ATI RV740 review/preview

When it was happening for gpu's with the same architecture, ie 8xxx and 9xxx series, I was sort of OK with it. But now they are selling stuff with a new name which is supposed to have minor but definite changes to the architecture(DP/better coalescing/warp voting/better atomics), so IMHO, this particular rebrand is deceptive marketing.
 
Hey, maybe we can look forward to a top-to-bottom GT3xx launch in the autumn on 40nm. That would be awesome.

Jawed
 
GTS250 is reducing 50% power consuption at hidle and load? :LOL::LOL:
Dude you must be dreaming.


Miss read his statement, at half the price and power reduction, it means half the price with some power reduction.


As far as DX_10.1 I remember ATI had 4 partnerships for new games with DX_10.1 suport. You have deal with Blizard also and Win 7 takes advantage of DX_10.1 on Aero Peak.


Q3 right? ;)

Also DX_11 will incorporate DX_10.1 and Tesselation, so by DX_11 time this ATI GPU can enable features of DX_11.


The tesselator of ATi's current gpus is a sub set and won't give the full benefits of DX 11 tesselation.

Nvidia + New = :LOL:
This days be careful to what you buy from Nvidia. In case you don´t know GTX280 and GTX260 mobile are G92 based and not GT200 based.
This is equal that you are eating the same crap again.


Blame ATi too they have been doing that quite often

The only chip @40nm taped out for now was GT218 witch is the very low low end.
The other chips are in one unknown state.


you were already wrong about the gts 250 being the same stuff as the 9800 gtx + and you are wrong, again about nV 40nm transitions, stop reading the Inq.
 
Another:


http://www.dailytech.com/article.aspx?newsid=14480

I rest my case about who is early or late to 40nm when ATI is kicking RV740 in 1 month in desktop + mobile.


Thats the same rumor from the INQ, there is another reason for this, a financial one, which at this time definitly fits in with what is going on. Its stupid to think a chip is designed for "65nm", well if they drop a full node, the chip has to be redesigned again.
 
Thats the same rumor from the INQ, there is another reason for this, a financial one, which at this time definitly fits in with what is going on. Its stupid to think a chip is designed for "65nm", well if they drop a full node, the chip has to be redesigned again.

Yeah that sounds like a shot in the dark. We'll know for sure whether or not they had issues with 40nm if GT218/6 show up in the next few months.
 
They should have maintained the name 9800GTX and lower the price to compete. Renaming it just have one effect: make consumers confused to buy the "new video card".

I think it actually has the opposite effect.

Consurmers displaying the level of ignorance you're suggesting could quite easily have thought a 9800GTX+ is faster than a GTX 260. Afterall, its a higher number and has a plus on the end, some SKU's even have more memory.

Renaming it to a GTS 250 though leaves no room for misinterpretation. Its obviously slower than a GTX 260. NV are simplifying their product lines naming scheme while at the same time, removing the (in this case unjustified) stigma of purchasing a "last generation" product.

If that last generation product lacked features that the new generation had, or it was slower than its name suggested then we would have a problem. But thats not the case here. The GTS 250 whether its based on a 128sp G92b or a 128sp GT2xx (aka: slightely tweaked G92b) produces exactly the same result for the consumer. In fact, you could argue its better for the consumer to be based on G92b since it can be priced lower thanks to the relative lack of R&D costs to recoup.
 
Miss read his statement, at half the price and power reduction, it means half the price with some power reduction.

Half the price?
Someone is dreaming no?
You can buy today one 9800GTX+ 512Mb for 145$ + rebate 10$= 135$
http://www.newegg.com/Product/Product.aspx?Item=N82E16814130339

Half the price means that GTS 250 = 73$ without accounting rebate. Give me that price to shop and I get one just now.

Let's cut the crap ;)



Razor1 said:
you were already wrong about the gts 250 being the same stuff as the 9800 gtx + and you are wrong, again about nV 40nm transitions, stop reading the Inq.
I have being wrong that GTS250 = 9800GTX+ ?
Where have you being dreaming or what?
Open any review and the first thing you read is GTS250 = 9800GTX+ ;)
Do I need to put reviews quotes?

40nm for Nvidia the sources are plain and simple and multiple. RV740 is around the corner for 6 April ;)
GT218 that was told to be taped out and in good conditions was supposed to be in this schedule:
VR-Zone managed to score a GT218 card drawing which should give us an idea how the actual card might look like. Nvidia is working on the entry level GT218 cards currently and we will probably see some samples during CeBIT in March and a launch in April.
http://vr-zone.com/articles/nvidia-gt218-card--specs-surfaced/6529.html?doc=6529

We are in Cebit where are the samples? ;)
 
Consurmers displaying the level of ignorance you're suggesting could quite easily have thought a 9800GTX+ is faster than a GTX 260. Afterall, its a higher number and has a plus on the end, some SKU's even have more memory.

Exactly. The dumb consumer argument holds no water at all because they'll be dumb regardless.
 
Another:
According to our sources, NVIDIA's attempts to produce a die-shrunk 40nm GT200 chip were "disastrous at best". Design problems became evident, since the GT200 was originally designed for the 65nm node. Two shrinks in a row without a major redesign was just too much for NVIDIA, and our most recent information from Taiwan is that the first 40nm chips from NVIDIA will be in the GeForce 300 series.
I rest my case about who is early or late to 40nm when ATI is kicking RV740 in 1 month in desktop + mobile.
And a very weak case it is...

I love these kind of statements from gossip sites. They're so very easy to dismiss even if they sound juicy and are gefundenes fressen for the uninformed masses.

There is no such thing as "a redesign was just too much", at least not for technical reasons. There is nothing particularly hard about shrinking a design from one process to the next. I've seen cores with quite a bit of custom logic shrink from 0.25um to 110nm. It could have gone down further but the market finally wanted something different. The fact that you cross process nodes increases the effort in terms of effort, sometimes, but it doesn't become "too much". (In some cases, the effort goes down: a custom multiplier may get replaced a synthesized when your process gets faster.)

There are many very good reasons not to shrink a design, but "a shrink too much" as a technical explanation is BS. There are no reasonable explanations for it.
 
Yeah that sounds like a shot in the dark. We'll know for sure whether or not they had issues with 40nm if GT218/6 show up in the next few months.

40nm parts were supposed to be on the market in march, then it became "behind closed doors" at cebit Then it became Q2 and now it's Q3. Why would nvidia take CeBit of ALL exhibitions to introduce their rebadged products and let the 40nm parts miss the limelight?

AMD would have looked immensely weak if they just put out that one sheet claiming the first to market with 40nm if nVidia had parts at cebit.
 
Half the price?
Someone is dreaming no?
You can buy today one 9800GTX+ 512Mb for 145$ + rebate 10$= 135$
http://www.newegg.com/Product/Product.aspx?Item=N82E16814130339

Half the price means that GTS 250 = 73$ without accounting rebate. Give me that price to shop and I get one just now.

Let's cut the crap ;)

Ok I'll spell it out for you, Launch Price :), so you don't want to look at the power anymore? How about 1/4 of the price of the original 9800 gtx.

40nm for Nvidia the sources are plain and simple and multiple. RV740 is around the corner for 6 April ;)
GT218 that was told to be taped out and in good conditions was supposed to be in this schedule:

http://vr-zone.com/articles/nvidia-gt218-card--specs-surfaced/6529.html?doc=6529

We are in Cebit where are the samples? ;)

Internal sechedules shifted for other reasons, if this card is released in the next 2-3 months after inventory of G9x's are depleted, what would you say then? You do know this card is not trageted at the gts 250, and 240 lines, its actaully lower.
 
And a very weak case it is...

I love these kind of statements from gossip sites. They're so very easy to dismiss even if they sound juicy and are gefundenes fressen for the uninformed masses.

There is no such thing as "a redesign was just too much", at least not for technical reasons. There is nothing particularly hard about shrinking a design from one process to the next. I've seen cores with quite a bit of custom logic shrink from 0.25um to 110nm. It could have gone down further but the market finally wanted something different. The fact that you cross process nodes increases the effort in terms of effort, sometimes, but it doesn't become "too much". (In some cases, the effort goes down: a custom multiplier may get replaced a synthesized when your process gets faster.)

There are many very good reasons not to shrink a design, but "a shrink too much" as a technical explanation is BS. There are no reasonable explanations for it.

can you explain about the library changes though, I was under the impression that would cause a redesign of the entire chip?
 
Ok I'll spell it out for you, Launch Price :), so you don't want to look at the power anymore? How about 1/4 of the price of the original 9800 gtx.

You are comparing prices from 2007 to 2009?
Don't make up things. Here we are discussing the renaming from 9800GTX+ -> GTS250.

But if ATI didn´t pull out RV770 you can be sure that you should be still paying the same 2007 prices... like 300$ for the super new GTI, XXX, FTW GTS250 wow amazing.
 
Both ATI and NVidia have tried this 'renaming' malarkey a number of times in the past. The only reason for such renaming is to try and get more money in from a chip by hook or by crook and it will only ever confuse the consumer. I'm sure, despite all their protests to the contrary, both companies are more than happy if they make more sales due to consumer confusion.

As such, both IHVs should attract suitable opprobrium for their renaming antics and, in this case of a twice-renamed card, double opprobrium for NVidia.
 
You are comparing prices from 2007 to 2009?
Don't make up things. Here we are discussing the renaming from 9800GTX+ -> GTS250.

But if ATI didn´t pull out RV770 you can be sure that you should be still paying the same 2007 prices... like 300$ for the super new GTI, XXX, FTW GTS250 wow amazing.


Ok 9800 gtx+ launch price was $229, the launch price of the 250 gtx 512 is $125, now we are just nitpicking
 
Ok 9800 gtx+ launch price was $229, the launch price of the 250 gtx 512 is $125, now we are just nitpicking

Wrong. 9800GTX+ where projected to launch @ 229$ but with HD 4850 selling for 199$ Nvidia was forced to do the same.
By that time Nvidia made multiple price drops almost every week in G92 and GT200 GPU´s.

And GTS250 512Mb is projected to 129$.
We are far from 50% because in this price segment every dolar count. For more 30$ you buy one HD 4870 and for less 30$ you get one 9800/9600GT.
 
Both ATI and NVidia have tried this 'renaming' malarkey a number of times in the past. The only reason for such renaming is to try and get more money in from a chip by hook or by crook

But why shouldn't they? Its a chip thats perfectly suited to the marget segment that its being positioned in. If people are shying away from buying it simply because it *sounds* outdated compared to a the GT2xx series then I see no harm in renaming it. In effect its a quick and simple re-education of the uninformed public that this chip is indeed what they are looking for in that price segment, they just didn't realise it before.

and it will only ever confuse the consumer. I'm sure, despite all their protests to the contrary, both companies are more than happy if they make more sales due to consumer confusion.

I don't see how the following:

GTS 240, GTS 250, GTX 260, GTX 280

Is more confusing than:

9800GT, 9800GTX+, GTX 260, GTX 280

Why do you think an ignorant consumer would be less confused by the lower naming scheme?
 
Wrong. 9800GTX+ where projected to launch @ 229$ but with HD 4850 selling for 199$ Nvidia was forced to do the same.
By that time Nvidia made multiple price drops almost every week in G92 and GT200 GPU´s.

And GTS250 512Mb is projected to 129$.
We are far from 50% because in this price segment every dolar count. For more 30$ you buy one HD 4870 and for less 30$ you get one 9800/9600GT.


I got to get back to work but, yes $129 sorry about that, but still you are nitpicking with 44%, AMD did the same thing now as they did with the 9800+ price drop. nV will most likely drop prices to fit along with what is out there, unlike before though, these cards are equally matched, when the 9800+ came out they weren't, the 4850 actually had a performance lead at the time.
 
Back
Top