therealcamino

This would be interesting to read if not for the LLM prose style.

If it requires physically contiguous RAM to work, then it's not really participating in the full virtual memory system, really. It would be using an exception to it, that can be accommodated to some extent by the OS, but not sitting in demand-paged storage like the rest of the system.

Maybe. The use cases have always been around FP arithmetic over arrays, because that's what is easy to parallelize. I saw a standalone systolic array box attached to a MicroVAX circa 1990. Lots of PIM approaches in the mid-90s, too, but mostly what survived from that era are shared memory NUMA multiprocessors and using GPUs for general purpose computing.

What does "watch your arguments" even mean? It's just "Dont say anything I disagree with" with a threatening tone.

Thanks for this. RISC-V brings out the armchair critics for some reason.

Uh, pretty hard?

I love how there's a section called "The SuperML Take" when the whole thing is obviously written start to finish by Claude or GPT.

I'll save you a click: it'd be bad if you can no longer choose what underlying model to use in Cursor after the SpaceX acquisition.

Not worth the time to read it.

Well, VHDL was heavily based on Ada.

That's certainly an interesting data point, but it was a 90 minute programming contest, not peer-reviewed research.

They weren't exotic, they just weren't part of your writing style

The reason "--" autocorrects to an em dash in practically any word processing software (not talking about browsers) is that that's the accepted way to type it on a typewriter. And you don't need to go into any system settings to enable it. It came in around when things like Smart Quotes came in.

Complexity of the fab processes is isn't what the parent was talking about. They're talking about the major changes in the relationship between fabless semiconductor companies and commercial foundries.

The complexity of actual fabrication was always, and still is, entirely within the foundry. But in the early days of that model, designs could be more easily handed off at the logical level, leaving the physical design to back end companies, which makes designs much more portable between foundries. (The publisher analogy.) What's changed is that the complexity of physical design has exploded, and you can't make the handoff at nearly as high a level, and there is much more work that depends directly on the specific process you are targeting. Much more work at the physical level falls to the fabless semi companies. So it is much more work to retarget a design to a different foundry or process.

The site looks nice, but I think you'd benefit from having some beta testers who are not familiar with HW design already. I mention a few issues below, which I hope you take as constructive suggestions of how to improve the site, and not just as criticism.

It feels a bit like you are expecting completely inexperienced users, but the site doesn't quite anticipate their needs. Loading on mobile was not legible (which is fine, it's an early version.) Switching to the desktop version, the instruction for the initial design to "set" a bit is unclear. What is the function you want the user to implement? It's underspecified.

Further, there needs to be an explanation of what a testbench is, before you present a "Run" button, as well as an explanation as to what stimui the TB will present, and even the entire idea of Verilog simulation. It would be good to have an opportunity to see the testbench code and what the site expects the correct output to be; I didn't see an option for that. New users may not understand waveforms at all without an explanation.

The AI component is fine, but it feels a bit like all of the educational aspect has been delegated to the user to ask questions of the AI. A user who is inexperienced would not even know to use the word "testbench" is to frame their questions. I would suggest some careful thought as to who exactly your target audience is, and specifying early on what prior knowledge you expect them to have.

You are buried in the details. The guy is a hero who opposed a fascist takeover of the US government. He's not going to have any difficulty finding employment.

Yeah, this made me laugh. The chip industry spends literally billions of dollars each year on simulation and formal verification tools.

I had a CS professor as an undergrad who would teach a couple of advanced seminars in his own research area. His approach to those simplifications was to announce, "I'm going to lie to you now, but just go with it and I promise that later we're going to learn the real truth." I liked that as a compromise, to make some practical progress, but not to mistake the simplification for full understanding. (And he wasn't rigid about it -- if somebody would ask a deeper question he'd happily answer it to some level and then get on with his plan.)

According to this link, Paulo Coelho has a net worth of over $500 million and didn't get there by giving away books, so perhaps your example is not well-chosen.

https://www.nasdaq.com/articles/how-rich-are-jk-rowling-jame...

Pretty presumptuous to tell someone that they shouldn't be paid for their life's work, and then to tell them they should be happy someone pirated it. For the exposure!

At the top of the readme it says "There will be no attempt at making this synthesizable (at this time)!".

Yes, the site and the video are complete vaporware. But from the examples, it sounds they are targeting architectural and RTL-level design. There's no indication that they are trying to replace the physical design flow. So it wouldn't have any bearing on what foundry fyoure able to use to fab your chips. Anyone using this would be in a position no different than if they had hand-written their RTL.

I hope we get more concrete information on this. It's very concerning if verified, especially with the Spain and Portugal blackout being so recent.

Remote bricking has already happened on a small scale through normal internet connectivity: [Sol-Ark manufacturer reportedly disables all Deye inverters in the US](https://news.ycombinator.com/item?id=42279010) Installed inverters remotely disabled after a dispute between a contract manufacturer and a client. In the HN discussion from November there are comments from security-conscious and off-grid folks talking about how they protect their systems, and none of that would be effective if there's a hidden channel.

Do any of those techniques use unmodified DRAM or are you talking about processor-in-memory approaches?

PP above says working on a grounds crew was their favorite job ever. I think that's what they're talking about.

To allow the sender to set the TTL, right? Without adding another field to the packet header.

If you count up from zero, then you'd also have to include in every packet how high it can go, so that a router has enough info to decide if the packet is still live. Otherwise every connection in the network would have to share the same fixed TTL, or obey the TTL set in whatever random routers it goes through. If you count down, you're always checking against zero.

"Suárez, a 33-year-old native of Caracas, Venezuela"

is in the second sentence of the Mother Jones article. He is not a Salvadoran citizen, he's been sent to a third country by the US.

Here's the thing, there's never going to be convincing evidence for you to decide that it wasn't what your hunch said it was. That's the nature of suspicion.

You could Google "national plant services van" on image search and find similar vans, and that the company is owned by is the Carylon Corporation, with revenue of $300m/year -- but that couldn't convince you that a government agency (it wouldn't be the NSA unless they're violating the law) didn't borrow it or copy it.

You could read that their services include "Digital CCTV inspection. Laser profiling. Sonar pipeline inspection." but that couldn't convince you that the monitor+joystick and other equipment is needed for sewer inspection, because you already believe it is for surveillance. (The irony being that the kind of mass surveillance Mark Klein exposed, or Snowden exposed, means there's absolutely no need to park a truck outside someone's house. You can track who they're communicating with already, and you can subvert their own devices to listen in, instead of parking a van out front for their neighbors to notice.)

You could look at who has the contract to inspect sewers in your town -- it's public record. But you could still choose to believe that the federal government did the same check, and went out and got an identical truck so as to be less suspicious (although in this thread half the people are saying "that's too clean/fancy/technological to be a sewer inspection van!" so if they did it would have backfired.)

Was he under surveillance? Who knows. Does this truck prove anything either way? No. Everybody is going to leave this thread with whatever hunch they came in with.

This is really interesting just for the details on the microcode mechanisms inside the chip (and there's a link to similar research on Intel chips.)

Over on Android it's the opposite situation. The voice interface to Google Assistant was very reliable for simple things like reminders and appointments, and even for general knowledge questions. It was part of why I didn't switch to an iPhone. Then Gemini came along, and that core functionality got a lot worse.

Just to be clear that's a similar story about a different university (University of Pennsylvania vs. University of Pittsburgh).

The purpose of firing Inspectors General en masse is so that there are no independent overseers to investigate illegal or corrupt actions within the executive branch during your term in office.

Reversing it four years later is just too late.

There's a famous annotated version of Unix V6 that falls into this category. I heard that it had copyright issues for years, though. It'd be interesting to see people write more of these about open source code.

https://cs3210.cc.gatech.edu/r/unix6.pdf