Nvidia's GPU Technology Conference Liveblog 10:30p/1:30e

[blazorthon]

[citation][nom]dragonsqrrl[/nom]Wow... we really like to argue semantics. True, true, and true, but again I don't think that's what he was saying. Unless I'm mistaken, "Kepler" doesn't refer to any specific GPU in the lineup. Both gk110 and gk104 are derivatives of the Kepler architecture. I don't think that simply saying, a lot of compute functionality was removed from the "Kepler series", is accurate.[/citation]

True. They didn't take out functionality, just performance, in the consumer Kepler series (the *new kepler series* that he referred to), so to say that they removed functionality is technically wrong.

You're also arguing semantics. You're the one who replied to him in the first place about it and then again to me.

 

[dragonsqrrl]

[citation][nom]blazorthon[/nom]Considering the many things wrong with his post, I'm going to give him the benefit of the doubt on this one and assume that he didn't even realize that his post could be interpreted as him saying that there won't be GK110s used in compute cards. See what I'm getting at?[/citation]
Yes? But I was saying its existence in any form, not specifically a compute card. In any case, the comment was clearly ignorant.

 

[blazorthon]

[citation][nom]dragonsqrrl[/nom]Yes? But I was saying its existence in any form, not specifically a compute card. In any case, the comment was clearly ignorant.[/citation]

Well, I can agree with you in that the comment was clearly ignorant. He had no idea what he was talking about.

 

[dragonsqrrl]

[citation][nom]blazorthon[/nom]True. They didn't take out functionality, just performance, in the consumer Kepler series (the *new kepler series* that he referred to).You're also arguing semantics. You're the one who replied to him in the first place about it.[/citation]
...yes, i said "we" like to argue semantics. I'm not trying to deny that I do it sometimes .

And yes, performance, not functionality.

 

[fatality1515]

@caedenv "If they are such firm believers in these other uses then why did they take out a lot of that functionality from the new Kepler series?"

"Quadro" AKA "let's steal money from the rich"

GeForce cards are the same as Quadro cards, they are just crippled on purpose to get more money out of professionals. Few years back I turned my GeForce 8600GT card into an expensive Quadro card through softmod. OpenGL in Maya worked perfectly, with greater performance.. The same applies to CUDA.

It's all about corporate greed.. I rather support openCL (open standards) than getting screwed in the end by proprietary systems.

 

[tsnor]

@Marcus Yam : Excellent read. really well done.

 

[CaedenV]

[citation][nom]fatality1515[/nom]@caedenv "If they are such firm believers in these other uses then why did they take out a lot of that functionality from the new Kepler series?""Quadro" AKA "let's steal money from the rich"GeForce cards are the same as Quadro cards, they are just crippled on purpose to get more money out of professionals. Few years back I turned my GeForce 8600GT card into an expensive Quadro card through softmod. OpenGL in Maya worked perfectly, with greater performance.. The same applies to CUDA.It's all about corporate greed.. I rather support openCL (open standards) than getting screwed in the end by proprietary systems.[/citation]
The 8000 series was the first time that nVidia used the same basic architecture for both the GeForce and Quadro series. That now ended with the 500 series, and kepler will be very different between the gaming cards and pro cards.
On the other hand we now see AMD making the opposite move; They have always had their Radion and FirePro cards as separate entity, but now they are doing what nVidia's 8000 series did. I am not saying that it is all bad because Adobe is moving away from CUDA anyways, and while I am a huge fan of nVidia, I am not above moving over to AMD if they provide the card that will work for what I want to do the next time I upgrade. I am just disapointed that if things remain the way they are now I will not have the option that I want in the future... but I just upgraded, and will likely keep this platform for another 3-5 years, so maybe in that time things will change to where it is a moot point in the first place.

 

[aviral]

A really rich content on the GPU computation power in different different fields........

 

[lordstormdragon]

Nvidia and AMD should both stop screwing around with their falsified "professional" card lines outright. Instead, make up the difference in service subscriptions for big studios. Quadros and FireGL cards are a complete scam, and of course the consumer-grade Kepler cards are debilitated out of the box just to continue scamming people.

The GTS250 demolished all prior Quadros by itself, even just being a retooled 8800GT. Ahh, for the good old days when Nvidia was in it to win, not just to make money.