high performance computing on graphics processing units: hgpu.org

Good old on-line back-propagation for plain multi-layer perceptrons yields a very low 0.35% error rate on the famous MNIST handwritten digits benchmark. All we need to achieve this best result so far are many hidden layers, many neurons per layer, numerous deformed training images, and graphics cards to greatly speed up learning.

Good old online backpropagation for plain multilayer perceptrons yields a very low 0.35% error rate on the MNIST handwritten digits benchmark. All we need to achieve this best result so far are many hidden layers, many neurons per layer, numerous deformed training images to avoid overfitting, and graphics cards to greatly speed up learning. Good […]

In this paper, we propose a multi-camera application capable of processing high resolution images and extracting features based on colors patterns over graphic processing units (GPU). The goal is to work in real time under the uncontrolled environment of a sport event like a football match. Since football players are composed for diverse and complex […]

Interest in Graphical Processing Units (GPUs) is skyrocketing due to their potential to yield spectacular performance on many important computing applications. Unfortunately, writing such efficient GPU kernels requires painstaking manual optimization effort which is very error prone. We contribute the first comprehensive symbolic verifier for kernels written in CUDA C. Called the ‘Prover of User […]

While advanced 3D graphics techniques are well understood and supported by industry standards, this is less true in the emerging mobile applications and games market. This book redresses this imbalance, providing an in-depth look at the new OpenGL ES (The Standard for Embedded Accelerated 3D Graphics), and shows what these new embedded systems graphics libraries […]

This paper presents a technique for mapping relief textures onto arbitrary polygonal models in real time. In this approach, the mapping of the relief data is done in tangent space. As a result, it can be applied to polygonal representations of curved surfaces producing correct self-occlusions, interpenetrations, shadows and per-pixel lighting effects. The approach can […]

We present a sampling strategy and rendering framework for intersectable models, whose surface is implicitly defined by a black box intersection test that provides the location and normal of the closest intersection of a ray with the surface. To speed up image generation despite potentially slow intersection tests, our method exploits spatial coherence by adjusting […]

In this work we present a hardware-accelerated direct volume rendering system for visualizing multivariate wave functions in semiconducting quantum dot (QD) simulations. The simulation data contains the probability density values of multiple electron orbitals for up to tens of millions of atoms, computed by the NEMO3-D quantum device simulator software run on large-scale cluster architectures. […]

Graphics Processing Units (GPUs) offer tremendous computational power. CUDA (Compute Unified Device Architecture) provides a multi-threaded parallel programming model, facilitating high performance implementations of general-purpose computations. However, the explicitly managed memory hierarchy and multi-level parallel view make manual development of high-performance CUDA code rather complicated. Hence the automatic transformation of sequential input programs into efficient […]

With the advent of multi-core processors the problem of designing application that efficiently can utilize it performance become more and more important. Moreover developing programs for these processors requires from the programmers some additional, specific knowledge about the processor architecture. In multi-core systems efficient program execution is the main issue. It can even happen that […]

Stream based languages are a popular approach to expressing parallelism in modern applications. The efficient mapping of streaming parallelism to multi-core processors is, however, highly dependent on the program and underlying architecture. We address this by developing a portable and automatic compiler-based approach to partitioning streaming programs using machine learning. Our technique predicts the ideal […]

In this paper we discuss a framework for modeling the 3D lung dynamics of normal and diseased human subjects and visualizing them using an Augmented Reality (AR) based environment. The framework is based on the results obtained from pulmonary function tests and lung image-data of human subjects obtained from 4D High-Resolution Computed Tomography (HRCT). The […]