high performance computing on graphics processing units: hgpu.org

hgpu.org » Performance

Evaluating the Performance and Portability of OpenCL

Jarno van der Sanden

View

Tags: Algorithms, ATI, ATI Radeon HD 5850, Computer science, CUDA, nVidia, nVidia GeForce GTX 470, OpenCL, Performance, Thesis

October 18, 2011 by hgpu

Optimization strategies for parallel CPU and GPU implementations of a meshfree particle method

Jose M. Dominguez, Alejandro J.C. Crespo, Moncho Gomez-Gesteira

View

Download (PDF)

Tags: Computational Engineering, Computer science, CUDA, Fluid dynamics, nVidia, nVidia GeForce GTX 480, OpenMP, Optimization, Performance, Tesla C1060

October 18, 2011 by hgpu

Fast Implementation of DGEMM on Fermi GPU

Guangming Tan, Linchuan Li, Sean Triechle, Everett Phillips, Yungang Bao, Ninghui Sun

View

Download (PDF)

Source codes

Tags: Algorithms, Benchmarking, Computer science, CUBLAS, CUDA, Matrix multiplication, nVidia, Optimization, Performance, Tesla C2050

October 17, 2011 by hgpu

Dynamic Fine-Grain Scheduling of Pipeline Parallelism

Daniel Sanchez, David Lo, Richard M. Yoo, Jeremy Sugerman, Christos Kozyrakis

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, Performance, Programming techniques

October 17, 2011 by hgpu

GPU-to-CPU callbacks

Jeff A. Stuart, Michael Cox, John D. Owens

View

Download (PDF)

Tags: Computer science, CUDA, Heterogeneous systems, nVidia, nVidia GeForce GTX 280, Performance, Programming techniques

October 16, 2011 by hgpu

Data Layout Pruning on GPU

Xinbiao Gan, Zhiying Wang, Li Shen, Qi Zhu

View

Download (PDF)

Tags: Computer science, CUDA, Memory, Memory model, nVidia, nVidia GeForce GTX 280, Performance

October 16, 2011 by hgpu

Skeleton Programming for Heterogeneous GPU-based Systems

Usman Dastgeer

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, Heterogeneous systems, nVidia, Performance, Tesla C1060, Thesis

October 16, 2011 by hgpu

Physis: An Implicitly Parallel Programming Model for Stencil Computations on Large-Scale GPU-Accelerated Supercomputers

Naoya Maruyama, Tatsuo Nomura, Kento Sato, Satoshi Matsuoka

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, MPI, nVidia, Optimization, Package, Performance, Programming Languages, Programming techniques, Tesla M2050

October 15, 2011 by hgpu

Dymaxion: Optimizing Memory Access Patterns for Heterogeneous Systems

Shuai Che, Jeremy W. Sheaffer, Kevin Skadron

View

Download (PDF)

Tags: Computer science, CUDA, Heterogeneous systems, Memory, nVidia, nVidia GeForce GTX 285, nVidia GeForce GTX 480, Optimization, Performance

October 15, 2011 by hgpu

GPU fluids in production: a compiler approach to parallelism

Dan Bailey, Ian Masters, Matt Warner

View

Download (PDF)

Tags: Code generation, Compilers, Computer science, Image processing, nVidia, Performance, Presentation, PTX, Tesla C2050

October 15, 2011 by hgpu

Accelerating code on multi-cores with FastFlow

Marco Aldinucci, Marco Danelutto, Peter Kilpatrick, Massimiliano Meneghin, Massimo Torquati

View

Download (PDF)

Source codes

Tags: Computer science, Memory, Package, Performance, Programming techniques

October 15, 2011 by hgpu

CudaDMA: Optimizing GPU Memory Bandwidth via Warp Specialization

Michael Bauer, Henry Cook, Brucek Khailany

View

Download (PDF)

Source codes

Tags: Benchmarking, Computer science, CUDA, Memory model, nVidia, Optimization, Package, Performance, Tesla C2050

October 14, 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

Evaluating the Performance and Portability of OpenCL

Optimization strategies for parallel CPU and GPU implementations of a meshfree particle method

Fast Implementation of DGEMM on Fermi GPU

Dynamic Fine-Grain Scheduling of Pipeline Parallelism

GPU-to-CPU callbacks

Data Layout Pruning on GPU

Skeleton Programming for Heterogeneous GPU-based Systems

Physis: An Implicitly Parallel Programming Model for Stencil Computations on Large-Scale GPU-Accelerated Supercomputers

Dymaxion: Optimizing Memory Access Patterns for Heterogeneous Systems

GPU fluids in production: a compiler approach to parallelism

Accelerating code on multi-cores with FastFlow

CudaDMA: Optimizing GPU Memory Bandwidth via Warp Specialization

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)