Welcome to KMR#

This is KMR, a high-performance map-reduce library. KMR-1.0 is available since 2013-04-26. KMR works on ordinary clusters as well as large-scale supercomputers. KMR source code is available under the BSD license.

Latest release is KMR-1.10 (2018-11-16).

KMR is a set of high-performance map-reduce operations in the MPI (Message Passing Interface) environment. It makes programming for data-processing much easier by hiding low-level details of message passing. Its main targets are large-scale supercomputers with thousands of compute nodes. KMR provides utilities other than map-reduce operations to address issues such as accessing very large file-systems, on platforms K and Fujitsu FX10.

KMR is designed to work in-memory and to exploit large amount of memory available on supercomputers, whereas most map-reduce implementations are designed to work with external (disk-based) operations. So, data exchanges in KMR occur as message passing instead of remote file operations. The KMR routines work in bulk-synchronous and the most part of the code is sequential, but the code inside the mapper and reducer are multi-threaded.

Documents#

Downloading#

Tutorials#

Project Site#

Publications#

  • K MapReduce: A Scalable Tool for Data-Processing and Search/Ensemble Applications on Large-Scale Supercomputers. Motohiko Matsuda, Naoya Maruyama, and Shinichiro Takizawa. IEEE Cluster Computing (CLUSTER) 2013. (C) Copyright IEEE. ieeexplore.ieee.org
    It describes an overview and optimizations used in KMR.
  • Supporting Workflow Management of Scientific Applications by MapReduce Programming Model. Shinichiro Takizawa, Motohiko Matsuda, and Naoya Maruyama. IPSJ HPCS 2014. (in Japanese). http://id.nii.ac.jp/1001/00096874
    It describes some scientific applications workflow implemented in MapReduce using KMR.
  • Evaluation of Asynchronous MPI Communication in Map-Reduce System on the K Computer. Motohiko Matsuda, Naoya Maruyama, and Shinichiro Takizawa. EuroMPI Workshop 2014. (C) Copyright ACM. dl.acm.org
    It compares all-to-all collective communication versus asynchronous communication in shuffling communication, to qualify believed effectiveness of overlapping of communication and computation.

Acknowledgment#

KMR is a product of RIKEN R-CCS. Part of the results is obtained by using K computer at RIKEN R-CCS.


DISCLAIMER#

KMR comes with ABSOLUTELY NO WARRANTY. This wiki also comes with ABSOLUTELY NO WARRANTY. Contents are liable to change.