New supercomputer just dropped

These certainly are server cabinets alright…

Today marks the launch of CU Boulder’s shiny new research supercomputer, Alpine. Text of the university press release:

The celebratory event signals the official launch of CU Boulder’s third-generation high performance computing infrastructure, which is provisioned and available to campus researchers immediately.

On May 18, numerous leaders from on- and off-campus will gather to celebrate, introduce and officially launch the campus’s new high-performance computing infrastructure, dubbed “Alpine.”

Alpine replaces “RMACC Summit,” the previous infrastructure, which has been in use since 2017. Comparable to systems now in use at top peer institutions across the country, Alpine will improve upon RMACC Summit by providing cutting-edge hardware that enhances traditional High Performance Computing workloads, enables Artificial Intelligence/Machine Learning workloads, and provides user-friendly access through tools such as Open OnDemand.

“Alpine is a modular system designed to meet the growing and rapidly evolving needs of our researchers,” said Assistant Vice Chancellor and Director of Research Computing Shelley Knuth. “Alpine addresses our users’ requests for faster compute and more robust options for machine learning.”

Notable among the technical specifications that will make Alpine an invaluable tool in research computing for researchers, industry partners and others, Alpine boasts: 3rd generation AMD EPYC CPUs, which provide enhanced energy efficiency per cycle compared to the Intel Xeon E5-2680 CPUs on RMACC Summit; Nvidia A100 GPUs; AMD MI100 GPUs; HDR InfiniBand; and 25 Gb Ethernet.

The kick-off event on May 18 will celebrate the Alpine infrastructure being fully operational and allow the community to enjoy a 20-minute tour, including snacks, an introduction to Research Computing, and a tour of the supercomputer container. The opportunity is open to the public and free of charge, and CU Boulder Research Computing staff will be on site to answer questions. CU Boulder Chief Information Officer Marin Stanek, Chief Operating Officer Patrick O’Rourke, and Acting Vice Chancellor for Research and Innovation Massimo Ruzzene will offer remarks at 1:30 p.m.

In addition to the main launch event, Research Computing is offering a full slate of training and informational events the week of May 16—20.

Researchers seeking to use Research Computing resources, which includes not only the Alpine supercomputer, but also large scale data storage, cloud computing and secure research computing, are invited to visit the Research Computing website to learn about more training offerings, the community discussion forum, office hours and general contact information.

Alpine is funded by the Financial Futures strategic initiative.

This is the biggest project I have ever worked on. It was in the works months before I arrived but has consumed most of my professional time since September. It’s exciting that we can finally welcome our researchers to use it.

What’s next

Some personal news… 🙂

I have been at Earlham College for almost seven years, including my time as a student and as CS faculty. Today is my last day there.

It’s been an incredible place to grow as a person, deepen my skills, collaborate with talented people from all walks of life, and try to make the world a little bit better. I’ve seen a few generations of the community cycle through and watched us withstand everything up to and including a literal pandemic. I capped it with the trip of a lifetime, spending a month doing research in Iceland – on a project I hope to continue working on in the future.

To the Earlham Computer Science community in particular I owe a big thanks. I have had a supportive environment in which to learn and grow for virtually the entirety of those years. The value they’ve added to my life can’t be quantified. I am deeply grateful.

What’s next?

I am elated to announce that in mid-September I will go to work as a Research Computing HPC Cluster Administrator at the University of Colorado Boulder! I’m excited to take the skills I’ve built at Earlham and apply them at the scale of CU Boulder. Thanks to the many people who’ve helped make this opportunity possible.

Highlights of an amazing trip

Today is the last day most of us are in Iceland for this trip. As I started this post, we were completing a tour of the Golden Circle after a few days in beautiful Reyjkavik. Now we are preparing for departure.

Our view of the volcano

I wanted to post some of the highlights of our trip. There’s a rough order to them, but don’t take the numbering too seriously – it’s been a great experience all-around. Without further ado:

  1. The volcano is truly incredible. It was not uncommon for people to spontaneously shout “Wow!” and “Oh my god!” as the lava burst up from the ground.
  2. We woke up every day for a few weeks with a view of a fjord.
  3. We did a glacier hike on Sólheimajökull, with two awesome guides.
  4. This was a historically successful round of data collection, both on the drone side and on the biology side. We’ll write and share a lot more about this in the next few months.
  5. We shared space with the group of phenomenal students from the University of Glasgow. We also collaborated with them on multiple occasions, learning a lot about different ways to study wildlife and local sites.
  6. THE FOOD – you probably don’t associate Iceland with food culture (I certainly didn’t), but our meals were delicious.
  7. The architecture and decorations are so distinctly Icelandic.
  8. Amazing photography and video – in high quality and high quantity.
  9. Walking along the boundary between the North American and European plates.
  10. Guided tour from our Skalanes hosts – who incidentally are awesome people – of a stretch of eastern Iceland.
Getting the rundown about glaciers at Solo

Some of my personal honorable mentions include:

  • Trail running at Skalanes is breathtaking.
  • Blue glacier ice is real neat.
  • The National Museum of Iceland is fascinating and well-done.
  • Rainbow roads in both Seyðisfjörður and Reykjavik highlight what a welcoming place this country is – also perfect reminders of Pride Month in the U.S.!
  • My first-in-my-lifetime tour of a beautiful country happened alongside people I admire who teach me things every single day. What more could I ask for?
A drone photo of the coast by the fjord

If you haven’t already, check out this interview with Charlie and Emmett, conducted by Cincinnati Public Radio.

Davit and Tamara flying

In addition to our success this year, we’ve also set up some great new opportunities for future years. With our long-time friend and collaborator Rannveig Þórhallsdóttir, we’ve added the cemetery in Seyðisfjörður to our list of sites to survey. We believe there may be historically-significant artifacts to be found there, and our drone work lends itself well to finding out.

The fjord at Skalanes

Finally, here’s the trip by the numbers:

  • 7 Earlhamites
  • 26 days
  • 183 GB of initial drone images and initial assemblies
  • 2 great hosts at Skalanes
  • 6 outstanding co-dwellers
  • 4 guides at 2 sites
  • 1 perfect dog
  • N angry terns
  • 1 amazing experience
Admiring the view

And that’s a wrap. Hope to see you again soon, Iceland!

Cross-posted at the Earlham Field Science blog.

Flying cameras are good

We recently chose not to use ground control points (GCP’s) as part of our surveying work. This is a departure from standards and conventions in the near-Earth surveying space. However, we believe we have made a sound decision that will support equally effective and more time and cost-effective research. In this post, I’ll explain that decision.

The short version: drone imagery and open-source assembly software (e,g. OpenDroneMap) are now so good that, for our purposes, GCP’s have no marginal benefit.

We have high-quality information about our trial area from an established authority – the Cultural Heritage Agency of Iceland. Their 2007 report of finds is the basis of our trial runs here at Skalanes. Surveying these predefined areas, we’ve now flown multiple flights, gathered images, and then run three assembles with OpenDroneMap.

Here’s a simple run over the area with no GCP’s:

Here’s a run over the area with GCP’s, adding no location metadata other than the craft’s built-in GPS coordinates (you’ll note that the ground footprint is slightly different, but the roundhouse in the middle is the key feature):

We also manually geocoded the GCP’s for one run.

In the end, we observed no meaningful difference between an assembly with GCP’s and an assembly without them. Adding the images as raster layers to a QGIS project confirmed this to our satisfaction:

With GCP:

Without GCP:

In summary, ground control points just don’t help us much compared to just taking a bunch of good photos and using high quality software to assemble them. They also cost us in portability: even four GCP’s are difficult to carry, occupying significant space in airport luggage and weighing down walks in the field. For scientists interested in doing work over a large area, potentially multiple times, that inconvenience is not a trivial cost.

The ODM assemblies are outstanding by themselves. We have good technology and build on the work of a lot of brilliant people. That frees us to be more nimble than we might have been before.

It wouldn’t be a post by me if it didn’t end with a cool picture. Here’s a drone image from a cliff near the house where we’re staying:

Cross-posted at the Earlham Field Science blog.

“A lot of people” – a brief note

Pet peeve: “A lot of people say X” or similarly “A lot of people do Y”.

There’s a lot of people in general: ~330,000,000 in America alone. If you look hard enough, you can find *somebody* who will say/do almost literally anything.

If 1% of Americans believe something, that’s over 3 million believers. That’s both a huge number of people and hardly anybody, depending on your context.

I find this usually isn’t a problem in writing, where with minimally competent phrasing/structure the context is clear. During chit-chat or as used by the likes of Fox News, it can be (often purposely) obtuse.

I like us to try to be specific, is what I’m saying. 🙂

Originally a Twitter thread.