SMP-SIM: An SMP-based discrete-event execution-driven performance simulator
نویسندگان
چکیده
Designing and implementing a large-scale parallel system can be time-consuming and costly. It is therefore desirable to enable system developers to predict the performance of a parallel system at its design phase so that they can evaluate design alternatives to better meet performance requirements. Before the target machine is completely built, the developers can always build an symmetric multi-processor (SMP) for evaluation purposes. In this paper, we introduce an SMP-based discrete-event execution-driven performance simulation method for message passing interface (MPI) programs and describe the design and implementation of a simulator called SMP-SIM. As the processes share the same memory space in an SMP, SMP-SIM manages the events globally at the granularity of central processing units (CPUs). Furthermore, by re-implementing core MPI point-to-point communication primitives, SMP-SIM handles the communication virtually and sequential computation actually. Our experimental results show that SMP-SIM is highly accurate and scalable, resulting in errors of less than 7.60% for both SMP and SMP-Cluster target machines.
منابع مشابه
Parallel Iterative Solvers for Ill-Conditioned Problems with Reordering
1. Preconditioned Iterative Solvers with Multicoloring In the previous work [1], author developed an efficient parallel iterative solver for finite-element applications on the Earth Simulator (ES) [2] using multi-level hybrid parallel programming model with MPI and OpenMP. The method employs three-level hybrid parallel programming model for SMP cluster architectures, consisting of MPI, OpenMP a...
متن کاملScaling SMP Machines Through Hierarchical Snooping
We examine an approach to scaling SMP nodes by using a hierarchical bus with transaction filtering to reduce bus traffic. An analysis of messages in a snoop-based cache coherence protocol reveals the types of transactions that can be filtered from the bus hierarchy. We implemented our filtering mechanism in Simics/Ruby, a full-system simulator, and show that bus traffic can be reduced when runn...
متن کاملShared Memory Multiprocessor Architectures for Software IP Routers
In this paper, we propose new shared memory multiprocessor architectures and evaluate their performance for future Internet Protocol (IP) routers based on Symmetric Multi-Processor (SMP) and Cache Coherent Non-Uniform Memory Access (CC-NUMA) paradigms. We also propose a benchmark application suite, RouterBench, which consists of four categories of applications representing key functions on the ...
متن کاملGroup-Based Performance Analysis for Multithreaded SMP Cluster Applications
Performance optimization remains one of the key issues in parallel computing. With the emergence of large clustered SMP systems, the task of analyzing and tuning scientific applications actually becomes harder. Tools need to be extended to cover both distributed and shared– memory styles of performance analysis and to handle the massive amount of information generated by applications on today’s...
متن کاملMely: Efficient Workstealing for Multicore Event-Driven Systems
Many high-performance communicating systems are designed using the event-driven paradigm. As multicore platforms are now pervasive, it becomes crucial for such systems to take advantage of the available hardware parallelism. Event-coloring is a promising approach in this regard. First, it allows programmers to simply and progressively inject support for the safe, parallel execution of multiple ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Comput. Sci. Inf. Syst.
دوره 9 شماره
صفحات -
تاریخ انتشار 2012