Friday, October 15th 2010
NVIDIA to Counter Radeon HD 6970 ''Cayman'' with GeForce GTX 580
AMD is undertaking its product development cycle at a breakneck pace, NVIDIA trailed it in the DirectX 11 and performance leadership race by months. This November, AMD will release the "Cayman" GPU, its newest high end GPU, the expectations are that it will outperform the NVIDIA GF100, that is a serious cause for concern, for the green team. It's back to its old tactics of talking about GPUs that haven't even taken shape, to try and water down AMD's launch. Enter, the GF110, NVIDIA's new high-end GPU under design, on which is based the GeForce GTX 580.
The new GPU is speculated to have 512 CUDA cores, 128 TMUs, and a 512-bit wide GDDR5 memory interface holding 2 GB of memory, with a TDP of close to that of the GeForce GTX 480. In the immediate future, there are prospects of a more realistic-sounding GF100b, which is basically GF100 with all its 512 CUDA cores enabled, while retaining its 384-bit GDDR5 memory interface, 64 TMUs, and slightly higher TDP than that of the GTX 480.
Sources:
3DCenter.org, PCGH
The new GPU is speculated to have 512 CUDA cores, 128 TMUs, and a 512-bit wide GDDR5 memory interface holding 2 GB of memory, with a TDP of close to that of the GeForce GTX 480. In the immediate future, there are prospects of a more realistic-sounding GF100b, which is basically GF100 with all its 512 CUDA cores enabled, while retaining its 384-bit GDDR5 memory interface, 64 TMUs, and slightly higher TDP than that of the GTX 480.
195 Comments on NVIDIA to Counter Radeon HD 6970 ''Cayman'' with GeForce GTX 580
Also there is interest in the product and the capabilities, if anyone saw the GTC, there's a lot of actual companies using Fermi for amazing things and you can see they are getting ostensible benefits from the use of it**.
So i think that's something that can only grow, at least for the next 2-5 years and is a good way to become relevant in something more than the volatile gaming crowd and I think that's something investors care for, so they should be at least semi-happy.
I said semi-happy, because yes it could have been better, but it's been good so far. Also the new Quadro cards kick FirePro cards in the arse big time (50%-100% faster), and the professional GPU market has been the only segment of the semiconductor market that has seen an increase since the recession I believe, so any superiority in that market should put at least half a smile in investor's face IMO.
Reminder for fanboys:
* It took I think 15 years of attempts and 3-4 different chips to Intel and AMD to enter these same market, so think twice before trying to underestimate this achievement.
** We are talking about CEO from companies with really big names that have revenues 10 to 50 times higher than Nvidia and would eat them for lunch if they were hungry, so please Ati fanboys and general trolls, refrain from the typical "he's been paid to say that" that seems so unavoidable for some of you you to say whenever a developer of any kind praises anything Nvidia does.
I can smell lowered 4Q revenue coming.
AMD's release is critical. WTF do you tihnk there's no real concrete info ut yet, so close to release?
:laugh:
As if there is any other reason.
:rolleyes:
I cant say much... i already have but like I said 2 yrs ago I have blood working in Toronto.
Troy tells me there isn't going to be issues with drivers like the 5 series drivers has,... that's all :pimp:
Wow :eek:
One thing is clear, the most clever investors (though of a different type) sold Nvidia shares MONTHS ago, just after shares topped out and started falling. Anyone who still has Nvidia shares now and sells them now, it's plainly stupid. Period.
fallen stock=sunk cost. people want to hold on to stocks that fell in hopes of earning their money back. in this case it paid off, in some most cases.
I have lots of investments in stock. The mentality you describe is what a lot of recent "Wall Street losers" have done recently. The parameters of logic in the market changes, it is not constant. Going by one set of logic in a time when the market does not go with that logic is a bad move. When the market is flat like it is right now, one should concentrate on long term and safe stocks. Bad time to sell like the rest of the sheeple have been doing. There is no quick money to be made right now.
In a short time may be a good time to buy Nvidia stock. Now is a great time to buy AMD stock.
EDIT: OR in the best case you end up like Erocker said, exchanging long term for long term. The reason that what I said above happens is psycological actually. People that sell because shares have been falling for several months, also typically only buy shares that have been on the rise for several months, so there's nothing to be made there, they are always 2 or 3 steps behind. Most usually they buy sell, 2 months away from the change, so they lose either money or their time and effort.
In any case, I never said that it's not best to sell when they start falling, but after many months of falling shares the only smart thing is to hold on, again unless you are 100% sure that you are going to profit from another one, which is never the case. You should never put all your eggs in one basket anyway, so having some not profiting for a few months shuld never be a problem. If you do, well you are a bad investor to begin with.
The best investors in the Forbes list almost ALWAYS sell when the shares are still growing (just before the fall) and buy shares when they are low and still falling. Investing is all about having balls, balls to say: this is enough profit, time to invest into the next "sinking boat".
AMD fanboys scream the loudest. I just want to see GPU tech progressing. TBH with architectural changes like we see in Fermi display much better innovation and especially for its use in scientific research. I know most don't think of this, but curing diseases through GPU tech is much more important than FPS or power consumption. Nvidia is doing fine with FPS but needs to go a little greener if possible. I like both companies. Hate is never a good thing guys.
For the past decade or more since i stopped using 3dfx after my 3500-tv (yes i was a bit of a 3dfx fanboy back then but i was a teenage bear give me a break :p) i have been constantly swapping between nvidia and ati all depending on what they can give me for the money i can spend, everyone should love both companys as even if they both do things that annoy people (renaming, rebranding, fail with software now and then, etc) in the end we win as we keep getting insane ammounts more comute power each generation recently and is that not what we all want?
I'm always looking forward to every new release like right now i am excited abut the next year for kepler and southern islands, bulldozer and sandy bridge, i will never really care who makes them it's all about what they can do, i just wish everyone else could think in a simmilar way (yes i know things like support and drivers effect why people like specfic companys but those are things that constantly change with new product cycles).
*end early morning coffee lacking rant* :laugh:
I don't expect nvidia to bring out anything that awesome untill they start on 28nm chips, i just hope they can release them close to amd's 28m gpu's so that there is no stupidly long waiting time to see what both are like to make a good choice.