The EU Is Funding Work Into Low-Power GPU Tech

[phoronix]

Phoronix: The EU Is Funding Work Into Low-Power GPU Tech

LPGPU is a new research initiative funded by the European Union to explore low-power GPU technologies...

http://www.phoronix.com/scan.php?page=news_item&px=LPGPU-Low-Power

[tessio]

Where's Imagination? Ah.. it's UK based..

[starshipeleven]

My 7th and 8th senses are tingling a lot here.

[Azrael5]

it's right.

[bug77]

Money down the drain, most likely.

[schmidtbag]

This is an inevitable failure. It's not that their goals are bad, but they're pointed in the wrong direction:

http://lpgpu.org/wp/project-overview/

These demands cannot be met through hardware improvements alone, but the software must fully exploit the available resources. Unfortunately, application developers are seriously hindered when creating low-power GPU software by the limited quality of current performance analysis tools. In low-power GPU contexts there is only a minimal amount of performance information, and essentially no power information, available to the programmer.

As software becomes more complex it becomes increasingly unmanageable for programmers to optimise the software for low-power devices.

Shouldn't they be focusing more on fixing the software issues? Creating another hardware platform is not going to fix this, because they somehow have to convince people to use this hardware instead of anything from any competitors. If anything, the problem will only get worse, since they dividing attention even more. Had it not occurred to them that one of the primary reasons it is difficult for developers is because there are too many varying products?


Shouldn't the EU be spending this money on more important things, like Greece's or Spain's debt situation, or refugees?

[davidbepo]

This is an inevitable failure. It's not that their goals are bad, but they're pointed in the wrong direction:

http://lpgpu.org/wp/project-overview/

Shouldn't they be focusing more on fixing the software issues? Creating another hardware platform is not going to fix this, because they somehow have to convince people to use this hardware instead of anything from any competitors. If anything, the problem will only get worse, since they dividing attention even more. Had it not occurred to them that one of the primary reasons it is difficult for developers is because there are too many varying products?


Shouldn't the EU be spending this money on more important things, like Greece's or Spain's debt situation, or refugees?

you are very right, but this money its much less than the required for solving spain debt problem

by the way im spanish

[starshipeleven]

This is an inevitable failure. It's not that their goals are bad, but they're pointed in the wrong direction:

http://lpgpu.org/wp/project-overview/

Shouldn't they be focusing more on fixing the software issues? Creating another hardware platform is not going to fix this, because they somehow have to convince people to use this hardware instead of anything from any competitors. If anything, the problem will only get worse, since they dividing attention even more. Had it not occurred to them that one of the primary reasons it is difficult for developers is because there are too many varying products?

Please try to read better lol. This project's goal isn't about creating hw but about tackling the issues you just mentioned. Even Micheael mentions this in his article. From the same link you posted, a few lines below what you quoted.

This project proposes to aid the application developer in creating software for low-power GPUs by building on the results of the first LPGPU project by providing a complete performance and power analysis process for the programmer. This project will address all aspects of performance analysis, from hardware power and performance counters, to a framework that processes and visualises information from these counters, to applications that will be used as use-cases to drive the entire design.

They intend to make some kind of performance and power analysis tool to help devs find issues in their software.

Shouldn't the EU be spending this money on more important things, like Greece's or Spain's debt situation, or refugees?

This is less than "pocket change" level of funding, dealing with PIGS debts (Including Italy and Portugal, that's the acronym used) or "solving" the refugee situation requires a completely different scale of funding.


What is debatable is why the fuck the EU needs to be involved in this stuff that isn't even relevant in the slightest to anything the EU is supposed to work on. Might as well go and fund AMD to make a better CPU or for someone to rewrite Linux kernel in Rust or whatever.

[Toboe]

What is debatable is why the fuck the EU needs to be involved in this stuff that isn't even relevant in the slightest to anything the EU is supposed to work on. Might as well go and fund AMD to make a better CPU or for someone to rewrite Linux kernel in Rust or whatever.

Imho, it seems relevant to furthering the scientific and technological bases of the EU.
Sure, not something where I'd say "If it doesn't do that, it is absolutely failing its tasks" but still, reasonable for it to do that.

[coder]

What is debatable is why the fuck the EU needs to be involved in this stuff that isn't even relevant in the slightest to anything the EU is supposed to work on.

They do plenty of basic R&D funding, like what the US used to do more of. It generally has a good multiple of return on investment, and it's often not the kind of research the industry will do. Granted, this is getting a bit away from basic R&D, much closer to applications. It's still pocket change, though.

Venture capitalists invest in dozens of startups for every one that's wildly successful. I think R&D grants can be viewed in a similar way. Maybe not every one delivers a good return on investment, but as the aggregate result is good, that's what matters. In that sense, I think they do much better than VC's.

As a non-EU citizen, it's not really for me to say whether or how they should invest in future economic development, but I think it should be seen in that light. Do you also take issue with ESA and CERN?