high performance computing on graphics processing units: hgpu.org

hgpu.org » Performance

Performance and Productivity of Parallel Python Programming: A study with a CFD Test Case

Achim Basermann, Melven Rohrig-Zollner, Joachim Illmer

View

Download (PDF)

Tags: CUDA, Fluid dynamics, Fortran, nVidia, Performance, Python, Tesla C2075

December 22, 2015 by hgpu

Investigation of the SYCL for OpenCL Programming Model

Tim Beattie

View

Download (PDF)

Tags: Computer science, Heterogeneous systems, Intel Xeon Phi, OpenCL, Performance, Thesis

December 19, 2015 by hgpu

High Performance Histograms on SIMT and SIMD Architectures

M.E.R. Berger

View

Download (PDF)

Tags: AMD Radeon R9 290X, Computer science, CUDA, nVidia, nVidia GeForce GTX 570, nVidia GeForce GTX 660, nVidia GeForce GTX 750, OpenCL, Performance, Thesis

December 10, 2015 by hgpu

A Semi-Automated Tool Flow for Roofline Anaylsis of OpenCL Kernels on Accelerators

Servesh Muralidharan, Kenneth O'Brien, Christian Lalanne

View

Download (PDF)

Tags: Computer science, FPGA, Heterogeneous systems, Intel Xeon Phi, nVidia, OpenCL, Performance, Tesla K20

December 8, 2015 by hgpu

Programming in CUDA for Kepler and Maxwell Architecture

Esteban G. W. Clua, Marcelo Zamith

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, Performance

December 1, 2015 by hgpu

GEMMbench: a framework for reproducible and collaborative benchmarking of matrix multiplication

Anton Lokhmotov

View

Download (PDF)

Source codes

Tags: ARM, Benchmarking, Computer science, Linear Algebra, Mathematical Software, Matrix multiplication, OpenCL, Package, Performance

November 13, 2015 by hgpu

Autotuning OpenCL Workgroup Size for Stencil Patterns

Chris Cummins, Pavlos Petoumenos, Michel Steuwer, Hugh Leather

View

Download (PDF)

Tags: ATI, ATI Radeon HD 7970, Computer science, Machine learning, nVidia, nVidia GeForce GTX 590, nVidia GeForce GTX 690, nVidia GeForce GTX Titan, OpenCL, Performance

November 11, 2015 by hgpu

Evaluation of the Intel Xeon Phi and NVIDIA K80 as accelerators for two-dimensional panel codes

Lukas Einkemmer

View

Download (PDF)

Tags: Computer science, CUDA, Differential equations, Intel Xeon Phi, nVidia, Partial differential equations, PDEs, Performance, Tesla K80

November 10, 2015 by hgpu

On the Effectiveness of OpenMP teams for Programming Embedded Manycore Accelerators

Alessandro Capotondi, Andrea Marongiu

View

Download (PDF)

Tags: Computer science, Heterogeneous systems, OpenMP, Performance, SoC

November 8, 2015 by hgpu

Performance of GTX Titan X GPUs and Code Optimization

Hwancheol Jeong, Sangbaek Lee, Weonjong Lee, Jeonghwan Pak, Jangho Kim, Juhyun Chung

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, nVidia GeForce GTX Titan X, Performance

November 4, 2015 by hgpu

On the programmability of multi-GPU computing systems

Javier Cabezas Rodriguez

View

Download (PDF)

Tags: Computer science, CUDA, MPI, nVidia, Performance, Tesla C1060, Tesla K20, Tesla K40, Thesis

November 3, 2015 by hgpu

Padding Free Bank Conflict Resolution for CUDA-Based Matrix Transpose Algorithm

Ayaz ul Hassan Khan, Mayez Al-Mouhamed, Allam Fatayer, Anas Almousa, Abdulrahman Baqais, Mohammed Assayony

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, Linear Algebra, nVidia, nVidia Quadro FX 7000, Performance

October 29, 2015 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

Performance and Productivity of Parallel Python Programming: A study with a CFD Test Case

Investigation of the SYCL for OpenCL Programming Model

High Performance Histograms on SIMT and SIMD Architectures

A Semi-Automated Tool Flow for Roofline Anaylsis of OpenCL Kernels on Accelerators

Programming in CUDA for Kepler and Maxwell Architecture

GEMMbench: a framework for reproducible and collaborative benchmarking of matrix multiplication

Autotuning OpenCL Workgroup Size for Stencil Patterns

Evaluation of the Intel Xeon Phi and NVIDIA K80 as accelerators for two-dimensional panel codes

On the Effectiveness of OpenMP teams for Programming Embedded Manycore Accelerators

Performance of GTX Titan X GPUs and Code Optimization

On the programmability of multi-GPU computing systems

Padding Free Bank Conflict Resolution for CUDA-Based Matrix Transpose Algorithm

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)