high performance computing on graphics processing units: hgpu.org

hgpu.org » CUDA

Cross-platform programming model for many-core lattice Boltzmann simulations

Jonas Latt, Christophe Coreixas, Joël Beny

View

Tags: Algorithms, cfd, Computational Physics, CUDA, Fluid dynamics, Heterogeneous systems, Lattice Boltzmann model, nVidia, nVidia GeForce GTX 1080, nVidia GeForce RTX 2080, Physics

October 25, 2020 by hgpu

FlowPM: Distributed TensorFlow Implementation of the FastPM Cosmological N-body Solver

Chirag Modi, Francois Lanusse, Uros Seljak

View

Download (PDF)

Source codes

Tags: Astrophysics, Cosmology, CUDA, N-body simulation, nVidia, Package, Physics, TensorFlow, Tesla V100

October 25, 2020 by hgpu

Portable high-order finite element kernels I: Streaming Operations

Noel Chalmers, Tim Warburton

View

Download (PDF)

Tags: AMD, AMD Radeon Instinct MI60, AMD Radeon VII, Computer science, CUDA, FEM, HIP, Mathematical Software, nVidia, nVidia GeForce GTX Titan V, OCCA, Portability, Tesla V100

October 18, 2020 by hgpu

A Tensor Compiler for Unified Machine Learning Prediction Serving

Supun Nakandala Karla Saur, Gyeong-In Yu, Konstantinos Karanasos, Carlo Curino, Markus Weimer, Matteo Interlandi

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Machine learning, nVidia, Package, Tesla K80, Tesla P100

October 18, 2020 by hgpu

LoopBench: An Evaluation of Loop Acceleration in Heterogeneous Systems

Saman Biookaghazadeh, Fengbo Ren, Ming Zhao

View

Download (PDF)

Source codes

Tags: Benchmarking, Computer science, CUDA, FPGA, Heterogeneous systems, OpenCL, Package

October 4, 2020 by hgpu

Flexible Performant GEMM Kernels on GPUs

Thomas Faingnaert, Tim Besard, Bjorn De Sutter

View

Download (PDF)

Source codes

Tags: Computer science, CUBLAS, CUDA, Julia, Machine learning, Mathematical Software, Matrix multiplication, Mixed precision, nVidia, nVidia GeForce RTX 2080 Ti, Package, Performance

October 4, 2020 by hgpu

Accelerating Sparse Matrix-Matrix Multiplication with GPU Tensor Cores

Orestis Zachariadis, Nitin Satpute, Juan Gómez-Luna, Joaquín Olivares

View

Download (PDF)

Source codes

Tags: Algorithms, Computer science, CUDA, Matrix multiplication, Mixed precision, nVidia, nVidia GeForce RTX 2070, nVidia Titan RTX, Package, Performance, Sparse matrix

October 4, 2020 by hgpu

Hybrid MPI and CUDA Parallelization for CFD Applications on Multi-GPU HPC Clusters

Jianqi Lai, Hang Yu, Zhengyu Tian, Hua Li

View

Download (PDF)

Tags: cfd, CUDA, Fluid dynamics, GPU cluster, HPC, MPI, nVidia, nVidia GeForce GTX 1070, OpenMP, Tesla V100

September 27, 2020 by hgpu

Performance Evaluation of Mixed Precision Algorithms for Solving Sparse Linear Systems

Mawussi Zounon, Nicholas J. Higham, Craig Lucas, Françoise Tisseur

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, Factorization, Mixed precision, nVidia, Tesla P100, Tesla V100

September 27, 2020 by hgpu

Designing Efficient Barriers and Semaphores for Graphics Processing Units

Rohan Mahapatra

View

Download (PDF)

Tags: Algorithms, Benchmarking, Computer science, CUDA, nVidia, nVidia GeForce GTX 1080, nVidia GeForce GTX Titan V, nVidia GeForce RTX 2080 Ti, Thesis

September 20, 2020 by hgpu

A Comparison of Optimal Scanline Voxelization Algorithms

Tim Håkansson

View

Download (PDF)

Source codes

Tags: 3D Graphics and Realism, CUDA, GLSL, nVidia, OpenGL, Package, Tesla T4, Thesis, Voxelization

September 20, 2020 by hgpu

WarpCore: A Library for fast Hash Tables on GPUs

Daniel Jünger, Robin Kobus, André Müller, Christian Hundt, Kai Xu, Weiguo Liu, Bertil Schmidt

View

Download (PDF)

Tags: Bioinformatics, Computer science, CUDA, Hashing, nVidia, nVidia Quadro GV100, Tesla V100

September 20, 2020 by hgpu

SimSYCL: Synchronous, single-threaded, library-only SYCL implementation for debugging and verification

SimSYCL: A SYCL Implementation Targeting Development, Debugging, Simulation and Conformance

gpu_tracker: Context manager and CLI that tracks the computational-resource-usage of a code block or shell command, particularly the GPU usage

gpu_tracker: Python package for tracking and profiling GPU utilization in both desktop and high-performance computing environments

CIFAR-10 Airbench: 94% on CIFAR-10 in 3.29 second

94% on CIFAR-10 in 3.29 Seconds on a Single GPU

LOOPer: a polyhedral compiler for expressing fast and portable data parallel algorithms

LOOPer: A Learned Automatic Code Optimizer For Polyhedral Compilers

OpenMC Monte Carlo Code

Performance Portable Monte Carlo Particle Transport on Intel, NVIDIA, and AMD GPUs

Polygeist: C/C++ frontend for MLIR

Retargeting and Respecializing GPU Workloads for Performance Portability

Parallel Gaussian process with kernel approximation in CUDA

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Cross-platform programming model for many-core lattice Boltzmann simulations

FlowPM: Distributed TensorFlow Implementation of the FastPM Cosmological N-body Solver

Portable high-order finite element kernels I: Streaming Operations

A Tensor Compiler for Unified Machine Learning Prediction Serving

LoopBench: An Evaluation of Loop Acceleration in Heterogeneous Systems

Flexible Performant GEMM Kernels on GPUs

Accelerating Sparse Matrix-Matrix Multiplication with GPU Tensor Cores

Hybrid MPI and CUDA Parallelization for CFD Applications on Multi-GPU HPC Clusters

Performance Evaluation of Mixed Precision Algorithms for Solving Sparse Linear Systems

Designing Efficient Barriers and Semaphores for Graphics Processing Units

A Comparison of Optimal Scanline Voxelization Algorithms

WarpCore: A Library for fast Hash Tables on GPUs

Recent source codes

SimSYCL: Synchronous, single-threaded, library-only SYCL implementation for debugging and verification

GPU plugin for PySCF

QArray

Celerity: High-level C++ for Accelerator Clusters

gpu_tracker: Context manager and CLI that tracks the computational-resource-usage of a code block or shell command, particularly the GPU usage

CIFAR-10 Airbench: 94% on CIFAR-10 in 3.29 second

LOOPer: a polyhedral compiler for expressing fast and portable data parallel algorithms

OpenMC Monte Carlo Code

Polygeist: C/C++ frontend for MLIR

Parallel Gaussian process with kernel approximation in CUDA

Most viewed papers (last 30 days)