high performance computing on graphics processing units: hgpu.org

hgpu.org » Performance

Streaming-Oriented Parallelization of Domain-Independent Irregular Kernels

Jacobo Lobeiras, Margarita Amor, Manuel Arenaz, Basilio B. Fraguela

View

Download (PDF)

Tags: Algorithms, ATI, ATI Radeon HD 4850, Brook, Computer science, OpenMP, Performance, Presentation

October 10, 2011 by hgpu

Evaluation of GPU Architectures Using Spiking Neural Networks

Vivek K. Pallipuram, Mohammad A. Bhuiyan, Melissa C. Smith

View

Download (PDF)

Tags: ATI, ATI Radeon HD 5870, Computer science, Neural networks, nVidia, OpenCL, Optimization, Performance, Presentation, Tesla C2050

October 10, 2011 by hgpu

GPUs, a New Tool of Acceleration in CFD: Efficiency and Reliability on Smoothed Particle Hydrodynamics Methods

Alejandro C. Crespo, Jose M. Dominguez, Anxo Barreiro, Moncho Gomez-Gesteira, Benedict D. Rogers

View

Download (PDF)

Source codes

Tags: CUDA, Fluid dynamics, nVidia, nVidia GeForce GTX 260, nVidia GeForce GTX 285, nVidia GeForce GTX 480, Performance, Tesla M1060, Visualization

October 10, 2011 by hgpu

Multifrontal computations on GPUs and their multi-core hosts

Robert F. Lucas, Gene Wagenbreth, Dan M. Davis, Roger Grimes

View

Download (PDF)

Tags: Computer science, CUDA, Factorization, nVidia, Performance, Sparse matrix, Tesla C1060

October 7, 2011 by hgpu

Run-time Reconfigurable Multiprocessors

Madhura Purnaprajna

View

Download (PDF)

Tags: ATI, Computer science, FPGA, Hardware Architecture, nVidia, Performance, Thesis

October 7, 2011 by hgpu

CUDA performance analyzer

Aniruddha Dasgupta

View

Download (PDF)

Tags: Analytical model, Computer science, CUDA, Fast multipole method, nVidia, Optimization, Performance, Tesla C1060, Thesis

October 6, 2011 by hgpu

Static GPU threads and an improved scan algorithm

Jens Breitbart

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, nVidia, nVidia GeForce GT 280, OpenCL, Performance, Presentation, Programming techniques

October 6, 2011 by hgpu

Applying software-managed caching and CPU/GPU task scheduling for accelerating dynamic workloads

Mark Silberstein, Assaf Schuster, John D. Owens

View

Download (PDF)

Source codes

Tags: Algorithms, Computer science, CUDA, nVidia, nVidia GeForce 8800 GTX, nVidia GeForce GTX 285, Optimization, Package, Performance, Probability, Task scheduling, Tesla C2050

October 5, 2011 by hgpu

A Framework for Automated Performance Tuning and Code Verification on GPU Computing Platforms

Allison S. Gehrke, Ilkyeun Ra, Daniel A. Connors

View

Download (PDF)

Tags: Code generation, Computer science, Numerical simulation, nVidia, Optimization, Performance, PTX

October 5, 2011 by hgpu

Tranformation of CPU-based Applications To Leverage on Graphics Processors using CUDA

Fawnizu Azmadi Hussin, Anas Mohd Nazlee, Noohul Basheer Zain Ali

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, Lattice Boltzmann model, nVidia, nVidia GeForce GTX 260, Performance, Programming techniques, Security

October 3, 2011 by hgpu

GPU-Accelerated DNA Distance Matrix Computation

Zhi Ying, Xinhua Lin, Simon Chong-Wee See, Minglu Li

View

Download (PDF)

Tags: ATI, ATI Radeon HD 5850, Bioinformatics, Biology, Genetics, nVidia, OpenCL, Performance, Tesla C2050

October 3, 2011 by hgpu

An Auto-tuning Solution to Data Streams Clustering in OpenCL

Jianbin Fang, Ana Lucia Varbanescu, Henk Sips

View

Download (PDF)

Tags: ATI, ATI Radeon HD 5870, Clustering, Computer science, CUDA, nVidia, nVidia GeForce GTX 480, OpenCL, Optimization, Performance

October 3, 2011 by hgpu

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

MSCCL++: Rethinking GPU Communication Abstractions for Cutting-edge AI Applications

Benchmark compute shader of Unity against InteropUnityCUDA

InteropUnityCUDA: A Tool for Interoperability Between Unity and CUDA

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

* * *

high performance computing on graphics processing units: hgpu.org

Streaming-Oriented Parallelization of Domain-Independent Irregular Kernels

Evaluation of GPU Architectures Using Spiking Neural Networks

GPUs, a New Tool of Acceleration in CFD: Efficiency and Reliability on Smoothed Particle Hydrodynamics Methods

Multifrontal computations on GPUs and their multi-core hosts

Run-time Reconfigurable Multiprocessors

CUDA performance analyzer

Static GPU threads and an improved scan algorithm

Applying software-managed caching and CPU/GPU task scheduling for accelerating dynamic workloads

A Framework for Automated Performance Tuning and Code Verification on GPU Computing Platforms

Tranformation of CPU-based Applications To Leverage on Graphics Processors using CUDA

GPU-Accelerated DNA Distance Matrix Computation

An Auto-tuning Solution to Data Streams Clustering in OpenCL

Recent source codes

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

Shamrock: Multi-GPU hydrodynamics for astrophysics

LLMPerf: GPU Performance Modeling meets Large Language Models

Most viewed papers (last 30 days)