Boost clock is application specific, there is no real GP100 boost clock. All we know is P100's boost clock.
antihelten, notice that you don't know real gpu boost clock for GP100. Nvidia says that GTX 980 Ti boosts to 1075 MHz but like you noticed, many of them boosts to ~1200 MHz
Performance relative to what? Ideally price would be based on cost. It's always based on perceived market value, though.
Yes.... This is why I refuse to buy those phones and only buy import phones from Korea and China. This is also why I push the Wasabi mango monitors and also bought xiamoi (whatever you know what company I'm talking about) headphones. Far better purchase than the headphones I have costing 10 times as much.This.
I wonder how many people here complaining about NV also own iPhones or Galaxy phones? Should those phones also decrease in price since new features are few and far between and the profit margins are 'too high'? They only cost $100 in materials, so is it criminal to sell it for more? A bunch of entitled-ists here!!
Anyway, back on topic.
Relative to previous/competing products? Remember, when AMD dropped prices on 290s? The price drop was certainly triggered by its poor performance and demand at the time. They may have sold some GPUs at near or even below their costs (I have no idea, though).Performance relative to what? Ideally price would be based on cost. It's always based on perceived market value, though.
Ideally price would be based on value not cost, otherwise there's no incentive for companies to reduce their costs.
Apple just launched their cheapest phone yet, with their latest chip inside, and you're giving them as example? The irony...I wonder how many people here complaining about NV also own iPhones or Galaxy phones? Should those phones also decrease in price since new features are few and far between and the profit margins are 'too high'? They only cost $100 in materials, so is it criminal to sell it for more? A bunch of entitled-ists here!!
Capitalism does not work if you reward companies for charging more while delivering less.
Nvidia isn't charging more while delivering less, they're charging the same ($500), whilst delivering more.
People are complaining because they want Nvidia to charge less whilst still delivering more, because they believe that Nvidia delivering more with smaller die sizes (and thus lower cost) entitles them to this.
Nvidia isn't charging more while delivering less, they're charging the same ($500), whilst delivering more.
People are complaining because they want Nvidia to charge less whilst still delivering more, because they believe (rightly or wrongly) that Nvidia delivering more with smaller die sizes (and thus lower cost) entitles them to this.
Any company charges more for less is either it has complete control of the market or the its CEO is nuts.
People want nVidia charge less for its products that AMD's equivalents are on par if not better. It has always been this case.
People give 2 shit about die sizes; the average consumer cares about 4 things: performance, brand, price tag and power consumption.
I think that the problem is that in the past, both companies charged the same while giving more performance in their next products. Because they are now charging more for more performance, the perception is that people are receiving less value for what they are spending. Whether that's fair or not, the perception is what drives opinions.
While on topic of IHVs poking. We are seeing big gains with async compute - just saying.
In the tech world brand is far more important than the other 3 sadly, otherwise 40nm where AMD only gained 50% share while being utterly dominant would never have happened.
Brand > Price > Performance > Power
What the hell are you talking about, both companies charge more for more. It is basic business.
Because the 7970 was neck and neck with the 680 at the time?
Yes, but I would argue that Performance has a HUGE impact on Brand, both positively and negatively. It just happens that positive impact takes a lot longer to achieve than negative impact (seriously, it only takes one or two missteps compared to the rest of the market to have your Brand severely hurt, but will take 4-5x as many positive events/wins to bring the Brand back up).
This I feel is part of the problem AMD is facing. Right now for them, it almost doesn't matter if they have competing products at their price/performance levels. If they don't have a high end product that beats Nvidia and don't have their driver updates as quickly with good performance for their new products at launch as Nvidia, their brand will continue to spiral downward.
So because the 7970 was neck and neck with the 680, $500 is more than $500. Awesome logic you got going there.
Because nvidia had to sell the 680 at similar price to the 7970? If the 7970 hadn't been that stellar then no doubt nVidia would put the $550 or even $600 price tag on it.
Both companies charge more for more and it's basic business. Do you have anything else to refute my argument?
How does Nvidia charging $500 for GTX 580 and then the same $500 for GTX 680 constitute them charging more? If anything Nvidia is charging less if you take inflation into account.
Since the last 3-4 quarters NV ships almost 80% of the total dGPUs, it sure looks like most of those that buy NV cards spending more money for the same or lower performance than AMD dGPUs are either sheeps or are uninformed.
ps. Those buying GTX980Ti know very well why they pay that much.
Keep the threadcrapping and flames like this out of these forums. Thank you. -Admin DrPizza
Is it still not obvious at this point? 680 was not a successor to 580, regardless of its moniker. It was successor to 560(Ti), but sold for 580 price. Then OG Titan was sold for 1000. Thats how Nvidia started to charge more. This was beaten to death several times.
And why was the 680 not the successor to the 580? Because you refuse to accept a 300mm2 GPU as the successor to a 500mm2? Because it doesn't have the right codename? Honestly I don't think Nvidia gives a crap about what people think the proper successor should or should not be, since at the end of the day it's their cards and their rules, if you don't like the new successor then just don't buy it.
Also I never made any claims about Titan not increasing prices, I simply said that nvidia did not charge more for the 680 than they did for the 580, and thus one cannot possibly claim that they raised prices when Kepler first launched. One could rightly make the claim that they brought a smaller performance improvement to the table than usual, but the prices stayed the same.
Maybe for the same reason why is not this year Mercedes E successor the last year´s S class?
You are clutching at straws with this same price thing. Its the die size and codename, what matters, when separating GPUs into product lines, not the marketing name.
You could indeed claim the actual performance is more important than die size, but funnily, these 2 are connected. If the relative perf difference between 680 and 580 was equal to relative difference between 580 and 285, 285 and 9800, etc... you would have an argument that die size does not matter. Except that did not happen. 680 was only cca 1,3x of 580, far cry from expected 2x. Unsurprisingly, it took 550 mm2 Titan to bring that performance jump. Which was priced at 1000.
So yeah, i am making that claim. Its the reason why 680 was not a successor to 580 and why it had no business to be sold at the same price. Well, it would have no business in ideal world, with proper competition. Clearly in this sad reality it sold pretty well. Be sure though, i did not buy it.
I agree with you that Nvidia does not give a crap. But they will keep hiking the prices and ultimately kill their own market altogether, cause the price of a new gaming PC will become outrageously high compared to consoles. Its already happening.