high performance computing on graphics processing units: hgpu.org

hgpu.org » CUDA

Ansor: Generating High-Performance Tensor Programs for Deep Learning

Lianmin Zheng, Chengfan Jia, Minmin Sun, Zhao Wu, Cody Hao Yu, Ameer Haj-Ali, Yida Wang, Jun Yang, Danyang Zhuo, Koushik Sen, Joseph E. Gonzalez, Ion Stoica

View

Download (PDF)

Tags: ARM, Compilers, Computer science, CUDA, Deep learning, Neural networks, nVidia, Optimization, Search strategies, Tesla V100

June 21, 2020 by hgpu

AutoMat – Automatic Differentiation for Generalized Standard Materials on GPUs

Johannes Blühdorn, Nicolas R. Gauger, Matthias Kabel

View

Download (PDF)

Tags: Computer science, CUDA, FFT, Mathematical Software, nVidia, nVidia Quadro GV100

June 14, 2020 by hgpu

Efficient Sparse-Dense Matrix-Matrix Multiplication on GPUs Using the Customized Sparse Storage Format

Shaohuai Shi, Qiang Wang, Xiaowen Chu

View

Download (PDF)

Source codes

Tags: Algorithms, Computer science, CUBLAS, CUDA, Matrix multiplication, nVidia, nVidia GeForce GTX 980, nVidia GeForce GTX Titan X, Package, Sparse matrix, Tesla P100

June 7, 2020 by hgpu

Lessons learned in a decade of research software engineering GPU applications

Ben van Werkhoven, Willem Jan Palenstijn, Alessio Sclocco

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, OpenCL, Software Engineering

May 31, 2020 by hgpu

Character-level Transformer-based Neural Machine Translation

Nikolay Banar, Walter Daelemans, Mike Kestemont

View

Download (PDF)

Tags: Computer science, CUDA, Deep learning, NLP, nVidia, nVidia GeForce GTX 1080 Ti

May 31, 2020 by hgpu

Brief Announcement: On the Limits of Parallelizing Convolutional Neural Networks on GPUs

Behnam Pourghassemi, Chenghao Zhang, Joo Hwan Lee, Aparna Chandramowlishwaran

View

Download (PDF)

Tags: Computer science, CUDA, Deep learning, Neural networks, nVidia, TensorFlow, Tesla K40

May 31, 2020 by hgpu

HetPipe: Enabling Large DNN Training on (Whimpy) Heterogeneous GPU Clusters through Integration of Pipelined Model Parallelism and Data Parallelism

Jay H. Park, Gyeongchan Yun, Chang M. Yi, Nguyen T. Nguyen, Seungmin Lee, Jaesik Choi, Sam H. Noh, Young-ri Choi

View

Download (PDF)

Tags: Computer science, CUDA, Data parallelism, Deep learning, GPU cluster, Heterogeneous systems, Neural networks, nVidia, nVidia GeForce GTX Titan V, nVidia GeForce RTX 2060, nVidia Quadro P 4000, nVidia Titan RTX

May 31, 2020 by hgpu

PDAWL: Profile-based Iterative Dynamic Adaptive WorkLoad Balance on Heterogeneous Architectures

Tongsheng Geng, Marcos Amaris, Stephane Zuckerman, Alfredo Goldman, Guang R. Gao, Jean-Luc Gaudiot

View

Download (PDF)

Tags: Computer science, CUDA, Heterogeneous systems, Machine learning, nVidia, nVidia GeForce GTX Titan, Performance, Sparse matrix, Task scheduling, Tesla K20, Tesla K40

May 24, 2020 by hgpu

Literature Review and Implementation Overview: High Performance Computing with Graphics Processing Units for Classroom and Research Use

Nathan George

View

Download (PDF)

Tags: Computer science, CUDA, Deep learning, Education, GPU cluster, HPC, nVidia, nVidia GeForce GTX 1080 Ti, nVidia Quadro RTX 5000, Overview

May 24, 2020 by hgpu

Deep Learning with GO

Derek L. Stinson

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Deep learning, Go, nVidia, nVidia GeForce GTX 1080 Ti, Package, Thesis

May 17, 2020 by hgpu

Heterogeneous CPU/GPU co-execution of CFD simulations on the POWER9 architecture: Application to airplane aerodynamics

R. Borrell, D. Dosimont, M. Garcia-Gasulla, G. Houzeaux, O. Lehmkuhl, V. Mehta, H. Owen, M. Vazquez, G. Oyarzun

View

Download (PDF)

Tags: cfd, CUDA, Fluid dynamics, Heterogeneous systems, MPI, nVidia, OpenMP, Tesla V100

May 17, 2020 by hgpu

Task-Based Parallel Strategies for CFD Application in Heterogeneous CPU/GPU Resources

Lucas Leandro Nesi, Matheus S. Serpa, Lucas Mello Schnorr, Philippe Olivier Alexandre Navaux

View

Download (PDF)

Source codes

Tags: cfd, CUDA, Fluid dynamics, Heterogeneous systems, nVidia, nVidia GeForce GXT 1080 Ti, Package

May 17, 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

Ansor: Generating High-Performance Tensor Programs for Deep Learning

AutoMat – Automatic Differentiation for Generalized Standard Materials on GPUs

Efficient Sparse-Dense Matrix-Matrix Multiplication on GPUs Using the Customized Sparse Storage Format

Lessons learned in a decade of research software engineering GPU applications

Character-level Transformer-based Neural Machine Translation

Brief Announcement: On the Limits of Parallelizing Convolutional Neural Networks on GPUs

HetPipe: Enabling Large DNN Training on (Whimpy) Heterogeneous GPU Clusters through Integration of Pipelined Model Parallelism and Data Parallelism

PDAWL: Profile-based Iterative Dynamic Adaptive WorkLoad Balance on Heterogeneous Architectures

Literature Review and Implementation Overview: High Performance Computing with Graphics Processing Units for Classroom and Research Use

Deep Learning with GO

Heterogeneous CPU/GPU co-execution of CFD simulations on the POWER9 architecture: Application to airplane aerodynamics

Task-Based Parallel Strategies for CFD Application in Heterogeneous CPU/GPU Resources

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)