ATI RV740 review/preview

Discussion in 'Architecture and Products' started by LunchBox, Feb 25, 2009.

  1. rpg.314

    Veteran

    Joined:
    Jul 21, 2008
    Messages:
    4,298
    Likes Received:
    0
    Location:
    /
    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.
     
  2. mczak

    Veteran

    Joined:
    Oct 24, 2002
    Messages:
    3,016
    Likes Received:
    112
    Oh, sounds pretty bad. Not sure though on the two shrinks, 65nm -> 55nm is just a optical shrink (half node). I thought pretty much everybody could handle these painlessly (though nvidia seemed to have problems with even that, any ideas why?
    I wonder though what the trouble is they are facing from transitioning to 40nm. Too much custom design for easy transition?
     
  3. Jawed

    Legend

    Joined:
    Oct 2, 2004
    Messages:
    10,873
    Likes Received:
    767
    Location:
    London
    Hey, maybe we can look forward to a top-to-bottom GT3xx launch in the autumn on 40nm. That would be awesome.

    Jawed
     
  4. Razor1

    Veteran

    Joined:
    Jul 24, 2004
    Messages:
    4,232
    Likes Received:
    749
    Location:
    NY, NY

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



    Q3 right? ;)


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


    Blame ATi too they have been doing that quite often


    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.
     
  5. Razor1

    Veteran

    Joined:
    Jul 24, 2004
    Messages:
    4,232
    Likes Received:
    749
    Location:
    NY, NY

    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.
     
  6. trinibwoy

    trinibwoy Meh
    Legend

    Joined:
    Mar 17, 2004
    Messages:
    10,492
    Likes Received:
    515
    Location:
    New York
    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.
     
  7. pjbliverpool

    pjbliverpool B3D Scallywag
    Legend

    Joined:
    May 8, 2005
    Messages:
    7,583
    Likes Received:
    704
    Location:
    Guess...
    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.
     
  8. v_rr

    Newcomer

    Joined:
    Apr 30, 2007
    Messages:
    147
    Likes Received:
    0
    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 :wink:



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

    We are in Cebit where are the samples? ;)
     
  9. trinibwoy

    trinibwoy Meh
    Legend

    Joined:
    Mar 17, 2004
    Messages:
    10,492
    Likes Received:
    515
    Location:
    New York
    Exactly. The dumb consumer argument holds no water at all because they'll be dumb regardless.
     
  10. silent_guy

    Veteran Subscriber

    Joined:
    Mar 7, 2006
    Messages:
    3,754
    Likes Received:
    1,379
    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.
     
  11. neliz

    neliz GIGABYTE Man
    Veteran

    Joined:
    Mar 30, 2005
    Messages:
    4,904
    Likes Received:
    23
    Location:
    In the know
    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.
     
  12. Razor1

    Veteran

    Joined:
    Jul 24, 2004
    Messages:
    4,232
    Likes Received:
    749
    Location:
    NY, NY
    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.

    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.
     
  13. Razor1

    Veteran

    Joined:
    Jul 24, 2004
    Messages:
    4,232
    Likes Received:
    749
    Location:
    NY, NY
    can you explain about the library changes though, I was under the impression that would cause a redesign of the entire chip?
     
  14. neliz

    neliz GIGABYTE Man
    Veteran

    Joined:
    Mar 30, 2005
    Messages:
    4,904
    Likes Received:
    23
    Location:
    In the know
  15. v_rr

    Newcomer

    Joined:
    Apr 30, 2007
    Messages:
    147
    Likes Received:
    0
    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.
     
  16. Mariner

    Veteran

    Joined:
    Feb 6, 2002
    Messages:
    1,626
    Likes Received:
    262
    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.
     
  17. Razor1

    Veteran

    Joined:
    Jul 24, 2004
    Messages:
    4,232
    Likes Received:
    749
    Location:
    NY, NY

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

    Newcomer

    Joined:
    Apr 30, 2007
    Messages:
    147
    Likes Received:
    0
    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.
     
  19. pjbliverpool

    pjbliverpool B3D Scallywag
    Legend

    Joined:
    May 8, 2005
    Messages:
    7,583
    Likes Received:
    704
    Location:
    Guess...
    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.

    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?
     
  20. Razor1

    Veteran

    Joined:
    Jul 24, 2004
    Messages:
    4,232
    Likes Received:
    749
    Location:
    NY, NY

    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.
     
Loading...

Share This Page

  • About Us

    Beyond3D has been around for over a decade and prides itself on being the best place on the web for in-depth, technically-driven discussion and analysis of 3D graphics hardware. If you love pixels and transistors, you've come to the right place!

    Beyond3D is proudly published by GPU Tools Ltd.
Loading...