high performance computing on graphics processing units: hgpu.org

This paper presents a graphics processing unit with energy-saving techniques. Several techniques and architectures are proposed to achieve high performance with low power consumption. First of all, low power core pipeline is designed with 2-issue VLIW architecture to reduce power consumption while achieving the processing capability of 400MFLOPS or 800MOPS. In addition, inter/intra adaptive mutli-threading […]

Speaker recognition systems classify a test signal as a speaker or an imposter by evaluating a matching score between input and reference signals. We propose a new information theoretic approach for computation of the matching score using the Renyi entropy. The proposed entropic distance, the Kernelized Renyi distance (KRD), is formulated in a non-parametric way […]

In this paper we consider a multiresolution filter and its realization on the Cell BE and GPUs. We not only present common and specific optimization strategies undertaken for obtaining maximum performance on these architectures, but also how to obtain a speedup of 6.57x and 33.24x compared to an optimized OpenMP baseline implementation. Furthermore, we also […]

Orthopedic surgery treats the musculoskeletal system, in which bleeding is common and can be fatal. To help train future surgeons in this complex practice, researchers designed and implemented a serious game for learning orthopedic surgery. The game focuses on teaching trainees blood management skills, which are critical for safe operations. Using state-of-the-art graphics technologies, the […]

View-reconstruction and display is an important part of many applications in digital holography such as computer vision and microscopy. Thus far, this has been an offline procedure for megapixel sized holograms. This paper introduces an implementation of real-time view-reconstruction using programmable graphics hardware. The theory of Fresnel-based view-reconstruction is introduced, after which an implementation using […]

We present an extension of Loop and Schaefer’s approximation of Catmull-Clark surfaces (ACC) for surfaces with creases and corners. We discuss the integration of ACC into Valve’s Source game engine and analyze performance of our implementation.

Dynamic water surface simulation is an important part of simulating natural scene. Ben Humphrey used projection texture mapping, depth texture and mobile texture to render dynamic water surface and got a good result. In this paper, an improvement method will presented for speeding up its rendering speed and enhancing the rendering effects. It uses a […]

A low-power and high-performance 4-way 32-bit stream processor core is developed for handheld low-power 3-D graphics systems. It contains a floating-point unified matrix, vector, and elementary function unit. By exploiting the logarithmic arithmetic and the proposed adaptive number conversion scheme, a 4-way arithmetic unit achieves a single-cycle throughput for all these operations except for the […]

We present a technique for the illustrative rendering of 3D line data at interactive frame rates. We create depth-dependent halos around lines to emphasize tight line bundles while less structured lines are de-emphasized. Moreover, the depth-dependent halos combined with depth cueing via line width attenuation increase depth perception, extending techniques from sparse line rendering to […]

Video visualization is a computation process that extracts meaningful information from original video data sets and conveys the extracted information to users in appropriate visual representations. This paper presents a broad treatment of the subject, following a typical research pipeline involving concept formulation, system development, a path-finding user study, and a field trial with real […]

Quantitative trading requires a lot of computing power in order to analyze derivatives prices and financial microstructure. We will describe different ways to use parallel computing that are used within a proprietary trading firm. We will discuss in-house tools that we developed in order to quickly transcribe mathematical concepts into working parallel implementation to develop […]

This paper presents a computer simulator for the CAFADIS camera. CAFADIS is a patented camera (PCT/ES2007/000046) that measures wave-front phases and 3D distances under different scenarios (from microns to kilometres), using highly specialised electronic technology, namely Graphics Processing Units (GPUs) and Field Programmable Gate Arrays (FPGAs). Since 3DTV is one of the most important applications […]