Top all-time · #19417
M
Mike Warot
Personal blog · bitgrid.blogspot.comhardwaresystems
Mike Warot writes BitGrid, a personal blog at bitgrid.blogspot.com about hardware and systems. Since 2021, 4 different Hacker News readers have linked it 26 times. It is still writing: the last post was on 2024-11-27, and you can follow it by feed.
26mentions?
4HN people?
2021–2025first – last linked?
Too few sampled comments (3) to say how often HN recommends it.?
Why HN links it
Posts by Mike Warot on BitGrid, a chip idea using a grid of 4x4 LUTs with only neighbour connections, presented as an alternative to FPGA interconnect-heavy designs.
Summarised by Claude from a sample of 3 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Wherein Mike Warot describes a novel approach to computing which follows George Gilders call to waste transistors .
Most-linked posts?
What Hacker News says?
Cool.... if you want to make a general purpose compute engine out of it, you could go full BitGrid[1]. ;-) [1] https://bitgrid.blogspot.com/2005/03/bitgrid-story.html
Comment linking /2005/03/bitgrid-story.html
on “Launch HN: Deepsilicon (YC S24) – Software and hardware for ternary transformers”Submitted BitGrid – Brilliant, or Waste of Time? as a story · 2 points
HN discussionI assume it's somewhere here: https://bitgrid.blogspot.com/
Comment linking /
on “The FPGA turns 40”If you've read the article, and thought to yourself... I wonder what it was like back then, and if there might be some other direction it could have gone , oh boy do I have a story (and opportunity) for you! It's my birthday today(61)... I'm up early to get a tooth pulled, and I read this wonderful story, and all I have is a tangent I hope some of you think is interesting. It would be nice if someone who isn't brain…
Comment linking /2024/09/bitgrid-and-isolinear-memory.html
on “The Soul of an Old Machine: Revisiting the Timeless von Neumann Architecture”>"If you disclose your invention publicly and do not file an application within one year, you could be barred from receiving a patent on that exact invention." Does this mean if I disclose an invention, that nobody can patent it after a year? This is my explicit reason for writing about BitGrid out in the open, since 2004.[1] If it turns out to be useful, that's awesome. If not, it's been a fun mud ball to polish.[2…
Comment linking /2004/
on “Advice for first-time inventors from a patent engineer”I believe it is possible to have a computing fabric that is so simple there isn't anywhere to hide bugs in it, yet extremely performant. The downside is it wastes transistors, and isn't a Von-Neuman architecture at all. It's a grid of 4 in, 4 out look up tables (that's 64 bits of state each), each exchanging 1 bit with its cartesian neighbors, clocked in alternate phases like a chess board to prevent all race condit…
Comment linking /
on “Why It’s So Difficult – and Costly – To Secure Chips”http://bitgrid.blogspot.com The idea is dead simple, 4 bit input, 4 bit output lookup tables clocked in alternative phases, like a chess board, as a general purpose computing fabric.
Comment linking /
on “Ask HN: Which important problem are you working on?”You could try my idea if you really want to follow this path.. the bitgrid, a 2d array of 4x4 bit look up tables, clocked in two phases like the squares of a checkerboard. No routing overhead at all. You can do very interesting things to programs as you load them, route around bad cells, flip and rotate programs in space to move I/O into better places, you can put a ring around a routine and fence it off from all th…
Comment linking /
on “Is programmable overhead worth the cost?”Blog: http://Bitgrid.blogspot.com The guts of an FPGA are a lot of D-flip-flops in chains, that shift in the bitstream, and then send control signals to LUTs, switching fabric, etc. What I propose is to remove most of the switching fabric, so that every cell is identical, and add latching to every cell's output, to eliminate timing (especially race conditions) as a concern. Every cell only has short connections to n…
Comment linking /
on “What is your bet in 2025?”I've had a chip design bouncing around in my head since the 1980s, now I can finally get it made. Thanks so much for posting this. The idea is simple... a grid of 4x4 LUTs, each geographic neighbor has 1 bit in, and 1 bit out, there are 16 states, each with 4 outputs. Turns out that this route-less FPGA can do some fairly amazing things, at least in theory. Now I intend to find out. The really old blog I had about i…
Comment linking /
on “Chip Ignite: Rapid IC Creation”Bitgrid[1][2] is a continuation of an idea I've been carrying around since the 1980s, and tweaking from time to time. If I can maintain focus long enough, I intend to learn RTL, VHDL or Verilog well enough to get it entered in one of the Google open source chip shuttles. I think this approach to computing if applied to neural networks may offer a cheap way to get far more compute, perhaps exaflop performance out of…
Comment linking /2005/03/bitgrid-story.html
on “Ask HN: Tell us about your project that's not done yet but you want feedback on”Ok... this is a wall of text, looks like a screed... suggestions welcome for taming it down, and making it reader friendly would be most welcome. Here are the current things in the "Mike invents the future" queue. Everything is open source, and out in the public, and I'm happy to collaborate. BitGrid - a cartesian grid of cells[1], each currently a 4x4 bit look up table, and a latch, so that you have all local conne…
Comment linking /
on “Ask HN: What are you working on (December 2024)?”Bitgrid - http://bitgrid.blogspot.com In 1993, after reading George Gilder's call to waste transistors[1], I came up with the insane idea of just making a fabric of 4x4 bit lookup tables, with each table taking a bit from each neighbor, and generating a bit to send as well. It was the minimum configuration that I thought would be suitable for general purpose computation. There turn out to be several advantages that…
Comment linking /
on “Ask HN: Tell us about your dead or never finished startup ideas”1) Abstract thinking about Turing Machine Equivalents 2) Turing machine equivalents, Reconfigurable Computing, FPGAs, RetroComputing 3) Windows32 Apps, ASICS, 7400 Series TTL 4) Old retired person time 5) Central Time Zone, US, Chicagoland 6) Fun for me, you can do profit if you want, learning 7) The BitGrid, a Turing machine equivalent which might yield cheap Petaflops, or not. Someone could make billions off of th…
Comment linking /
on “Ask HN: Who wants to collaborate (thread) – 5 Sep 2024”I've seen the appearance of PCs, and the impact of 4 decades of Moore's law on price/performance. With O1 and now O3, the main limits of what you can do with an LLM seem to center on just how much compute you can give it. I hope to offer a few more decades of performance boost to the show, with Isolinear Memory[1], to help dissolve those limitations. ;-) [1] https://bitgrid.blogspot.com/2024/09/bitgrid-and-isolinear…
Comment linking /2024/09/bitgrid-and-isolinear-memory.html
on “Ask HN: What can LLMs not do?”I'm learning FPGAs, using the $25 Tang NANO 9K that I bought on Amazon Prime[1]. I just figured out how to use the PLL to generate clocks of arbitrary frequency, rather than the stock 27 Mhz. I'm interested in using this board as the core of a SDR transceiver for the HF Amateur radio bands. Driving all the phases for a Tayloe polyphase mixer[4] should be trivial. The real question is, how high of a frequency can I g…
Comment linking /
on “Ask HN: What Are You Working On? (Feb 2024)”I think I can do it far, far cheaper than that... and I've been talking about it, in public, for over a decade.[1] I could easily be wrong, of course. It really all depends on how much power a 4x4 LUT and 4 bit latch Latch Leak, and how much energy it takes to clock data through them for a cycle, and how fast they can be cycled. If the number are good, this thing will be amazingly cool. I can't find good numbers any…
Comment linking /
on “Ask HN: Why is it taken for granted that LLM models will keep improving?”Here's my old blog on the subject https://bitgrid.blogspot.com/ Here's my github repository where I have an emulator written in Pascal https://github.com/mikewarot/Bitgrid Here's a writeup on the idea, from a computing language perspective, on the esoteric languages wiki https://esolangs.org/wiki/Bitgrid
Comment linking /
on “Ask HN: Comment here about whatever you're passionate about at the moment”I'd go one step further, and just have a massive cartesian grid of 4x4 Look Up Tables (LUTS) clocked in a checkerboard manner... all of one color is active, then all of the other color... it prevents all race conditions. There are HUGE advantages to computing this way, in terms of relocating code, routing around defective cells, security, etc. I've blogged about it at length in the past.[1] [1] https://bitgrid.blogs…
Comment linking /
on “Ask HN: If money was no object what software would you create?”I've been following home-made semiconductors since Jeri Ellsworth made her own NMOS FETs in 2010.[1] When Sam managed to make his own ICs, I was happy for him, and for the hobby. Now he seems to be on the verge of democratizing access to semiconductor production in very low volumes. I've got my own project to try out once I can get my hands on it.[2] Who knows, petaflop chips made in the garage could be right around…
Comment linking /
on “22-Year-Old Builds Chips in His Parents' Garage (2022)”In another blog post from 2008 he seems to say that FPGA uses way too much on interconnects, some other technology called HRSA realizes the problem, BitGrid takes it to an extreme [1]. So you can build simple circuits like muxes and latches. What about complex circuits like adders or registers? Could you build a CPU with a BitGrid, or do you run into problems (e.g. topological issues because the clock needs to be ro…
Comment linking /2008/07/hrsa-close-but-no-cigar.html
on “BitGrid – Brilliant, or Waste of Time?”HN user mikewarrot writes the following, in the following two articles/posts: https://news.ycombinator.com/item?id=27230989 >"I've had a chip design bouncing around in my head since the 1980s, now I can finally get it made. Thanks so much for posting this. The idea is simple... a grid of 4x4 LUTs, each geographic neighbor has 1 bit in, and 1 bit out, there are 16 states, each with 4 outputs. Turns out that this rout…
Comment linking /
on “BitGrid – Brilliant, or Waste of Time?”When I was young, I wanted to be a computer programmer, but I was totally convinced there wasn't any money in it, so I picked a EE major instead when I started college in 1981.... Boy was I wrong!!! I ended up dropping out (I picked the school I barely got into, Rose-Hulman, instead of the one I could afford, Purdue Calumet), and had a varied career doing programming and some hardware before settling into a SysAdmin…
Comment linking /2008/07/bitgrid-minimalist-systolic-array.html?m=1
on “Ask HN: Childhood dream vs. your actual job”