high performance computing on graphics processing units: hgpu.org

We optimize parameters in OpenACC clauses for a stencil evaluation kernel executed on Graphical Processing Units (GPUs) using a variety of machine learning and optimization search algorithms, individually and in hybrid combinations, and compare execution time performance to the best possible obtained from brute force search. Several auto-tuning techniques – historic learning, random walk, simulated […]

In this PhD thesis, we present our research in the domain of high performance software for computational fluid dynamics (CFD). With the increasing demand of high-resolution simulations, there is a need of numerical solvers that can fully take advantage of current manycore accelerated parallel architectures. In this thesis we focus more specifically on developing an […]

Today servers, desktops, mobile devices, and embedded systems contain many processors in addition to the CPU that runs programs. These extra processors are generally called accelerators and could be a GPU, FPGA, Xeon Phi, or other programmable device. There are many types of accelerators available, from many vendors, for many different environments. Khronos developed the […]

Key derivation functions are a key element of many cryptographic applications. Password-based key derivation functions are designed specifically to derive cryptographic keys from low-entropy sources (such as passwords or passphrases) and to counter brute-force and dictionary attacks. However, the most widely adopted standard for password-based key derivation, PBKDF2, as implemented in most applications, is highly […]

The internet is a huge collection of websites in the order of 10^8 bytes. Around 90% of the world’s population uses search engines for getting relevant information. According to Wikipedia, more than 200 million Indians use the Internet every day. Thus the correct data retrieval least time domain is the most important task. Hence need […]

There have been a number of research proposals to use discrete graphics processing units (GPUs) to accelerate database operations. Although many of these works show up to an order of magnitude performance improvement, discrete GPUs are not commonly used in modern database systems. However, there is now a proliferation of integrated GPUs which are on […]

In this work we focus on tailoring and optimizing the computational Private Information Retrieval (cPIR) scheme proposed in WAHC 2014 for efficient execution on graphics processing units (GPUs). Exploiting the mass parallelism in GPUs is a commonly used approach in speeding up cPIRs. Our goal is to eliminate the efficiency bottleneck of the Dor"{o}z et […]

In this paper, the performance and scalability of different multi-core systems is experimentally evaluated for the Tsunami simulation EasyWave. The target platforms include a standard Ivy Bridge Xeon processor, an Intel Xeon Phi accelerator card, and also a GPU. OpenMP, MPI and CUDA were used to parallelize the program to these platforms. The absolute performance […]

The main topic of this thesis was to implement a computer program that can render photorealistic images by simulating the laws of physics. In practice the program builds an image by finding every possible path that a light ray can travel. Technique presented in this thesis will naturally simulate many physical phenomenons such as reflections, […]

Power density constraints are limiting the performance improvements of modern CPUs. To address this we have seen the introduction of lower-power, multi-core processors, but the future will be even more exciting. In order to stay within the power density limits but still obtain Moore’s Law performance/price gains, it will be necessary to parallelize algorithms to […]

There is large consent that successful training of deep networks requires many thousand annotated training samples. In this paper, we present a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently. The architecture consists of a contracting path to capture context and a […]

Users of heterogeneous computing systems face two problems: firstly, understanding the trade-off relationship between the observable characteristics of their applications, such as latency and quality of the result, and secondly, how to exploit knowledge of these characteristics to allocate work to distributed resources efficiently. A domain specific approach addresses both of these problems. By considering […]