high performance computing on graphics processing units: hgpu.org

The goal of the course is to study parallel algorithms and their implementation on distributed and shared memory computers, using message passing, OpenMP, and threads. In the second half of the course we will consider general purpose graphics processing units. Prerequisites are a working knowledge of C (or willingness to acquire programming skills) and a […]

Block-structured matrices arise in several contexts in circuit simulation problems. These matrices typically inherit the pattern of sparsity from the circuit connectivity. However, they are also characterized by dense spots or blocks. Direct factorization of those matrices has emerged as an attractive approach if the host memory is sufficiently large to store the block-structured matrix. […]

The Intel Xeon Phi coprocessor is a PCI Express form factor card designed to work in tangent with Intel Xeon processors in order to allow faster execution of highly parallelizable code. Efficient execution of highly parallel applications is achieved through the use of many smaller, lower clock speed cores; allowing for many more simultaneous execution […]

Writing high-performance GPU implementations of graph algorithms can be challenging. In this paper, we argue that three optimizations called throughput optimizations are key to high-performance for this application class. These optimizations describe a large implementation space making it unrealistic for programmers to implement them by hand. To address this problem, we have implemented these optimizations […]

Efforts at understanding the computational processes in the brain have met with limited success, despite their importance and potential uses in building intelligent machines. We propose a simple new model which draws on recent findings in Neuroscience and the Applied Mathematics of interacting Dynamical Systems. The Feynman Machine is a Universal Computer for Dynamical Systems, […]

Power capping is a fundamental method for reducing the energy consumption of a wide range of modern computing environments, ranging from mobile embedded systems to datacentres. Unfortunately, maximising performance and system efficiency under static power caps remains challenging, while maximising performance under dynamic power caps has been largely unexplored. We present an adaptive power capping […]

Domain specific languages have successfully been used in a variety of fields to cleanly express scientific problems as well as to simplify implementation and performance optimization on different computer architectures. Although a large number of stencil languages are available, finite difference domain specific languages have proved challenging to design because most practical use cases require […]

We propose a new parallel framework for fast computation of inverse and forward dynamics of articulated robots based on prefix sums (scans). We re-investigate the well-known recursive Newton-Euler formulation of robot dynamics and show that the forward-backward propagation process for robot inverse dynamics is equivalent to two scan operations on certain semigroups. We show that […]

We advocate the Loop-of-stencil-reduce pattern as a means of simplifying the implementation of data-parallel programs on heterogeneous multi-core platforms. Loop-of-stencil-reduce is general enough to subsume map, reduce, map-reduce, stencil, stencil-reduce, and, crucially, their usage in a loop in both data-parallel and streaming applications, or a combination of both. The pattern makes it possible to deploy […]

Accuracy, descriptor size, and the time required for extraction and matching are all important factors when selecting local image descriptors. To optimize over all these requirements, this paper presents a CUDA port for the recent Learned Arrangement of Three Patches (LATCH) binary descriptors to the GPU platform. The design of LATCH makes it well suited […]

We propose an approximate strategy to efficiently train neural network based language models over very large vocabularies. Our approach, called adaptive softmax, circumvents the linear dependency on the vocabulary size by exploiting the unbalanced word distribution to form clusters that explicitly minimize the expectation of computational complexity. Our approach further reduces the computational cost by […]

Soon to be operational HI survey instruments such as APERTIF and ASKAP will produce large datasets. These surveys will provide information about the HI in and around hundreds of galaxies with a typical signal-to-noise ratio of ~10 in the inner regions and ~1 in the outer regions. In addition, such surveys will make it possible […]