high performance computing on graphics processing units: hgpu.org

Programming

Performance Upper Bound Analysis and Optimization of SGEMM on Fermi and Kepler GPUs

Junjie Lai, Andre Seznec

View

Tags: Algorithms, Benchmarking, Computer science, CUBLAS, CUDA, nVidia, nVidia GeForce GTX 680, Optimization, Performance

February 22, 2013 by hgpu

A Parallel Active-Set Method for Solving Frictional Contact Problems

Joshua Alexander Litven

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, Factorization, nVidia, nVidia GeForce GTX 580, Physics, Thesis

February 22, 2013 by hgpu

Investigating performance variations of an optimized GPU-ported granulometry algorithm

Vincent Boulos, Vincent Fristot, Dominique Houzet, Luc Salvo, Pierre Lhuissier

View

Download (PDF)

Tags: Algorithm optimization, Algorithms, CUDA, FEM, Finite element method, Image processing, Materials Science, nVidia, nVidia GeForce GTX 285, nVidia GeForce GTX 480, nVidia Quadro FX 4000

February 22, 2013 by hgpu

GPU-based Motion Planning under Uncertainties using POMDP

Taekhee Lee, Young J. Kim

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, Data parallelism, nVidia, nVidia GeForce GTX 680

February 22, 2013 by hgpu

Computation of Air-Vortices Based on GPU Technology: Optimizing and Parallelizing a Model for Wake-Vortex Prediction Using OpenCL

Erik Peldan

View

Download (PDF)

Tags: Algorithms, Computer science, Differential equations, nVidia, OpenCL, Thesis

February 21, 2013 by hgpu

Complexity Analysis and Algorithm Design for Reorganizing Data to Minimize Non-Coalesced Memory Accesses on GPU

Bo Wu, Zhijia Zhao, Eddy Z. Zhang, Yunlian Jiang, Xipeng Shen

View

Download (PDF)

Tags: Algorithms, Computational Complexity, Computer science, CUDA, nVidia, nVidia GeForce GTX 480, Tesla C1060

February 20, 2013 by hgpu

Exploring SIMD for Molecular Dynamics, Using Intel Xeon Processors and Intel Xeon Phi Coprocessors

S. J. Pennycook, C. J. Hughes, M. Smelyanskiy, S. A. Jarvis

View

Download (PDF)

Tags: Algorithms, Benchmarking, Computer science, Intel, Intel Phi, Molecular dynamics

February 14, 2013 by hgpu

Nonlinear dynamic finite element analysis with GPU

T. Bahcecioglu, O. Kurc

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, Nonlinear analysis, nVidia, Tesla C2050

February 14, 2013 by hgpu

Efficient Exploitation of Heterogeneous Platforms for Images Features Extraction

Sidi Ahmed Mahmoudi, Pierre Manneback

View

Download (PDF)

Tags: Algorithms, Computer science, Computer vision, CUDA, Heterogeneous systems, Image processing, nVidia, nVidia GeForce GTX 280, Pattern recognition, Tesla C1060

February 14, 2013 by hgpu

Partial Volume Effect Correction using Anisotropic Backward Diffusion

Zsolt Marta, Laszlo Szirmay-Kalos

View

Download (PDF)

Tags: Algorithms, Computed tomography, CT, Medicine, OpenCL, PET, Tomography

February 14, 2013 by hgpu

A volume segmentation approach based on GrabCut

Esmitt Ramirez J., Pablo Temoche, Rhadames Carmona

View

Download (PDF)

Tags: Algorithms, CUDA, Image processing, nVidia, nVidia GeForce GT 240, nVidia GeForce GTX 470

February 12, 2013 by hgpu

Fast 3D Wavelet Transform on Multicore and Manycore Computing Platforms

V. Galiano, O. Lopez-Granado, M.P. Malumbres, H. Migallon

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, Image processing, nVidia, nVidia GeForce GTX 280, Optimization, Wavelet

February 9, 2013 by hgpu

MATLAB Tensor Core models

Accurate Models of NVIDIA Tensor Cores

TritonForge: Transform PyTorch Operations into Optimized GPU Kernels with LLMs

TritonForge: Profiling-Guided Framework for Automated Triton Kernel Optimization

RLTune: Hybrid Learning and Optimization-Based Dynamic Scheduling for DL Workloads on Heterogeneous GPU Clusters

Hybrid Learning and Optimization-Based Dynamic Scheduling for DL Workloads on Heterogeneous GPU Clusters

tritonBLAS: A Lightweight Triton-based General Matrix Multiplication (GEMM) Library

tritonBLAS: Triton-based Analytical Approach for GEMM Kernel Parameter Selection

hls4ml: Machine learning on FPGAs using HLS

hls4ml: A Flexible, Open-Source Platform for Deep Learning Acceleration on Reconfigurable Hardware

NVIDIA Nemotron Parse 1.1

ThunderKittens: Tile primitives for speedy kernels

ParallelKittens: Systematic and Practical Simplification of Multi-GPU AI Kernels

Iris: AMD RAD's multi-GPU Triton-based framework for seamless multi-GPU programming

Iris: First-Class Multi-GPU Programming Experience in Triton

HipKittens: Fast and Furious AMD Kernels

Fortran xDSL dialects

An MLIR pipeline for offloading Fortran to FPGAs via OpenMP

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Programming

Performance Upper Bound Analysis and Optimization of SGEMM on Fermi and Kepler GPUs

A Parallel Active-Set Method for Solving Frictional Contact Problems

Investigating performance variations of an optimized GPU-ported granulometry algorithm

GPU-based Motion Planning under Uncertainties using POMDP

Computation of Air-Vortices Based on GPU Technology: Optimizing and Parallelizing a Model for Wake-Vortex Prediction Using OpenCL

Complexity Analysis and Algorithm Design for Reorganizing Data to Minimize Non-Coalesced Memory Accesses on GPU

Exploring SIMD for Molecular Dynamics, Using Intel Xeon Processors and Intel Xeon Phi Coprocessors

Nonlinear dynamic finite element analysis with GPU

Efficient Exploitation of Heterogeneous Platforms for Images Features Extraction

Partial Volume Effect Correction using Anisotropic Backward Diffusion

A volume segmentation approach based on GrabCut

Fast 3D Wavelet Transform on Multicore and Manycore Computing Platforms

Recent source codes

MATLAB Tensor Core models

TritonForge: Transform PyTorch Operations into Optimized GPU Kernels with LLMs

RLTune: Hybrid Learning and Optimization-Based Dynamic Scheduling for DL Workloads on Heterogeneous GPU Clusters

tritonBLAS: A Lightweight Triton-based General Matrix Multiplication (GEMM) Library

hls4ml: Machine learning on FPGAs using HLS

NVIDIA Nemotron Parse 1.1

ThunderKittens: Tile primitives for speedy kernels

Iris: AMD RAD's multi-GPU Triton-based framework for seamless multi-GPU programming

HipKittens: Fast and Furious AMD Kernels

Fortran xDSL dialects

Most viewed papers (last 30 days)