Analyzing the runtime, energy usage, and performance of Tensorflow training on a M1 Mac Mini and Nvidia V100
An interesting comparison of Apple Intel and M1 chips machines with Nvidia 100 when using Tensorflow.
We ran a sweep of 8 different configurations of our training script and show that the Apple M1 offers impressive performance within reach of much more expensive and less energy efficient accelerators such as the Nvidia V100 for smaller architectures and datasets.
Code is available on Colab https://colab.research.google.com/drive/1RvZBpzJRW9MNPWQ2rZG8HIyHJbaCwnTI.
They also include tips on setting up a Mac mini to run Tensorflow.
Only initial results on modest data sets, will be interesting to see the performance when Apple releases more Pro hardware.
The latest RSC CICAG newsletter (Winter 2020) is now available http://rsccicag.org/newsletters.htm. It includes:-
Chemical Information & Computer Applications Group Chair's Report
CICAG Planned and Proposed Future Meetings
Memories of Dr Angus McDougall, 1934-2020
CASP14: DeepMind’s AlphaFold 2 – an Assessment
Meeting Report: 3rd RSC BMCS & CICAG AI in Chemistry Meeting
ReadMe and HowTo for Lightning Poster Presentations
As Conferences went Online: What do we miss the most?
Alan F Neville, 1943-2020, BSc, PhD
Parallel Processing for Molecular Modeling in ChemDoodle 3D
Catalyst Science Discovery Centre & Museum Trust: A Year in Review
The 6th Tony Kent Strix Annual Memorial Lecture 2020
Open Chemical Science Meetings and Workshops - Introduction
Open Access Publishing for Chemistry – Meeting Reports
Open Data for Chemistry – Meeting Reports
Open Source Tools for Chemistry – Workshop Reports
RSC Open Access Journals and Future Plans
RSC’s Journal Archives Available for Text and Data Mining
Chemical Information / Cheminformatics and Related Books
News from AI3SD 64 Other Chemical Information Related News
A technical but still very accessible (15 min) analysis of the latest Apple M1 chip. Well worth spending a coffee break viewing.
JupyterLab is the next-generation web-based user interface for Project Jupyter.
To install using conda
conda install -c conda-forge jupyterlab=3
However note that some extensions may not yet have been updated.