high performance computing on graphics processing units: hgpu.org

Theses

hgpu.org » Applications

Techniques to maximize memory bandwidth on the Rigel compute accelerator

William J. Tuohy

View

Tags: ATI, ATI Radeon HD 5870, Computer science, Memory, nVidia, nVidia GeForce GTX 480, Optimization, Performance, Tesla T10, Thesis

October 27, 2011 by hgpu

Efficient Implementation and Evaluation of Methods for the Estimation of Motion in Image Sequences

Robert Hegner

View

Download (PDF)

Source codes

Tags: Algorithms, Computer science, Computer vision, CUDA, nVidia, nVidia GeForce GTX 260, Optical flow, Package, Thesis

October 27, 2011 by hgpu

The Model of Computation of CUDA and its Formal Semantics

Axel Habermaier

View

Download (PDF)

Tags: Computer science, CUDA, Memory model, nVidia, nVidia GeForce GTX 480, PTX, Thesis

October 25, 2011 by hgpu

Design and implementation of a high-performance stream-based computing platform on multigenerational GPUs

Pablo Lamilla Alvarez

View

Download (PDF)

Tags: Computer science, GPU cluster, nVidia, nVidia GeForce GT 220, OpenCL, Performance, Thesis

October 24, 2011 by hgpu

Design and Implementation of Centrally-Coordinated Peer-to-Peer Live-streaming

Roberto Roverso

View

Download (PDF)

Tags: Algorithms, Computer science, Consensus, CUDA, Network communications, Networks, nVidia, nVidia GeForce GTX 295, Optimization, Thesis

October 23, 2011 by hgpu

Power and Performance Studies of the Explicit Multi-Threading (XMT) Architecture

Fuat Keceli

View

Download (PDF)

Source codes

Tags: Algorithms, ASIC, Benchmarking, Computer science, CUDA, FPGA, nVidia, nVidia GeForce GTX 280, Package, Performance, Thesis

October 23, 2011 by hgpu

Computer Finite-Difference Time-Domain Simulation of Electromagnetic Wave Propagation using GPUs

Anna Bonet Manchado

View

Download (PDF)

Tags: Algorithms, CUDA, Data parallelism, Electrodynamics, FDTD, Finite-difference time-domain, Maxwell's equations, nVidia, nVidia GeForce GTX 280, Tesla C2050, Thesis, Visualization

October 23, 2011 by hgpu

Massively Parallel Algorithms for CFD Simulation and Optimization on Heterogeneous Many-Core Architectures

Austen C. Duffy

View

Download (PDF)

Tags: Algorithms, CUDA, Fluid dynamics, Fortran, GPU cluster, Heterogeneous systems, nVidia, nVidia GeForce GTX 470, nVidia GeForce GTX 480, Optimization, Partial differential equations, PDEs, Thesis

October 23, 2011 by hgpu

STT-RAM for Shared Memory in GPUs

Prateeksha Satyamoorthy

View

Download (PDF)

Tags: Benchmarking, Computer science, CUDA, Memory, nVidia, nVidia GeForce GTX 285, OpenCL, Thesis

October 23, 2011 by hgpu

Accelerating Component-Based Dataflow Middleware with Adaptivity and Heterogeneity

Timothy D. R. Hartley

View

Download (PDF)

Tags: Computer science, CUDA, Heterogeneous systems, nVidia, nVidia Quadro FX 5600, Optimization, Performance, Thesis

October 22, 2011 by hgpu

Implementing a Preconditioned Iterative Linear Solver Using Massively Parallel Graphics Processing Units

Amirhassan Asgari Kamiabad

View

Download (PDF)

Tags: Computer science, Conjugate gradient solver, CUDA, nVidia, nVidia GeForce GTX 280, Power Systems Simulation, Thesis

October 22, 2011 by hgpu

GPU performance prediction using parametrized models

Andreas Resios

View

Download (PDF)

Tags: Computer science, CUDA, Heterogeneous systems, nVidia, nVidia GeForce GTX 460, Optimization, Performance, Thesis

October 22, 2011 by hgpu

Data-efficient LLM Fine-tuning for Code Generation

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

DeepCompile: A Compiler-Driven Approach to Optimizing Distributed Deep Learning Training

Large Language Model Powered C-to-CUDA Code Translation: A Novel Auto-Parallelization Framework

GigaAPI: a user-space API that simplifies multi-GPU programming, bridging the gap between the capabilities of parallel GPU systems and the ability of developers to harness their full potential

GigaAPI for GPU Parallelization

Coccinelle: a C code transformation engine using SmPL for matches, refactorings, and bug fixing

Advances in Semantic Patching for HPC-oriented Refactorings with Coccinelle

DuoReduce: MLIR's benchmark

Hardware-Assisted Software Testing and Debugging for Heterogeneous Computing

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Theses

Techniques to maximize memory bandwidth on the Rigel compute accelerator

Efficient Implementation and Evaluation of Methods for the Estimation of Motion in Image Sequences

The Model of Computation of CUDA and its Formal Semantics

Design and implementation of a high-performance stream-based computing platform on multigenerational GPUs

Design and Implementation of Centrally-Coordinated Peer-to-Peer Live-streaming

Power and Performance Studies of the Explicit Multi-Threading (XMT) Architecture

Computer Finite-Difference Time-Domain Simulation of Electromagnetic Wave Propagation using GPUs

Massively Parallel Algorithms for CFD Simulation and Optimization on Heterogeneous Many-Core Architectures

STT-RAM for Shared Memory in GPUs

Accelerating Component-Based Dataflow Middleware with Adaptivity and Heterogeneity

Implementing a Preconditioned Iterative Linear Solver Using Massively Parallel Graphics Processing Units

GPU performance prediction using parametrized models

Recent source codes

PELSI: Power-Efficient Layer-Switched Inference

Ouroboros: Virtualized Queues for dynamic memory management

MSCCL++: A GPU-driven communication stack for scalable AI applications

Benchmark compute shader of Unity against InteropUnityCUDA

Data-efficient LLM Fine-tuning for Code Generation

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Large Language Model Powered C-to-CUDA Code Translation: A Novel Auto-Parallelization Framework

GigaAPI: a user-space API that simplifies multi-GPU programming, bridging the gap between the capabilities of parallel GPU systems and the ability of developers to harness their full potential

Coccinelle: a C code transformation engine using SmPL for matches, refactorings, and bug fixing

DuoReduce: MLIR's benchmark

Most viewed papers (last 30 days)