NVIDIA Announces GeForce GTX 480M Mobile GPU

Printable View

Show 100 post(s) from this thread on one page

05-25-2010, 12:10 PM
Sly Fox

I'm all for faster mobile gpu's, but Nvidia is gonna have their work cut out for them keeping the heat acceptable.

I'd like to have non-deformed sperm for at least a while longer! :D
05-25-2010, 12:19 PM
Sam_oslo

Quote:

Originally Posted by mk-ultra

lol the jokes went from slow,hot unmanufaturable to hot only :rofl:

LOL, yeah i remember that genius with insider info. He was insisting that GTX 258 would be the fastest nVidia GPU. Then was taking about a broken and unmanufaturable product. That genius doesn't dare to write in this forum any more, but many kids are still repeating his ideas and attitude.

There is not such a thing as a hot product, there is only bad cooling solutions in the world of OCers.
05-25-2010, 12:22 PM
Oberon

Quote:

Originally Posted by Sam_oslo

LOL, yeah i remember that genius with insider info. He was insisting that GTX 258 would be the fastest nVidia GPU. Then was taking about a broken and unmanufaturable product. That genius doesn't dare to write in this forum any more, but many kids are still repeating his ideas and attitude.

How man 512SP GF100s are there, again? ;)
05-25-2010, 12:29 PM
Jowy Atreides

Quote:

Originally Posted by Mats

Wanted: Lots of jokes about how hot it is and how much power it uses, maybe throw in "can it play crysis?" while you're at it, or a pic of a burning laptop. We just can't get enough of it.

Really.

http://img99.imageshack.us/img99/3921/1272001302169.jpg
05-25-2010, 12:32 PM
Sam_oslo

Quote:

Originally Posted by Oberon

How man 512SP GF100s are there, again? ;)

How knows, maybe they need time to fix the drivers, BIOS, yield, heat, power usage, or other stuff. But, and it is a big butt :slapass:. maybe nVidia doesn't feel the need for 512, at least as long as GTX 480 beats the 5870.
In my opinion, nVidia needs a double GPU to compete with 5970, not a 512 single GPU.

Why should they drop the 512 now, to compete with what you think?
05-25-2010, 12:38 PM
Jowy Atreides

http://img691.imageshack.us/img691/3149/16816179.png
05-25-2010, 12:42 PM
Sam_oslo

^^ you got something constructive to say, or just trying to be funny in the middle of a serious discussion? Grow up.
05-25-2010, 12:43 PM
BenchZowner

Quote:

Originally Posted by Oberon

How man 512SP GF100s are there, again? ;)

Come 485 September we'll find out ;)
05-25-2010, 12:45 PM
Jowy Atreides

Quote:

Originally Posted by Sam_oslo

^^ you got something constructive to say, or just trying to be funny in the middle of a serious discussion? Grow up.

There is no serious discussion, merely some light speculation.

What is said and happens in this thread will in no way affect anything of value.

Maturity is a three stage process.
1. Being too open and accepting situations that contradict your feelings of valour.
2. Becoming entirely unreasonable and controlling.
3. A mix of 1 and 2.

ie; grow up yourself and stop being stubborn, a mere calling on someone's bluff in a comical manner in a thread is entirely viable as a response.
05-25-2010, 12:51 PM
Sam_oslo

Quote:

Originally Posted by Jowy Atreides

There is no serious discussion, merely some light speculation.

What is said and happens in this thread will in no way affect anything of value.

Maturity is a three stage process.
1. Being too open and accepting situations that contradict your feelings of valour.
2. Becoming entirely unreasonable and controlling.
3. A mix of 1 and 2.

ie; grow up yourself and stop being stubborn, a mere calling on someone's bluff in a comical manner in a thread is entirely viable as a response.

Can't you catch the point that we are talking about the fastest Mobile GPU on earth?
What else would be serious enough to stop your childish pictures and funny comments? Got an example what you would consider as serious enough to act as a grown up?
05-25-2010, 01:02 PM
zanzabar

Quote:

Originally Posted by Sam_oslo

It was actually pretty fast, after all Fermi is just a few months old. Why should we call it "castrated Fermi"? nobody puts a full blown desktop GPU in a notebook. Maybe a flexible and scalable Fermi-architecture is making this possible so fast?

that dose not show flexibility a new chip would, this shows that it can be castrated, cutting those clusters out dose not help power consumption so its clocked lower and will suck up extra power for no reason.

Quote:

Originally Posted by Macadamia

Hmm, if the way they cut the units are the same...

0.7x core clock
~0.75x memory clock

So you get 0.8x (max) perf of a GTX 465, which itself like a GTX 285/275 or so...
GTX260 performance or so?

It will definitely be the fastest mobile GPU, no thanks to the anemic 128-bit memory interface of Juniper (you can't really clock RAM fast on notebooks). But the gap should be less than expected- about 15-20% more performance? For double the TDP...

I'm still seeing HP's Envy 15 (if it didn't have that many problems)/17 as the perfect notebook blend for the majority of gamers (who really game)- definitely enough graphics performance, without the heft or uglyness associated with a gaming notebook. These are just gonna sell way more than any Alienware/Clevo, so nVidia really needs a 20-40W lineup on Fermi soon, and hopefully GF104 is (part) of the answer.

But really, congrats to nVidia on making a 530mm2 chip fit with 100W cooling on a design, and actually selling it! ATI would have a hard time doing that for several reasons.

there is no chance of this beating the 5870m, the clock speed is to low and that low clock speed will make its texture processing way to slow like close to a mobile g92 but with more geometry like what a 260 original would have. there is no chance that it will compete with the 5870m. the 5870m is close to the 5770 so since the desktop 465 is slower than the desktop 5850 and the desktop 5770 isnt to far behind so with this massive clock down i would expect it to be bottleneck its self in the texture fill rate.

i will agree that its an accomplishment to get it sub 100W but i would expect that for the gpu not the platform.

we really need that new fermi die to bring the prices down, it should even match the stupidly giant die in performance with normal power and normal cooling
05-25-2010, 01:09 PM
Sam_oslo

Quote:

Originally Posted by zanzabar

that dose not show flexibility a new chip would, this shows that it can be castrated, cutting those clusters out dose not help power consumption so its clocked lower and will suck up extra power for no reason.

..

This is a new chip based on Fermi-architecture. I don't get what do you man by a new chip? maybe you want a new architecture?

By your logic all mobile GPUs should be called "castrated", but you are wrong, all mobile GPUs are new chips based on the respective desktop models.
05-25-2010, 01:10 PM
Jowy Atreides

Quote:

Originally Posted by Sam_oslo

Can't you catch the point that we are talking about the fastest Mobile GPU on earth?
What else would be serious enough to stop your childish pictures and funny comments?

Got an example what you would consider as serious enough to act as a grown up?

Beating down on someone you shall never meet, who will never have any relation to your power of choice in your physical life with vigour and distaste.

You're all very mature people. ;)

As much as all your 'talking' matters (which is nought considering none of you have responsibility for nvidia) why would a light-hearted and whimsical post emotionally influence you in a NEGATIVE manner?

Unless you have emotional boundary issues and can't stand the actions of others without trying to assert control.
05-25-2010, 01:12 PM
zanzabar

Quote:

Originally Posted by Sam_oslo

This is a new chip based on Fermi-architecture. I don't get what do you man by a new chip? maybe you want a new architecture?

By your logic all mobile GPUs should be called "castrated", but you are wrong, all mobile GPUs are new chips based on the respective desktop models.

wasnt this a physically cut down gf100, if it is a new chip that is not just a gf100 with parts disabled then i take my comment back, also its gddr3 so the 256bit bus is not an advantage over a 128bit gddr5
05-25-2010, 01:19 PM
ElSel10

Quote:

Originally Posted by Manicdan

is the chip going into the laptops really that big, just shut off pieces by lazer cuts or whatever the hell they do? i dont think i would want such a big chip in a laptop, takes up way too much space

IMO that is some pretty poor reasoning. Takes up too much space? Seriously? Are you the one designing and building the laptop? No, they are prebuilt with all space considerations already taken into account... What do you expect, it will prevent you from installing an extra memory stick or two? Maybe there won't be room for that TEC? :rolleyes:

Quote:

Originally Posted by Jowy Atreides

Beating down on someone you shall never meet, who will never have any relation to your power of choice in your physical life with vigour and distaste.

You're all very mature people. ;)

As much as all your 'talking' matters (which is nought considering none of you have responsibility for nvidia) why would a light-hearted and whimsical post emotionally influence you in a NEGATIVE manner?

Unless you have emotional boundary issues and can't stand the actions of others without trying to assert control.

Well dad, how about the quote in your signature? That sure is a mature and unbiased reflection of yourself.
05-25-2010, 01:20 PM
Sam_oslo

Quote:

Originally Posted by zanzabar

wasnt this a cut down gf100, if it is a new chip that is not just a cut down gf100 then i take my comment back

It is a mobile GPU, and all mobile GPUs are a form of cut down version of their respective desktop GPU. But you shouldn't mix it with a full blown desktop GPU and call it "castrated". It is a new chip based on the Fermi-architecture. It is very simple, and shouldn't need any explanation, actually.
05-25-2010, 01:20 PM
Helmore

Quote:

Originally Posted by zanzabar

wasnt this a physically cut down gf100, if it is a new chip that is not just a gf100 with parts disabled then i take my comment back, also its gddr3 so the 256bit bus is not an advantage over a 128bit gddr5

AFACT this is a castrated GF100, in other words, not a new chip. It's using GDDR5 and I actually think that it will be faster than the Mobile Radeon 5870, but not by a huge margin.
05-25-2010, 01:26 PM
-Sweeper_

HD5870M gives you the horsepower of a desktop HD57xx in 50 W

really, dont expect a GTX465 with core/shader clock reduced from 607/1215 mhz to 425/850 mhz to be very fast and power efficient :yepp:
05-25-2010, 01:26 PM
Xoulz

is it dx11 compatable..?
05-25-2010, 01:30 PM
stangracin3

Quote:

Originally Posted by Helmore

AFACT this is a castrated GF100, in other words, not a new chip. It's using GDDR5 and I actually think that it will be faster than the Mobile Radeon 5870, but not by a huge margin.

its not using GDDR5, its using GDDR3 for the fifth time. how many times do we have to say this. just go look at the memory bandwidth

1200 Mhz mem clock
76.8 GB/sec

you do the math and it = gddr3
05-25-2010, 01:30 PM
Sam_oslo

Quote:

Originally Posted by Helmore

AFACT this is a castrated GF100, in other words, not a new chip. It's using GDDR5 and I actually think that it will be faster than the Mobile Radeon 5870, but not by a huge margin.

It doesn't need to be hugely better, a little better would do!

Of course it is based on Fermi-architecture, what else would you expecting? but what would qualify as a a new chip in your book? Do you want a new architecture, gf15000 to call it new chip? This is not a desktop chip, it is a new Mobile chip.
05-25-2010, 01:32 PM
3NZ0

Quote:

Originally Posted by Xoulz

is it dx11 compatable..?

No, DX11 does not exist. Nothing supports it.

:D
05-25-2010, 01:33 PM
Boissez

Quote:

Originally Posted by Macadamia

Hmm, if the way they cut the units are the same...

0.7x core clock
~0.75x memory clock

So you get 0.8x (max) perf of a GTX 465, which itself like a GTX 285/275 or so...
GTX260 performance or so?

It will definitely be the fastest mobile GPU, no thanks to the anemic 128-bit memory interface of Juniper (you can't really clock RAM fast on notebooks). But the gap should be less than expected- about 15-20% more performance? For double the TDP...

I'm still seeing HP's Envy 15 (if it didn't have that many problems)/17 as the perfect notebook blend for the majority of gamers (who really game)- definitely enough graphics performance, without the heft or uglyness associated with a gaming notebook. These are just gonna sell way more than any Alienware/Clevo, so nVidia really needs a 20-40W lineup on Fermi soon, and hopefully GF104 is (part) of the answer.

But really, congrats to nVidia on making a 530mm2 chip fit with 100W cooling on a design, and actually selling it! ATI would have a hard time doing that for several reasons.

Why so? A desktop HD5770 has a TDP of 108W and is about equal to a GTX260 - therefore I don't really see any problems for ATI to match this. I do however doubt they'll do it. The 100W mobile GPU market is minuscule - and then you're probably better off with 2*60W mobility Hd5870 anyway.
05-25-2010, 01:41 PM
Sam_oslo

^^ The performance and TDP remains to be determined by hands on tests and reviews, but for now nVidia is claiming "Expect the fastest performance and visually-stunning graphics".
05-25-2010, 01:49 PM
Boissez

Quote:

Originally Posted by Sam_oslo

^^ The performance and TDP remains to be determined by hands on tests and reviews, but for now nVidia is claiming "Expect the fastest performance and visually-stunning graphics".

TDP is not determined by reviewers. And Nvidia proclaims so many things these days...

Show 100 post(s) from this thread on one page