Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Cray versus Raspberry Pi

aardvark.co.nz

Post reply on HN
Print view View original

131–136 of 136 posts

Re: Cray versus Raspberry Pi

#131

Post by pjmlp »

inkyoto wrote: post #117
anthk wrote: post #104

Earlier quoted context omitted.

Gear shifting it's still a thing in Europe, and mandatory if you want to get your driver's license.

At this point, it is a historical artefact that will cease to exist soon enough. Electric vehicles do not have gearboxes as there are no converters, so there is nothing to shift up or down. A few performance EV's that have been announced (and maybe even have released) with a gear stick, do so for nostalgic reasons and the gear shift + the accompanying experience is simulated entirely in the software.

At the rate EV are being sold in Europe, that soon enough is a couple of decades away.

I certainly don't plan to buy anything but hybrids, until EV prices and ranges are at comparable levels.

Our current hybrid has a six gear box.

Re: Cray versus Raspberry Pi

#132

Post by Tajnymag »

bigfatkitten wrote: post #71
kdndnrndn wrote: post #22

Earlier quoted context omitted.

I'm not aware of any optical mouse using a general purpose MCU, to my knowledge they are all using ASICs

There are millions, if not tens of millions of USB and PS/2 keyboards and mice out there powered by Cypress MCUs with 8051 cores.

That's a lot of cores

Re: Cray versus Raspberry Pi

#133

Post by lesny_ludek »

zelos wrote: post #121
inkyoto wrote: post #117

Earlier quoted context omitted.

At this point, it is a historical artefact that will cease to exist soon enough. Electric vehicles do not have gearboxes as there are no converters, so there is nothing to shift up or down. A few performance EV's that have been announced (and maybe even have released) with a gear stick, do so for nostalgic reasons and the gear shift + the accompanying experience is simulated entirely in the software.

The Porsche Taycan has two forward gears, but it's apparently the only EV that does: https://www.wired.com/story/electric-car-two-speed-transmiss...

New Mercedes CLA has that too

Re: Cray versus Raspberry Pi

#134

Post by jjkaczor »

BizarroLand wrote: post #124
dizhn wrote: post #32

Earlier quoted context omitted.

Kitt was funny though. (For its time)

For the time yes, but if I bought a car tomorrow and it had Kitt's sass I would cut his speakers in a week. I don't need my car to constantly whine, needle, harass, demean, and insult me.

Had the same thing happen when standalone GPS units were introduced to the mass market, I got one - and one of my tech friends suggested replacing the stock voice with a sarcastic/whiny one (maybe ... C3PO)...

My response was: "you obviously haven't used one yet"...

They were already bossy enough... 'MAKE A LEGAL U-TURN NOW!'"

Re: Cray versus Raspberry Pi

#136

Post by rahen »

fentonc wrote: post #111
rahen wrote: post #47

Earlier quoted context omitted.

No need for an RPi 5. Back in 1982, a dual or quad-CPU X-MP could have run a small LLM, say, with 200–300K weights, without trouble. The Crays were, ironically, very well suited for neural networks, we just didn’t know it yet. Such an LLM could have handled grammar and code autocompletion, basic linting, or documentation queries and summarization. By the late 80s, a Y-MP might even have been enough to support a small…

I think a quad-CPU X-MP is probably the first computer that could have run (not train!) a reasonably impressive LLM if you could magically transport one back in time. It supported a 4GB (512 MWord) SRAM-based "Solid State Drive" with a supported transfer bandwidth of 2 GB/s, and about 800 MFLOPS CPU performance on something like a big matmul. You could probably run a 7B parameter model with 4-bit quantization on it w…

This sounds plausible and fascinating. Let’s see what it would have taken to train a model as well.

Given an estimate of 6 FLOPs per token per parameter, training a 7B parameter model would require about 1.26×10^22 FLOPs. That translates to roughly 500 000 years on an 800 MFLOPS X-MP, far too long to be feasible. Training a 100M parameter model would still take nearly 70 years.

However, a 7M-parameter model would only have required about six months of training, and a 14M one about a year, so let’s settle on 10 million. That’s already far more reasonable than the 300K model I mentioned earlier.

Moreover, a 10M parameter model would have been far from useless. It could have performed decent summarization, categorization, basic code autocompletion, and even powered a simple chatbot with a short context, all that in 1984, which would have been pure sci-fi back in those days. And pretty snappy too, maybe around 10 tokens per second if not a little more.

Too bad we lacked the datasets and the concepts...

Post reply on HN