high performance computing on graphics processing units: hgpu.org

hgpu.org » PDEs

Exploring Optimisations for the Local Assembly phase of Finite Element Methods on GPUs

Hector Dearman

View

Tags: Benchmarking, Computer science, CUDA, Differential equations, FEM, Finite element method, nVidia, nVidia GRID K520, OpenCL, Partial differential equations, PDEs, Thesis

November 3, 2015 by hgpu

Toward a Multi-level Parallel Framework on GPU Cluster with PetSC-CUDA for PDE-based Optical Flow Computation

S. Cuomo, A. Galletti, G. Giunta, L. Marcellino

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, Differential equations, GPU cluster, Heterogeneous systems, nVidia, nVidia Quadro K5000, Optical flow, Partial differential equations, PDEs

June 24, 2015 by hgpu

A Parallel Implementation of the Galerkin Method for Solving Partial Differential Equations on a Triangular Mesh

Rachel N. Hess

View

Download (PDF)

Tags: Differential equations, FEM, Finite element method, Mathematics, OpenCL, Partial differential equations, PDEs, PyOpenCL, Thesis, Triangular meshes

June 7, 2015 by hgpu

High Performance Computing for solving large sparse systems. Optical Diffraction Tomography as a case of study

Gloria Ortega Lopez

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Differential equations, FEM, Finite difference, Finite element method, GPU cluster, Heterogeneous systems, Linear Algebra, nVidia, nVidia GeForce GTX 480, nVidia GeForce GTX 680, Package, Partial differential equations, PDEs, Sparse matrix, Tesla C2050, Tesla M2070, Tesla M2090, Thesis, Tomography

March 30, 2015 by hgpu

A Switched Dynamical System Framework for Analysis of Massively Parallel Asynchronous Numerical Algorithms

Kooktae Lee, Raktim Bhattacharya, Vijay Gupta

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, Differential equations, nVidia, Partial differential equations, PDEs, Tesla C2050

March 18, 2015 by hgpu

Performance Analysis and Optimization of Hermite Methods on NVIDIA GPUs Using CUDA

Evan T. Dye

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, Differential equations, Mathematics, nVidia, nVidia GeForce GTX 560 Ti, Partial differential equations, PDEs, Thesis

February 2, 2015 by hgpu

Productive and Efficient Computational Science Through Domain-specific Abstractions

Florian Rathgeber

View

Download (PDF)

Tags: Computer science, CUDA, Differential equations, FEM, Finite element method, nVidia, OpenCL, Partial differential equations, PDEs, Thesis

February 1, 2015 by hgpu

Global finite element matrix construction based on a CPU-GPU implementation

Francisco Javier Ramírez-Gil, Marcos de Sales Guerra Tsuzuki, Wilfredo Montealegre-Rubio

View

Download (PDF)

Tags: Analysis of PDEs, Computational Engineering, CUDA, FEM, Numerical Analysis, parallel computing, PDEs, Performance

January 21, 2015 by fjramireg

A CUDA implementation of the High Performance Conjugate Gradient benchmark

Everett Phillips, Massimiliano Fatica

View

Download (PDF)

Tags: Algorithms, Benchmarking, Computer science, CUDA, Differential equations, nVidia, Partial differential equations, PDEs, Tesla K20

November 29, 2014 by hgpu

A stencil-based implementation of Parareal in the C++ domain specific embedded language STELLA

Andrea Arteaga, Daniel Ruprecht, Rolf Krause

View

Download (PDF)

Tags: Computer science, CUDA, Differential equations, MPI, nVidia, Partial differential equations, PDEs, Tesla K20

October 3, 2014 by hgpu

A CUDA Back-End for the Equelle Compiler

Havard Heitlo Holm

View

Download (PDF)

Source codes

Tags: Compilers, Computer science, CUDA, Differential equations, Finite volume method, Heterogeneous systems, nVidia, nVidia Quadro NVS 5200 M, Package, Partial differential equations, PDEs, Tesla K40, Thesis

September 8, 2014 by hgpu

Algorithms for Solving Non-Stationary Heat Conduction Problem for Design of a Technical Device

Alexander Ayriyan, Jan Busa Jr., Eugeny E. Donets, Hovik Grigorian, Jan Pribis

View

Download (PDF)

Tags: Algorithms, Computational Physics, Differential equations, Finite difference, nVidia, nVidia GeForce GTX 470, OpenCL, Partial differential equations, PDEs, Physics

August 27, 2014 by hgpu

PTXBench: an open-source environment for kernel agents with architecture-specific CUDA/PTX

PTXBench: Benchmark and Adapt LLMs for GPU Kernel Optimization with Architecture-specific PTX

RealisticTritonBench: A Benchmark for Triton-Kernel Generation in Real-World AI Frameworks

TensorCorePTX: PTX Tensor Core GEMM Exploration

Hand-Written PTX Tensor-Core GEMM Kernels: A Multi-Precision Study on NVIDIA L4

FlashPDE: Triton-fused PDE stencil kernels for physics-informed neural networks

FlashPDE: A Drop-In Fused Triton Operator Library for Neural PDE Solvers

PortLBM: Portable GPU-accelerated Lattice Boltzmann Method Simulations

PortLBM: A Portable Lattice Boltzmann Tool Leveraging SYCL on AMD, NVIDIA, and Intel GPUs

Harness Engineering for LLM-Driven GPU Kernel Generation

CANNBot Skills

Compiler-Grounded Hierarchical Diagnosis for LLM-Based Triton Kernel Optimization

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Exploring Optimisations for the Local Assembly phase of Finite Element Methods on GPUs

Toward a Multi-level Parallel Framework on GPU Cluster with PetSC-CUDA for PDE-based Optical Flow Computation

A Parallel Implementation of the Galerkin Method for Solving Partial Differential Equations on a Triangular Mesh

High Performance Computing for solving large sparse systems. Optical Diffraction Tomography as a case of study

A Switched Dynamical System Framework for Analysis of Massively Parallel Asynchronous Numerical Algorithms

Performance Analysis and Optimization of Hermite Methods on NVIDIA GPUs Using CUDA

Productive and Efficient Computational Science Through Domain-specific Abstractions

Global finite element matrix construction based on a CPU-GPU implementation

A CUDA implementation of the High Performance Conjugate Gradient benchmark

A stencil-based implementation of Parareal in the C++ domain specific embedded language STELLA

A CUDA Back-End for the Equelle Compiler

Algorithms for Solving Non-Stationary Heat Conduction Problem for Design of a Technical Device

Recent source codes

FP4 FlashAttention forward, backward, and TorchTitan reproduction code

EinsummableV3 - graph-based computation with tensor operations support

MaxKernel: Intelligent TPU Kernel Engineering Agents

PTXBench: an open-source environment for kernel agents with architecture-specific CUDA/PTX

RealisticTritonBench: A Benchmark for Triton-Kernel Generation in Real-World AI Frameworks

TensorCorePTX: PTX Tensor Core GEMM Exploration

FlashPDE: Triton-fused PDE stencil kernels for physics-informed neural networks

PortLBM: Portable GPU-accelerated Lattice Boltzmann Method Simulations

Harness Engineering for LLM-Driven GPU Kernel Generation

CANNBot Skills

Most viewed papers (last 30 days)