Citation Context

...omputed over all prefixes of an N element array in log N time on N processors using parallel prefix computations [6, 9, 13]. MapReduce can be considered a simplification and distillation of some of these models based on our experience with large real-world computations. More significantly, we provide a fault-tolerant implementation that scales to thousands of processors. In contrast, most of the parallel processing systems have only been implemented on smaller scales and leave the details of handling machine failures to the programmer. Bulk Synchronous Programming [17] and some MPI primitives [11] provide higher-level abstractions that make it easier for programmers to write parallel programs. A key difference between these systems and MapReduce is that MapReduce exploits a restricted programming model to parallelize the user program automatically and to provide transparent fault-tolerance. Our locality optimization draws its inspiration from techniques such as active disks [12, 15], where computation is pushed into processing elements that are close to local disks, to reduce the amount of data sent across I/O subsystems or the network. We run on commodity processors to which a small n...

Citation Context

...ample: • The Generic Security Service (GSS) API [48] defines standard functions for verifying identify of communicating parties, encrypting messages, and so forth. • The Message Passing Interface =-=API [43]-=- defines standard interfaces, in several languages, to functions used to transfer data among processes in a parallel computing system. An API may define multiple language bindings or use an Interface ...

Citation Context

...renements were made in the spring of 1995, and Version 1.1 of the MPI Standard is now available [17]. For a detailed presentation of the Standard itself, see [42]� for a tutorial approach to MPI, see =-=[29]-=-. In this paper we assume that the reader is relatively familiar with the MPI speci cation, but we provide a brief overview in Section 2.2. The project to provide a portable implementation of MPI bega...

Citation Context

...ingle process. MPI provides routines for generating new communicators consisting of subsets of processors, though most users rarely need to use these. The book Using MPI, by Lusk, Gropp, and Skjellum =-=[10]-=- provides an excellent introduction to the concepts in MPI, see also the MPI homepage http://www.mcs.anl.gov/mpi/. Note that PETSc users need not program much message passing directly with MPI, but th...

Citation Context

...es of this sort often incorporated implicit state such as default message buffers, and hence were not easily integrated with thread libraries [13, 22]. The more modern Message Passing Interface (MPI) =-=[31]-=- is designed to be thread safe, but provides no explicit support for communication between threads. The Chant runtime system [34] augments MPI calls with a thread identifier. In Mach [46] and NewThrea...

Citation Context

...g. Myrinet [6]. Other advantages are that these systems are scalable, i.e., can be tuned to available budget and needs, and that they use standard software components, i.e., UNIX, PVM [8] and the MPI =-=[10] para-=-llel programming environments. Two examples of such systems are the UC Berkeley NOW project [1], which uses a cluster of SPARC based workstations connected by Myrinet, and NASA's Beowulf "pile-of...