high performance computing on graphics processing units: hgpu.org

Oliver Hennigh, Susheela Narasimhan, Mohammad Amin Nabian, Akshay Subramaniam, Kaustubh Tangsali, Max Rietmann, Jose del Aguila Ferrandis, Wonmin Byeon, Zhiwei Fang, Sanjay Choudhry

View

Download (PDF)

Tags: cfd, CUDA, Fluid dynamics, Linear Algebra, Machine learning, Neural networks, nVidia, nVidia A100, Partial differential equations, PDEs, Physics, Tesla V100, Video

December 20, 2020 by hgpu

Evaluating the Performance of NVIDIA’s A100 Ampere GPU for Sparse Linear Algebra Computations

Yuhsiang Mike Tsai, Terry Cojean, Hartwig Anzt

View

Download (PDF)

Tags: Computer science, CUDA, Linear Algebra, nVidia, nVidia A100, Performance, Sparse, Sparse matrix

August 23, 2020 by hgpu

GCN Inference Acceleration HLS

GCN Inference Acceleration using High-Level Synthesis

Climate Machine: an Earth System Model that automatically learns from data

Large-eddy simulations with ClimateMachine: a new open-source code for atmospheric simulations on GPUs and CPUs

HLS Portability from Intel to Xilinx: A Case Study

HEXL: Intel Homomorphic Encryption Acceleration Library

Accelerating Encrypted Computing on Intel GPUs

Taskflow: A General-purpose Parallel and Heterogeneous Task Programming System

Taskflow: A Lightweight Parallel and Heterogeneous Task Graph Computing System

CompilerGym: a library performant reinforcement learning environments for compiler tasks

CompilerGym: Robust, Performant Compiler Optimization Environments for AI Research

WarpDrive: Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning on a GPU

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Achieving near native runtime performance and cross-platform performance portability for random number generation through SYCL interoperability

Performance comparison of CFD-DEM solver MFiX-Exa, on GPUs and CPUs

KAISA: An Adaptive Second-order Optimizer Framework for Deep Neural Networks

Performance analysis and optimization of highly diverging algorithms on GPUs

AutoFreeze: Automatically Freezing Model Blocks to Accelerate Fine-tuning

NVIDIA SimNet: an AI-accelerated multi-physics simulation framework

Evaluating the Performance of NVIDIA’s A100 Ampere GPU for Sparse Linear Algebra Computations

Recent source codes

GCN Inference Acceleration HLS

Climate Machine: an Earth System Model that automatically learns from data

HLS Portability from Intel to Xilinx: A Case Study

HEXL: Intel Homomorphic Encryption Acceleration Library

Taskflow: A General-purpose Parallel and Heterogeneous Task Programming System

CompilerGym: a library performant reinforcement learning environments for compiler tasks

HPCToolkit

NVPTX-SPIR-V Translator

Taichi Lattice Boltmann

WarpDrive: Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning on a GPU

Most viewed papers (last 30 days)