Seems obvious that we need some type of SETI model
Would you all mind lending your Apples, PCs, and phones to the US government - they have some real work to do? If you don't mind, it might involve targeting missiles and other fun things.
New storage technologies are needed for exabyte-munching exaflop supercomputers. The same-old-same-old disk tech used for supercomputers won’t do for the exaflop generation promised by President Obama’s US leadership supercomputing order. This is Obama’s moonshot, the equivalent of President Kennedy’s man on the moon vision …
One of the fun things might be to process all that data the NSA has collected... and once they cut back, process all the data they get from what the 5-eyes will collect and give to them. There has to be a serious amount of data there.... possibly even more than "aerodynamic testing".
Micron's new crosspoint memory may have a place in the sun here, at 1000x faster than flash. Package it in Hybrid Memory cube modules close to the DRAM/CPU/GPU complex and that is a screamingly fast solution - timeframe to able to do that is about 3 years which is when real money starts getting spent on the new super.
Note that HMC could be touching 1 TB/s bandwidth for DRAM in that timeframe, and that's per CPU/GPU module.
NVMe may form the second tier memory, but it really isn't enough on its own. The data has to go to networked storage, so compression accelerators are needed to get the data rate down, assuming there is reasonable compressibility in the data. Then we'll need some rally fast networks to move data out.
Dear Prez. Obama,
I hear the Chinese are doing great things in supercomputing and are even developing their own chips. Perhaps we could ask them if they could sell us a few of those.
mkay thx bye,
Eddy
1) Do you really think Obama writes a up a shopping list? He is handed a letter to sign by some gremium of sages.
2) He doesn't even mention 3D TLC flash: announcement
3) That the stuff around the tech has to be designed appropriately should be obvious to the meanest intelligence
In the end this is just another "industrial policy" effort like the 80's "Strategic Computing Initiative" (this one is even called "National Strategic Computing Initiative" again) which started as response to Japan's Fifth-Generation Computer project but veered off into supercomputing and weapons technology within 2 years. More here: Strategic Computing Initiative and Book Reference. It is very unclear whether this is going to help one way or the other or from where the money is going to come from given the parlous, if not cancerous, state of finances with the next recession looming. There will be bailouts to push...
The reason the moonshot had a lasting spinoff was that it engaged thousands of kids who got hooked on a fantastic dream about the capabilities of technology.
The late 1960s saw model lunar modules hanging from the ceiling in every second kid's bedroom. Tens of thousands of kids walked around on Halloween dressed up in tin foil space suits.
What are the exabyte generation going to hang from their ceilings and do for Halloween costumes?
Until you can engage a population like that, you won't get a long term benefits.
How is that going to help?
Plus it is not about "figuring out part of". It's about the existence of smooth solutions. This has nothing to do with computation or even practical applicability. And you will have to await a mathematical mind, prize money or not. Maybe Terry Tao will have a lucky break in solving a it?