PartIR: Composing SPMD Partitioning Strategies for Machine Learning

no code implementations • 20 Jan 2024 • Sami Alabed, Daniel Belov, Bart Chrzaszcz, Juliana Franco, Dominik Grewe, Dougal Maclaurin, James Molloy, Tom Natan, Tamara Norman, Xiaoyue Pan, Adam Paszke, Norman A. Rink, Michael Schaarschmidt, Timur Sitdikov, Agnieszka Swietlik, Dimitrios Vytiniotis, Joel Wee

Training of modern large neural networks (NN) requires a combination of parallelization strategies encompassing data, model, or optimizer sharding.

Automatic Discovery of Composite SPMD Partitioning Strategies in PartIR

no code implementations • 7 Oct 2022 • Sami Alabed, Dominik Grewe, Juliana Franco, Bart Chrzaszcz, Tom Natan, Tamara Norman, Norman A. Rink, Dimitrios Vytiniotis, Michael Schaarschmidt

Large neural network models are commonly trained through a combination of advanced parallelism strategies in a single program, multiple data (SPMD) paradigm.

Automap: Towards Ergonomic Automated Parallelism for ML Models

no code implementations • 6 Dec 2021 • Michael Schaarschmidt, Dominik Grewe, Dimitrios Vytiniotis, Adam Paszke, Georg Stefan Schmid, Tamara Norman, James Molloy, Jonathan Godwin, Norman Alexander Rink, Vinod Nair, Dan Belov

The rapid rise in demand for training large neural network architectures has brought into focus the need for partitioning strategies, for example by using data, model, or pipeline parallelism.

Synthesizing Optimal Parallelism Placement and Reduction Strategies on Hierarchical Systems for Deep Learning

no code implementations • 20 Oct 2021 • Ningning Xie, Tamara Norman, Dominik Grewe, Dimitrios Vytiniotis

We present a novel characterization of the mapping of multiple parallelism forms (e. g. data and model parallelism) onto hierarchical accelerator systems that is hierarchy-aware and greatly reduces the space of software-to-hardware mapping.

Program Synthesis

Acme: A Research Framework for Distributed Reinforcement Learning

5 code implementations • 1 Jun 2020 • Matthew W. Hoffman, Bobak Shahriari, John Aslanides, Gabriel Barth-Maron, Nikola Momchev, Danila Sinopalnikov, Piotr Stańczyk, Sabela Ramos, Anton Raichuk, Damien Vincent, Léonard Hussenot, Robert Dadashi, Gabriel Dulac-Arnold, Manu Orsini, Alexis Jacq, Johan Ferret, Nino Vieillard, Seyed Kamyar Seyed Ghasemipour, Sertan Girgin, Olivier Pietquin, Feryal Behbahani, Tamara Norman, Abbas Abdolmaleki, Albin Cassirer, Fan Yang, Kate Baumli, Sarah Henderson, Abe Friesen, Ruba Haroun, Alex Novikov, Sergio Gómez Colmenarejo, Serkan Cabi, Caglar Gulcehre, Tom Le Paine, Srivatsan Srinivasan, Andrew Cowie, Ziyu Wang, Bilal Piot, Nando de Freitas

These implementations serve both as a validation of our design decisions as well as an important contribution to reproducibility in RL research.

DQN Replay Dataset reinforcement-learning +1