high performance computing on graphics processing units: hgpu.org

The STI Cell Broadband Engine (BE) is a highly capable heterogeneous multicore processor with large bandwidth and computing power perfectly suited for numerical simulation. However, all performance benefits come at the price of productivity since more responsibility is put to the programmer. In particular, programming with the IBM Cell SDK is hampered by not only […]

In this paper we present the design and implementation of a dynamic instrumentation infrastructure for PTX programs that procedurally transforms kernels and manages related data structures. We show how performing instrumentation within the GPU Ocelot dynamic compiler infrastructure provides unique capabilities not available to other profiling and instrumentation toolchains for GPU computing. We demonstrate the […]

Computer systems are moving towards a heterogeneous architecture with a combination of one or more CPUs and one or more accelerator processors. Such heterogeneous systems pose a new challenge to the parallel programming community. Languages such as OpenCL and CUDA provide a program environment for such systems. However, they focus on data parallel programming where […]

Parallel programming is used extensively for general-purpose computations. However, performance of parallel APIs varies for a given problem and a given architecture. This gives rise to the need for having an abstract way to express the parallel problems. This poster presents a new approach through which programmers can access these APIs without having to focus […]

In the field of video analytics for surveillance, the trend towards the use of multi-camera and high definition video is increasing. This poses significant technical challenges in terms of video transmission and real-time processing for surveillance analytics, such as people recognition and tracking. Currently, available solutions are typically proprietary commercial systems which are costly to […]

Traditional Beowulf clusters have been homogeneous platforms for distributed-memory MIMD parallelism. However, the shift to multicore architectures has made shared-memory MIMD parallelism increasingly important, and inexpensive manycore GPGPUs have revived SIMD parallelism. This paper presents a case study in designing and building a heterogeneous cluster as a learning platform for tera-scale distributed- and shared-memory MIMD […]

This paper introduces an industry strength, multi-purpose, benchmark: Shamrock. Developed at the Atomic Weapons Establishment (AWE), Shamrock is a two dimensional (2D) structured hydrocode; one of its aims is to assess the impacts of a change in hardware, and (in conjunction with a larger HPC Benchmark Suite) to provide guidance in procurement of future systems. […]

A dense 3-d terrain model obtained using reconstruction methods from aerial images is represented in a probabilistic volumetric framework. The choice of probabilistic representation is to represent inherent ambiguity in reconstruction of surface from images. Such probabilistic representation handles the ambiguity very well but leads to expensive dense volumetric storage. The area coverage required for […]

Graphics Processing Units (GPU) have become the platform of choice for accelerating a large range of data parallel and task parallel applications. Both AMD and NVIDIA have developed GPU implementations targeted at the high performance computing market. The rapid adoption of GPU computing has been greatly aided by the introduction of high-level programming environments such […]

SkePU is a C++ template library that provides a simple and unified interface for specifying data-parallel computations with the help of skeletons on GPUs using CUDA and OpenCL. The interface is also general enough to support other architectures, and SkePU implements both a sequential CPU and a parallel OpenMP backend. It also supports multi-GPU systems. […]

The development of standard processors changed in the last years moving from bigger, more complex, and faster cores to putting several more simple cores onto one chip. This changed also the way programs are written in order to leverage the processing power of multiple cores of the same processor. In the beginning, programmers had to […]

We present SkePU, a C++ template library which provides a simple and unified interface for specifying data-parallel computations with the help of skeletons on GPUs using CUDA and OpenCL. The interface is also general enough to support other architectures, and SkePU implements both a sequential CPU and a parallel OpenMP backend. It also supports multi-GPU […]