Architecture of the Playstation 2

It may have been 4 years! I'm pretty sure the R5900 deal was just done when I joined in December '95, and the PS2 wasn't announced until 1999.

I have a... heavily modified Browser 2 install on an insanely large (for a PS2) 1TB HDD. Between that and some other tools you can install and run full games onto the console. I even figured out how to make custom Browser icons for them, although in practice selecting one game out of even a decently-sized PS2 collection is ungodly slow. It's still cool as a retro hobby project, if you're willing to jump through the hoops to get a working setup.

AFAIK the official purpose of Browser 2 was to support PSBBN and distributing software through it. They never launched that service outside of Japan. Hell, most of the games that supported the HDD got that functionality stripped out of it in the US. PS2 games could install themselves to the hard drive for faster load times, much like the later install features on Xbox 360 and PS3. However, as far as I am aware this was exclusively for online service games in the US and Europe. On the original Xbox, Microsoft was already trying DLC and digital distribution (no, seriously, it had it, but you needed a special Arcade disc to run games). So I have to wonder how Sony wound up sleeping on something they were already doing for a whole generation.

The PS2 OS is truly a work of art, such beautiful sound/graphics and ui design.

Indeed awsome hardware to code for. It was amusing when the Sony guys joked people are writing their VU assembler in Excel. To make it easier to mentally keep track of the instructions in each pipe.

There is a work-in-progress port of the newer Linux 5.x kernel to the PS2: https://github.com/frno7/linux

I got the official PS2 Linux kit on launch and even with the hard drive and all the accessories, it was still slow as molasses. There just wasn't nearly enough RAM to make a usable desktop environment.

Nice. I have a Red Hat Linux port for PS2, but haven't booted it in almost 20 years thanks to missing a sync-on-green monitor.

Cell was a disappointment in the PS3 though. It was such an underperformer that the SPEs couldn’t be used for their intended role as a GPU and got shanghied into being used like SMT cores, while a whole separate GPU chip had to be added into the design at the last minute to compensate. The Cell’s weak CPU performance, strange programming model, and weak developer tooling was a problem for pretty much the whole generation.

The much more traditional XB360 tri-core plus GPU design was widely considered the better design and Sony reverted to a similarly traditional design the next generation as well.

It was a highly heterogeneous design, and yes the world has adapted to those much better now than they did in 2007 (and maybe it would have been more successful with better tooling), but there are also prior heterogeneous designs like Saturn that were also widely considered a mess apart from rare cases where developers were skilled enough to effectively utilize them. The tasks where it succeeded (like the oft-referenced air force supercomputer) tended to be embarrassingly parallel workloads (matrix math, password cracking, etc) that didn't have a high degree of dependencies in their processing workflow. That is pretty much the lowest-hanging fruit for a heterogeneous throughput-oriented system, if it couldn't do even that it would be fully useless, but merely doing that doesn't make it good.

I guess maybe think of it like a GPGPU - but a GPGPU would have been a terrible choice to use as your control CPU for a console even if it did allow higher degrees of processing in some narrow use-cases. Just not how that type of programming is usually done. Maybe at best you can say it was mis-understood and mis-applied by Sony but it really just wasn't as great a chip for most things as people thought at the time. Wasn't a great GPU, wasn't a great CPU, wasn't good enough to be the first "APU" to bridge to having both one one chip as originally intended.

It clearly was designed for HPC/supercomputing situations where someone understood the architecture. Probably still was held back by the tooling and documentation anyway. I know it was in some supercomputers, but there probably is a reason that 10 years later nobody is designing follow-on processors or inspired by that particular architecture.

People at the time jerked off heavily about it, both in HPC and the PS3, and I get that it powered a lot of people's fond childhood memories, but I think in hindsight it pretty much was a failed design and an architectural dead end. You can say that maybe APUs took some inspiration from it but the cost-savings of an integrated CPU+GPU are pretty much an obvious goal, and later processors used a much more standard CPU and GPU that happen to live on the same chip and have some coherent memory access protocols. They share nothing in common with the Cell's SPE/ring concept. Nobody ever used that in a design ever again, for a reason.

I had no idea she had such a career..

Nice! I loved the Mega Drive one [0]. This series is so cool! Its full of details on sprites and architecture. I admire the work that was put on this.

[0] https://www.copetti.org/writings/consoles/mega-drive-genesis...

Ok, the internet is finished. No more need to put more work into it. This is the best thing ever.

There also exists the "Fortuna" exploit (and also recently reimplemented and documented as open source "OpenTuna"), which uses a buffer overflow in the memory card icon reading code, providing a disc-less exploit for the later models of PS2 (including the "PS2 TV", aka the Sony Bravia KDL-22PX300 television set including a built-in PS2 console)

With FreeMCBoot and Fortuna, all PS2 consoles can be exploited from boot time. With FreeDVDBoot, it provides a convenient entrypoint to install the aforementioned exploits.

People still hack GH2 a little bit. Clone Hero is also a pretty big thing for ease of use.

I bet they were writing Vector Unit assembly in Excel. The VLIW design meant that you literally packed 2 assembly instructions together into a 64-bit word. Each side had it's own subset of execution units it could utilize and would have it's own separate latency for each operation. So, to keep track of everything going on you pretty much had to write out two columns of code containing your own no-op notation to represent the delay cycles between instructions. That would be much more convenient to do in Excel than in a linear text editor.

It might have made things simpler. From memory there was also a VU compiler that would take a single stream of instructions and then try to interleave the the 'left/right' instructions of the VLIW in the most efficient orders. It never was quite as good as hand coding - which is something kind of satisfying once you've memorized the stats of the entire ISA.

One half of the instruction word was mostly devoted to vector instructions which would each have a 4 cycle latency, and a single cycle throughput, to say, multiple one 4 word vector of floats with another. The other half had the kitchen sink, like trancendental functions (sin/cos/tan/etc), divide (x/y, 1/x), etc. However an instruction would stall if a calculation was depending on a register whose calculation was still in flight.

So if an instruction has a latency of 4 cycles, you could interleave 4 similar calculations on more of the dataset in parallel. So in 4 cycles, you could start 16 float calculations, and by the 8th cycle, they would be available. Though likely you'd be looping with something like Duff's device to maximize throughput. It would also mean you might use the vector calculations with a taylor series, in preference to the sine instruction which had a latency of something like 15 cycles.

Excel as in microsoft excel!?

Including the Xbox and GameCube. Well, the Xbox was built out of significantly more "general purpose" parts than the GameCube, but both still handily outperformed the PS2.

I suppose you might argue that the amiga paved the way for the architecture of the PS2 - the copper chip ran a rudimentary display list, the blitter hardware accelerated graphics operations. But I wouldn't say there is a direct relationship... wait you're not talking about the CDTV, are you?