DeepAI AI Chat
Log In Sign Up

Connecting MapReduce Computations to Realistic Machine Models

by   Peter Sanders, et al.

We explain how the popular, highly abstract MapReduce model of parallel computation (MRC) can be rooted in reality by explaining how it can be simulated on realistic distributed-memory parallel machine models like BSP. We first refine the model (MRC^+) to include parameters for total work w, bottleneck work ŵ, data volume m, and maximum object sizes m̂. We then show matching upper and lower bounds for executing a MapReduce calculation on the distributed-memory machine –Θ(w/p+ŵ+log p) work and Θ(m/p+m̂+log p) bottleneck communication volume using p processors.


Communication-Optimal Parallel Standard and Karatsuba Integer Multiplication in the Distributed Memory Model

We present COPSIM a parallel implementation of standard integer multipli...

I/O-Optimal Algorithms for Symmetric Linear Algebra Kernels

In this paper, we consider two fundamental symmetric kernels in linear a...

Parallel Matrix Condensation for Calculating Log-Determinant of Large Matrix

Calculating the log-determinant of a matrix is useful for statistical co...

Communication Lower-Bounds for Distributed-Memory Computations for Mass Spectrometry based Omics Data

Mass spectrometry based omics data analysis require significant time and...

Communication Bounds for Convolutional Neural Networks

Convolutional neural networks (CNNs) are important in a wide variety of ...

Optimal Multithreaded Batch-Parallel 2-3 Trees

This paper presents a batch-parallel 2-3 tree T in the asynchronous PPM ...

Taurus: Lightweight Parallel Logging for In-Memory Database Management Systems (Extended Version)

Existing single-stream logging schemes are unsuitable for in-memory data...