Efficient Distributed Shared State for Heterogeneous Machine Architectures

نویسندگان

  • Chunqiang Tang
  • DeQing Chen
  • Sandhya Dwarkadas
  • Michael L. Scott
چکیده

InterWeave is a distributed middleware system that supports the sharing of strongly typed, pointer-rich data structures across heterogeneous platforms. As a complement to RPC-based systems such as CORBA, .NET, and Java RMI, InterWeave allows processes to access shared data using ordinary reads and writes. Experience indicates that InterWeave-style sharing facilitates the rapid development of distributed applications, and enhances performance through transparent caching of state. In this paper, we focus on the aspects of InterWeave specifically designed to accommodate heterogeneous machine architectures. Beyond the traditional challenges of message-passing in heterogeneous systems, InterWeave (1) identifies and tracks data changes in the face of relaxed coherence models, (2) employs a wire format that captures not only data but also diffs in a machine and languageindependent form, and (3) swizzles pointers to maintain long-lived (cross-call) address transparency. To support these operations, InterWeave maintains an extensive set of metadata structures, and employs a variety of performance optimizations. Experimental results show that InterWeave achieves performance comparable to that of RPC parameter passing when transmitting previously uncached data. When updating data that have already been cached, InterWeave’s use of platform-independent diffs allows it to significantly outperform the straightforward use of RPC.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

S-DSM for Heterogeneous Machine Architectures

Many—indeed most—distributed applications employ some notion of distributed shared state: information required at more than one location. For applications that span the Internet, this state is almost always maintained by means of hand-written, application-specific messagepassing protocols. These protocols constitute a significant burden on the programmer. Rochester’s InterWeave project seeks to...

متن کامل

Distributed Matrix Factorization using Asynchrounous Communication

Using the matrix factorization technique in machine learning is very common mainly in areas like recommender systems. Despite its high prediction accuracy and its ability to avoid over-fitting of the data, the Bayesian Probabilistic Matrix Factorization algorithm (BPMF) has not been widely used on large scale data because of the prohibitive cost. In this paper, we propose a distributed high-per...

متن کامل

Support for Machine and Language Heterogeneity in a Distributed Shared State System

InterWeave is a distributed middleware system that supports the sharing of strongly typed, pointer-rich data structures across heterogeneous platforms. Unlike RPC-style systems (including DCOM, CORBA, Java RMI), InterWeave does not require processes to employ a procedural interface: it allows them to access shared data using ordinary reads and writes. To save bandwidth in wide area networks, In...

متن کامل

A Comparison of Parallel Compositing Techniques on Shared Memory Architectures

Parallel compositing techniques have traditionally focused on distributed memory architectures with communication of pixel values usually being the main bottleneck. On shared memory architectures, communication is handled through memory accesses, obviating the need for explicit communication steps. Shared memory architectures with multiple graphics accelerators provide the capability for parall...

متن کامل

Hardware Supported Synchronization Primitives for Clusters

Parallel architectures with shared memory are well suited to many applications, provided that efficient shared memory access and process synchronization mechanisms are available. When the parallel machine is a cluster with physically distributed memory, software based synchronization mechanisms together with virtual memory infrastructure can implement Software Distributed Shared Memory (S-DSM),...

متن کامل

ذخیره 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 نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2003