high performance computing on graphics processing units: hgpu.org

hgpu.org » Thesis

Finding, Measuring, and Reducing Inefficiencies in Contemporary Computer Systems

Melanie Rae Kambadur

View

Download (PDF)

Source codes

Tags: Computer science, Intel HD 4600, Intel HD Graphics 4000, LLVM, OpenCL, Package, Performance, Thesis

February 16, 2016 by hgpu

Towards Improving Programmability of Heterogeneous Parallel Architectures

Michele Scandale

View

Download (PDF)

Tags: Compilers, Computer science, Heterogeneous systems, LLVM, OpenCL, Thesis

February 16, 2016 by hgpu

Parallel and Scalable Sparse Basic Linear Algebra Subprograms

Weifeng Liu

View

Download (PDF)

Tags: Algorithms, AMD Radeon R9 290X, ATI, Benchmarking, Computer science, Heterogeneous systems, Linear Algebra, Matrix multiplication, nVidia, nVidia GeForce GTX 980, nVidia GeForce GTX Titan Black, OpenCL, Sparse matrix, Thesis

February 16, 2016 by hgpu

Portable Programming Models for Heterogeneous Platforms

Deepak Majeti

View

Download (PDF)

Source codes

Tags: ATI, ATI Radeon HD 5970, ATI Radeon HD 7660, Computer science, Heterogeneous systems, nVidia, OpenCL, Package, Tesla M2050, Thesis

February 8, 2016 by hgpu

High performance high-order numerical methods: applications in ocean modeling

Rajesh Gandham

View

Download (PDF)

Tags: ATI, ATI Radeon HD 7970, cfd, Computer science, CUDA, Fluid dynamics, Numerical simulation, nVidia, nVidia GeForce GTX Titan, OCCA, OpenCL, OpenMP, real time systems, Tesla C2050, Tesla K20, Tesla K40, Thesis

February 8, 2016 by hgpu

A novel approach to evaluating compact finite differences and similar tridiagonal schemes on GPU-accelerated clusters

Ashwin Trikuta Srinath

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, Finite difference, Fluid dynamics, GPU cluster, Numerical simulation, nVidia, OpenMPI, Tesla K20, Tesla K40, Thesis

February 3, 2016 by hgpu

Fast, Realistic Terrain Synthesis

Justin Crause

View

Download (PDF)

Tags: 3D Graphics and Realism, Computer science, CUDA, nVidia, nVidia GeForce GTX 660 Ti, Thesis

February 2, 2016 by hgpu

Hardware Acceleration for Unstructured Big Data and Natural Language Processing

Prateek Tandon

View

Download (PDF)

Tags: ASIC, big data, Computer science, FPGA, Hadoop, hardware acceleration, Machine learning, MapReduce, NLP, Thesis

February 2, 2016 by hgpu

Extracting Flow Features Using Bag-of-Features and Supervised Learning Techniques

Yifei Li

View

Download (PDF)

Source codes

Tags: Algorithms, Clustering, Computer science, Computer vision, CUDA, Machine learning, nVidia, nVidia GeForce GTX 580, OpenMP, Package, Thesis, Visualization

February 2, 2016 by hgpu

GPGPU Multi Object Bayesian Tracking with an embedded System on a Chip

David Webb

View

Download (PDF)

Tags: Bayesian, Computer science, Computer vision, CUDA, FPGA, Heterogeneous systems, nVidia, nVidia GeForce GTX 960, nVidia Jetson TK1, SoC, Thesis

February 2, 2016 by hgpu

Deep learning review and its applications

Andoni Azkarate Saiz

View

Download (PDF)

Tags: Computer science, CUDA, Deep learning, Machine learning, Neural networks, nVidia, nVidia GeForce GTX 660, Review, Thesis

February 1, 2016 by hgpu

A Reproducible Research Methodology for Designing and Conducting Faithful Simulations of Dynamic HPC Applications

Luka Stanisic

View

Download (PDF)

Tags: Computer science, CUDA, Heterogeneous systems, Linear Algebra, nVidia, nVidia Quadro FX 5800, Tesla C2050, Tesla K20, Tesla K40, Tesla M2070, Tesla M2075, Thesis

February 1, 2016 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

Finding, Measuring, and Reducing Inefficiencies in Contemporary Computer Systems

Towards Improving Programmability of Heterogeneous Parallel Architectures

Parallel and Scalable Sparse Basic Linear Algebra Subprograms

Portable Programming Models for Heterogeneous Platforms

High performance high-order numerical methods: applications in ocean modeling

A novel approach to evaluating compact finite differences and similar tridiagonal schemes on GPU-accelerated clusters

Fast, Realistic Terrain Synthesis

Hardware Acceleration for Unstructured Big Data and Natural Language Processing

Extracting Flow Features Using Bag-of-Features and Supervised Learning Techniques

GPGPU Multi Object Bayesian Tracking with an embedded System on a Chip

Deep learning review and its applications

A Reproducible Research Methodology for Designing and Conducting Faithful Simulations of Dynamic HPC Applications

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)