Tendrils raises $30M to rebuild the CPU from scratch
$30M Raised to Redo the CPU
Tendrils has closed a $30M round led by Benchmark to design a general-purpose processor free of the backwards-compatibility constraints that have shaped CPUs since the 1970s. Instead of a sequential, single-core foundation, the chip targets thousands of parallel cores, which means abandoning shared mutable memory and linear instruction sequences. The company is also developing Vine, an open-source language built for parallel-first architectures. Visionaries Club, the UK Sovereign AI Fund, and others participated, and Jack Altman joins the board.
Accumulated layers of historical designs are locking engineers into decisions dating back to the 1970s.
- Animats
This is a "build it and they will come" project.
It's not a "we put the inner loop of ML entirely in hardware" project. That would make more sense technically. You could cram a lot of little independent neural net inference units on one chip. But if it was pitched that way, the questions would be "Why isn't NVidia doing this", and "After you do it, what keeps NVidia from doing it". There are lots of people pitching "AI chips", with modest success.
The history of general-purpose massively parallel machines isn't good. From the Illiac IV to the Playstation 3, there's been dud after dud in this space. You can build them, but the users don't come. This sort of architecture is great if you have some specific problem that parallelizes, such as finite-element analysis or neural networks.
(I've used an NCube, and I kind of liked the Transputer concept. But both were dead ends.)
- librasteve
By my reckoning you can build about 256 small fast CPUs each with 16kiB RAM and IO on an M4 die area. Most of a modern CPUs gates are wasted on out of order execution and cache coherency.
https://bil-lang.org is a more explicit language that imo is needed for coders (or LLMs) to grapple with hammering algorithms onto a CPU array. But AI is a big lever to overcome this historic barrier.
- AlotOfReading
This feels a decade late. I don't really see the value prop for customers in 2026 (or realistically, 2030+). Let's say I'm willing to rewrite all my software to a language that compiles down into interaction nets. Why don't I use HVM2 instead and buy GPUs from Nvidia? If I just want to use an exotic architecture, AMD is shipping dataflow processors at scale today, and they'll license related IP. And if I just want a massively parallel architecture to run my existing ML code on, I could just rent google cloud TPUs instead.
Who's the customer that wants an exotic architecture on an old process node running a custom programming language half a decade from now?
- tyingq
Hmm. The story over at https://millcomputing.com/ always looked compelling.
Pitchbook shows it as "Out of Business" since 2019.
- nukanse
As a programmer, I always wanted a cpu which instead of having n 64 bit registers, had a single register with 2^m bits, which could be split in arbitrary length sub registers, not all the same size, and could be treated as an array of bits, or a swar machine
- jojohohanon
I thought greenarrays was incredibly cool. (144 native-forth cores on a chip)
I loved the mill architecture (self declared clean sheet cpu).
I thought transmeta had a good chance because they could inline across kernel boundaries.
But none of them was special enough.
- hingler36
New CPU architectures have lived and died by supporting existing software, with Rosetta on Apple Silicon being an example of it working and Itanium an example of it falling apart.
All the best to anyone trying to design a new paradigm of processor, but I'm interested to hear how they'll avoid the pitfalls of their predecessors.
- mikewarot
I think we all have projects and ideas like this that go back decades. In my case, it's the BitGrid, which is a theoretical sea of look up tables that are clocked in alternating phases like a chessboard, to eliminate race conditions and the need to worry about timing.
I couldn't quite follow the diagrams of the theory page, but I'd be willing to bet a very small sum of cash that it'll eventually be something very much like the BitGrid.