high performance computing on graphics processing units: hgpu.org

Deepak Narayanan, Mohammad Shoeybi, Jared Casper, Patrick LeGresley, Mostofa Patwary, Vijay Korthikanti, Dmitri Vainbrand, Prethvi Kashinkunti, Julie Bernauer, Bryan Catanzaro, Amar Phanishayee, Matei Zaharia

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Data parallelism, Deep learning, GPU cluster, NLP, nVidia, nVidia DGX-A100, Package

April 18, 2021 by hgpu

AutoFreeze: Automatically Freezing Model Blocks to Accelerate Fine-tuning

Yuhan Liu, Saurabh Agarwal, Shivaram Venkataraman

View

Download (PDF)

Source codes

Tags: Computer science, Deep learning, Machine learning, NLP, nVidia, nVidia A100, Package, Python, Tesla P100

February 7, 2021 by hgpu

NaturalCC: A Toolkit to Naturalize the Source Code Corpus

Yao Wan, Yang He, Jian-Guo Zhang, Yulei Sui, Hai Jin, Guandong Xu, Caiming Xiong, Philip S. Yu

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Deep learning, NLP, nVidia, Package, Programming Languages, Python, Video

December 13, 2020 by hgpu

TopicBERT for Energy Efficient Document Classification

Yatin Chaudhary, Pankaj Gupta, Khushbu Saxena, Vivek Kulkarni, Thomas Runkler, Hinrich Schütze

View

Download (PDF)

Tags: classification, Computer science, CUDA, Deep learning, NLP, nVidia, Tesla T4

November 8, 2020 by hgpu

Efficient Inference For Neural Machine Translation

Yi-Te Hsu, Sarthak Garg, Yi-Hsiu Liao, Ilya Chatsviorkin

View

Download (PDF)

Tags: Computer science, NLP, nVidia, Tesla V100

October 11, 2020 by hgpu

* * *

Open-source FPGA-ML codesign for the MLPerf Tiny Benchmark

MapReduce for Counting Word Frequencies with MPI and GPUs

CoDL: Efficient CPU-GPU Co-execution for Deep Learning Inference on Mobile Devices

SYCLCOMP Utilities

On the Compilation Performance of Current SYCL Implementations

M1 GPUs for (scientific) computations in C++

Seamless GPU acceleration for C++ based physics with the Metal Shading Language on Apple’s M series unified chips

CUB: Cooperative primitives for CUDA C++

Onesweep: A Faster Least Significant Digit Radix Sort for GPUs

Simulator and workload generator for Edge-to-Cloud environments

FELARE: Fair Scheduling of Machine Learning Applications on Heterogeneous Edge Systems

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

MapReduce for Counting Word Frequencies with MPI and GPUs

Lossless Acceleration for Seq2seq Generation with Aggressive Decoding

The Ecological Footprint of Neural Machine Translation Systems

Autotuning CUDA: Applying NLP Techniques to LS-CAT

Small-Bench NLP: Benchmark for small single GPU trained models in Natural Language Processing

Easy and Efficient Transformer: Scalable Inference Solution For large NLP mode

How to Train BERT with an Academic Budget

Efficient Large-Scale Language Model Training on GPU Clusters

AutoFreeze: Automatically Freezing Model Blocks to Accelerate Fine-tuning

NaturalCC: A Toolkit to Naturalize the Source Code Corpus

TopicBERT for Energy Efficient Document Classification

Efficient Inference For Neural Machine Translation

Recent source codes

Rodinia Benchmarks for DPC++

DCA++: a state of the art implementation of the dynamical cluster approximation

tntorch - Tensor Network Learning with PyTorch

Open-source FPGA-ML codesign for the MLPerf Tiny Benchmark

MapReduce for Counting Word Frequencies with MPI and GPUs

CoDL: Efficient CPU-GPU Co-execution for Deep Learning Inference on Mobile Devices

SYCLCOMP Utilities

M1 GPUs for (scientific) computations in C++

CUB: Cooperative primitives for CUDA C++

Simulator and workload generator for Edge-to-Cloud environments

Most viewed papers (last 30 days)