Hacker News Reader

Comment by mjevans | Hacker News Reader

If they had picked RISC-V then there's a strong chance of international support from ecosystems outside of China, such as open source compilers and operating systems.

IIRC most of the advantages this architecture claims to have should also be addressed by the RISC-V specification (at least in baseline profile) and they're also free to add vendor specific extensions?

Other than not-invented-here, a project already in the pipeline, or possible national security (for China) applications; I fail to see the advantage of yet another standard.

View on HN

RISC-V is being widely adopted in China, just not by this one company. I'm sure they have their reasons but the decision seems to make little sense for Loongson. They'll have to port the toolchains and kernels (which was a multi-year effort for RISC-V). If they needed extended instructions for specific features, then RISC-V is ideal for that since it's built around the concept of extending the ISA.

> possible national security applications

I wonder how much of a benefit that would be.

To have an entirely separate instruction set and all the hardware / software that builds upon it that is only really used in your country _sounds_ like it would be a good way to frustrate espionage / hacking to a layman since adversaries lack the expertise.

I am sure adversarial agencies would appoint a person or a small team to become experts in this specific technology though so maybe not so much although the costs would be more than for a "common" tech.

Interesting theoretical situation to play with though.

A national security advantage could be a simple as: a foreign nation can’t cut off the supply.

But it also means you can't seek extra supply from outside your borders.

In reality this is going to be a hugely limited benefit: to be useful it has to be widely dispersed, probably internationally. Which means everyone is going to wind up with samples in hand, and realistically it closes no exploits (which usually operate higher then architecture level).

It's in fact far more likely that some devastating architectural flaws are discovered.

"hugely limited benefit"

Erm, no, independance of supply is the entire point. Multiple nations, such as Iran and Cuba, have seen their economies rekt by US sansctions or embargoes. This is literally priority N1 for any country on bad terms with US, whatever the reasons.

I meant in regards to going your own way on architecture.

In-countrying your chip making just makes sense, but there's no reason not to use an existing architecture that experiences global cooperative development for as long as possible.

Isn't RISC-V a supply merely of freely available information that you only need to download once? There are reasons why cutting of your relationship with ARM is problematic, but RISC-V doesn't care about anything other than the ISA spec

Per this comment

https://www.cnx-software.com/2021/04/17/loongson-loongarch-c...

It seems risc-v relies on a patent pool dominated by us companies. So the us can arbitrarily extrajudicially stomp on chinese chip manufacturer as they did with Huawei

Can you point to a "RISC-V patent pool"? I've never heard of such a thing. The ISA was shown to be patent free. Microarchitectures have heavily patented features, but microarchitectures are generally independent of the ISA, so changing ISA doesn't help.

> The ISA was shown to be patent free.

Please stop repeating this.

First of all, before winning a few court cases we can't really be sure.

Also, probably well above 99% of patents in this area are not about the ISA but various implementation and optimization details.

As fun as riscv is, the patent free statement is (at this point) just marketing talk by Berkley.

I knew FUD was going to show up sooner than latter.

How is the law extrajudicial?

RISC-V was OK before the 1.1 spec. Version 1.1 is self-sabotaged by the RISC-V team, in such a way that you can't create a cycle-accurate software emulator running at reasonable speed. The dirty deed is in changes in the instruction encodings, multiple bit shuffling instructions in the emulator are now required to decode some 1.1 insns.

To me, this indicates that the RISC-V team has bad intentions, and I dropped RISC-V for this reason.

Fortunately, RISC-V is really strong in China.

This decision by one CPU vendor is unlikely to change this.

Reply on news.ycombinator.com