high performance computing on graphics processing units: hgpu.org

hgpu.org » Optimization

A stream-computing extension to OpenMP

Antoniu Pop, Albert Cohen

View

Download (PDF)

Tags: Compilers, Computer science, OpenMP, Optimization

September 9, 2011 by hgpu

Experiences with Mapping Non-linear Memory Access Patterns into GPUs

Eladio Gutierrez, Sergio Romero, Maria A. Trenas, Oscar Plata

Tags: Computer science, CUDA, Memory, nVidia, Optimization, Programming techniques

September 8, 2011 by hgpu

A Fast GPU Implementation for Solving Sparse Ill-Posed Linear Equation Systems

Florian Stock, Andreas Koch

View

Download (PDF)

Tags: Cell processor, Conjugate gradient solver, CUDA, FPGA, Image processing, Image reconstruction, nVidia, nVidia GeForce 8800 GTS, nVidia GeForce GTX 280, Optimization, Sparse matrix

September 8, 2011 by hgpu

Automatic OpenCL Device Characterization: Guiding Optimized Kernel Design

Peter Thoman, Klaus Kofler, Heiko Studt, John Thomson, Thomas Fahringer

View

Download (PDF)

Tags: Algorithms, ATI, ATI Radeon HD 5870, Benchmarking, Cell processor, Computer science, nVidia, nVidia GeForce GTX 275, nVidia GeForce GTX 460, OpenCL, Optimization, Tesla C2050

September 8, 2011 by hgpu

Automatic CPU-GPU communication management and optimization

Thomas B. Jablin, Prakash Prabhu, James A. Jablin, Nick P. Johnson, Stephen R. Beard, David I. August

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, nVidia, nVidia GeForce GTX 480, Optimization, Performance, Programming techniques

September 7, 2011 by hgpu

MacroSS: macro-SIMDization of streaming applications

Amir H. Hormati, Yoonseo Choi, Mark Woh, Manjunath Kudlur, Rodric Rabbah, Trevor Mudge, Scott Mahlke

View

Download (PDF)

Tags: Code generation, Compilers, Computer science, Optimization, Performance, Programming Languages

September 7, 2011 by hgpu

GPU-based asynchronous particle swarm optimization

Luca Mussi, Youssef S.G. Nashed, Stefano Cagnoni

Tags: Algorithms, Computer science, CUDA, Genetic programming, nVidia, Optimization, Performance

September 7, 2011 by hgpu

Parallel implementation of conjugate gradient method on graphics processors

Marcin Wozniak, Tomasz Olas, Roman Wyrzykowski

Tags: Algorithms, Computer science, Conjugate gradient solver, CUDA, nVidia, nVidia GeForce 8800 GTX, Optimization, Sparse matrix, Tesla C1060

September 7, 2011 by hgpu

Compiler-directed memory management for heterogeneous MPSoCs

Miao Wang, Francois Bodin

View

Download (PDF)

Tags: Cell processor, Computer science, Heterogeneous systems, Memory, Memory model, Optimization

September 7, 2011 by hgpu

Fast Construction of SAH BVHs on the Intel Many Integrated Core (MIC) Architecture

Ingo Wald

View

Download (PDF)

Tags: 3D Graphics and Realism, Computer science, KD-tree, nVidia, nVidia GeForce GTX 280, Optimization

September 5, 2011 by hgpu

A CUDA-based parallel implementation of K-nearest neighbor algorithm

Shenshen Liang, Ying Liu, Cheng Wang, Liheng Jian

Tags: Algorithms, Computer science, CUDA, Nearest neighbour, nVidia, Optimization

September 5, 2011 by hgpu

Using Graphics Processing Units for Logic Simulation of Electronic Designs

Alper Sen, Baris Aksanli, Murat Bozkurt

View

Download (PDF)

Tags: Algorithms, Benchmarking, Computer science, CUDA, Electronic design automation, nVidia, nVidia Quadro FX 3800, Optimization

September 2, 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

A stream-computing extension to OpenMP

Experiences with Mapping Non-linear Memory Access Patterns into GPUs

A Fast GPU Implementation for Solving Sparse Ill-Posed Linear Equation Systems

Automatic OpenCL Device Characterization: Guiding Optimized Kernel Design

Automatic CPU-GPU communication management and optimization

MacroSS: macro-SIMDization of streaming applications

GPU-based asynchronous particle swarm optimization

Parallel implementation of conjugate gradient method on graphics processors

Compiler-directed memory management for heterogeneous MPSoCs

Fast Construction of SAH BVHs on the Intel Many Integrated Core (MIC) Architecture

A CUDA-based parallel implementation of K-nearest neighbor algorithm

Using Graphics Processing Units for Logic Simulation of Electronic Designs

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)