When I was still dual-booting Windows and Linux, I found that “raw disk” mode virtual machines worked wonders. I used VirtualBox, so you’d want a guide somewhat like this: https://superuser.com/questions/495025/use-physical-harddisk-in-virtual-box - other VM solutions are available, which don’t require you to accept an agreement with Oracle.

Essentially, rather than setting aside a file on disk as your VM’s disk, you can set aside a whole existing disk. That can be a disk that already has Windows installed on it, it doesn’t erase what you have. Then you can start Windows in a VM and let it do its updates - since it can’t see the bootloader from within the VM, it can’t fuck it up. You can run any software that doesn’t have particularly high graphics requirement, too.

I was also able to just “restart in Windows” if I wanted full performance for a game or something like that, but since Linux has gotten very good indeed at running games, that became less and less necessary until one day I just erased my Windows partition to recover the space.

PS3 most certainly had a separate GPU - was based on the GeForce 7800GTX. Console GPUs tend to be a little faster than their desktop equivalents, as they share the same memory. Rather than the CPU having to send eg. model updates across a bus to update what the GPU is going to draw in the next frame, it can change the values directly in the GPU memory. And of course, the CPU can read the GPU framebuffer and make tweaks to it - that’s incredibly slow on desktop PCs, but console games can do things like tone mapping whenever they like, and it’s been a big problem for the RPCS3 developers to make that kind of thing run quickly.

The cell cores are a bit more like the ‘tensor’ cores that you’d get on an AI CPU than a full-blown CPU core. They can’t speak to the RAM directly, just exchange data between themselves - the CPU needs to copy data in and out of them in order to get things in and out, and also to schedule any jobs that must run on them, they can’t do it themselves. They’re also a lot more limited in what they can do than a main CPU core, but they are very very fast at what they can do.

If you are doing the kind of calculations where you’ve a small amount of data that needs a lot of repetitive maths done on it, they’re ideal. Bitcoin mining or crypto breaking for instance - set them up, let them go, check in on them occasionally. The main CPU acts as an orchestrator, keeping all the cell cores filled up with work to do and processing the end results. But if that’s not what you’re trying to do, then they’re borderline useless, and that’s a problem for the PS3, because most of its processing power is tied up in those cores.

Some games have a somewhat predictable workload where offloading makes sense. Got some particle effects - some smoke where you need to do some complicated fluid-and-gravity simulations before copying the end result to the GPU? Maybe your main villain has a very dramatic cape that they like to twirl, and you need to run the simulation on that separately from everything else that you’re doing? Problem is, working out what you can and can’t offload is a massive pain in the ass; it requires a lot of developer time to optimise, when really you’d want the design team implementing that kind of thing; and slightly newer GPUs are a lot more programmable and can do the simpler versions of that kind of calculation both faster and much more in parallel.

The Cell processor turned out to be an evolutionary dead end. The resources needed to work on it (expensive developer time) just didn’t really make sense for a gaming machine. The things that it was better at, are things that it just wasn’t quite good enough at - modern GPUs are Bitcoin monsters, far exceeding what the cell can do, and if you’re really serious about crypto breaking then you probably have your own ASICs. Lots of identical, fast CPU cores are what developers want to work on - it’s much easier to reason about.

Yeah.

There’s a couple of ways of looking at it; general purpose computers generally implement ‘soft’ real time functionality. It’s usually a requirement for music and video production; if you want to keep to a steady 60fps, then you need to update the screen and the audio buffer absolutely every 16 ms. To achieve that, the AV thread runs at a higher priority than any other thread. The real-time scheduler doesn’t let a lower-priority thread run until every higher-priority thread is finished. Normally that means worse performance overall, and in some cases can softlock the system - if the AV thread gets stuck in a loop, your computer won’t even respond to keyboard input.

Soft real-time is appropriate for when no-one will die if a timeslot is missed. A video stutter won’t kill you. Hard real-time is for things like industrial control. If the anti-lock breaks in your car are meant to evaluate your wheels one hundred times a second, then taking 11 ms to evaluate that is a complete system failure, even if the answer is correct. Note that it doesn’t matter if it gets the right answer in 1 ms or 9 ms, as long as it never ever takes more than 10. Hard real-time performance does not mean good performance, it means predictable performance.

When we program up PLCs in industrial settings, for our ‘critical sections’, we’ll processor interrupts, so that we know our code will absolutely run in time. We use specialised languages as well - no loops, no recursion - that don’t let you do things that can’t be checked for an upper time bound. Lots of finite state machines! But when we’re done, we know that we’ve got code that won’t miss a time slot in the next twenty years of operation.

That does mean, ironically, that my old Amiga was a better music computer than my current desktop, despite being millions of times less powerful. OctaMED could take over the whole CPU whenever it liked. Whereas a modern desktop might always have to respond to a USB device or a hard drive, leading to a potential stutter at any time. Tiny probability, but not an acceptable one.