high performance computing on graphics processing units: hgpu.org

hgpu.org » nVidia DGX-2

Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism

Mohammad Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper, Bryan Catanzaro

View

Download (PDF)

Source codes

Tags: Computer science, Deep learning, NLP, nVidia, nVidia DGX-2, Package, Tesla V100

September 22, 2019 by hgpu

Performance Analysis of Deep Learning Workloads on Leading-edge Systems

Yihui Ren, Shinjae Yoo, Adolfy Hoisie

View

Download (PDF)

Tags: Cloud, Computer science, Computer vision, CUDA, Deep learning, Machine learning, NLP, nVidia, nVidia DGX-2, nVidia GeForce RTX 2080 Ti, Performance, Tesla V100

May 23, 2019 by hgpu

EASYPAP: a Framework for Learning Parallel Programming

LOGAN: High-Performance GPU-Based X-Drop Long-Read Alignment

Interoperable GPU Kernels as Latency Improver for MEC

MNN: a lightweight deep neural network inference engine

An Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile Devices

See all packages

* * *

2020

April

27-29

Munich, Germany

8th International Workshop on OpenCL, including SYCLCon, 2019

2019

May

13-15

Boston, USA

7th International Workshop on OpenCL, 2019

2019

May

Boston, MA, USA

Distributed Heterogeneous Programming in C/C++ (DHPCC++), 2019

2019

May

Larnaca, Cyprus

3rd International Workshop on Theoretical Approaches to Performance Evaluation, Modeling and Simulation (TAPEMS), 2019

2019

July

26-28

Rome, Italy

International Conference on Frontiers of Neural Networks (ICFNN), 2019

Add event

See all events

high performance computing on graphics processing units: hgpu.org

Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism

Recent source codes

EASYPAP: a Framework for Learning Parallel Programming

LOGAN: High-Performance GPU-Based X-Drop Long-Read Alignment

StarNEig: A Task-based Library for Solving Nonsymmetric Eigenvalue Problems

FLAMEGPU: a high performance GPU extension to the FLAME framework

CommAnalyzer

elevate: implementation of the Elevate language

reproducibility of TensorFlow with ResNet

SCHNAPS

Interoperable GPU Kernels as Latency Improver for MEC

MNN: a lightweight deep neural network inference engine

Most viewed papers (last 30 days)

Featured events

8th International Workshop on OpenCL, including SYCLCon, 2019

7th International Workshop on OpenCL, 2019

Distributed Heterogeneous Programming in C/C++ (DHPCC++), 2019

3rd International Workshop on Theoretical Approaches to Performance Evaluation, Modeling and Simulation (TAPEMS), 2019

International Conference on Frontiers of Neural Networks (ICFNN), 2019