Thread Migration on Distributed-memory Multiprocessors
نویسندگان
چکیده
Executing multi-threaded programs on multiproces-sors can exploit the inherent parallelism among threads. However, the load imbalance and frequent remote data access factors may degrade the performance in distributed-memory parallel systems. To cope with these problems, one of the solutions is to enhance threads with dynamic migration capability. This paper describes our experiences with the design and implementation issues of thread migration in the Xthreads library, which is currently running on the nCUBE2 and iPSC860 machines. Performance measurements of the current implementation are also included .
منابع مشابه
Memory Latency Reduction with Fine-grain Migrating Threads in Numa Shared-memory Multiprocessors
In order to fully realize the potential performance benefits of large-scale NUMA shared memory multiprocessors, efficient techniques to reduce/tolerate long memory access latencies in such systems are to be developed. This paper discusses the concept, software and hardware support for memory latency reduction through fine-grain non-transparent thread migration, referred to as mobile multithread...
متن کاملScheduler-Activated Dynamic Page Migration for Multiprogrammed DSM Multiprocessors
The performance of multiprogrammed shared-memory multiprocessors suffers often from scheduler interventions that neglect data locality. On cachecoherent distributed shared-memory (DSM) multiprocessors, such scheduler interventions tend to increase the rate of remote memory accesses. This paper presents a novel dynamic page migration algorithm that remedies this problem in iterative parallel pro...
متن کاملOn the compilation of data-parallel languages on a distributed memory multithreaded environment with thread migration
This paper focuses on the use of distributed memory multithreaded environments in data parallel programs and has two main goals. The rst is to show that data parallel programs can support features like communication overlapping, load balancing without global data parallel object redistribution and the eecient use of clusters of uniprocessor and/or symmetric multiprocessors (SMPs). Our extended ...
متن کاملSystem Software Support for Reducing Memory Latency on Distributed Shared Memory Multiprocessors
This paper overviews results from our recent work on building customized system software support for Distributed Shared Memory Multiprocessors. The mechanisms and policies outlined in this paper are connected with a single conceptual thread: they all attempt to reduce the memory latency of parallel programs by optimizing critical system services, while hiding the complex architectural details o...
متن کاملA Summary of Research in System Software and Concurrency at the University of Malta: Multithreading
Multithreading has emerged as a leading paradigm for the development of applications with demanding performance requirements. This can be attributed to the benefits that are reaped through the overlapping of I/O with computation and the added bonus of speedup when multiprocessors are employed. However, the use of multithreading brings with it new challenges. Cache utilisation is often very poor...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1994