high performance computing on graphics processing units: hgpu.org

hgpu.org » Performance

Reverse Computation for Rollback-based Fault Tolerance in Large Parallel Systems: Evaluating the Potential Gains and Systems Effects

Kalyan S. Perumalla, Alfred J. Park

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, nVidia GeForce GTX 580, Particle simulation, Performance, Tesla X2090

August 24, 2013 by hgpu

Comparative Analysis of OpenACC, OpenMP and CUDA using Sequential and Parallel Algorithms

Cleverson Lopes Ledur, Carlos M. D. Zeve, Julio C. S. dos Anjos

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, nVidia GeForce GTX 650, OpenACC, OpenMP, Performance

August 21, 2013 by hgpu

Comparison of Cilk, Kaapi and CUDA for the Jacobi Method

Luis Felipe Millani, Nicolas Maillard

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, nVidia GeForce GTX 480, Performance

August 21, 2013 by hgpu

Accurate Analytic Models to Estimate Execution Time on GPU Applications

Pedro Velho, Daniel A. G. de Oliveira, Edson L. Padoin, Philippe O. A. Navaux

View

Download (PDF)

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

August 21, 2013 by hgpu

Performance Drawbacks for Matrix Multiplication using Set Associative Cache in GPU devices

Leonid Djinevski, Sime Arsenovski, Sasko Ristov, Marjan Gusev

View

Download (PDF)

Tags: Computer science, CUDA, Matrix multiplication, nVidia, nVidia GeForce GTX 680, Performance

August 19, 2013 by hgpu

Transfer Time Reduction of Data Transfers between CPU and GPU

Julius Sandgren

View

Download (PDF)

Tags: ATI, ATI Radeon HD 3650, Computer science, CUDA, nVidia, nVidia Quadro FX 370, OpenCL, Performance, Thesis

August 19, 2013 by hgpu

A GPU implementation for improved granular simulations with LAMMPS

Emmanuel N. Millan, Christian Ringl, Carlos S. Bederian, Maria Fabiana Piccoli, Carlos Garcia Garino, Herbert M. Urbassek, Eduardo M. Bringa

View

Download (PDF)

Tags: CUDA, Molecular dynamics, nVidia, Performance, Physics, Tesla C2050, Tesla C2075, Tesla M2090

August 18, 2013 by hgpu

General Transformations for GPU Execution of Tree Traversals

Michael Goldfarb, Youngjoon Jo, Milind Kulkarni

View

Download (PDF)

Tags: Algorithms, Compilers, Computer science, CUDA, KD-tree, nVidia, Performance, Tesla C2070

August 15, 2013 by hgpu

First experiences with the Intel MIC architecture at LRZ

Volker Weinberg, Momme Allalen

View

Download (PDF)

Tags: Computer science, Intel, Intel Phi, OpenMP, Performance

August 15, 2013 by hgpu

Barrier Invariants: A Shared State Abstraction for the Analysis of Data-Dependent GPU Kernels

Nathan Chong, Alastair F. Donaldson, Paul H.J. Kelly, Jeroen Ketema, Shaz Qadeer

View

Download (PDF)

Source codes

Tags: Algorithms, Computer science, CUDA, OpenCL, Package, Performance

August 13, 2013 by hgpu

Scheduling by Work-Stealing in Hybrid Parallel Architectures

Vinicius Garcia Pinto, Nicolas Maillard

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, nVidia GeForce GTX 480, Performance, Task scheduling

July 24, 2013 by hgpu

An overview of techniques for predicting the performance of GPU accelerated applications

Rafael Keller Tesser, Philippe O. A. Navaux

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, Overview, Performance

July 22, 2013 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

Reverse Computation for Rollback-based Fault Tolerance in Large Parallel Systems: Evaluating the Potential Gains and Systems Effects

Comparative Analysis of OpenACC, OpenMP and CUDA using Sequential and Parallel Algorithms

Comparison of Cilk, Kaapi and CUDA for the Jacobi Method

Accurate Analytic Models to Estimate Execution Time on GPU Applications

Performance Drawbacks for Matrix Multiplication using Set Associative Cache in GPU devices

Transfer Time Reduction of Data Transfers between CPU and GPU

A GPU implementation for improved granular simulations with LAMMPS

General Transformations for GPU Execution of Tree Traversals

First experiences with the Intel MIC architecture at LRZ

Barrier Invariants: A Shared State Abstraction for the Analysis of Data-Dependent GPU Kernels

Scheduling by Work-Stealing in Hybrid Parallel Architectures

An overview of techniques for predicting the performance of GPU accelerated applications

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)