high performance computing on graphics processing units: hgpu.org

Applications

hgpu.org » Applications » Computer science

High Performance Non-Blocking Collective Communication for Next Generation Infiniband Clusters

Krishna Kandalla

View

Download (PDF)

Tags: Benchmarking, Computer science, InfiniBand, Intel Xeon Phi, Linear Algebra, MPI

March 14, 2014 by hgpu

Fast Exact Hyper-Graph Matching with Dynamic Programming for Spatio-Temporal Data

Oya Celiktutan, Christian Wolf, Bulent Sankur, Eric Lombardi

View

Download (PDF)

Tags: Algorithms, Computer science, Computer vision, CUDA, Graph theory, nVidia, nVidia GeForce GTS 450, nVidia GeForce GTX 580, Sorting

March 14, 2014 by hgpu

Visualizing Trends on Twitter

Cheng Hau Tong

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, nVidia GeForce GTX 680, Thesis, Visualization

March 13, 2014 by hgpu

The Flocking Based and GPU Accelerated Internet Traffic Classification

Zhiguang Xu

View

Download (PDF)

Tags: Computer science, CUDA, Network communications, nVidia, nVidia GeForce GTX 480, Tesla C2070

March 13, 2014 by hgpu

Fast hydrodynamics on heterogenous many-core hardware

Allan Peter Engsig-Karup, Stefan L. Glimberg, Allan S. Nielsen, Ole Lindberg

View

Download (PDF)

Tags: Computer science, CUDA, free surface, GPGPU, hydrodynamics, massively parallel computing, multigrid

March 12, 2014 by apek

Development of High-Performance Software Components for Emerging Architectures

Stefan Lemvig Glimberg, Allan Peter Engsig-Karup, Allan S. Nielsen, Bernd Dammann

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, GPGPU, iterative methods, Mathematics, multigrid, Package, parallel computing, Partial differential equations, Software development

March 12, 2014 by apek

Configuration and Benchmarks of Peer-to-Peer Communication over Gigabit Ethernet and InfiniBand in a Cluster with Intel Xeon Phi Coprocessors

Vadim Karpusenko and Andrey Vladimirov

View

Download (PDF)

Tags: InfiniBand, Intel Xeon Phi, MPI, RDMA

March 12, 2014 by Andrey Vladimirov

Locality optimization on a NUMA architecture for hybrid LU factorization

Adrien Remy, Marc Baboulin, Masha Sosonkina, Brigitte Rozoy

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, Factorization, Linear Algebra, nVidia, Tesla S2050

March 12, 2014 by hgpu

Genetically Improved CUDA kernels for StereoCamera

W. B. Langdon, M. Harman

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Evolutionary Computations, Genetic programming, nVidia, nVidia GeForce GTX 580, Package, Tesla C2050, Tesla K20, Tesla T10

March 12, 2014 by hgpu

OpenCL-Accelerated Simplified General Perturbations 4 Algorithm

Juan Andres Fraire, Pablo Ferreyra, Carlos Marques

View

Download (PDF)

Tags: ATI, ATI Radeon HD 5870, Earth and Space Sciences, Heterogeneous systems, nVidia, nVidia GeForce 9500 GT, OpenCL, Security

March 10, 2014 by hgpu

GPU-EvR: Run-time Event Based Real-time Scheduling Framework on GPGPU Platform

Haeseung Lee, Mohammad Abdullah Al Faruque

View

Download (PDF)

Tags: Computer science, nVidia, Task scheduling, Tesla K20

March 10, 2014 by hgpu

Massively parallel read mapping on GPUs with PEANUT

Johannes Koster, Sven Rahmann

View

Download (PDF)

Source codes

Tags: Computer science, Data Structures and Algorithms, nVidia, nVidia GeForce GTX 580, nVidia GeForce GTX 780, OpenCL, Package, Python

March 10, 2014 by hgpu

True 4-Bit Quantized CNN Training on CPU

True 4-Bit Quantized Convolutional Neural Network Training on CPU: Achieving Full-Precision Parity

cuFuzz: A GPU-oriented coverage-guided fuzzer for userland CUDA application

Hunting CUDA Bugs at Scale with cuFuzz

KernelSkill: A Multi-Agent Framework for GPU Kernel Optimization

MSKernelBench & CUDAMaster

Making LLMs Optimize Multi-Scenario CUDA Kernels Like Experts

EvoScientist: Harness Vibe Research with Self-evolving AI Scientists

EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discovery

RepoLaunch: Automating Build and Test Pipeline of Code Repositories on ANY Language and ANY Platform

RepoLaunch: Automating Build & Test Pipeline of Code Repositories on ANY Language and ANY Platform

RepoLaunch: Automating Build and Test Pipeline of Code Repositories on ANY Language and ANY Platform

RepoLaunch: Automating Build & Test Pipeline of Code Repositories on ANY Language and ANY Platform

CONCUR: a benchmark designed to evaluate multithreaded Java code generated by LLMs

CONCUR: Benchmarking LLMs for Concurrent Code Generation

HIPRT: Ray Tracing using HIP

Ray Tracing using HIP

MXFP4 Training Support Codebase

Practical FP4 Training for Large-Scale MoE Models on Hopper GPUs

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Applications

High Performance Non-Blocking Collective Communication for Next Generation Infiniband Clusters

Fast Exact Hyper-Graph Matching with Dynamic Programming for Spatio-Temporal Data

Visualizing Trends on Twitter

The Flocking Based and GPU Accelerated Internet Traffic Classification

Fast hydrodynamics on heterogenous many-core hardware

Development of High-Performance Software Components for Emerging Architectures

Configuration and Benchmarks of Peer-to-Peer Communication over Gigabit Ethernet and InfiniBand in a Cluster with Intel Xeon Phi Coprocessors

Locality optimization on a NUMA architecture for hybrid LU factorization

Genetically Improved CUDA kernels for StereoCamera

OpenCL-Accelerated Simplified General Perturbations 4 Algorithm

GPU-EvR: Run-time Event Based Real-time Scheduling Framework on GPGPU Platform

Massively parallel read mapping on GPUs with PEANUT

Recent source codes

True 4-Bit Quantized CNN Training on CPU

cuFuzz: A GPU-oriented coverage-guided fuzzer for userland CUDA application

KernelSkill: A Multi-Agent Framework for GPU Kernel Optimization

MSKernelBench & CUDAMaster

EvoScientist: Harness Vibe Research with Self-evolving AI Scientists

RepoLaunch: Automating Build and Test Pipeline of Code Repositories on ANY Language and ANY Platform

RepoLaunch: Automating Build and Test Pipeline of Code Repositories on ANY Language and ANY Platform

CONCUR: a benchmark designed to evaluate multithreaded Java code generated by LLMs

HIPRT: Ray Tracing using HIP

MXFP4 Training Support Codebase

Most viewed papers (last 30 days)