Technology

Id say more like 20-40 years. x86 won't die that easily

I agree it will take awhile to completely take over even the low end market, but like there is already a data center running on RISC-V that was in the news cycle a month or two back. Intel has been putting a lot of money into it too because they know the change is coming. We are on the edge of a major shift needed for AI anyways. I think that will be the death knell for x86. The memory and cache bus structures need to change to accommodate tensor math much more efficiently. Why restructure the dying x86 so substantially when it could be done in RISC-V and make most hardware antiquated at the same time to finance the bleeding edge shift. I think The big players will still be on top, except ARM will fade into irrelevance like MIPS. Proprietary/planned obsolescence/exploitation in the digital landscape is a major problem that needs to go away. All the relevant companies have access to reverse engineered hardware from their competitors. Proprietary only exists to exploit end users. RISC-V is a small step in the right direction of restoring the right to fundamental ownership.

I agree on the time line.

RISCV has to completely slaughter ARM in the uC and SBC arenas before it can be a serious contender for the desktop market.

Basically, RISCV’s selling point is that it’s royalty free. Anyone can implement it without paying anything to anyone, no NDA’s nothing. In the uC market, where chips cost a fraction of a dollar in quantity and margins are practically non existent, not paying the ARM tax makes a HUGE difference.

Once they take over the uC market, it can move up, leveraging the experience the experience of being the world most popular core into more beefy SoCs. This is your raspberry pi equivalents and your budget phones.

From there, you can add performance features and move up to tablets, flagship phones and low power laptops. And then, eventually, performance laptops, desktop machines and servers.

This will take at least a decade.

This is not how ISA, fab nodes, or hardware design work at all. ARM is not special. It was just a company that made it easier to put together a bunch of processor blocks and peripherals for a fee and royalty. It was just a convince thing for the trailing edge. Everything ARM can do RISC-V can do as far as ISA. No one is going to pay a royalty when the same thing is free. This is the realm of big money where the choice is obvious. Not to mention, we are on the final node already when it comes to scaling, the progress of the last 40 years has stopped. There is potential in new technologies like computing with light, but silicon lithography will never drop below 3-5 nanometers because that is the end of what physics allows with quantum tunneling effects. We will eventually move past the stone age of computing with silicon. Organic technology is the holy grail, but until a major shift is made, we are at the end of silicon progress despite what all the marketing fools hype and moan about. ARM has no where to go. The people that created it bailed ages ago because the writing was on the wall all the way back then.