On-Line Debugging and Performance Monitoring with Barriers
نویسندگان
چکیده
We introduce the Stupid Barrier Tricks (SBT) library for on-line debugging and performance monitoring of sharedmemory parallel programs. Single-program-multiple-data (SPMD) programs often use barriers to synchronize threads of execution and to delimit the start and end of different phases of computation. Through the novel (and simple) named barriers construct, dynamic performance warnings, and integration with lightweight performance counter libraries, SBT helps programmers localize deadlocks and performance bottlenecks in their programs. SBT is a portable library that currently supports both POSIX threads and SGI Irix sproc threads. SBT also supports both the PCL and Irix libperfex performance counter libraries. For production runs, the SBT overheads can be eliminated using conditional compilation.
منابع مشابه
موانع و تسهیل کننده های انجام نظارت بر درمان در دانشگاه علوم پزشکی همدان
Background: Monitoring and/or control are the management main duties. This duty is so important which some of authorities believed that efficient management depends on Effective Control System (ECS).This study aimed at identifyingbarriersandfacilitators of performance monitoring and providing some strategies for effective health care monitoring.Materials and Method: This study was a qualitative...
متن کاملA Case Study of Selected SPLASH-2 Applications and the SBT Debugging Tool
SBT is portable library and tool for on-line debugging and performance monitoring of shared-memory parallel programs using the single-program-multiple-data (SPMD) model of parallelism. SPMD programs often use barriers to synchronize threads of execution and to delimit the start and end of different phases of computation. Through its useful barrier constructs, dynamic performance warnings, and i...
متن کاملSupporting On-line Distributed Monitoring and Debugging
Monitoring systems have traditionally been developed with rigid objectives and functionalities, and tied to specific languages, libraries and run-time environments. There is a need for more flexible monitoring systems which can be easily adapted to distinct requirements. On-line monitoring has been considered as increasingly important for observation and control of a distributed application. In...
متن کاملApplication-Dependent Dynamic Monitoring of Distributed and Parallel Systems
Achieving high performance for parallel or distributed programs often requires substantial amounts of information about the programs themselves, about the systems on which they are executing, and about specific program runs. The monitoring system presented in this paper collects, analyzes, and makes application-dependent monitoring information available to the programmer and to the executing pr...
متن کاملIn search of a standards-based approach to hybrid performance monitoring
A new multicomputer performance monitoring system is described in this paper. Where possible, the system employs portable performance monitoring instrumentation technology and leverages previous work. Trace event acquisition is hardware assisted and based on the MultiKron, a single–chip measurement solution developed at the National Institute for Standards and Technology. The user interface is ...
متن کامل