high performance computing on graphics processing units: hgpu.org

The massive parallelism and faster random memory access of Graphics Processing Units (GPUs) promise to further accelerate complex analytics operations such as joins and grouping, but also provide additional challenges to optimizing their performance. There are more implementation alternatives to consider on the GPU, such as exploiting different types of memory on the device and […]

Array-based languages such as MATLAB and Python (with NumPy) have become very popular for scientific computing. However, the performance of the implementations of these languages is often lacking. For example, some of the implementations are interpreted. Further, these languages were not designed with multi-core CPUs and GPUs in mind and thus don’t take full advantage […]

The multilingual nature of the world makes translation a crucial requirement today. Parallel dictionaries constructed by humans are a widely-available resource, but they are limited and do not provide enough coverage for good quality translation purposes, due to out-of-vocabulary words and neologisms. This motivates the use of statistical translation systems, which are unfortunately dependent on […]

We derive a new class of fast algorithms for convolutional neural networks using Winograd’s minimal filtering algorithms. Specifically we derive algorithms for network layers with 3×3 kernels, which are the preferred kernel size for image recognition tasks. The best of our algorithms reduces arithmetic complexity up to 4X compared with direct convolution, while using small […]

We present a brute-force approach for finding k-nearest neighbors on the GPU for many queries in parallel. Our program takes advantage of recent advances in fundamental GPU computing primitives. We modify a matrix multiplication subroutine in MAGMA library [6] to calculate the squared Euclidean distances between queries and references. The nearest neighbors selection is accomplished […]

We discuss an approach for solving sparse or dense banded linear systems ${bf A} {bf x} = {bf b}$ on a Graphics Processing Unit (GPU) card. The matrix ${bf A} in {mathbb{R}}^{N times N}$ is possibly nonsymmetric and moderately large; i.e., $10000 leq N leq 500000$. The ${it split and parallelize}$ (${tt SaP}$) approach seeks […]

A growing number of commercial and enterprise systems increasingly rely on compute-intensive machine learning algorithms. While the demand for these compute-intensive applications is growing, the performance benefits from general-purpose platforms are diminishing. To accommodate the needs of machine learning algorithms, Field Programmable Gate Arrays (FPGAs) provide a promising path forward and represent an intermediate point […]

Insider threat is one of the risks both government and private organizations have to deal with in protecting their important information. Data exfiltration and data leakage resulting from insiders activities can be very difficult to identify and quantify. Unfortunately, existing solutions that efficiently check whether data moving across a network is known to be sensitive […]

Emerging processor architectures such as GPUs and Intel MICs provide a huge performance potential for high performance computing. However developing software using these hardware accelerators introduces additional challenges for the developer such as exposing additional parallelism, dealing with different hardware designs and using multiple development frameworks in order to use devices from different vendors. The […]

Dataflow models are valuable tools for representing, analyzing, and synthesizing embedded systems. Heterogeneous computing platforms with multi-core CPU and Graphics Processing Units (GPUs) provide a low cost platform for high performance computations. In this report, we present a dataflow based automated design framework that incorporates analysis, optimization and synthesis tools for embedded systems. Our framework […]

The intractability of the ECDLP is part of what makes many cryptographic application work. As such, viewing this problem from as many angles as possible is worthwhile. In this thesis, we explore the angle of creating a GPU ECDLP solver using OpenCL. In the process, we discuss the many issues, limitations and solutions we encounter. […]

Data-efficient learning in continuous state-action spaces using high-dimensional observations remains an elusive challenge in developing fully autonomous systems. An instance of this challenge is the pixels to torques problem, which identifies key elements of an autonomous agent: autonomous thinking and decision making using sensor measurements only, learning from mistakes, and applying past experiences to novel […]