Third Workshop on Programmability Issues for Multi-Core Computers (MULTIPROG-3)
نویسندگان
چکیده
In this paper we present a complete Java STM framework, called Deuce, intended as a platform for developing scalable concurrent applications and as a research tool for designing new STM algorithms. It was not clear if one could build an e cient Java STM without compiler support. Deuce provides several bene ts over existing Java STM frameworks: it avoids any changes or additions to the JVM, it does not require language extensions or intrusive APIs, and it does not impose any memory footprint or GC overhead. To support legacy libraries, Deuce dynamically instruments classes at load time and uses an original eld-based locking strategy to improve concurrency. Deuce also provides a simple internal API allowing di erent STMs algorithms to be plugged in. We show empirical results that highlight the scalability of our framework running benchmarks with hundreds of concurrent threads. This paper shows for the rst time that one can actually design a Java STM with reasonable performance without compiler support.
منابع مشابه
Second Workshop on Programmability Issues for Multi-Core Computers (MULTIPROG-2)
Despite the speed up of PC technology over the years, real-time performance of video processing in medical X-ray procedures continues to be an issue as the size and number of concurrent data streams is increasing steadily. Since the computing evolves quicker than memory technology, there is an increasing pressure on an efficient use of the off-chip memory bandwidth. Additionally, as a multitude...
متن کاملFirst Workshop on Programmability Issues for Multi-Core Computers (MULTIPROG-1)
We are certainly approaching the construction of very powerful supercomputers based on large multicore chips and approaching counts of millions of cores. Is the situation very different from the description in the book of Genesis of the attempt to build the Tower of Babel and the confusion of tongues? How to program such machines is certainly one of the most challenging issues for the immediate...
متن کاملPerformance comparison of finite-difference modeling on Cell, FPGA and multi-core computers
How does the performance of Cell, field-programmable gate array (FPGA), and multi-core computers compare for finitedifference modeling of the acoustic wave equation? In this paper I answer this question by assessing implementations on each of these architectures. Results show that on average, 7.49, 5.01, and 3.74 GFLOPs were sustained, respectively, by the FPGA, quad-core, and Cell machines for...
متن کاملHand Gestures Classification with Multi-Core DTW
Classifications of several gesture types are very helpful in several applications. This paper tries to address fast classifications of hand gestures using DTW over multi-core simple processors. We presented a methodology to distribute templates over multi-cores and then allow parallel execution of the classification. The results were presented to voting algorithm in which the majority vote was ...
متن کاملFastFlow: high-level and efficient streaming on multi-core∗ (A FastFlow short tutorial)
Computer hardware manufacturers have moved decisively to multi-core and are currently experimenting with increasingly advanced many-core architectures. In the long term, writing efficient, portable and correct parallel programs targeting multiand many-core architectures must become no more challenging than writing the same programs for sequential computers. To date, however, most applications r...
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 2010