Chris Fenton

I love stuff like this! I have a Kaypro 2/84, which supports a display resolution of 160x100 with colors ranging from green, to 'less green' to black, and I went down a rabbit hole of trying to push the graphics: https://www.chrisfenton.com/exploring-kaypro-video-performance/ - I was eventually able to get it do display (short!) 50 fps video clips.

Man, this guy has some great articles. http://www.chrisfenton.com/cray-1-digital-archeology/ http://www.chrisfenton.com/cos-recovery/ I just wish he'd made higher resolution pictures. He's also seriously hardcore (or maybe I feel out of depth because I'm a software guy): > I built a robot that would manually move the head forward 1/5200th of an inch at a time (there are 400 data tracks per inch, so this gives me a whopping 13 steps per data track!), while a high-speed analog-to-digital converter would take the analog signal straight from the drive’s read amplifier and buffer it into an FPGA at a blistering 80 million samples-per-second (like I said earlier, the theme here was overkill…the data was only changing at ~10 MHz or so) Related: http://www.modularcircuits.com/blog/articles/the-cray-files/

The rationale is that most people will never approach those kind of number of P/E cycles The flip side of that is most people could now have drives that don't cost all that much more, but last much longer. Most SLC tends to be rated for 100K cycles and 10 years of retention; assuming a roughly inverse correlation, at 10K or 1K cycles the retention goes up considerably to a century or more. The consumer market is similar: Most people don't ever buy replacements for failed drives - they buy a newer computer. That is true, but the long-term implications are more subtle; the fact is that most people don't backup, and quite a few of them keep the old drives (that were still working when they were replaced) around as "backup", with the implicit assumption that the data on them will likely still be there if they ever decide e.g. that they wanted to find an older version of some file they had. With flash memory, this assumption no longer holds. On a longer timescale, we've been able to "recover data" from stone tablets, ancient scrolls and books, this being a very valuable source of historical information; and most if not all of that data was probably never considered to be worth archiving or preserving at the time. More recently, rare software has been recovered from old disks ( http://www.chrisfenton.com/cray-1-digital-archeology/ ). Only the default, robust nature of the media made this possible. Despite modern technology increasing amount of storage available, and the…

Of course it depends on what you consider "low end" - it's relative to your expectations. I have a G4 TiBook, the definition of a high-end laptop, by 2002 standards. If you consider a $300 laptop a good daily driver, I'll one-up you with this: <https://www.chrisfenton.com/diy-laptop-v2/>

I suspect the Cray is "competitive" for some value of "doesn't absolutely stink" for things that are designed for it. But you can emulate a Cray on an FPGA: https://www.chrisfenton.com/homebrew-cray-1a/ so I suspect that while it could still do "real work" you can also beat the pants off it if you setup your code as designed to run on modern GPUs.

https://www.chrisfenton.com/homebrew-cray-1a/ (You'll still need a pretty big drawer)

There's also the Cray-on-an-FPGA: http://www.chrisfenton.com/homebrew-cray-1a/

To be honest, it's not exactly Cray, and not even Cray at all. Here is the homebrew cycle-accurate Cray-1, and it's a really impressive project: http://www.chrisfenton.com/homebrew-cray-1a/

Somewhat similar story walks you though porting an existing game to a Z80 Kaypro. The author is able to get the straight port from 0.25 FPS to 4FPS with some optimizations. Which is impressive given what you have to work with for graphics there. http://www.chrisfenton.com/dd9-kaypro-edition/

It's not hard to emulate the early Cray machines. Someone did it in an FPGA.[1] They're not that complicated; they just have large numbers of identical units. But apparently almost all Cray software has been lost. [1] http://www.chrisfenton.com/homebrew-cray-1a/

Here’s a simulator: https://www.chrisfenton.com/homebrew-cray-1a/

A real working Cray 1 is a bit hard to find today, but in addition to the FPGA version by Chris Fenton that was already mentioned (https://www.chrisfenton.com/homebrew-cray-1a/), there is also a simulator for various Cray models at https://github.com/andrastantos/cray-sim The biggest problems will be finding a C compiler for the Cray and adding a framebuffer output, I think... but this is a very nice challenge :).

This guy made one. https://www.chrisfenton.com/homebrew-cray-1a/

Have you seen this replica of Cray 1A? http://www.chrisfenton.com/homebrew-cray-1a/

The recovery of the data from the HD is particularly impressive: http://www.chrisfenton.com/cray-1-digital-archeology/

A hand-cranked computer that uses punch cards (also mostly 3D-printed): http://www.chrisfenton.com/the-turbo-entabulator/

Ahh yes, modern computers put these older systems to shame in some regards, but what did the typical desktop have back then? There's a person out there who made a 1/10th scale cycle-accurate Cray-1A...which is truly pretty cray http://www.chrisfenton.com/the-numbotron/

Couldn't find a link to the project in the article, so here you go: http://www.chrisfenton.com/homebrew-cray-1a/ Also, gigaom has a much better article up here: http://gigaom.com/2014/01/14/the-search-for-the-lost-cray-supercompute… .. with a link to an interesting walkthough of the emulator in-progress: http://www.youtube.com/watch?feature=player_embedded&v=D6R8FOANclc

Did anything ever become of that work? Based on the project link to http://opencores.org/websvn,listing,seqalign , I see that that the last modification time is 2009-08-17 18:21:06 GMT, so it's been 4 years. BTW, there are more details at http://chrisfenton.com/wp-content/uploads/2009/08/final_report.pdf , which has a date one day before the above "last modified" time.

btw, if you all haven't seen, he found a hard drive with an OS for this and pulled the data, but needs someone to figure out the filesystem and stuff; you can download the binary dump off his site. http://www.chrisfenton.com/cray-1-digital-archeology/

http://chrisfenton.com/homebrew-cray-1a/ The detail article with architecture & photos from the building process.

Here you go: https://www.chrisfenton.com/homebrew-cray-1a/

> It's too bad it's always existing companies that get their source leaked. Just once I'd like to see "Archive of Digital Equipment Corporation source code leaked online". I can dream... The problem is those companies are defunct, so their source repositories may not even exist anymore, let alone be online, e.g.: http://www.chrisfenton.com/homebrew-cray-1a/ > After searching the internet exhaustively, I contacted the Computer History Musuem and they didn’t have any either. They also informed me that apparently SGI destroyed Cray’s old software archives before spinning them off again in the late 90’s. I know at my employer, there's always pressure to half-ass things that aren't directly connected to some mechanism for making money. We recently migrated our company intranet site from one vendor to another, and the team that was running that project it as a "feature" that they would help us "clean up" by not assisting us migrating anything older than one year. Similarly, source control migrations (of which we've done several) often drop history, since it's usually way easier just to download the latest version and check it into the new system than figure out how to migrate the metadata. IIRC, Microsoft's TFS-VC to git migration tool will only migrate something like 180 days of history.

There are no doubt some systems still running under emulation doing the same thing as they were 40 years ago. The software might even be maintained. But the truth for decades now. CP/M is dead. Long live CP/M! It's just hobbyists now. One hacker ported his game to a Kaypro under CP/M a couple years ago: http://www.chrisfenton.com/dd9-kaypro-edition/ Much of the focus is on porting CP/M to whatever new or old Z80 system someone has built or found. Speaking of which... CP/Mish is an attempt to bring all the free software CP/M tools together. It is to CP/M as Linux is to UNIX, or FreeDOS is to MS-DOS. A mostly complete, improved, libre reimplementation: https://github.com/davidgiven/cpmish RunCPM is a CP/M Z80 virtual machine under modern OSes for development etc. https://github.com/MockbaTheBorg/RunCPM In terms of recent new programs, here are some pointers if you wanted to write something yourself: Also written by the maintainer of the CP/Mish project (and not CP/M specific) is Cowgol. Alpha quality. But it's a self-hosted Pascal/Ada-like language with compiler. Runs on 8-bit systems, at least theoretically. It is written, of course, entirely in Cowgol: https://github.com/davidgiven/cowgol Millfork is another new language which targets CP/M systems, among others. It's a whole-program optimizing cross-compiler for a language somewhat lower level than C, with properties that make it very nice to compile for 8-bit systems like no recursion, and no automatic…

A powder gun like the one used in Harp and a gas gun like Sharp both work in the same basic way – expanding gases. The lighter the gases molecular weight, the faster it expands in air. Gunpowder has a molecular weight of 22, slightly less than air at around 28, but ignited gunpowder is incredibly hot, so that’s why it expands so quickly. The hydrogen used in gas guns, however, has a molecular weight of two so expands extraordinarily quickly in air. I couldn't understand from the article how the hydrogen was being used in a "gas gun". Since pure hydrogen doesn't ignite, wouldn't we care about the molecular weight of the oxidizer as well? It turns out the "light gas" is important just for it's low molecular molecular weight. It's never ignited, and one could substitute Helium for Hydrogen if one wanted. The gas is a second stage in addition to, rather than instead of the gunpowder. It's like a spring-air gun, but instead of spring you use an explosive charge. Here's Wikipedia: https://en.wikipedia.org/wiki/Light-gas_gun And here's some PVC experimentation: http://www.chrisfenton.com/2-stage-light-gas-gun/

print it http://www.chrisfenton.com/the-turbo-entabulator/

But only because hardware got much faster, with larger resources (memory, disk). I just did a Stupid Benchmark, compiling this code: /* * Standard 'C' demo... Say hello to the world * * Compile command: cc hello */ #include <stdio.h> main() { printf("Hello world\n"); } (I know, not completely valid ANSI C code). On my home system (32 bit 2.6GHz intel gobs of RAM yada yada) it took GCC 0.2 seconds to compile and link the program (as a static program---by default it did it in 0.05 seconds). On the system I grabbed the code from (an operating system for the 8-bit MC6809) it took 35 seconds. And that was on a simulated MC6809 running on said 2.6GHz system, which is still faster, at approximately 50MHz, than a real MC6809 system of 1MHz (I thing you could get a 2MHz MC6809, but not much faster than that). Even a state-of-the-art computer in 1980 (say, a Cray supercomputer) would have a hard time keeping up with <a href="http://www.chrisfenton.com/homebrew-cray-1a/">hobbyist system of today</a>, and it's because of this increase in computing power that we've been able to have the "toy languages" of yesterday be useful languages today. But given that CPU speeds have leveled off, the easy performance gains are pretty much gone these days.

click-able: http://chrisfenton.com/cos-recovery/