high performance computing on graphics processing units: hgpu.org

Jeffrey Krupa, Kelvin Lin, Maria Acosta Flechas, Jack Dinsmore, Javier Duarte, Philip Harris, Scott Hauck, Burt Holzman, Shih-Chieh Hsu, Thomas Klijnsma, Mia Liu, Kevin Pedro, Natchanon Suaysom, Matt Trahms, Nhan Tran

View

Download (PDF)

Source codes

Tags: Deep learning, FPGA, HEP, nVidia, Package, Physics, Tesla T4, Tesla V100

July 26, 2020 by hgpu

* * *

KLARAPTOR: A Tool for Dynamically Finding Optimal Kernel Launch Parameters Targeting CUDA Programs

Three Contributions to the Theory and Practice of Optimizing Compilers

HETU: a high-performance distributed deep learning system targeting large-scale and automated distributed training

Galvatron: Efficient Transformer Training over Multiple GPUs Using Automatic Parallelism

TorchOpt: an efficient library for differentiable optimization built upon PyTorch

TorchOpt: An Efficient Library for Differentiable Optimization

NaturalCC: An Open-Source Toolkit for Code Intelligence

A Study on Neural-based Code Summarization in Low-resource Settings

mt4g: Memory Topology for GPUs

Capturing the Memory Topology of GPUs

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Real-Time High-Performance Computing for Embedded Control Systems

BAT: A Benchmark suite for AutoTuners

Bolt: Bridging the Gap between Auto-tuners and Hardware-native Performance

LS-CAT: A Large-Scale CUDA AutoTuning Dataset

DISC: A Dynamic Shape Compiler for Machine Learning Workloads

Performance of CPU and GPU HPC Architectures for off-design aircraft simulation

TopicBERT for Energy Efficient Document Classification

A Comparison of Optimal Scanline Voxelization Algorithms

Optimizing Block-Sparse Matrix Multiplications on CUDA with TVM

GPU coprocessors as a service for deep learning inference in high energy physics

Recent source codes

KLARAPTOR: A Tool for Dynamically Finding Optimal Kernel Launch Parameters Targeting CUDA Programs

HETU: a high-performance distributed deep learning system targeting large-scale and automated distributed training

SYCL-DNN: a library implementing neural network algorithms written using SYCL

SW#SYCL

Flink-TornadoVM-Artifact

StateMover: a checkpoint-based debugging framework for FPGAs

Kernel Tuner

TorchOpt: an efficient library for differentiable optimization built upon PyTorch

NaturalCC: An Open-Source Toolkit for Code Intelligence

mt4g: Memory Topology for GPUs

Most viewed papers (last 30 days)