redshirt

Seems like if you want to migrate between big-little which they currently have then you can’t have things like differing avx widths…just a hunch.

Best decision we could have made. Wish it was done years ago. Only thing to do now is make darned sure we get out the people that helped the US and allies as quickly as possible. It’s not going to be easy, but it must be done.

But what about FPGAs or DSPs? I want one environment for all....

This is an utterly stupid move by ARM...if it's legit. Looks like it's a different domain registry than all the other ARM websites...not sure why, but that seems a bit fishy.

yes, it does.

I suspect there might be a wider market...we'll see. To keep costs down there would have to be a commercial pathway, but that'll probably mean just data center.

No need for paging for the most part with these. Current virtual memory systems won’t be able to deal...can’t wait to see what’s next.

Not surprising. Many “tech” companies enter the field with arrogance, thinking of course they can do health better. They unfortunately often have no comprehension of the regulatory regimes for the markets they enter and therefore the projects are doomed to failure before they start.

Found this after reading the tastes paper on front page. It’s the most fabulously long and complete GitHub issues post I’ve ever seen, almost a blog post in and of itself. I can definitely appreciate the details in the allocation process the authors of RaftLib have implemented after reading this. I’ve never seen garbage collection implemented in a dataflow framework before..actually, haven’t seen that many actual dataflow/channels implementations for C++...they typically die out quickly. Definitely going to check this out more.

Meh, for a retrospective paper, I think the authors probably provided more hints as to the future than they really needed to. I feel like they captured the exact reasons why ISA is so difficult to do right. As for “doing it wrong”, I didn’t take it that way. I think the authors lament the influence of what they seem to feel is a mantra that dictates the programmer must deal directly with the hardware versus providing a sufficiently abstract ISA. Building circuits for ML accelerators, etc. is actually damned easy, exposing those to the programmer in a portable way that does not require rearchitectng the program every time you change the accelerator is tough. I literally loathe porting for Intel b/c the AVX insn behave differently and are essentially architecting in the microarch, passing the complexity directly to the programmer. I’d much rather the Risc-V solution or the ARM solution.

One point the authors make is that registers are memory. I’m not sure they’re saying screw registers, just that they’re counter to portability and in general only a yet faster cache for programs to use. The other point they seem to make is that a secondary reason we have architected registers is that renaming over an arbitrarily large space was (and in some ways is still) difficult. By using graph coloring and reg allow in compiler, we narrow the encoding space before execution and give the hardware a much simpler problem. Recent research results on register less arch show that there are quite a few benefits. There’s a lie in calling it registerless though, it’s still there, just transparent and hence portable.

The problem with the US Social Security trust fund is that it's misnamed. It should be called the giant equity stash that the US Government can convert to bonds and borrow against. The fund should be flush with cash, however, that'd be fibbing. It would be flush with cash, if it weren't borrowed against for other things in one form or another. For example, the GW, Reagan, and Clinton used this to their benefit. src: http://www.nytimes.com/2005/03/08/politics/at-heart-of-socia... Given that these were bonds, the payments will come due back to the trust fund in one form or another....I'd suspect financed with more debt.

Motley Fool predicted something was up back in 19 December 2017 -> https://www.fool.com/investing/2017/12/19/intels-ceo-just-so...

Nothing like this should have ever made it into hardware. It's lazy implementation (or performance at the expense of security).

Exactly, break them apart while they still can.

The nice clean dependency graph is pretty cool. Not having tabs and spaces as an integral part of syntax, priceless.

Problem with RISC-V is exactly what makes it strong. The lack of verified software ecosystem will keep it from being main stream for at least a decade(something that until recently has held back the Arm server market, well, that and not having a reasonable server core..fixed with the ThunderX2). The fact that you can add instructions quickly is another problem, well, that and the lack of a standardized verification suite for the ISA so that software devs know that implementations are up to spec when they write code for them. I can definitely see RISC-V accelerators taking off though, driven by a more stable x86/Arm/Power core. To me, that path for RISC-V makes a lot of sense.

I'm waiting for Intel to divest of either the arch/micro-arch business or the fab business. They can invest in one or the other, but what is crippling them is having to invest in both simultaneously. I can definitely see them doing something like HP and split off into Intel-Fab and just Intel. Would enable the arch/micro-arch to use all the fabs and allow the fab to focus on what it does best, processes research and development. Intel already fabs chips for other people (https://www.forbes.com/sites/jeanbaptiste/2013/10/29/exclusi...) why not expand that relationship to maximize their profits/capacity.

This is entirely to lacking an optimized version for the new aarch64 instruction set. Similar problem noted in Go benchmarks awhile back, see 100x speed up here: https://blog.minio.io/accelerating-sha256-by-100x-in-golang-...

Yes. I recently mentioned to my partner how many days I have left in the form of sunsets. Not that many when we think about it. You know what, I approach everything with that attitude and make the most of what little time we have. That includes re-reading number theory books in my spare time :).

Very cool. I'm adding this to my list of easy concurrency tools. The main thing I like is the statelessness. That's where most people screw up parallel programs.

Seems like there are many languages/libraries trying to make concurrency easier to implement in practice. Most notably for C++ (my fav since I have to use it for most of my work projects): Intel TBB (definitely the go to for most things), RaftLib (saw at C++Now last year) is probably the easiest to understand (same theme as this post, super easy concurrency for c++). Even Java seems to make concurrency rather easy with it's thread pools and relatively strait-forward synchronized sections.

From a technical standpoint it’s far easier to be net neutral than throttle traffic which takes processing power, energy, and programmer time to do so. This is entirely about the ISPs making yet more money.

When will America wake up and realize that it is living with a government bought and paid for. It is an oligarchy, plain and simple. Screw the consumer, wanna repair something in America, I hope you have a degree in electrical engineering and are good at micro soldering. Are you sick, want healthcare, hah, good luck if you’re poor. Wanna lodge a complaint against somebody, file charges for a crime? First thing police will do is ask the address and then they’ll go...hmm, that’s the rich neighborhood, excuse me ma’am we need more evidence that a crime was actually committed, if it’s a poor neighborhood they’ll just go shoot somebody or lock them up for good. This is America, the Idiocracy for rent. I’m being sarcastic, but at this point, you know what, when I watch the news it seems quite true.

Yup. Same for code that looks unused :). Very good advice. Sometimes fences can come down, sometimes they make better neighbors.

I’d skip protobufs too. They’re horrible for performance. Many data center apps blow more cycles there than on compute. For actual applications where performance is necessary, binary “strict” formats are he only way to go. Protobufs are nice for ease of use, but they’re horrible otherwise.

How about not buying stuff with poor packaging. Sure, sometimes we don’t have a choice, but many times we do. Often it’s as simple as preparing food at home versus getting take out. I’d prefer laws to mandate recycleable packaging. Problem solved. Petrochemical industry will be ticked.

You know, if the us federal government can’t get its stuff together, why not? It’s not a bad thing.

Seems like Germany had this one figured out. One non-recyclable thing found in your building’s garbage and you’re all in trouble. The US is way too lax on enforcing good practices. We waste too much, and when we do feel good recycling drives we do it lazily.

> you've likely had positive experiences with research as an undergraduate.

This guy is really really out of touch with reality. People that go get PhD’s are driven. I know many that had entirely shit experiences with undergrad research, horrible advisors, but new what they wanted and were darned determined to get it.

>Also, you've been a good student in school, scoring at the top of your class on exams and projects. And you've probably been praised throughout childhood for being a smart kid.

Umm, hmm. This is actually a problem. He’s looking for less diverse, vanilla, 1% kids. Sure, the entrance criteria are smart kids with good grades. Likely the best and most driven will be the scrappy ones from really odd backgrounds with few “projects” of official nature and even fewer actual undergrad research experiences. I hate people like this that walk the walk of “diversity” but then they go off and try to find the exact same as themselves, silver spoon kids of academics. If you look at the really successful people, they have some really interesting and truly diverse backgrounds. Just my .02

If you want to get a PHD, do it because you love learning, teaching, are extremely creative and have tremendous follow through. Are you a person that constantly thinks, “why am I here?” The. Get out and find a job, it’s not worth it.

Actually, just ordered one. https://www.avantek.co.uk/store/avantek-32-core-cavium-thund... They’re pretty easy to find these days. Soft iron has a desktop box too.