The Semantics of Blocking and Nonblocking Send and Receive Primitives

نویسندگان

  • Robert Cypher
  • Eric Leu
چکیده

Current message-passing parallel computers provide send and receive primitives with a wide variety of blocking, synchronization , selectivity and ordering properties. Unfortunately , the interactions between the diierent properties of the send and receive primitives can be extremely complex, and as a result, the precise semantics of these primitives are not well understood. In this paper we present formal models for message-passing systems that provide both synchronous and asynchronous sends, both blocking and nonblocking sends and receives, and a variety of ordering properties. In addition, the receive primitives are very general in that they can specify the desired source and/or tag value of a message. Our models apply to all message-passing programs, including ones with errors, and they apply to parallel computers with arbitrary amounts of buuering. To the best of our knowledge , this is the rst time that such rich message-passing models have been deened formally. In addition to presenting the formal models, we also give a number of theorems that capture the properties of the models.

برای دانلود رایگان 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

Nonblocking collectives for scalable Java communications

This paper presents a Java implementation of the recently published MPI 3.0 nonblocking message passing collectives in order to analyze and assess the feasibility of taking advantage of these operations in shared memory systems using Java. Nonblocking collectives aim to exploit the overlapping between computation and communication for collective operations to increase scalability of message pas...

متن کامل

A Process Algebraic View of Linda Coordination Primitives

The main Linda coordination primitives (asynchronous communication, read operation, nonblocking in/rd predicates) are studied in a process algebraic setting. A lattice of eight languages is proposed, where its bottom element L is a process algebra differing from CCS only for the asynchrony of the output operation, while all the other languages in the lattice are obtained as extension of this ba...

متن کامل

A Scalable Lock-Free Universal Construction with Best Effort Transactional Hardware

The imminent arrival of best-effort transactional hardware has spurred new interest in the construction of nonblocking data structures, such as those that require atomic updates to k words of memory (for some small value of k). Since transactional memory itself (TM) was originally proposed as a universal construction for crafting scalable lock-free data structures, we explore the possibility of...

متن کامل

Embedding the free-choice semantics of AND/XOR-EPCs into the Boolean semantics

Abstract. Each Event-driven Process Chain (EPC) translates into a free-choice system if its control flow branches and joins only at ANDor XOR-connectors. This free-choice system defines the free-choice semantics of the AND/XOR-EPC. But free-choice systems are not capable to deal with OR-connectors. Therefore a general EPC with OR-connectors obtains a semantics not until it has been translated i...

متن کامل

New CMT-SCTP with increased speed of data transmission

Communication protocols issues are one of the effective factors in communicated networks performance. One of challenging problem in CMT-SCTP which sends data by multipath concurrently is Receive Buffer Blocking. This problem has important role in data transmission speed in computer networks. In this paper, we propose a control method based on fuzzy logic so that can solve Receive Buffer Blockin...

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

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1994