core arithmetic logic units (ALUs). Bulld Over, presented in this paper, improves thread scheduling by exploiting this hardware characteristic to increase performance of floating point-intensive workloads on Linux-based operating systems. Bulld Over is a user-space monitoring tool that automatically identifies FPU-intensive threads and schedules them in a more efficient way without requiring any patches or modifications at the kernel level. Our measurements using standard benchmark suites show that speedups of up to 10% can be achieved by simply allowing Bulld Over to monitor applications, without any modification of the workload.
Keywords :
Linux; floating point arithmetic; multi-threading; multiprocessing systems; parallel architectures; performance evaluation; processor scheduling; ALU; AMD Bulldozer processor; Bulldozer processor architecture; FPU-intensive threads; Linux-based operating systems; asymmetric multicore processors; asymmetric simultaneous multithreading implementation; floating point-intensive workloads; hardware characteristics; hardware-aware thread scheduling; hardware-oriented performance optimization; per-core arithmetic logic units; shared floating point units; user-space monitoring tool; Benchmark testing; Hardware; Instruction sets; Land vehicles; Monitoring; Radiation detectors; asymmetric processors; multicore; performance; workload characterization;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Parallel and Distributed Systems (ICPADS), 2012 IEEE 18th International Conference on
Conference_Location :
Singapore
ISSN :
1521-9097
Print_ISBN :
978-1-4673-4565-1
Electronic_ISBN :
1521-9097
Type :
conf
DOI :
10.1109/ICPADS.2012.62
Filename :
6413670
Link To Document :
بازگشت