A blistering critique of RISC-V recently hit the front page of Hacker News. The response from an embedded engineer in Trinidad and Tobago explains something the original critic missed entirely: why the cheapest chip matters more than instruction set elegance.
The Original Critique
Dmitry Grinberg published a long, technical, and angry piece titled "RISC-V: They Should Have Known Better." It went viral on Hacker News and Lobsters, and it's the most substantial criticism the RISC-V architecture has received in a while. The core argument: the things a high-end CPU needs are diametrically opposed to what a small cost-saving microcontroller needs, and no single ISA can serve both ends well.
The complaints are technical and specific — compressed store offsets that are strange, Zicsr being a separate extension you have to remember to ask for, encoding decisions that seem suboptimal. For engineers working at the high end, these are real frustrations.
The Response From Somewhere Else
An embedded engineer in Trinidad and Tobago wrote a response that reframes the entire debate. The perspective shift is important: when you're writing from a small island nation off the coast of Venezuela, the conversation about instruction set elegance looks very different.
The key point: when you want a development board and you're not in the US or Europe, you're not checking next-day delivery. You're checking whether the seller ships to your country at all, what customs will do to it, and what the total lands at in local currency. "Free shipping" from DigiKey, Mouser, or any US/European manufacturer doesn't apply. You pay anywhere from $60 to $200 to ship dollar chips that everyone else gets free shipping on.
The students being taught are in the same position. And so are students in Nigeria, Bangladesh, and everywhere else the industry doesn't think about when it writes its blog posts.
From that position, the difference between a ten-cent part and a one-dollar part is not a rounding error. It's not a detail you wave past on the way to the interesting discussion about encodings. It is the difference between a class of thirty students each having their own chip and a class of thirty students watching one demo board — if any at all.
The Part Everyone Scrolled Past
Grinberg, in his critique, asks what a cheap microcontroller core is actually for. His answer: it sits inside a larger chip, prodding registers and configuring hardware blocks. In an MP3 player, an SD card, a USB stick. The real work is done by custom silicon around it.
From that, he derives what such a core needs: low interrupt latency, small die area, good code density. No hardware divider, possibly not even a multiplier. No privilege separation, because nothing untrusted ever runs there.
Then he writes the line that undermines his own argument: "But," you might say, "you just described RV32IC (or RV32EC)!" And elsewhere, plainly: "I am 100% sure that RISC-V will own the cheap-as-dirt single-use microcontroller space eventually."
The most credible RISC-V critic of the month sat down, worked out from first principles what a cheap microcontroller core should be, arrived at the instruction set a ten-cent chip implements, and stated that this segment is going to be RISC-V's. He derives the case for the chip and then spends the rest of the article annoyed that the chip exists.
Instruction Set Elegance Is a Luxury
The response makes a point that should be obvious but isn't: instruction set elegance is a thing you can afford to care about once the hardware is already on your desk. Whether the hardware can get to your desk at all comes first.
This isn't just about RISC-V. It's about the entire conversation around hardware and software ecosystems. When engineers in wealthy countries debate the merits of architectures, they're debating from a position where access is assumed. The chips are on the shelf. The shipping is free. The credit card works.
For most of the world's developers, those assumptions don't hold. The question isn't "is this the optimal ISA?" — it's "can I get this chip, at this price, shipped to my location, with the payment methods I have access to?" RISC-V creates a space for the other 99% outside of "the world" (which in hardware discussions is mainly the US and Europe), and it has nothing to do with architecture.
The Real Argument
Grinberg's central claim is that no single ISA can serve both high-end CPUs and cheap microcontrollers. From a pure architecture standpoint, the premise has merit — the needs are different. But the conclusion doesn't follow.
The engineer in Trinidad points out that from three parts sitting on his desk, he can show why. The cheap RISC-V chips aren't competing with high-end cores. They're competing with the absence of any chip at all. They're enabling a class of developer and student who, without a ten-cent RISC-V microcontroller, would have no microcontroller.
The RISC-V critic's quarrel is with whether RISC-V's dominance in the cheap-chip segment was "earned" through architectural merit. That's a real question, and it's fair to be bothered by it. But it's not a question that affects anyone deciding what to learn on, because the chip is on the shelf either way.
What This Means for the Industry
The debate reveals a blind spot that affects more than RISC-V. The technology industry's conversations are shaped by the people who can afford to participate in them. When the conversation about instruction sets happens without the voices of developers in the developing world, it reaches conclusions that are technically correct and practically incomplete.
The next billion developers aren't in San Francisco. They're in places where a ten-cent chip and free shipping would be transformational. The architecture that reaches them — at the right price, with the right availability, through the right supply chains — will define the next era of computing. Not the architecture with the cleanest encoding.
RISC-V's most important feature isn't its instruction set. It's the fact that it exists at a price point where a student in Trinidad can own one. Everything else is a conversation among people who already have theirs.
Top comments (0)