[HN Gopher] AMD Am386 released March 2, 1991
       ___________________________________________________________________
        
       AMD Am386 released March 2, 1991
        
       Author : jnord
       Score  : 83 points
       Date   : 2026-03-02 12:56 UTC (10 hours ago)
        
 (HTM) web link (dfarq.homeip.net)
 (TXT) w3m dump (dfarq.homeip.net)
        
       | Zardoz84 wrote:
       | > Technically, the Am386 could run Windows 95, but it wasn't a
       | great experience.
       | 
       | Technically not. It can run it. Was slow? Yes, but my Am386DX40
       | keep working fine from 1991 to 1996. Running DR-DOS 6, MS-DOS
       | 6.11, Windows 3.1 and finally Windows 95. And, of course, I could
       | play DooM 2 on it. At some point, I got a math copro. Finally, my
       | father upgraded the machine with an AMD 486DX5 133MHz.
        
         | iberator wrote:
         | NETBSD still can run on it too :) Best and most portable os in
         | the history
        
           | messe wrote:
           | > most portable os
           | 
           | Eh... I think the Linux kernel + your choice of libc/userland
           | has it beat these days.
        
             | actionfromafar wrote:
             | Modern Linux dropped support for a lot of old and niche
             | CPUs.
        
               | messe wrote:
               | And NetBSD is missing support for an order of magnitude
               | more SoCs. I _like_ NetBSD. I 've run it on several
               | systems in the past, and not just as a toy. I like the
               | whole BSD family, and even deploy FreeBSD in production
               | at work, and use OpenBSD on my home router. But NetBSD's
               | claim as the most portable OS doesn't hold up these days.
        
             | anthk wrote:
             | Modern Linux can't even scratch a 486 and some Motorola
             | platforms. Or VAX. Heck, I run NetBSD 10.1 vanilla under
             | simh 3.8 for 9front emulated on an amd64 laptop (old
             | Celeron, 2GB). Slow, but enough to play Slashem.
             | 
             | On portability on compilers, plan9/9front it's unbeatable.
             | Do you now Go compiling from any OS to any arch? The same
             | here, but just for an OS obviously. Albeit I can still run
             | Golang under i386, and tools like Rclone under 9front i386.
             | That's really cool.
        
               | messe wrote:
               | That's a very limited view of what portability means.
               | 
               | Driver support for a niche SoC? Good luck getting NetBSD
               | on before Linux. The sheer amount of SoCs supported by
               | the Linux kernel dwarfs anything NetBSD has to offer.
        
               | spijdar wrote:
               | Yeah, NetBSD's support for modern hardware isn't amazing
               | compared to Linux. I love it (and run my personal web
               | server on it!), but the portability thing feels like a
               | meme from the 4.4BSD days, where it ran on basically
               | every workstation platform.
               | 
               | Like sure, it runs on my VAX, my Sun4/75, and my Alpha
               | box, but it doesn't run on my POWER9 workstation nor does
               | it run my Amlogic A311D ARM device (at least in a usable
               | capacity), and I couldn't even get i.MX 8M running. I
               | didn't try super hard, to be fair, but why would I burn
               | cycles getting an OS with less peripheral support running
               | when Linux "just works"?
        
               | hulitu wrote:
               | I don't think Linux "just works" on VAX, Sun4/75, or
               | Alpha.
               | 
               | My experience with Linux on a Sun Sparcstation 20 circa
               | 2000 was that it was slow as hell compared to Net or
               | OpenBSD.
        
               | messe wrote:
               | I doubt NetBSD "just works" fully on those systems
               | either. I see a lot of rose tinted glasses when NetBSD
               | portability comes up. Those older systems barely get
               | stress tested, as the system has become too large to be
               | self-hosted on them anymore and has to resort to using
               | cross compilation to build a working base.
               | 
               | At least OpenBSD, when it says it supports a platform,
               | _actually supports that platform_, and the system is
               | stable enough that it can build itself.
        
               | spijdar wrote:
               | I was saying that NetBSD works on those older systems,
               | while it either has no support (64-bit POWER) or spotty
               | support (modern ARM) on more modern platforms. I've got
               | netbooting set up for all of them, and it's "useful" for
               | testing, though even a 20 MHz VAX is pain and suffering
               | (12+ hours to generate RSA private keys for SSH).
               | 
               | FWIW, Linux does work fine on the Alpha, it's just slow.
               | Both NetBSD and Linux have busted framebuffers on my
               | workstation, which has a 3DLabs graphics chipset. Having
               | acceleration enabled causes Linux to output pure garbage,
               | and NetBSD to kernel panic. The CPU performance is
               | surprisingly okay, though. About half the performance of
               | an original Raspberry Pi, in pure integer math...
               | 
               | Linux _is_ busted on my SPARC box though, not because of
               | the system itself, but a bug in the Weitek 2000A CPU. It
               | was an aftermarket part from Weitek, and in order to
               | retrofit an 80 MHz CPU into a system with discrete MMU
               | and cache chips that expect a 40 MHz single-issue RISC
               | processor, it adds a funky on-chip cache, branch-
               | predictor, and instruction prefetcher.
               | 
               | Details on specifics are ~impossible to find nowadays,
               | but the word on Usenet was that chips made before 1995
               | are no good for Linux. My limited testing with a '93 chip
               | corroborates this. I really ran into this while building
               | a new Sprite [0] distribution, where I learned this chip
               | makes tons of spurious page faults from the branch
               | predictor hitting bogus instructions, which causes the
               | Sprite (and Linux?) kernel to freak out. This
               | corroborates the Usenet reports for random signal 11s
               | killing processes on Linux...
               | 
               | Doesn't effect NetBSD, though. I think this [1] code is
               | why (replaces the bogus fault address with the process
               | counter) but I'm not sure. I have a partial fix for
               | Sprite's kernel which allows userspace to boot up and
               | work, and have networking fixed, but if you sneeze it
               | kernel panics and murders the Sprite-bespoke filesystem,
               | so testing has been a slog. :-)
               | 
               | [0]
               | https://en.wikipedia.org/wiki/Sprite_(operating_system)
               | 
               | [1] https://github.com/NetBSD/src/blob/trunk/sys/arch/spa
               | rc/spar...
        
             | lproven wrote:
             | The Linux kernel dropped 386 support _fourteen years_ ago.
             | 
             | https://www.theregister.com/2012/12/12/linux_no_longer_runs
             | _...
        
               | messe wrote:
               | I'm well aware, thank you. I'm not contesting ability to
               | run on a 386, I'm contesting the title of "most portable
               | OS".
        
               | lproven wrote:
               | OK. In context -- discussing an article talking
               | specifically about AMD 386 chips -- that was not at all
               | clear.
               | 
               | I was at a talk celebrating NetBSD's 30th anniversary. I
               | wrote about it:
               | 
               | https://www.theregister.com/2024/04/17/30yo_netbsd_releas
               | es_...
               | 
               | They're well aware of this.
               | 
               | But as Linux edges closer to dropping 32-bit x86
               | completely -- most distros already have -- I think NetBSD
               | may suddenly regain some relevance in this specific area.
               | 
               | There's also a new initiative to improve its jails
               | facility:
               | 
               | https://netbsd-jails.petermann-digital.de/
        
           | Zardoz84 wrote:
           | I have a 486DX2 at 66 that I have as pet project to mess with
           | Windows 95, MSDOS and S.u.S.E. Linux 5.3 . SuSE 5.3 was my
           | first full distro (the whole pack of 6 cdroms), and I had
           | good memories of how was easy to install stuff with YaST.
           | 
           | I could try to upgrade to the mighty Am486DX5 at 133. I
           | managed to get one, but I need to mod the MBO to give the low
           | voltage required by it. The MBO it's prepared to it, but
           | don't have populated the regulator...
        
         | killerstorm wrote:
         | My father got me a second-hand computer with Am386DX-40
         | somewhere around 1997, IIRC. An upgrade to older 286.
         | 
         | It was two generations old at that time but still a lot of fun:
         | it could run a lot of games (incl. DOOM, of course),
         | programming (largely Turbo Pascal 7), and some word processing
         | under Windows 3.11.
         | 
         | I didn't bother with Win95, though.
         | 
         | I've been using it up until 1999, when I finally got a then-
         | modern computer with Windows 98. But in some ways MS-DOS felt
         | more capable - I really knew what each file is for, what
         | computer is doing, etc. I.e. the entire machine is fully
         | comprehensible. You really don't get it with Windows unless
         | you're Russinovich or something.
         | 
         | So in a way 386 was a peak computer for me
        
         | snarfy wrote:
         | Which math copro? If you had a 386DX then I believe you had the
         | math copro? The 386SX did not have an FPU and needed the
         | additional 387SX.
        
           | to11mtm wrote:
           | > If you had a 386DX then I believe you had the math copro?
           | The 386SX did not have an FPU and needed the additional
           | 387SX.
           | 
           | Neither had FPUs... Closest you can get is RapidCAD (which is
           | really a 486DX adapted to 386 bus, IIRC it uses a 'jumper'
           | for the 387 slot.)
           | 
           | For 386, the difference between SX and DX was whether it was
           | a 16 or 32 bit data bus.
           | 
           | Where things can get more curious, is that some early 386
           | motherboards actually took a 287 instead of a 387...
        
           | dragonwriter wrote:
           | > If you had a 386DX then I believe you had the math copro?
           | The 386SX did not have an FPU and needed the additional
           | 387SX.
           | 
           | The 386DX/386SX distinction was the external databus (32-bit
           | on the DX, 16-bit on the SX)
           | 
           | DX was "Double word eXternal", SX was "Single word eXternal".
           | Neither had an FPU builtin, and there were corresponding
           | 387DX and 387SX coprocessors.
           | 
           | Then Intel used the same naming split (despite the
           | abbreviations not applying) for high-end vs low-end of the
           | 486 where the DX had a builtin FPU and the SX required a
           | "487SX coprocessor" to get an FPU (which IIRC was internally
           | just a 486DX processor which went into a separate
           | "coprocessor slot" which just bypassed the "main" processor
           | when populated.)
        
             | snarfy wrote:
             | ah, thanks for clearing up my brain cobwebs
        
             | Zardoz84 wrote:
             | Exactly
        
       | burnt-resistor wrote:
       | TI with the TMS9900 was in a similar position as IBM with the
       | 386: both threatened their micro/minicomputer markets. This is
       | why TI didn't release other TI-99-like machines. TI also
       | expressed disdain towards hobbyists.
       | 
       | Edit: It might be cool to make a higher-spec TMS9900 home brew
       | system.
        
         | KeyBoardG wrote:
         | The TI-99/8 looks like it would have been awesome. It solved
         | the issues of the 99/4a, had improved basic and pascal built
         | in, all while being backward compatible.
        
       | p0w3n3d wrote:
       | My friend used to have amd ~586 I think. I remember that when
       | playing Colonization on dos you were not allowed to move the
       | mouse beyond the right edge of the screen or the graphics messed
       | up... But pinball fantasies worked well!
        
       ___________________________________________________________________
       (page generated 2026-03-02 23:01 UTC)