sifar

>> rather than something more like the difference between programming GPUs and CPUs.

Again, I get your point, but you are really trivializing HW design here and I don't want anyone starting or migrating from SW to get a wrong impression that you can just pick it up. Sure, with enough thought, patience, skill and hard work anyone can do it - but that applies to anything. But don't expect that just because you know Scala or are a good parallel programmer, you can design good HW that is PPA competitive. You have a better shot than others, but that's it.

>> Stuff runs in parallel. You occasionally have to know about really hardware things like timing and metastability. But the venn diagram of hardware/software design skills is pretty much two identical circles.

I don't know your background, but this feels like from someone who hasn't worked on both the aspects for a non-trivial industry project. The thing is software spans a huge range - web FE/BE, GUI, Database, networking, os, compiler, hpc, embedded etc. Not all of them have the same background to be a good HW designer. Sure you can design HW as if you are writing software, but it won't be production worthy - not when you are pushing the boundaries.

My work straddles both HW architecture and SW. I design processors, custom ISA optimized for SW application algorithms, and ensuring optimized micro-architecture implementation on the HW side to meet the PPA. I sit at the intersection of HW, SW and verification. People like me are rare, not just in my company but in the industry. Things fall through the gap, if you don't have someone to bridge it and then you have a sub-optimal design.

I don't deny that SW people cannot learn HW design, there is nothing magical after all; just hardwork and practice. But to say that the venn diagram is two identical circle is plain wrong. The cognitive load to shuttle up and down the two HW/SW stacks is a lot more than either of them.

And what happens when these different objectives conflict or diverge ? Will it be able to figure out the appropriate trade-offs, live with the results and go meta to rethink the approach or simply delude itself ? We would definitely lose these skills if it continues like this.

Gell-Mann Amnesia strikes again. It feels strange - almost as if Asimov hated Orwell. So many personal attacks.

And I say this as fan of Foundation/Robot series.

Despite quoting below from Fromm's afterword, how does Asimov miss it ? "Books like Orwell's are powerful warnings, and it would be most unfortunate if the reader smugly interpreted 1984 as another description of Stalinist barbarism, and if he does not see that it means us, too."

" Orwell was unable to conceive of computers or robots, or he would have placed everyone under non-human surveillance. Our own computers to some extent do this in the IRS, in credit files, and so on, but that does not take us towards 1984, except in fevered imaginations. "

Now apply this to many of today's experts/billionaires/technical celebrities whose words matter but are in reality quite myopic.

Multiplication can be sub-quadratic using Karatsuba's algorithm.

Same here, looking for an excuse to use it. It takes some time to get oriented. The BSV fronted makes it easier though. Have been dabbling in it as a hobby on the side.

While there have been tape-outs by universities, I think the learning curve would discourage traditional hardware companies focused on TTM. While bluespec has higher level abstractions, it also provides access to low level HW optimization features like multiple/gated clocks, integrate verilog etc. so I don't see any hindrances.

One needs to be familiar with both using SW abstractions and HW design, which iss a small subset that limits it's usage.

RVV defines add/sub with carry.

But the scam is still the same.

Well, the wisdom part is true.

That work is an opportunity cost that you could have used in taping out new designs.

I was referring to the general zeitgeist on the site rather than you specifically. Apologies if it seemed personal.

My point is that the discrimination to flag one and not the other seems arbitrary. It has nothing to do with promoting/preserving intellectual curiosity etc. We are deluding ourselves by repeating that.

In that we are practicing the very doublethink we criticize in the society.

>> Computers are more accountable. You just pull the plug, wipe the system.

I think you are anthropomorphizing here. How does a computer feel when unplugged ? How would a computer take responsibility for its' actions ?

>> I think a useful litmus test for these kinds of stories is: do the people who most actively participate on them believe there's a conversation to be had, with multiple perspectives, not all of which agree with theirs? That's what this site is for.

This would disqualify more than half of AI/LLM/<insert_tech_person> stories. This seems like a cope out. It is our inability as tech people to embrace the discomfort that is not rational and engage with it.

Exactly. It subrly hints at the limitations of language in capturing true understanding.

This is something I was impressed with. Almost every other ancient text starts of being full of certainty or being the authoratitve truth.

I am really surprised by this. While I know it can generate correct SIMD code, getting a performant version is non trivial, especially for RVV, where the instruction choices and the underlying micro architecture would significantly impact the performance.

IIRC, Depthwise is memory bound so the bar might be lower. Perhaps you can try some thing with higher compute intensity like a matrix multiply. I have observed, it trips up with the columnar accesses for SIMD.

Yet geopolitics gets discussed.

You cannot isolate technology from forces that shape and harness it. It is fine to restrict political discussion lest it overwhelm other more fruitful discussions, however burying one's head in sand while the society is being "engineered" is not the mark of a curious person.

" “Foreign persons” is broadly defined in the bill as any person who is not a United States person. However, the bill does not include “any corporation or partnership organized under the laws of a possession of the United States” in that definition of foreign person. "

Most offshoring companies don't pay directly to individuals - either they are employees of their own subsidiaries or those of offshoring entities. So, this is not going to change anything.

History indicates regulation always trails corporate accountants.

By telling yourself it is ok to feel this way and going back to things you are good at, things that you love and people you care about and enjoy being with. Also exercise - that works.

There is nothing to overcome. These feelings rise up sporadically. Acknowledge and move on.

Nested concolutikns, dilated convolutiona both can pull in data from further afar.

>> 2) expertise to develop code

This is wrong. Paradoxically, you need expertise to develop code with LLM.

And one thinks these things haven't been happening in other countries where one wishes to move?

What the GP is probably trying to say is that what the US is going through at present has been the default state for most of the developing world. And these things have been eroding in many of the western democracies for the past decade. Those that have been able to preserve it may not be more attractive in culture, geography or economic terms.

Hence the entitlement part where I think the people in the US took for granted what they have/had. We always realize the true value of something when we don't have it.

It is not clear though, which tools enable and which tools inhibit your development at the beginning of your journey.

What I have come to realize is that, at a societal level, no amount of rational discourse will counter the fear/emotional response. If it were, the world wouldnt' be in the state it is today.

Only time, reality shock or meeting a proportionate external force are the antidote. And even these can be stretched via the constant propaganda drip.

There is a great Charles Mackay quote applicable here: "Men, it has been well said, think in herds; it will be seen that they go mad in herds, while they only recover their senses slowly, and one by one."

You and the article's position about not ignoring his views are both right.

One cannot ignore his views (for the reasons stated) and yet there needs to be a feedback loop to limit the spread of their views using their wealth and influence.

That's an infinite loop.

What is also an example of stunning ignorance here is that a corporation (and by extension capitalism) cannot exist without the laws and the coercive power of the government to enforce them. One can argue a government is whoever can enforce rules for markets to function.

This, I think is the heart of the lie that people miss. Which leads to myths being established that companies/markets are something different from governments and not an extension.

>> The world in this view is a finite pie

But it is. The physical world is finite, with finite resources, human greed not so.

I think people stop at nothing matters or there is no meaning. So either one can be depressed about it or if one takes a step further, if nothing matters/things don't have a meaning, great, then I can focus on stuff that matters to me, gives meaning to me and people around me at large.