Hacker Newsnew | past | comments | ask | show | jobs | submit | zzzoom's commentslogin

Because most ARM SBCs are still limited to whatever linux distro they added support to. Intel SBCs might underperform but you can be sure it will run anything built for x86-64.

Why would the market jump from one proprietary ISA to another proprietary ISA?

Ask Apple.

Apple's A4 was launched 4 years before RISC-V.

So what? Are you suggesting that Apple would have switched to RISC-V?

I like RISC-V (it's my job and I'm very involved in the community) but even now it isn't ready for laptops/desktop class applications. RVA23 is really the first profile that comes close and that was only ratified very recently. But beyond that there are a load of other things that are very much work in progress around the periphery that you need on a laptop. ACPI, UEFI, etc. If you know RISC-V, what does mconfigptr point to? Nothing yet!

Anyway the question was why would anyone switch from one proprietary ISA to another, as if nobody would - despite the very obvious proof that yes they absolutely would.


> They could make a systolic array TPU and software, perhaps. But it would mean abandoning 18 years of CUDA.

Tensor cores are specialized and have CUDA support.


Tensor cores can help a lot for matrix maths, sure, definitely. They made a big splash in 2017 & have been essential. https://developer.nvidia.com/blog/programming-tensor-cores-c...

But it's still something grafted onto the existing architecture, of many grids with many blocks with many warps, and lots and lots of coordination and passing intermediary results around. It's only a 4x4x4 unit, afaik. There's still a lot of main memory being used to combine data, a lot of orchestration among the different warps and blocks and grids, to get big matrices crunched.

The systolic array is designed to allow much more fire and forget operations. It's inputs are 128 x 128 and each cell is its own compute node basically, shuffling data through and across (but not transitting a far off memory).

TPU architecture has plenty of limitations. It's not great at everything. But if you can design work to flow from cell to neighboring cell, you can crunch very sizable chunks of data with amazing data locality. The efficiency there is unparalleled.

Nvidia would need a radical change of their architecture to get anything like the massive data locality wins a systolic array can do. It would come with massively more constraints too.

Would love if anyone else has recommended reading. I have this piece earmarked. https://henryhmko.github.io/posts/tpu/tpu.html https://news.ycombinator.com/item?id=44342977


Yeah, Whatsapp is probably the largest moat in the world atm.


What matters is that the US' number keeps growing.


It hasn't. It's been down since 2007 despite increased population.


The article is literally about how it grew this year.



That's per-capita. China is by far the biggest polluter overall, and it is still increasing.

https://ourworldindata.org/explorers/co2?country=CHN~USA~IND...


Wouldn't you expect the country with the most manufacturing and one of the biggest population to also have the biggest pollution?

I feel you'd need to adjust the sum total by something, capita, or square footage or be more specific like does a manufacturing X in China pollute more than an equivalent one in the US, etc.


How about adjusted for GDP, which would measure efficiency of carbon use in output: https://en.wikipedia.org/wiki/List_of_countries_by_carbon_in...

China is still about double the US, and the US is lower than Canada.


Hum... GDP doesn't seem right to me.

Not all goods and services involve the same process, some come with more pollution.

For example, Nvidia will contribute to a big chunk of US GDP, but it only designs the chips, which won't have the same pollution impact as the country in which they'll have it manufactured.


Hum... I bet anything that criticizes China over the US won't seem right to you


Not at all, but it just feels like the emperor's new clothes if we just pretend we're doing better and aren't objective.


Doesn't really make sense in my opinion. Why boycott a specific group of people for their collective emissions when their individual emissions are lower than many others? The latter is the important metric, else you're simply punishing them for having a large population.


Don't worry, if you catch any disease you can use any antibiotic that still works after spraying farmed salmon willy-nilly for years.


Antibiotics only work on live bacteria, and only sometimes. "Any disease" is a much broader category.


Any disease you'd catch from lab-grown meat...


Does web-to-app tracking through localhost on Android that is illegal under GDPR count?


Did they intentionally lie about it? Parent post didn't claim Meta has never broken a law.


Lying by ommission is still lying.


I think they're talking about a standalone bidet.


You can use a mop if your aim is that bad.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: