high performance computing on graphics processing units: hgpu.org

Performance optimization is the art of continuous seeking a harmonious mapping between the application domain and hardware. Recent years have witnessed a surge of deep learning (DL) applications in industry. Conventional wisdom for optimizing such workloads mainly focus on compute intensive ops (GEMM, Convolution, etc). Yet we show in this work, that the performance of […]

High performance computing is an important asset to scientific research, enabling the study of phenomena such as nuclear physics or climate change, that are difficult or impossible to be studied in traditional experiments or allowing researchers to utilize large amounts of data from experiments such as the Large Hadron Collider. No matter the use of […]

In conclusion, the present work brings an overview of artificial intelligence and, mainly, deep learning fields with a focus on image recognition and the history behind the models and techniques present nowadays. Beyond that, we explored how embedded hardware work with the new scenarios that AI brings to the table and how companies are developing […]

There is growing interest in graph mining algorithms such as motif counting. Generic graph mining systems have been developed to provide unified interfaces for programming these algorithms. However, existing systems take minutes or even hours to mine even simple patterns in moderate-sized graphs, which significantly limits their real-world usability. We present Pangolin, a high-performance and […]

Deep learning and Convolutional Neural Network (CNN) have becoming increasingly more popular and important in both academic and industrial areas in recent years cause they are able to provide better accuracy and result in classification, detection and recognition areas, compared to traditional approaches. Currently, there are many popular frameworks in the market for deep learning […]

A large chunk of research on the security issues of neural networks is focused on adversarial attacks. However, there exists a vast sea of simpler attacks one can perform both against and with neural networks. In this article, we give a quick introduction on how deep learning in security works and explore the basic methods […]

Deep Neural Networks have now achieved state-of-the-art results in a wide range of tasks including image classification, object detection and so on. However, they are both computation consuming and memory intensive, making them difficult to deploy on low-power devices. Network binarization is one of the existing effective techniques for model compression and acceleration, but there […]

Modern parallel programming languages such as OpenMP provide simple, portable programming models that support offloading of computation to various accelerator devices. Coupled with the increasing prevalence of heterogeneous computing platforms and the battle for supremacy in the co-processor space, gives rise to additional challenges placed on compiler/runtime vendors to handle the increasing complexity and diversity […]

Deep learning natural language processing models often use vector word embeddings, such as word2vec or GloVe, to represent words. A discrete sequence of words can be much more easily integrated with downstream neural layers if it is represented as a sequence of continuous vectors. Also, semantic relationships between words, learned from a text corpus, can […]

The purpose of this project is to continue exploring new ways of accelerating sequential computer code, and finding out if the machine learning techniques available today are able to help us in this task. The core idea is trying to parallelize during run-time (in a way completely transparent to the programmer) the code that’s being […]

Conditional Restricted Boltzmann Machine (CRBM) is a promising candidate for a multidimensional system modeling that can learn a probability distribution over a set of data. It is a specific type of an artificial neural network with one input (visible) and one output (hidden) layer. Recently published works demonstrate that CRBM is a suitable mechanism for […]

The result of this thesis is a framework for auto-tuning of parallel kernels which are written in either OpenCL or CUDA language. The framework includes advanced functionality such as support for composite kernels and online auto-tuning. The thesis describes API and internal structure of the framework and presents several examples of its utilization for kernel […]