Skip to main content

Learn supercomputing,straight from the source.

Free education. Practical guides. Verified skills.

Courses, videos, and interactive demos for running real high-performance computing workloads on Eugo, written by the people building the platform. No cluster to procure, no scheduler to operate, no queue to wait in.

Start with the basicsBrowse all courses

Recently added

Scaling a real workload

Take a single-machine geospatial pipeline to a cluster, and find out where the time actually goes.

Advanced38m5 lessons

Distributed Python with eugo.hpc

Turn ordinary Python into distributed work with a decorator, then scale it across a cluster.

Intermediate50m7 lessons

How automatic optimizations work

Eugo rewrites and tunes your code as it runs. Here is what it does, and how to help it.

Intermediate29m4 lessons

What are you here to do?

Pick the task that matches your situation.

Run my first job on Eugo

Open a session, launch a cluster, and get something to complete end to end

Make my analysis finish faster

Distribute an existing pandas or NumPy workload across workers

Use GPUs for heavy numeric work

Request GPUs per task and confirm the work actually ran on one

Understand why my run was slow

Tell compute-bound from I/O-bound, and fix the right thing

Set up a workspace for my team

Organizations, workspaces, members, roles, and plans

See what the platform can actually do

Interactive charts of scaling and GPU trade-offs, plus a cluster sizer

Distributed compute

Tasks, futures, and actors. The whole model in a handful of API calls.

Distributed Python with eugo.hpc

Turn ordinary Python into distributed work with a decorator, then scale it across a cluster.

Intermediate50m7 lessons
Coming soon

The distribute decorator, explained

What @eugo.hpc.distribute actually changes about a function, and why the call site stays clean.

Intermediate · not yet published
Coming soon

Working with futures without blocking

The most common performance mistake in distributed code, and the two-line habit that avoids it.

Intermediate · not yet published
Coming soon

Actors for stateful work

When a task is the wrong shape: keeping an expensive object alive across many calls.

Advanced · not yet published
All distributed compute

Performance & GPUs

What the runtime optimizes on your behalf, and how to measure whether it worked.

GPU acceleration on Eugo

How work reaches the GPU, which operations benefit, and how to confirm it actually happened.

Intermediate26m4 lessons

How automatic optimizations work

Eugo rewrites and tunes your code as it runs. Here is what it does, and how to help it.

Intermediate29m4 lessons
Coming soon

Automatic GPU offloading

Which array operations Eugo moves to the GPU on its own, and how to confirm it happened.

Intermediate · not yet published
Coming soon

Sizing a cluster for your workload

Estimating worker count from the shape of your work, rather than guessing.

Intermediate · not yet published
All performance videos

Working at scale

Real datasets, real bottlenecks, and where the time actually goes.

Scaling a real workload

Take a single-machine geospatial pipeline to a cluster, and find out where the time actually goes.

Advanced38m5 lessons
Coming soon

Seven terabytes in three minutes

A real geospatial pipeline: 192,000 satellite files, resampled and written, start to finish.

Advanced · not yet published
Coming soon

Reading large datasets without stalling

When I/O is your bottleneck, more workers will not help. Here is what does.

Advanced · not yet published
Coming soon

Parallel pandas in practice

Split a dataframe workload across workers without rewriting your analysis.

Intermediate · not yet published

For your role

Curated sequences, depending on what you do.

Data scientistAnalyze large datasets in a notebook without provisioning serversML engineerTrain and serve models across GPU compute nodesResearch scientistRun simulations and scientific workloads at scaleHPC engineerTune cluster sizing, resources, and throughputWorkspace adminManage workspaces, members, and compute allocationOrg ownerOversee plans, billing, and organization-wide settings
All learning paths

Checklists to keep you on track

The practical lists: what to verify before, during, and after a run.

Checklist

Workload readiness checklist

Verify a workload is worth distributing before you spend cluster time on it.

11 items
Checklist

Performance tuning checklist

Work through the usual causes when a distributed run is slower than expected.

9 items
Checklist

Cost optimization checklist

Keep compute spend predictable without giving up throughput: what to check weekly, how to stop paying for idle clusters, and where to right-size.

7 items
All resources