high performance computing on graphics processing units: hgpu.org

hgpu.org » performance portability

Portability and Scalability of OpenMP Offloading on State-of-the-art Accelerators

Yehonatan Fridman, Guy Tamir, Gal Oren

View

Download (PDF)

Source codes

Tags: Benchmarking, Computer science, Intel, Intel Ponte Vecchio Max 1100, nVidia, nVidia A100, oneAPI, OpenMP, Package, performance portability

April 16, 2023 by hgpu

Kernel Launcher: C++ Library for Optimal-Performance Portable CUDA Applications

Stijn Heldens, Ben van Werkhoven

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Fluid dynamics, nVidia, nVidia A100, Package, Performance, performance portability

March 26, 2023 by hgpu

Towards a Benchmarking Suite for Kernel Tuners

Jacob O. Tørring, Ben van Werkhoven, Filip Petrovic, Floris-Jan Willemsen, Jirí Filipovic, Anne C. Elster

View

Download (PDF)

Source codes

Tags: Auto-Tuning, Benchmarking, Computer science, CUDA, nVidia, nVidia GeForce RTX 2080 Ti, nVidia GeForce RTX 3060, nVidia GeForce RTX 3090, nVidia Titan RTX, Package, performance portability

March 19, 2023 by hgpu

Machine Learning-Driven Adaptive OpenMP For Portable Performance on Heterogeneous Systems

Giorgis Georgakoudis, Konstantinos Parasyris, Chunhua Liao, David Beckingsale, Todd Gamblin, Bronis de Supinski

View

Download (PDF)

Tags: AMD Radeon Instinct Mi50, ATI, Benchmarking, Code generation, Compilers, Computer science, CUDA, Heterogeneous systems, Machine learning, nVidia, OpenMP, performance portability, Tesla P100, Tesla V100

March 19, 2023 by hgpu

Runtime Support for Performance Portability on Heterogeneous Distributed Platforms

Polykarpos Thomadakis, Nikos Chrisochoides

View

Download (PDF)

Tags: Computer science, CUDA, Heterogeneous systems, MPI, nVidia, performance portability, Tesla V100

March 12, 2023 by hgpu

Extending MAGMA Portability with OneAPI

Anna Fortenberry, Stanimire Tomov

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Heterogeneous systems, Linear Algebra, Matrix multiplication, nVidia, nVidia GeForce RTX 3060, oneAPI, Package, performance portability

December 25, 2022 by hgpu

Assessing Application Efficiency and Performance Portability in Single-Source Programming for Heterogeneous Parallel Systems

August Ernstsson, Dalvan Griebler, Christoph Kessler

View

Download (PDF)

Source codes

Tags: Benchmarking, Computer science, CUDA, Heterogeneous systems, nVidia, OpenCL, OpenMP, Package, performance portability, Tesla K20

December 11, 2022 by hgpu

Providing performance portable numerics for Intel GPUs

Yu-Hsiang M. Tsai, Terry Cojean, Hartwig Anzt

View

Download (PDF)

Source codes

Tags: AMD Radeon Instinct MI100, ATI, Computer science, CUDA, Linear Algebra, nVidia, nVidia A100, OpenCL, Package, performance portability, Sparse, SYCL

October 30, 2022 by hgpu

From Task-Based GPU Work Aggregation to Stellar Mergers: Turning Fine-Grained CPU Tasks into Portable GPU Kernels

Gregor Daiß, Patrick Diehl, Dominic Marcello, Alireza Kheirkhahan, Hartmut Kaiser, Dirk Pflüger

View

Download (PDF)

Source codes

Tags: AMD Radeon Instinct MI100, Astrophysics, ATI, CUDA, HIP, nVidia, nVidia A100, Package, performance portability, Physics

October 23, 2022 by hgpu

Towards Performance Portable Programming for Distributed Heterogeneous Systems

Polykarpos Thomadakis, Nikos Chrisochoides

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Heterogeneous systems, nVidia, OpenCL, Package, Performance, performance portability, Tesla V100

October 9, 2022 by hgpu

Performance portability study of epistasis detection using SYCL on NVIDIA GPU

Zheming Jin, Jeffrey S. Vetter

View

Download (PDF)

Tags: Computer science, CUDA, Genomics, nVidia, performance portability, SYCL, Tesla V100

October 9, 2022 by hgpu

Enhancing the Performance Portability of Heterogeneous Circuit Analysis Programs

Tsung-Wei Huang

View

Download (PDF)

Tags: AMD Radeon RX 6900 XT, ATI, Computer science, Deep learning, nVidia, nVidia GeForce RTX 3090, OpenCL, performance portability, PyTorch, SYCL

September 11, 2022 by hgpu

Over-synchronization in GPU Programs

profile_util: simple C++ library to report memory, timing, thread affinity

Profile Util library: A quick and easy way to get MPI, OpenMP and GPU runtime information

MaC: Mamba CPU performance predictor

MambaCPU: Enhanced Correlation Mining with State Space Models for CPU Performance Prediction

Mixed-precision finite element kernels

Mixed-precision finite element kernels and assembly: Rounding error analysis and hardware acceleration

SHMT: The Simultaneous and Heterogenous Multithreading project

General-Purpose Computing on Tensor Processors

Superpipeline: A Universal Approach for Reducing GPU Memory Usage in Large Models

EnergyUCB-Bandit

Online Energy Optimization in GPUs: A Multi-Armed Bandit Approach

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Portability and Scalability of OpenMP Offloading on State-of-the-art Accelerators

Kernel Launcher: C++ Library for Optimal-Performance Portable CUDA Applications

Towards a Benchmarking Suite for Kernel Tuners

Machine Learning-Driven Adaptive OpenMP For Portable Performance on Heterogeneous Systems

Runtime Support for Performance Portability on Heterogeneous Distributed Platforms

Extending MAGMA Portability with OneAPI

Assessing Application Efficiency and Performance Portability in Single-Source Programming for Heterogeneous Parallel Systems

Providing performance portable numerics for Intel GPUs

From Task-Based GPU Work Aggregation to Stellar Mergers: Turning Fine-Grained CPU Tasks into Portable GPU Kernels

Towards Performance Portable Programming for Distributed Heterogeneous Systems

Performance portability study of epistasis detection using SYCL on NVIDIA GPU

Enhancing the Performance Portability of Heterogeneous Circuit Analysis Programs

Recent source codes

Kokkidio: Kokkos+Eigen - write fast, readable multi-platform code

LLaMA-Inference-Bench

MATAR

Over-synchronization in GPU Programs

profile_util: simple C++ library to report memory, timing, thread affinity

MaC: Mamba CPU performance predictor

Mixed-precision finite element kernels

SHMT: The Simultaneous and Heterogenous Multithreading project

Superpipeline: A Universal Approach for Reducing GPU Memory Usage in Large Models

EnergyUCB-Bandit

Most viewed papers (last 30 days)