Blog posts like this one [1] from SiFive are claiming “billions of chips”, but I have no idea what devices those chips are going into, or whether this means there is a decent chance I’m going to be using a RISC-V desktop machine or phone sometime in the near future.<p>Thoughts?<p>[1] https://www.sifive.com/blog/risc-v-is-inevitable
I think they’re referring to the odd custom-ish embedded parts, e.g. Western Digital usage in mass produced storage devices that can afford novelty.<p>The problem is that there are really no current commodity embedded RISC-V architecture parts - Chinese dime-a-dozen pseudo-Cortex ripoffs don’t count - remotely comparable in performance/power to better current alternatives.<p>Benchmarks of SiFive’s high end are laughable, being grossly sub-RaspberryPi which is hardly ARM top of the line (and doesn’t claim to be such). As SiFive’s P550 hasn’t materialized beyond PR, one can hardly consider it real.<p>Unless some stealth startup appears with a real Zen/NeoVerse analog, I expect this triumph of hype over reality to continue.
Embedded.<p>I am not sure it's inevitable at all. That said, it sure looks like ARM did, minus the license fees. RISC-V can enter niche markets where price / performance is necessary on the low end of price and or power.<p>Things are still early though. Extensions are one ambiguity. How many will crop up and what will using them look like? Does one take over the ISA essentially?<p>Math performance, due to no flags and multiple instructions needed where single ones or even just a few less will matter too. Not saying the devices won't perform. They will, just at the cost of code size impacting effective cache size.<p>And no device is really performing today.