> The API = yes. The example chip designs put out by researchers = no
However, if you looked at the link I provided, you'd see that the RISC-V chip in question was actually a commercial prototype.
Micro Magic Inc.—a small electronic design firm in Sunnyvale, California—has produced a prototype CPU that is several times more efficient than world-leading competitors, while retaining reasonable raw performance.
And even then, the the benchmark figures are definitely to be taken with a pinch of salt, as Ars had to rely on the figures supplied by the company. In fact, to quote the last section of the article:
Micro Magic intends to offer its new RISC-V design to customers using an IP licensing model. The simplicity of the design—RISC-V requires roughly one-tenth the opcodes that modern ARM architecture does—further simplifies manufacturing concerns, since RISC-V CPU designs can be built in shuttle runs, sharing space on a wafer with other designs.
With that said, it would be an enormous undertaking to port [...] not just the kernel, but drivers for all hardware from GPU to Wi-Fi to LTE modem, and more—third-party app developers would need to recompile their own applications for the new architecture as well.
We're also still taking a pretty fair amount of Micro Magic's claims at face value. While we've seen a screenshot of an 8,200 CoreMark score, and we've seen a 69mW power reading, it's not entirely clear that the power reading was representative of the entire benchmark run.
Admittedly, some of the issues mentioned above will resolve themselves as the RISC-V eco-system matures. I can see China in particular taking great interest in it, especially with the ongoing US tech embargos.
> ARM's business model is to charge big players 1% less for licenses than it would cost them to just make their own API design, with RISC-V the cost to switch to vs designing from scratch is lower = tighter squeeze on ARM.
Oddly, as mentioned above, that's the same model that Micro Magic Inc. appears to be going for.
Fundamentally, a CPU cannot exist or operate in isolation; there's an entire eco-system which needs to be in place to support it, both when designing the device and when building software to run on it.
And unless you're willing to maintain and develop that eco-system in-house, then you'll need to pay for external support [*].
And that'll be charged at the market rate. Which as you said, will probably work out to be about 1% less than the competition...
[*] As ever, open source is free as in speech, not beer. Any commercial company which tries to use open source as a "free as in beer" resource is going to find themselves severely disadvantaged when compared to companies which are willing to pay for support.
Biting the hand that feeds IT
