Live data from Hacker News

Parallella: A Supercomputer For Everyone is Dying

kickstarter.com

41–50 of 67 posts

Re: Parallella: A Supercomputer For Everyone is Dying

#41

It's a shame they're not making something useless like a video game. Then they'd have millions.

Video games is exactly where heterogenous computers like this have flourished. But they don't have a game to market it yet - historically it hasn't even mattered much if that initial game used the platform anywhere near well. How did the Ouya sell, for instance? (It really resembles a Nexus 7 with a broken screen.)

Re: Parallella: A Supercomputer For Everyone is Dying

#42
post #5

For some reason, I thought it relates to the concept of copying the brain of the dead to the computer so that they can live on as disembodied souls in the computer. It just turns out to be a kickstarter project for a powerful computer.

I'm embarassed to say the same. I had forgotten about this Kickstarter, so I thought this was some sort of MRI-supercomputer backup plan, like cryostasis.

Personally, I'd prefer to blame my mental auto-correct. So used to seeing poor / simple grammar mistakes on the internet, I'm in the habit of simply reading in the missing words. In this case, the title wasn't "Parallela: A Supercomputer for Everyone Who is Dying". Which makes this less interesting, but at least this could be real. And from the looks of it, it probably will be.

Re: Parallella: A Supercomputer For Everyone is Dying

#43
post #39

Could someone explain how this is different from GPU computing and regular multi-core CPU computing? I realize there is a difference...but I'm not quite sure I grasp it yet. GPU computing is a lot of parallel math computations with limited shared memory. I'm assuming the Epiphany CPU is more capable than the simple GPU math units? How's it different from multi-core CPUs? Just the sheer quantity of cores they have pac…

IMO this combines some of the worse features of Cell (e.g. local memory and DMA) and GPUs, and while the power efficiency is good the absolute performance is very low. For a parallel noob who's using OpenMP/OpenCL I don't think it's any better than a desktop PC because programming it is going to feel the same and performance is going to be equal or lower. And if you don't use the libraries then you're in low-level ni…

It's not meant to compete with a desktop PC, or with a mass produced GPU.

It's meant to be a development platform for solutions based on their architecture and for people to get familiar with the development model, with an existing 64-core version of their chip and future versions intended to put 1000+ cores on a board as the eventual target.

That it's also a reasonably capable platform to run Linux on (on the ARM chip) so you can do development directly on the board is an added bonus.

Re: Parallella: A Supercomputer For Everyone is Dying

#44
post #43
post #39

Earlier quoted context omitted.

IMO this combines some of the worse features of Cell (e.g. local memory and DMA) and GPUs, and while the power efficiency is good the absolute performance is very low. For a parallel noob who's using OpenMP/OpenCL I don't think it's any better than a desktop PC because programming it is going to feel the same and performance is going to be equal or lower. And if you don't use the libraries then you're in low-level ni…

It's not meant to compete with a desktop PC, or with a mass produced GPU. It's meant to be a development platform for solutions based on their architecture and for people to get familiar with the development model, with an existing 64-core version of their chip and future versions intended to put 1000+ cores on a board as the eventual target. That it's also a reasonably capable platform to run Linux on (on the ARM ch…

If the architecture is not good then people don't want to get familiar with it. I'm skeptical that even an "eventual" version with hundreds of cores would be worth using.

Re: Parallella: A Supercomputer For Everyone is Dying

#45
post #30

Could someone explain how this is different from GPU computing and regular multi-core CPU computing? I realize there is a difference...but I'm not quite sure I grasp it yet. GPU computing is a lot of parallel math computations with limited shared memory. I'm assuming the Epiphany CPU is more capable than the simple GPU math units? How's it different from multi-core CPUs? Just the sheer quantity of cores they have pac…

I've done my master thesis on GPGPU, so maybe I can help out a bit. I'm not yet too familiar with Epiphany's design however. From what I could grasp what sets them apart the most is a different memory architecture compared to multicore CPUs, where the individual cores seem to be optimized for accessing adjacent memory locations as well as the locations of the direct neighbors. This is one point where the architecture…

Assuming you're programming it in OpenCL, it's effectively a GPU with many more SMs but with a narrower SIMD width. If they were to give it, say, 16-way predicated SIMD with incomplete IEEE compliance on par with the Cell (~4M transistors per core plus a wider internal bus), it would become a very interesting processor IMO with ~1.4 TFLOPs per 64-core epiphany board. At the very least, they'd get bought out if they built such a beast and undercut NVIDIA, AMD, and Intel. Just sayin'...

In the meantime, leave the fast atomic ops, ECC, and full IEEE compliance to the GPUs and Xeon Phis of the world until you have the transistor budget to go after them...

All IMO of course...

Re: Parallella: A Supercomputer For Everyone is Dying

#46
I did my part. I'm very much the archetypal broke college student at the moment, but I won't always be. I have big plans in the Artificial Intelligence and Machine Learning sectors, and I can't imagine a better, cheaper solution to get started on working with multi-agent systems.

I desperately want to see this sort of pricing for cluster computing available in the future, when I have the scratch and knowledge necessary to make these ideas into products.

I think that future is worth skipping the occasional movie or meal to pay into, and I'm looking forward to my somewhat unexpected end of year gift.

Re: Parallella: A Supercomputer For Everyone is Dying

#48
post #2

Dying? At $612K of $750K raised with 31 hours to go? Is there something I don't understand there? EDIT: Realizing that mods might change the title at any time, it is right now "Parallella: A Supercomputer For Everyone is Dying"

According to kicktraq, they're indeed trending towards not making it (trending to 651k, 86% of goal):

http://www.kicktraq.com/projects/adapteva/parallella-a-super...

Post reply on HN