But what RISC-V would provide is a "standard" ISA. You can avoid having a manufacturer/vendor lock-in. Anyone can manufacture a RV64EMAFDZicsr.
> Not PC Engines an easier time to design and source things
Isn't it better to rely on a "standard" technology than a proprietary one? x86 is not standard, it's widespread. The Duopoly in place can decide the price, the feature, even its client. They can decide one day to stop providing what you need and that's it. With a standard chip, you can go next door in Shenzhen and get what you need.
> Moreover any actual RISC-V chip that's worth replacing the AMD in PC Engines will be at least as proprietary as the AMD chip
Why? We are not talking about a supercomputer to train LLM here but simple network appliance than needs efficiency. The GX-412TC PC Engines was using, doesn't look that impressive. Aren't there already RISC-V chip today on par with it? Like VisionFive for example?
> But what RISC-V would provide is a "standard" ISA. You can avoid having a manufacturer/vendor lock-in. Anyone can manufacture a RV64EMAFDZicsr.
Anyone can manufacture a chip based around one of Arm's CPU core designs if they pay a licensing fee to Arm, and many different manufacturers do. If you want to, you can even make your own CPU design supporting an Arm ISA, again if you pay a licensing fee.
Likewise, you could license a RISC-V CPU design from some company… for a smaller licensing fee, but you will have RISC-V's worse software compatibility, and probably worse overall performance, efficiency, die area and quality.
The ISA is a tiny piece of the puzzle and not the most important one. RISC-V is cool because Arm won't sue you for making a hobby project that implements it in hardware, but it doesn't solve problems other than “Arm's license fees are too high”.
>and probably worse overall performance, efficiency, die area and quality.
Unlikely. E.g. SiFive offerings beat the crap of ARM equivalents, in performance, power and area.
>but you will have RISC-V's worse software compatibility,
Using the standard ISA gets you the widest possible ecosystem.
Of course, this isn't true yet, but it will be in practice, when considering the current trends and the fact hardware takes years from the time the decision is made till having hardware in hand.
>RISC-V is cool because Arm won't sue you for making a hobby project that implements it in hardware,
With 10b+ cores shipped in 2022, we're well past the "niche ISA for hobby projects" stage.
> The question on everyone’s mind is when RISC-V will come to user-facing applications. The answer is that this may be closer than people expect. There are currently 4 companies working on large RISC-V cores that compete with the biggest and fastest from Intel, AMD, Arm, Apple, etc. These 4 companies are Ventana Micro Systems, Tenstorrent, Rivos, and Akeana. Each of these companies have teams with impressive pedigrees, but that alone doesn’t guarantee success.
> Not PC Engines an easier time to design and source things
Isn't it better to rely on a "standard" technology than a proprietary one? x86 is not standard, it's widespread. The Duopoly in place can decide the price, the feature, even its client. They can decide one day to stop providing what you need and that's it. With a standard chip, you can go next door in Shenzhen and get what you need.
> Moreover any actual RISC-V chip that's worth replacing the AMD in PC Engines will be at least as proprietary as the AMD chip
Why? We are not talking about a supercomputer to train LLM here but simple network appliance than needs efficiency. The GX-412TC PC Engines was using, doesn't look that impressive. Aren't there already RISC-V chip today on par with it? Like VisionFive for example?