はてなブックマーク

Background A parallel program is intrinsically more complex than its serial counterpart. To write an efficient and scalable parallel program, one must understand the behavior and performance of the program. A powerful technique for this purpose is the visualization of trace files (also called log files). A trace file contains several basic elements. Typically, these are generated during the execut

Kazutomo Yoshii I am a Senior Software developer for the Mathematics and Computer Science Division of Argonne National Laboratory , currently working on ZeptoOS project. My major interests are OS bootstrap mechanism, OS detour(system noise),  parallel I/O, embedded system and build environment. Other than the ZeptoOS release: Specific to IBM BlueGene/L BG/L Compute Node socket program and NetPIPE

MPICH is a high performance and widely portable implementation of the Message Passing Interface (MPI) standard. MPICH and its derivatives form the most widely used implementations of MPI in the world. They are used exclusively on nine of the top 10 supercomputers (June 2016 ranking), including the world’s fastest supercomputer: Taihu Light.

Designing and Building Parallel Programs

Designing and Building Parallel Programs, by Ian Foster Designing and Building Parallel Programs (Online) is an innovative traditional print and online resource publishing project. It incorporates the content of a textbook published by Addison-Wesley into an evolving online resource. Here is a description of the book, and here is the table of contents. See also the list of mirror sites around the

Quick Access MPI Forum MPI Standard 1.1 MPI Standard 2.0 in HTML MPICH Home Page ANL/MSU MPI implementation Download MPICH Free implementation of MPI MPICH2 Home Page ANL MPI implementation Download MPICH2 Free implementation of MPI MPI Home Page Remove Frames What is MPI? MPI is a library specification for message-passing, proposed as a standard by a broadly based committee of vendors, implemento