Just a thought, if there's some way that you could have a chat sidebar during these live blogs, that'd be awesome. I'd love to be able to see everyone else's reactions and discuss as it's all happening.
Talking about Volta, when we know next to nothing about Maxwell is stupid. And we dont even know if Kepler will be followed by a Kepler refresh, or a series derived from GK110. Its the usual vagueness and pomp that Nvidia is good at.
Maxwell is Kepler with significant enhancements to how memory is addressed. Basically nVidia's version of AMD's HSA. I'd expect Maxwell to come in two variants: x86 focused and ARM focused for mobile.
Volta is creating buzz on the merit that stacked DRAM is going to be a massive jump in bandwidth and a likely a small reduction in latency.
Pretty much everything else about Maxwell and Volta will be the traditional increases in parallelism and clock speed new process nodes have permitted.
Talking about T5 and T6, when we dont even know if T4 will be present in any Smartphone or not. Or when will it finally start appearing in actual devices.
The bottom Line is the money coming into the company. Show me the money ! The NVDA stock is stuck in the Tegra 3 mode and cannot move up & it is holding the stock price at $12.50 for 2012-2013. Nvdia Stock has become like $0.05 to $.20 daily trading vehicle. All these technologies are great, BUT it is the CEO who needs to show the market the tractions of Tegra Parker, new businesses, B2B and passing Qualcom & Intel with the Speed of GPU on stroid.
I'm not convinced we actually need dedicated GPUs for each user or application. That's good for NV to sell many GPUs, but yields almost no load balancing. GK110 already can run many "threads" (as in threads for a CPU) in parallel. Instead of 8/16 GPUs all of the same size I imagine something like this to be cool:
A few, say 2 to 4 massive GPUs ala GK110 accompanied by many small ones. Apps / users can be put onto the small ones by default. however, if they require actual horse power their tasks can be shifted to the big guns quickly (it's internal PCIe, after all), and back afterwards. And one big GPU should be able to crunch through several medium-duty tasks with that parallel feature of GK110.
I can't help compare this presentation to the Samsung mess last week. Jen-Sun is in charge, the products are genuinely exciting, clearly the work of brilliant people.
yeah because that's what makes a great presentation from a CEO, incredibly detailed tech slides. Add to that a couple of them with CUDA code and you'll reap millions of hit on you tube.
Here it comes, hardware you can own but you can't use without a subscription. What a F****** wonderful disaster.
NVIDIA GRID: after spending $40,000 on the hardware... ... you then have pay $5,000 a year to be allowed to use it.
:::I can see the retort coming: "but that's for supporting the hardware... blah blah blah"::: to that I say... okay, fine. Offer an optional "support package" for $5000.
--------------------------------- This pricing will just cause serious people to look elsewhere for similar (read way more powerful) solutions at better prices.
So that's how they're making their designer cars on the fly over "car cad" ... and the rest of us will wait for 20 years before the public roll out - where you custom out your new car at the dealer lot using the computer cloud interface terminal.
We’ve updated our terms. By continuing to use the site and/or by logging into your account, you agree to the Site’s updated Terms of Use and Privacy Policy.
Facebook
Twitter
RSS
22 Comments
Back to Article
PrayForDeath - Tuesday, March 19, 2013 - link
Had no idea this was a thing. What kind of news are we expecting?mayankleoboy1 - Tuesday, March 19, 2013 - link
Hey guys, did you meet with the reporters from Tomshardware ?RetroEvolute - Tuesday, March 19, 2013 - link
Just a thought, if there's some way that you could have a chat sidebar during these live blogs, that'd be awesome. I'd love to be able to see everyone else's reactions and discuss as it's all happening.mayankleoboy1 - Tuesday, March 19, 2013 - link
Talking about Volta, when we know next to nothing about Maxwell is stupid.And we dont even know if Kepler will be followed by a Kepler refresh, or a series derived from GK110.
Its the usual vagueness and pomp that Nvidia is good at.
Kevin G - Tuesday, March 19, 2013 - link
Maxwell is Kepler with significant enhancements to how memory is addressed. Basically nVidia's version of AMD's HSA. I'd expect Maxwell to come in two variants: x86 focused and ARM focused for mobile.Volta is creating buzz on the merit that stacked DRAM is going to be a massive jump in bandwidth and a likely a small reduction in latency.
Pretty much everything else about Maxwell and Volta will be the traditional increases in parallelism and clock speed new process nodes have permitted.
mayankleoboy1 - Tuesday, March 19, 2013 - link
Talking about T5 and T6, when we dont even know if T4 will be present in any Smartphone or not. Or when will it finally start appearing in actual devices.ziedaniel1 - Tuesday, March 19, 2013 - link
What? Piz Daint isn't even close to the tallest mountain in Switzerland, in either elevation or prominence. Compare http://en.wikipedia.org/wiki/Piz_Daint and http://en.wikipedia.org/wiki/Monte_Rosa.varad - Tuesday, March 19, 2013 - link
You might want to get rid of the . at the end of your 2nd linkMez Toofan - Tuesday, March 19, 2013 - link
The bottom Line is the money coming into the company. Show me the money ! The NVDA stock is stuck in the Tegra 3 mode and cannot move up & it is holding the stock price at $12.50 for 2012-2013. Nvdia Stock has become like $0.05 to $.20 daily trading vehicle. All these technologies are great, BUT it is the CEO who needs to show the market the tractions of Tegra Parker, new businesses, B2B and passing Qualcom & Intel with the Speed of GPU on stroid.tipoo - Tuesday, March 19, 2013 - link
All I could think about the whole time was that during the Volta slide it looked like he had a jetpack on. Therefore:http://techreport.com/r.x/2013_3_19_Nvidias_Volta_...
tipoo - Tuesday, March 19, 2013 - link
http://i.imgur.com/Hl16dYY.jpgMrSpadge - Tuesday, March 19, 2013 - link
I'm not convinced we actually need dedicated GPUs for each user or application. That's good for NV to sell many GPUs, but yields almost no load balancing. GK110 already can run many "threads" (as in threads for a CPU) in parallel. Instead of 8/16 GPUs all of the same size I imagine something like this to be cool:A few, say 2 to 4 massive GPUs ala GK110 accompanied by many small ones. Apps / users can be put onto the small ones by default. however, if they require actual horse power their tasks can be shifted to the big guns quickly (it's internal PCIe, after all), and back afterwards. And one big GPU should be able to crunch through several medium-duty tasks with that parallel feature of GK110.
MrSpadge - Tuesday, March 19, 2013 - link
BTW: I know, step 2 after step 1.. :)watersb - Tuesday, March 19, 2013 - link
I can't help compare this presentation to the Samsung mess last week. Jen-Sun is in charge, the products are genuinely exciting, clearly the work of brilliant people.mayankleoboy1 - Wednesday, March 20, 2013 - link
And as long as you dont give much tech detail, (and concentrate on great visuals and marketing keywords,) you will dod fine.maximumGPU - Wednesday, March 20, 2013 - link
yeah because that's what makes a great presentation from a CEO, incredibly detailed tech slides. Add to that a couple of them with CUDA code and you'll reap millions of hit on you tube.colonelpepper - Wednesday, March 20, 2013 - link
Here it comes, hardware you can own but you can't use without a subscription.What a F****** wonderful disaster.
NVIDIA GRID: after spending $40,000 on the hardware...
... you then have pay $5,000 a year to be allowed to use it.
:::I can see the retort coming: "but that's for supporting the hardware... blah blah blah":::
to that I say... okay, fine. Offer an optional "support package" for $5000.
---------------------------------
This pricing will just cause serious people to look elsewhere for similar (read way more powerful) solutions at better prices.
Stuka87 - Wednesday, March 20, 2013 - link
This is par for the course when it comes to enterprise grade hardware. Everything has a license fee and has for many many years. This is not new.Art< - Wednesday, March 20, 2013 - link
That`s will be biggest "gun" in virtual war - "Cuda cores and Time".With that CUDA power any password wont be a problem to hack in couple days.
Pontius - Thursday, March 21, 2013 - link
Cool story, bro.Let me know when they stop not-so-subtly snubbing OpenCL. Titan drivers anyone?
CeriseCogburn - Friday, March 22, 2013 - link
So that's how they're making their designer cars on the fly over "car cad" ... and the rest of us will wait for 20 years before the public roll out - where you custom out your new car at the dealer lot using the computer cloud interface terminal.martixy - Monday, March 25, 2013 - link
Watched the replay. It was actually pretty cool.I was even thinking about getting a box like that... then he announced the price and I was forcibly returned to reality.