PyTorch is now available on Apple Silicon https://pytorch.org/blog/introducing-accelerated-pytorch-training-on-mac/.
In collaboration with the Metal engineering team at Apple, we are excited to announce support for GPU-accelerated PyTorch training on Mac. Until now, PyTorch training on Mac only leveraged the CPU, but with the upcoming PyTorch v1.12 release, developers and researchers can take advantage of Apple silicon GPUs for significantly faster model training. This unlocks the ability to perform machine learning workflows like prototyping and fine-tuning locally, right on Mac.
To get started, just install the latest Preview (Nightly) build on your Apple silicon Mac running macOS 12.3 or later with a native version (arm64) of Python https://pytorch.org/get-started/locally/
Whilst Activity Monitor gives a nice graphical display it perhaps lacks granularity
A Python-based nvtop-inspired command line tool for Apple Silicon (aka M1) Macs. Code is available on GitHub https://github.com/tlkh/asitop
Utilization info: CPU (E-cluster and P-cluster), GPU, Frequency and utilization, ANE utilization (measured by power)
Memory info: RAM and swap, size and usage, Memory bandwidth (CPU/GPU/total), Media engine bandwidth usage
Power info: Package power, CPU power, GPU power, Chart for CPU/GPU power, Peak power, rolling average display
asitop uses the built-in powermetrics utility on macOS, which allows access to a variety of hardware performance counters. Note that it requires sudo to run due to powermetrics needing root access to run. asitop is lightweight and has minimal performance impact.
asitop only works on Apple Silicon Macs on macOS Monterey
Install using pip
pip3 install asitop
Enter your password and you should see something like this
The latest version of iBabel is now available. The big change is iBabel is now a universal application.
More details here https://www.macinchem.org/ibabel/version5/ibabel5.php.
More details of the RSC CICAG meeting on Ultra-large Chemical Libraries are available.
This one-day meeting will be held on 10 August 2022 10:00-17:00, at Burlington House, London.
Registration is open https://www.rsc.org/events/detail/73675/ultra-large-chemical-libraries and a number of the speakers have been finalised and looks a great line-up.
Roger Sayle, NextMove Software Limited, United Kingdom
Carol Mulrooney, GSK, United States
Jan H Jensen, University of Copenhagen, Denmark
Noah Harrison, Evariste Technologies, United Kingdom
Peter Pogany, GSK, United Kingdom
There is still time to submit poster abstracts. A limited number of bursaries are available, the application form should be submitted to the organisers. A maximum of £300 will be reimbursed on submission of receipts.
If you would like to exhibit, sponsor or support this meeting please contact the organisers.
This meeting is supported by
A Noel O'Blog post giving a few useful tips for writing scripts or plugins for Vortex https://baoilleach.blogspot.com/2022/04/threading-time-through-vortex.html.
Vortex (a chemical spreadsheet/visualisation software from Dotmatics) has a plugin system built around Jython. Simply drop a .vpy file into a specific scripts folder, and a menu item immediately appears in the application. Here are some notes on using this to communicate with a webserver.
The tutorials page on this site also includes many examples of Vortex scripts.