I'm bullish on RISC-V, but sort of bearish on SiFive. The last several systems I've used have been StarFive systems (which is distinct from SiFive.) They (SiFive) seem to be more of a custom IP shop, where you go when you want to spin some custom silicon but not pay ARM. But now that we've broken with China re: chip production, is there anyone on this side of the pacific I can get catalog parts from?
So... their cores are great, but if I'm only going to see them if I write a very large check to SiFive, they're sort of irrelevant to my world. I would love to have SiFive IP that doesn't use Rocket/Scala/Chisel and does produce catalog parts.
That could be just me. I enjoy getting my hands dirty.
I agree with this, and suspect that if SiFive did get big enough they would start creating patented extensions as a defensive strategy.
Personally I'm more curious about RISC-V in tiny microcontrollers, and were I guiding semiconductor strategy I'd be way more concerned about ability to build embedded systems than GPU farms. The ecosystem to do the former can evolve into the latter, but skipping to the end is just a route to burn absolutely billions.
FWIW, after listening to Chuck Peddle's CHM Oral History interview, I sort of realized I didn't need the ARM ecosystem and just designed my own 6-bit microcontroller. Granted, I'm only doing some very simple control applications and fabbing at 800nm, so it's not going to be competing with an i7 or an A72 anytime soon.
IIRC, the RISC-V spec includes an "embedded profile" that specifies a CPU with 16 32-bit registers, so that should make RV32 even smaller than it would be otherwise. SiFive designed a dog-simple 2-stage pipeline 32 bit core that could even run without I-cache. I mean, it's not a speed demon, but it was implementable in many fewer gates than their earlier E cores.
I worked at SiFive for a year and couldn't make sense of their product strategy. But maybe that's a me problem and not a SiFive problem.
I really do sort of wonder what they're doing with 175m in Series F funding. Where do you go from there?
Here's a class at MIT that takes undergraduates who don't even know verilog and at then end of the class they have a mostly passable RV32I. Admittedly pushing that through VLSI CAD will not be push-button easy but many universities also have an undergraduate tape-out class, including MIT...
https://ocw.mit.edu/courses/6-004-computation-structures-spr...
Via MPW and assembly service one can easily have that die manufactured, packaged and mounted on custom PCBs for under $50K, a.k.a. much less than you'll pay in salary to have it designed, fabricated and tested. Even at non-American labor rates.
In 2023 producing a computing core, albeit not a state-of-the-art one, is just not the moat it once was...
Yes. I saw that too. It turns out that "building a chip" is different than "building a chip that meets specfic requirements we got from the customer."
I'm not saying "building a RV32x is impossible," I'm saying there are people with existing tool-chains that favour Verilog or SystemVerilog (or even VHDL, though I don't know of them personally.) And telling them "no, you should use Scala / Chisel / Firrtl to model the features you want to add to the system in order to meet customer requirements" is kind of a hard sell for many customers.
However, RISCV cores abound. In pretty much any HDL known to man with varying design trade-offs and capabilities. It's extremely difficult to differentiate at the RTL level at this time. Not impossible, but it would be a significant investment, which is I guess SiFive's business model. Sell IP at prices cheaper than that.
Here is a high quality, well documented, SystemVerilog version intended for embedded applications that I know has been included in multiple ASIC and FPGA designs successfully.