Nvidia Pascal GPU to Feature 17B Transistors and 32GB HBM2 VRAM • Hacker News Board

Re: Nvidia Pascal GPU to Feature 17B Transistors and 32GB HBM2 VRAM

#91

Post by blinkingled » Sat, Jul 25, 2015, 2:03 PM UTC

rasz_pl wrote: post #88

blinkingled wrote: post #5

AMD get it together, pretty please. Nobody wants to live in a world where only NVidia produces discrete GPUs! That 32GB seems too high for cost constrained consumer market though - may be they will have a leaner variant for desktops/gaming.

Funny you say 'AMD get it together', because its AMD who designed HBM in the first place. Just like it was AMD who pioneered GDDR5 in graphic cards. This article you just read is typical Nvidia "we are the best .. in 2 years, you just wait!!1". They produced same charts, slides and test results before releasing Tegra, Tegra2 and Tegra3. Every time it was supposed to revolutionize industry and beat competition, every…

I meant AMD get it together financially, of course AMD is to be thanked for lot of things including AMD64!

Re: Nvidia Pascal GPU to Feature 17B Transistors and 32GB HBM2 VRAM

#92

Post by bryanlarsen » Sat, Jul 25, 2015, 2:33 PM UTC

x3sphere wrote: post #28

bryanlarsen wrote: post #17

Earlier quoted context omitted.

It could be argued that AMD does have it together. If you look at the benchmarks for pretty much any particular price point, AMD & nVidia cards are roughly comparable. AMD is better at some games and resolutions, and nVidia is better at others. Rarely is the difference more than 10%. nVidia used to have a sizable power/noise advantage, but Fury appears to close that gap. AMD even seems to be closing the driver stabil…

As someone who has bought AMD cards for the past 5 years for gaming, I switched over to Nvidia this time. You've overlooked that Maxwell / 980 Ti has a ton of overclocking headroom. OC to OC, you're looking at 20-30% performance difference at more commonly used resolutions like 1440p and 1080p. The gap narrows only at 4K. Voltage is locked on Fury right now and AMD isn't saying why. The best OC I've seen on one is 10…

You're illustrating my point. You're OC'ing the cards (which the vast majority of consumers don't do), but even after taking that step there's only a 20-30% gap (and less at the more important resolution of 4K). That's a significant difference, but it's not huge. But it's winner-takes-all -- there's no reason to buy even a slightly inferior card.

Re: Nvidia Pascal GPU to Feature 17B Transistors and 32GB HBM2 VRAM

#93

Post by kozukumi » Sat, Jul 25, 2015, 4:18 PM UTC

rincebrain wrote: post #64

kozukumi wrote: post #54

Earlier quoted context omitted.

I don't think you could get 16GB SO-DIMMs until earlier this year could you? I know you can get 32GB in a W550s which is probably the thinnest/lightest laptop capable of 32GB.

Can you? I have a W550s and didn't see anyone hocking 16GB SODIMMs even earlier this year.

Yeah a colleague ordered one about 2 weeks ago. Lovely machine and Lenovo have done an amazing job with the weight. I still prefer the T series over the W series as I don't need that much power and prefer the much lighter machine.

Re: Nvidia Pascal GPU to Feature 17B Transistors and 32GB HBM2 VRAM

#94

Post by bbitmaster » Sat, Jul 25, 2015, 4:19 PM UTC

chillingeffect wrote: post #84

sidrajaram wrote: post #66

Earlier quoted context omitted.

The current deep dreaming fad is going to last about one more week before everyone gets sick of looking at those stupid pictures. They really serve no purpose other than "look how crazy this stuff is" - deep learning is cray-cray.

any thoughts on why all the current pix look like dog faces? Is that peculiar to the training set? Also I think there's a bit more than just ZOMGtrippy. The whole project points out that "if you're looking for it, you'll find it." The system amplifies noise until it sees something familiar. Understanding that humans do this too (to a point), is a critical point in comprehension and discussion of the world, opinions a…

The reason you mostly see dog faces is only because everyone seems to be running the default code google posted. It optimizes layer 4c, which seems to be biased to producing dog faces. Running the code on other layers, or other networks produces other things. They also recently posted code where you can provide a "guide" image to guide it to producing features that are in that image.

I'm thinking that using CNNs to generate or change images could be a huge game changing technology. It could potentially be bigger for hollywood than 3d graphics. In 10 years, we could see this stuff everywhere, albeit in a more developed state. It would be used to actually transform or enhance images in a more directed way.

Re: Nvidia Pascal GPU to Feature 17B Transistors and 32GB HBM2 VRAM

#95

Post by CyberDildonics » Sat, Jul 25, 2015, 5:06 PM UTC

largote wrote: post #71

CyberDildonics wrote: post #69

This is not a real site, they have a review from 4 months ago benchmarking a 990 Ti 24GB card with 'minesweeper' and 'solitaire'.

Was that review written on April 1st?

It must have been. They mixed in it with all their other headlines and the date was '4 months ago' so it wasn't labeled April 1st. All their other stories are shaky rumors so I thought the whole site was joke articles predicting extrapolating the next press release.

Re: Nvidia Pascal GPU to Feature 17B Transistors and 32GB HBM2 VRAM

#96

Post by varelse » Sat, Jul 25, 2015, 8:53 PM UTC

CHY872 wrote: post #79

varelse wrote: post #55

Earlier quoted context omitted.

GTX 580: 585M transistors GTX 680: 3.5B transistors GTX Titan: 7.1B transistors GTX 980: 5.2B transistors GTX Titan X: 8B transistors Core i7-5930k: 2.6B transistors What the data above suggests to me is that relying solely on Moore's Law to predict performance is a fool's errand. Going forward, process transitions are obviously slowing down and IMO victory will go to those who make the best use of the available tran…

Just to nitpick, backwards compatibility isn't really a huge issue for Intel. Most of the really old stuff that's a pain to maintain can be shoved in microcode; compilers won't emit those instructions. There are obvious downsides to the architecture, but the need to be backwards compatibility shouldn't hurt it too much. GPU workloads are very different in that generally you don't have to look particularly hard to fin…

"CPUs are super restricted by the single threaded, branching nature of the code you run on them, and this is what makes CPU performance a little more nuanced, and not directly comparable."

Ironically, to really hit peak performance of a modern AVX2 or later CPU, you have to embrace many of the design principles that lead to efficient GPU code:

1. Multiple threads per core to make use of the dual vector units introduced in Haswell

2. SIMD-like thinking to remap tasks into the 8-way and soon to be 16-way vector units

3. Running multiple threads across multiple cores

4. Micromanaging the L1 cache and treating the AVX/SSE registers as L0 cache

Where the CPU prevails is for fundamentally serial algorithms that cannot be mapped into a SIMD implementation. Mike Acton's Data-Oriented Design covers this case nicely IMO.

Re: Nvidia Pascal GPU to Feature 17B Transistors and 32GB HBM2 VRAM

#97

Post by jfb » Sun, Jul 26, 2015, 3:59 PM UTC

nitrogen wrote: post #77

jfb wrote: post #61

Earlier quoted context omitted.

That was my point. If all you do is read what passes for news on gamer sites, you might think that the discrete GPU overclocking market was important.

The notion that only the biggest of something is "important" is offensive and wrong.

Sure. I'm a fan of esoteric hardware and software and no big believer in the market success equalling virtue religious ideology, but I'm also not the one invested in the importance of how well this memory stick performs overclocked in Gamer Game IV: Games.