high performance computing on graphics processing units: hgpu.org

Two well-known bipartite graph matching algorithms, the Gale-Shapley algorithm and the Hungarian (Kuhn-Munkres) algorithm, has been ported to run on General-Purpose Graphics Processing Units (GPGPU) using kernels written with the CUDA programming model. This was done with the goal of characterising and assessing the performance and behaviour of these matching algorithms on the GPU, and […]

OpenCL SYCL is a new heterogeneous and parallel programming framework created by the Khronos Group that tries to bring OpenCL programming into C++. In particular, it enables C++ developers to create OpenCL kernels, using all the popular C++ features, such as classes, inheritance and templates. What is more, it dramatically reduces programming effort and complexity, […]

Hyperbolic conservation laws are important mathematical models for describing many phenomena in physics or engineering. The Finite Volume (FV) method and the Discontinuous Galerkin (DG) methods are two popular methods for solving conservation laws on computers. Those two methods are good candidates for parallel computing: a) they require a large amount of uniform and simple […]

Irregular algorithms such as Stochastic Gradient Descent (SGD) can benefit from the massive parallelism available on GPUs. However, unlike in data-parallel algorithms, synchronization patterns in SGD are quite complex. Furthermore, scheduling for scale-free graphs is challenging. This work examines several synchronization strategies for SGD, ranging from simple locking to conflict-free scheduling. We observe that static […]

Current Big Data era is generating tremendous amount of data in most fields such as business, social media, engineering, and medicine. The demand to process and handle the resulting "big data" has led to the need for fast data mining methods to develop powerful and versatile analysis tools that can turn data into useful knowledge. […]

ViennaCL is a free open-source linear algebra library for computations on many-core architectures (GPUs, MIC) and multi-core CPUs. The library is written in C++ and supports CUDA, OpenCL, and OpenMP. In addition to core functionality and many other features including BLAS level 1-3 support and iterative solvers, the latest release family ViennaCL 1.6.x provides fast […]

We give an overview of QPACE 2, which is a custom-designed supercomputer based on Intel Xeon Phi processors, developed in a collaboration of Regensburg University and Eurotech. We give some general recommendations for how to write high-performance code for the Xeon Phi and then discuss our implementation of a domain-decomposition-based solver and present a number […]

This document describes an implementation in C of a set of randomized algorithms for computing partial Singular Value Decompositions (SVDs). The techniques largely follow the prescriptions in the article "Finding structure with randomness: Probabilistic algorithms for constructing approximate matrix decompositions," N. Halko, P.G. Martinsson, J. Tropp, SIAM Review, 53(2), 2011, pp. 217-288, but with some […]

To enable the design of large sized caches, novel memory technologies (such as non-volatile memory) and novel fabrication approaches (e.g. 3D stacking) have been explored. The existing modeling tools, however, cover only few memory technologies, CMOS technology nodes and fabrication approaches. We present DESTINY, a tool for modeling 3D (and 2D) cache designs using SRAM, […]

On modern parallel architectures, floating-point computations may become non-deterministic and, therefore, non-reproducible mainly due to non-associativity of floating-point operations. We propose an algorithm to solve dense triangular systems by leveraging the standard parallel triangular solver and our, recently introduced, multi-level exact summation approach. Finally, we present implementations of the proposed fast reproducible triangular solver and […]

We present a fast and memory efficient algorithm for generating Compact Precomputed Voxelized Shadows. By performing much of the common sub-tree merging before identical nodes are ever created, we improve construction times by several orders of magnitude for large data structures, and require much less working memory. We also propose a new set of rules […]

Graphic processing units (GPUs) have gained popularity in scientific computing the recent years. This is because of the massive computing power they can provide for parallel tasks, and while GPUs are powerful, it is also hard to fully utilize their power. A part of this difficulty comes from the many parameters available, and tuning of […]