About PX

PX was founded by Andrew Montalenti, an open source developer and CTO who helped build the real-time streaming engine and petabyte-scale cloud cluster architecture that powered Parse.ly, a widely-used analytics product. PX stands for (p)arallel e(x)ecution.

As the simple parallelism company, our goal is to give cloud developers the superpower of supercomputers without the hassle of managing clusters.

Powered by parallelism

All programmers bang their heads against the wall when dealing with concurrency and parallelism. But, some clever automation can make it all easier.

Simple parallel execution is all about:

• Starting with a working program, running fine on a single core of your dev machine
• Going from a single-core working program to multi-core parallelism (1 core to C cores)
• Going from multi-core parallelism to multi-core x multi-node cloud parallel clusters (C cores to C cores x N nodes)
• Going from generic hardware to cost-and-performance optimized hardware (e.g. from Intel to AMD/ARM, from CPUs to GPUs/TPUs)
• With automatic monitoring and easy debugging
• In any programming language
• In any major cloud provider
• With no code changes!

Just px run your/code

At the center of the PX philosophy is the px command-line interface (CLI).

It takes inspiration from the tool GNU parallel which allows you to take working single-core programs and run them on the multiple cores available on your local machine with no code modifications simply by spawning multiple copies, partitioning the inputs, and multiplexing the outputs.

The px CLI extends this simple parallelism approach to the cloud, allowing you to achieve multi-node parallelism and deployments of your working code, in your cloud environment, on plain Linux VMs, with no code changes and no DevOps/InfraOps pain.

Just px.app/your/code

At the center of the PX debugging experience is the px.app domain, which gives you an instant web-based monitoring and debugging dashboard for your cloud parallel jobs.

Every running px job gets a corresponding https://px.app/ securely-provisioned and private job dashboard. Within that dashboard, you can see key metrics about your job:

• stdin, stdout, stderr
• lines, bytes, and files used in I/O
• CPU, GPU, and memory performance
• logs
• stacktraces

What's more, you'll be able to jump right into a shell and see how your job is doing with familiar tools like htop.

Just px it!

Are you sick of spending weeks getting your already-working code to run well in production in the cloud? Are you tired of a million different dashboards and log file locations?

We deserve better. It's time to reclaim our open source expertise and declare our independence as programmers. Let's bring back joy, transparency, and ease to our day-to-day development. Join us. Give px a try.