1. 14

  2. 8

    Itanium was the last platform for OpenVMS, so that’s the end of that.

    VMS Software has licensed OpenVMS and is porting it to x86_64, but it’s obviously a gargantuan task and it’s slow going. I await the day I can run OpenVMS on a laptop…how cool would that be.

    1. 8

      Feels kind of wrong to see how even though with Linux/BSD and LLVM, one should be able to run a standard *nix on any instruction set, and yet these keep disappearing, leaving just ARM and x86.

      I cut my teeth in a world with VAX, MIPS, SPARC, DragonBall, Intel, and so many other CPUs, all meant to lock a customer to a vendor’s proprietary Unix.

      I’d really like to have a chipset available with no space wasted on floating point, for database severs, and a chipset for gaming, and a chipset for mobile, and something that is good for sharing a bus with an FPGA, etc.

      Instead, it’s coke and pepsi now.

      1. 2

        one should be able to run a standard *nix on any instruction set

        In theory :). In practice, C is “machine-aware” enough that architecture-specific bugs are pretty common, and other compilers might or might not support the architecture you want. I remember a few years ago running Haskell programs on a Raspberry Pi was an adventure, though I think that particular situation has improved.

        On the bright side, RISC-V is gaining some traction. That could improve matters since hardware vendors can compete while software stays fully compatible.

      2. 4

        Wow, I didn’t realise the end would be quite so soon. Heck, I can remember a large oil company that was deploying Windows 2003 on Itanium systems in 2007. These were just regular application servers running SAP applications - no idea why they went for Itanium instead of x86_64 (which was not only cheaper but faster).

        I’m still surprised that HP bailed on porting HP-UX to x86. No, there isn’t huge money in proprietary Unix any more, but keeping customers locked in is surely the mantra of most enterprise software vendors?

        1. 4

          Served its purpose: making HP stupidly drop its PA-RISC which was a strong competitor.

          1. 5

            My understanding of the history was that it was the other way around: Itanium was largely an HP idea originally, which they partnered with Intel to develop, rather than an Intel idea that they sold HP on. A bunch of the researchers who had pioneered VLIW in the ‘80s were hired by HP Labs around 1990 (Josh Fisher, Bob Rau), and they argued within HP that RISC’s architectural superiority was reaching its limits and needed a major next step based on VLIW to stay ahead. That turned into an HP–Intel partnership around EPIC, which was a branding of a specific take on VLIW.

            1. 1

              I think we are just stressing different points. HP had an internal push for EPIC on the, obviously false, theory that RISC was a dead end . Intel jumped on board, swamping PA-RISC as well as SGI MIPS and DEC/Compaq Alpha. There were other reasons those companies all threw in the towel but intel profited enormously from becoming the only game in town for server CPUs and their excellent marketing of vaporware was enough to convince execs at their main competitors to become dependent customers rather than rivals.

              1. 1

                obviously false, theory that RISC was a dead end

                I think the Pentium Pro did a good job of that already.

          2. 4

            My takeaway from the whole Itanium debacle was that it was maybe the strongest example of “No, really, there is no such thing as a sufficiently advanced compiler that will save your ass.” The Cell chip being the second-strongest, but one that worked because it had so much consumer force behind it.

            The Itanium chip was awesome, but man what a mess for devs and compiler engineers.

            There’s a lot to be learned from that hubris.

            (hint hint)

            1. 2

              This is also what I remember from that time. The super-compiler was a technical bet that did not materialise.

              And also, it did not help the marketing budget of x86 was much bigger.

              At that time I was involved in some big HW pre-sales processes and Itanium never was cost effective in the business case. It was more expensive and the only thing we could explain to our prospects was that the roadmap was better and suited for the really high end market, a place where according to Itanium marketing x86 will eventually abandon. But of course the x86 marketers repeated that this would never happen.

              But clients felt this was a gamble and they preferred to stay with x86 and the higher freq means higher processing power rather than wait for the appearance of a magical compiler. This was a key point because the people making the decision Itanium/Intel were HW people that did not feel confortable changing the application landscape to introduce a new compiler.

              1. 1

                Idk. Both the Itanium and Cell sales were mostly driven by platform appeal (or lockin for HP) that wouldve happened just as easily with an Intel/AMD CPU as we’ve seen recently in both markets. Far as people buying them direct, both appealed to tiny niches of customers that liked their unique capabilities enough to forgoe benefits of mainstream platforms. And then they both died with Itanium outlasting the Cell in iteration count (IIRC).

                By died, I mean market demand and real investment into them. I think IBM and Mercury still sell Cell’s but most demand went to clusters of multjcore CPU’s and GPU’s.

              2. 2

                I bet Secure64 is working hard on a port to x86 right now for thdir SourceT OS. It was designed for Itanium’s security features. Xeon security has come far but I wonder if current extensions can imitate the memory keying on Itanium.

                1. 1

                  Interesting that Itanium was the last bastion of HPUX. Man, I do not miss HPUKES. :)

                  1. 0

                    As markets mature, you always end up with only a few competitors.

                    Boeing vs Airbus

                    Intel vs AMD

                    Nvidia vs AMD

                    It is only natural.