RoarVM

The RoarVM [1] is a research project that showed how to run Squeak Smalltalk on thousands of cores (at one point it ran on 10,000 cores). I'm re-implementing it as a metacircular adaptive compiler and VM for a production operating system. We rewrite the STEPS research software and the Frank code [2] on a million core environment [3]. On the M4 processor we try to use all types of cores, CPU, GPU, neural engine, video hardware, etc. We just applied for YC funding. [1] https://github.com/smarr/RoarVM [2] https://www.youtube.com/watch?v=f1605Zmwek8 [3] https://www.youtube.com/watch?v=wDhnjEQyuDk

Could have meant RoarVM. https://github.com/smarr/RoarVM

> Pharo has had GPU-support for a long time For highly parallel general-purpose computations? Tell us more! https://chapel-lang.org/docs/technotes/gpu.html As-already stated in this discussion RoarVM "hasn't been touched in over 10 years". This discussion is about the Pharo 12 release and supposedly RoarVM is "compatible with Squeak 4.1 and Pharo 1.2 ". https://github.com/smarr/RoarVM

https://github.com/smarr/RoarVM is the main thing that comes up when trying to learn about this, and it hasn't been touched in over 10 years. I have also seen people working on spawning child VMs to handle parallelism, though unfortunately I don't have links to those discussions immediately at hand. It seems like perhaps an unnecessarily heavyweight approach, too, not a canonical solution that you would want to use in production. I assume that step 1 towards parallelism, at least on the image side, would be going through the class library and making sure everything is thread-safe. I'd love to know where one would even get started with that effort. The Roar project claims to support Pharo 1.2, which doesn't seem to be very far after they forked from Squeak, but obviously a lot has changed since then. And the challenge is that Pharo is stil

You sound like talking about https://github.com/smarr/RoarVM RoarVM, formerly known as the Renaissance Virtual Machine (RVM) is developed as part of a IBM Research project to investigate programming paradigms and languages for manycore systems of the future. Specifically, this VM is meant to support manycore systems with more than 1000 cores in the future. The RVM was open sourced by IBM Research under the Eclipse Public License. Please see the open source announcement for further information. Today, the RoarVM supports the parallel execution of Smalltalk programs on x86 compatible multicore systems and Tilera TILE64-based manycore systems. It is tested with standard Squeak 4.1 closure-enabled images, and with a stripped down version of a MVC-based Squeak 3.9 image. The RoarVM provides parallel execution of Smalltalk pr

I wanted to keep the system as close to the original as possible, but some extensions such as increasing the available memory space and screen resolution would be nice even for the original system. It would also be interesting to implement the early ideas for a JIT compiler. Starting with Squeak is probably the easier way if you want advanced features such as color or network connectivity - still, there might be some interesting ideas to improve the system. One idea I had was to accelerate the bitblit functions using the Raspberry Pi's GPU. Currently, crosstalk uses a simple framebuffer and the runtime has to convert all monochrome bitblit operations into color ones since the Raspberry GPU doesn't have a 1bpp mode. Support for multiple cores (available in all but the most simple Raspberry Pis) would also be nice. Here, the Roar system (ht

The 2008 RoarVM project allowed Squeak to run on a 56 core Tilera chip and was later ported to run on multiprocessor x86 machines: https://stefan-marr.de/renaissance/ https://github.com/smarr/RoarVM This was a research project so performance on a single core was poor compared to the official Squeak virtual machine, but it was an interesting exploration of the natural fit between objects/message passing and multiple cores.

Check out the work on roar vm https://github.com/smarr/RoarVM if you are interested in such things. There are rad videos here too: http://stefan-marr.de/renaissance/