high performance computing on graphics processing units: hgpu.org

hgpu.org » Performance

Real-Time Scheduling Using GPUs – Advanced and More Accurate Proof of Feasibility

Peter Fodrek, Ludovit Farkas, Michal Blaho, Martin Foltin, Juraj Hnat, Tomas Murgas

View

Download (PDF)

Tags: Benchmarking, Computer science, OpenCL, Performance, Task scheduling

November 14, 2012 by hgpu

Impact of GPU Memory Access Patterns on FDTD

Matthew Livesey, James F. Stack Jr., Fumie Costenz, Takeshi Nanri, Norimasa Nakashima, Seiji Fujino

View

Download (PDF)

Tags: Computer science, CUDA, FDTD, Finite-difference time-domain, nVidia, Performance, Tesla M2050

October 30, 2012 by hgpu

Characterization and Exploitation of GPU Memory Systems

Kenneth Sydney Lee

View

Download (PDF)

Tags: AMD Fusion, ATI, ATI Radeon HD 5870, ATI Radeon HD 7970, Computer science, Memory model, nVidia, nVidia GeForce GTX 280, OpenCL, Performance, Tesla C2075, Thesis

October 30, 2012 by hgpu

GPUSync: A Framework for Real-Time GPU Management

Glenn A. Elliott, Bryan C. Ward, James H. Anderson

View

Download (PDF)

Source codes

Tags: Computer science, Computer vision, CUDA, nVidia, nVidia GeForce GTX 470, Package, Performance

October 23, 2012 by hgpu

Hybrid MPI/GPU Interpolation for Grid DEM Construction

Andrew Danner, Jake Baskin, Alexander Breslow, David Wilikofsky

View

Download (PDF)

Tags: Computer science, CUDA, MPI, Nearest neighbour, nVidia, Performance, Sensing, Tesla M2070

October 22, 2012 by hgpu

Generalized Resource Allocation for the Cloud

Anshul Rai, Ranjita Bhagwan, Saikat Guha

View

Download (PDF)

Tags: ATI, ATI Radeon HD 6990, Cloud, Computer science, nVidia, OpenCL, Performance, Tesla C2075, Virtualization

October 17, 2012 by hgpu

Optimization Solutions for Improving the Performance of the Parallel Reduction Algorithm Using Graphics Processing Units

Ion Lungu, Dana-Mihaela Petrosanu, Alexandru Pirjan

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, nVidia, nVidia GeForce GTX 280, nVidia GeForce GTX 480, nVidia GeForce GTX 680, Optimization, Performance

October 14, 2012 by hgpu

Programming NVIDIA cards by means of transitive closure based parallelization algorithms

Marek Palkowski, Wlodzimierz Bielecki

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, Performance, Tesla S1070

October 13, 2012 by hgpu

Extendable Pattern-Oriented Optimization Directives (extended version)

Huimin Cui, Jingling Xue, Lei Wang, Yang Yang, Xiaobing Feng, Dongrui Fan

View

Download (PDF)

Tags: Compilers, Computer science, nVidia, nVidia GeForce GTX 285, Optimization, Performance

October 13, 2012 by hgpu

Automatic Parallelization of Tiled Loop Nests with Enhanced Fine-Grained Parallelism on GPUs

Peng Di, Ding Ye, Yu Su, Yulei Sui, Jingling Xue

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, Performance, Tesla C1060, Tesla C2050

October 13, 2012 by hgpu

A Quantitative Study of Irregular Programs on GPUs

Martin Burtscher, Rupesh Nasre, Keshav Pingali

View

Download (PDF)

Tags: Benchmarking, Computer science, CUDA, nVidia, nVidia Quadro FX 6000, Performance

September 23, 2012 by hgpu

Fast and Efficient Automatic Memory Management for GPUs using Compiler-Assisted Runtime Coherence Scheme

Sreepathi Pai, R. Govindarajan, Matthew J. Thazhuthaveetil

View

Download (PDF)

Tags: Computer science, CUDA, Memory model, nVidia, Performance, Tesla C1060

September 21, 2012 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

Real-Time Scheduling Using GPUs – Advanced and More Accurate Proof of Feasibility

Impact of GPU Memory Access Patterns on FDTD

Characterization and Exploitation of GPU Memory Systems

GPUSync: A Framework for Real-Time GPU Management

Hybrid MPI/GPU Interpolation for Grid DEM Construction

Optimization Solutions for Improving the Performance of the Parallel Reduction Algorithm Using Graphics Processing Units

Programming NVIDIA cards by means of transitive closure based parallelization algorithms

Extendable Pattern-Oriented Optimization Directives (extended version)

Automatic Parallelization of Tiled Loop Nests with Enhanced Fine-Grained Parallelism on GPUs

A Quantitative Study of Irregular Programs on GPUs

Fast and Efficient Automatic Memory Management for GPUs using Compiler-Assisted Runtime Coherence Scheme

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)