Bottleneck identification and scheduling in multithreaded applications
Authors:
Open Access
- 3 March 2012
- journal article
- conference paper
- Published by Association for Computing Machinery (ACM) in ACM SIGARCH Computer Architecture News
- Vol. 40 (1) , 223-234
Abstract
Performance of multithreaded applications is limited by a variety of bottlenecks, e.g. critical sections, barriers and slow pipeline stages. These bottlenecks serialize execution, waste valuable execution cycles, and limit scalability of applications. This paper proposes Bottleneck Identification and Scheduling in Multithreaded Applications (BIS), a cooperative software-hardware mechanism to identify and accelerate the most critical bottlenecks. BIS identifies which bottlenecks are likely to reduce performance by measuring the number of cycles threads have to wait for each bottleneck, and accelerates those bottlenecks using one or more fast cores on an Asymmetric Chip Multi-Processor (ACMP). Unlike previous work that targets specific bottlenecks, BIS can identify and accelerate bottlenecks regardless of their type. We compare BIS to four previous approaches and show that it outperforms the best of them by 15% on average. BIS' performance improvement increases as the number of cores and the number of fast cores in the system increase.Keywords
This publication has 24 references indexed in Scilit:
- Parallel application memory scheduling2011
- Performance, Power Efficiency and Scalability of Asymmetric Cluster Chip MultiprocessorsIEEE Computer Architecture Letters, 2006
- Quantifying instruction criticality for shared memory multiprocessors2003
- Speculative synchronization2002
- Focusing processor policies via critical-path prediction2001
- An online computation of critical path profiling1996
- Transactional memory1993
- Synchronization without contention1991
- Dynamic decentralized cache schemes for mimd parallel processors1984
- Validity of the single processor approach to achieving large scale computing capabilities1967