Amd R290X early benchmarks

[buildzoid]

That PCB VRM Phase looks totally retarded. 5 1, really? I'd like to see a stronger VRM on the 2990X

I looked up the specs for the inductors and these can be anything between 55A-75A so it should work much better than the Titan's 6+2 made of components of questionable origin and either way this is probably an es and as such not a finished PCB design.

 

[Xzibit]

according to videocardz.com AMD Hawaii GPU has 2816 Stream Processors

There also saying that 290X might not be fully enabled Hawaii.

There confused about there own rumor/reports/leaks

Remember this from last month

If your to believe the scores the card is getting slower
or
We are seeing a variant of one of the Hawaii GPUs like the driver files indicated 3 variants so far LE, Pro & XT

2 days left

 

[RCoon]

There also saying that 290X might not be fully enabled Hawaii.

There confused about there own rumor/reports/leaks

Remember this from last month
http://cdn4.wccftech.com/wp-content/uploads/2013/08/AMD-Hawaii-GPU-Performance-635x476.jpg

If your to believe the scores the card is getting slower
or
We are seeing a variant of one of the Hawaii GPUs like the driver files indicated 3 variants so far LE, Pro & XT

2 days left

The difference in values could be this confusion between 2500 and 2800 SP's. If AMD were to make the 2.8K SP's on FirePro only, they'd be kicking themselves in the balls by having an answer to Titan, but refusing the gaming market the opportunity to buy it. I'd like to think they're smart enough to offer the 2.8K version the market so they can take top seat, even if it is almost as expensive as Titan. If all they offer consumers is the 2.5k version, I feel sorry for the PR department's(or lack of it) attempts at bigging up a lesser GPU for gamers.

 

[ne6togadno]

The difference in values could be this confusion between 2500 and 2800 SP's. If AMD were to make the 2.8K SP's on FirePro only, they'd be kicking themselves in the balls by having an answer to Titan, but refusing the gaming market the opportunity to buy it. I'd like to think they're smart enough to offer the 2.8K version the market so they can take top seat, even if it is almost as expensive as Titan. If all they offer consumers is the 2.5k version, I feel sorry for the PR department's(or lack of it) attempts at bigging up a lesser GPU for gamers.

http://www.tomshardware.com/reviews/workstation-graphics-card-gaming,3425.html

1 day left

 

[HumanSmoke]

I'd like to think they're smart enough to offer the 2.8K version the market so they can take top seat, even if it is almost as expensive as Titan. If all they offer consumers is the 2.5k version, I feel sorry for the PR department's(or lack of it) attempts at bigging up a lesser GPU for gamers.

Likely gamesmanship. Whomever launches last has a target to aim for. If AMD launch a full-fat card then it wouldn't take Nvidia too long to trump it with a fully enabled 2880 core GK 110 at whatever speed it needs to be to beat the Radeon- presumably, the enthusiast crowd covet horsepower over power use judging by most comments, so Nv could add the two missing power phases as Palit, Gigabyte etc have done and call it good. Likewise if Nvidia launch first, then AMD has the same luxury to tailor performance to suit (as per the 7970GE > GTX 680 scenario).

 

[Eric_Cartman]

It was impossible to produce those chips. They actually pulled an AMD (their CPUs mostly) and got ahead of themselves by making something too complex and big. It was at least a month before you even had a chance to buy the 1st kepler cards and 2 months, IIRC, before it reached the masses. Until 28nm was pretty mature, there was no way in hell nvidia could have ever made gk110 (from next to nothing wafer yields and not able to reach the needed clocks). To top it off, they removed all the compute power (dick move). But this has helped AMD a lot, so

AMD already learned that profitability takes a severe hit when you try doing that, so they've scaled back their operation to fit within the constraints of shitty TSMC and GloFo (and even that has to get delayed a lot). And they still got screwed. Tahiti never wasn't able to be made as power efficient as designed (killing all the 1300 MHz clock hopes by board partners). Fabs have been AMD's weak point forever. They don't have the capital to operate one (barely did before). There's nothing really wrong with either the CPU or GPU designs, but they can't physically be made correctly, so they get scaled back and stripped down (it was amazing that athlon 64 was made, even intel couldn't have done it haha - ever since has been a battle from design to production).

It was not impossible to make GK110 chips when they released the GTX 680.

In fact they demonstrated working GK110 based cards shortly after GTX 680 hit the market.

However, for about a year they dedicated the GK110 production entirely towards Tesla cards.

18,000+ of which went into the Titan super computer.

There was no need for them to use GK110 chips in the lower margin consumer market, so they dedicated stock entirely to the higher margin Tesla cards.