high performance computing on graphics processing units: hgpu.org

Parallel and heterogeneous computing are growing in audience thanks to the increased performance brought by ubiquitous manycores and GPUs. However, available programming models, like OPENCL or CUDA, are far from being straightforward to use. As a consequence, several automated or semi-automated approaches have been proposed to automatically generate hardware-level codes from high-level sequential sources. Polyhedral […]

E(A+M)PEC traces the ionization structure, cooling and emission spectra of plasmas. It is written in OpenCL, runs in NVIDIA Graphics Processor Units and can be coupled to any HD or MHD code to follow the dynamical and thermal evolution of any plasma in, e.g., the interstellar medium (ISM).

General-purpose computing on graphics processing units, also known as GPGPU, is a burgeoning technique to enhance the computation of parallel programs. Applying this technique to real-time applications, however, requires additional support for timeliness of execution. In particular, the non-preemptive nature of GPGPU, associated with copying data to/from the device memory and launching code onto the […]

Mining the increasing amount of genomic data requires having very efficient tools. Increasing the efficiency can be obtained with better algorithms, but one could also take advantage of the hardware itself to reduce the application runtimes. Since a few years, issues with heat dissipation prevent the processors from having higher frequencies. One of the answers […]

We present a framework for representing image processing kernels based on decoupled access/execute metadata, which allow the programmer to specify both execution constraints and memory access pattern of a kernel. The framework performs source-to-source translation of kernels expressed in highlevel framework-specific C++ classes into low-level CUDA or OpenCL code with effective device-dependent optimizations such as […]

The low-level virtual machine (LLVM) compiler infrastructure is a mature and stable framework to implement optimization and compiler passes. H. Rhodin presented an LLVM backend to generate Parallel Thread Execution (PTX) instructions from LLVM bitcode. PTX is used as intermediate representation for parallel programming. This paper discusses Rhodin’s PTX generator. Due to the similarity between […]

GPU-based computing has become one of the popular high performance computing fields. The field is called GPGPU. This paper is focused on design and implementation of a uniform GPGPU application that is optimized for both the legacy and the recent GPU architectures. As a typical example of such the GPGPU application, this paper will discuss […]

We describe a software platform for the rapid development of general purpose GPU (GPGPU) computing applications within the MATLAB computing environment, C, and C++: Jacket. Jacket provides thousands of GPU-tuned function syntaxes within MATLAB, C, and C++, including linear algebra, convolutions, reductions, and FFTs as well as signal, image, statistics, and graphics libraries. Additionally, Jacket […]

In this work, we evaluate OpenCL as a programming tool for developing performance-portable applications for GPGPU. While the Khronos group developed OpenCL with programming portability in mind, performance is not necessarily portable. OpenCL has required performance-impacting initializations that do not exist in other languages such as CUDA. Understanding these implications allows us to provide a […]

We propose a compiler analysis pass for programs expressed in the Single Program, Multiple Data (SPMD) programming model. It identifies statically several kinds of regular patterns that can occur between adjacent threads, including common computations, memory accesses at consecutive locations or at the same location and uniform control flow. This knowledge can be exploited by […]

Automatic parallelization is becoming more important as parallelism becomes ubiquitous. The first step for achieving automation is to develop a theoretical foundation, for example, the polyhedron model. The second step is to implement the algorithms studied in the theoretical framework and getting them to work in a compiler that can be used to parallelize real […]

Techniques used to implement an unstructured grid solver on modern graphics hardware are described. The three-dimensional Euler equations for inviscid, compressible flow are considered. Effective memory bandwidth is improved by reducing total global memory access and overlapping redundant computation, as well as using an appropriate numbering scheme and data layout. The applicability of per-block shared […]