Engineer creates CPU from scratch in two weeks, begins work on GPUs

Also, from the article:

Interestingly, Anthropic’s Claude Opus AI tools have been useful during this GPU designing stage. “I've been proposing my ideas for how each unit must work to Claude, and then somehow it will guide me toward the right implementation approaches which I can then go and confirm with open-source repos,” explained the engineer.

Maybe his next opus will be a disassembled clock radio in a pencil case?

The guy that wrote it looks like he's on a pretty brutal publishing schedule:

https://www.tomshardware.com/author/mark-tyson

That's like 2 articles a day. I can't imagine. I spend at least 10 weeks on each one I write.

As best as I can tell, this is someone who's speed-run something like nand2tetris and an intro-to-EDA-tools tutorial, and is now trying to move into GPUs and is somehow distraught about how hard it is to make that conceptual leap. And this was picked up by a reporter trying to make a quick article who doesn't fully understand what he is reporting on and thinks it's something more impressive than it really is.

To be clear: I think that a decently motivated person can go from "0 knowledge" to a toy implementation of a CPU in a digital logic simulator in something like 20 hours of focus or so (especially if the digital logic simulator gives you prebuilt components for things like adders and memory). I've never done digital design for circuits before, but I imagine it's a similar level of difficulty.

From parsing the Twitter user's comments, the GPU confusion seems to be the Twitter user skipping any attempt to learn advanced computer architecture because he thinks it's not on the critical path to building a GPU and doesn't realize that the information he's struggling to find is really just computer architecture 301.

Ben's kits are for a simple 6502 computer.

If you'd like to build a CPU from scratch, I would suggest https://monster6502.com/

If you want to get really fancy, build the Monster 6502 and then use that as the CPU in your Ben Eater 6502 kit!

Working my way through Nand2Tetris, turns out it's quite a slow grind unless you've done it before, but very satisfying challenge.

Verilog is kind of trash by modern standards. Unfortunately we are stuck with it (well SystemVerilog) until tool vendors support something else.

It's kind of a similar situation to JavaScript actually. And in a similar way, you can compile to Verilog, but just like with JS it makes debugging much more painful.

There was this interesting project but it seems inactive: https://llhd.io/

There's also various alternative HDLs that seem to have various levels of solving the wrong problem (SpinalHDL, MyHDL, Chisel). This one looks quite interesting though: https://filamenthdl.com/

"This is like Juicero" is an excellent takedown.