We introduce two Python frameworks to train neural networks on large datasets: Blocks and Fuel. Blocks is based on Theano, a linear algebra compiler with CUDA-support. It facilitates the training of complex neural network models by providing parametrized Theano operations, attaching metadata to Theano’s symbolic computational graph, and providing an extensive set of utilities to […]

June 5, 2015 by hgpu

With the advent of hardware accelerator technologies, multi-core processors and GPUs, much effort for taking advantage of those architectures by designing parallel algorithms has been made. To achieve this goal, one needs to consider both algebraic complexity and parallelism, plus making efficient use of memory traffic, cache, and reducing overheads in the implementations. Polynomial multiplication […]

April 25, 2014 by hgpu

We present a highly scalable algorithm for multiplying sparse multivariate polynomials represented in a distributed format. This algo- rithm targets not only the shared memory multicore computers, but also computers clusters or specialized hardware attached to a host computer, such as graphics processing units or many-core coprocessors. The scal- ability on the large number of […]

April 8, 2013 by hgpu

In this article we report on our experience in computing resultants of bivariate polynomials on Graphics Processing Units (GPU). Following the outline of Collins’ modular approach [6], our algorithm starts by mapping the input polynomials to a finite field for sufficiently many primes m. Next, the GPU algorithm evaluates the polynomials at a number of […]

October 4, 2012 by hgpu

Regular chains, introduced about twenty years ago, have emerged as one of the major tools for solving polynomial systems symbolically. In this thesis, we focus on different algorithmic aspects of the theory of regular chains, from theoretical questions to high-performance implementation issues. The inclusion test for saturated ideals is a fundamental problem in this theory. […]

January 30, 2012 by hgpu

We present a novel certified and complete algorithm to compute arrangements of real planar algebraic curves. It provides a geometric-topological analysis of the decomposition of the plane induced by a finite number of algebraic curves in terms of a cylindrical algebraic decomposition. From a high-level perspective, the overall method splits into two main subroutines, namely […]

January 23, 2012 by hgpu

Derivatives arise frequently in graphics and scientific computation applications. As GPU’s become more widely used for scientific computation the need for derivatives can be expected to increase. To meet this need we have added symbolic differentiation as a built in language feature in the HLSL shading language. The symbolic derivative is computed at compile time […]

November 26, 2011 by hgpu

In this paper we present a simulation environment enhanced with parallel processing which can be used on personal computers, based on a high-level user interface developed on Mathematicacopyright which is connected to C++ code in order to make our platform capable of communicating with a Graphics Processing Unit. We introduce the reader to the behavior […]

March 9, 2011 by hgpu

We propose different implementations of the sparse matrix–dense vector multiplication (spmv{}) for finite fields and rings $Zb/mZb$. We take advantage of graphic card processors (GPU) and multi-core architectures. Our aim is to improve the speed of spmv{} in the linbox library, and henceforth the speed of its black box algorithms. Besides, we use this and […]

November 11, 2010 by hgpu