Read more.Images said to show a new graphics card based on the GM204 Nvidia Maxwell GPU.
Read more.Images said to show a new graphics card based on the GM204 Nvidia Maxwell GPU.
It's going to have to be really good to tempt me into buying anything else pre-NVLink.
Main PC: Asus Rampage IV Extreme / 3960X@4.5GHz / Antec H1200 Pro / 32GB DDR3-1866 Quad Channel / Sapphire Fury X / Areca 1680 / 850W EVGA SuperNOVA Gold 2 / Corsair 600T / 2x Dell 3007 / 4 x 250GB SSD + 2 x 80GB SSD / 4 x 1TB HDD (RAID 10) / Windows 10 Pro, Yosemite & Ubuntu
HTPC: AsRock Z77 Pro 4 / 3770K@4.2GHz / 24GB / GTX 1080 / SST-LC20 / Antec TP-550 / Hisense 65k5510 4K TV / HTC Vive / 2 x 240GB SSD + 12TB HDD Space / Race Seat / Logitech G29 / Win 10 Pro
HTPC2: Asus AM1I-A / 5150 / 4GB / Corsair Force 3 240GB / Silverstone SST-ML05B + ST30SF / Samsung UE60H6200 TV / Windows 10 Pro
Spare/Loaner: Gigabyte EX58-UD5 / i950 / 12GB / HD7870 / Corsair 300R / Silverpower 700W modular
NAS 1: HP N40L / 12GB ECC RAM / 2 x 3TB Arrays || NAS 2: Dell PowerEdge T110 II / 24GB ECC RAM / 2 x 3TB Hybrid arrays || Network:Buffalo WZR-1166DHP w/DD-WRT + HP ProCurve 1800-24G
Laptop: Dell Precision 5510 Printer: HP CP1515n || Phone: Huawei P30 || Other: Samsung Galaxy Tab 4 Pro 10.1 CM14 / Playstation 4 + G29 + 2TB Hybrid drive
Considering the vast majority of the desktop and lapop market is still going to use PCI-E slots for years,I doubt NVLink is going to be massively adopted anytime soon in the consumer space,as it will break backward compatability. Plus it would need Intel to get onboard to have any hope of penetrating the consumer market,and this the same Intel which denied Nvidia an X86 license,screwed them out of the chipset market for Intel CPUs(which lead to litigation) and is attempting to take marketshare in the HPC market from them using MIC based cards. IBM has got onboard,but since their Power based CPU sales are decreasing each year,it makes sense they try and attack Intel in the HPC market from another angle,especially since they lack such compute cards themselves AFAIK.
Last edited by CAT-THE-FIFTH; 03-07-2014 at 12:41 PM.
If the rumours are anything to go on this could be the card that allows UHD gaming on a single reasonably priced card. I will patiently wait for release because the R9 295X2's price tag makes my wallet bleed.
The price-tag of the Titan Z will probably drain all blood from you!!
PS:INB4 is not a gaming card,it is:
http://www.nvidia.com/gtx-700-graphi...s/gtx-titan-z/
Last edited by CAT-THE-FIFTH; 03-07-2014 at 12:56 PM.
Ah, good. I needed to see this! I've been very close to buying a high-end 700 for a while, but I've been resisting the urge until the proper 800s appear.
Does this "leak" mean we should expect a couple of good 800s around October then, to capitalise on the autumn games release schedule?
Please be around Sept/Oct, I have told a friend I'll sell him my 670-OC in Sept and would like to go up to one of these bad boys!
I also can't see any Nvidia-proprietary CPU-GPU interconnect being kindly added to AMD/Intel chipsets, nor can I see it making any realistic difference in desktop graphics use anyway. http://forums.hexus.net/hexus-news/3...ml#post3238473
Going by that picture, the die looks pretty huge; I wouldn't expect it to be cheap. I've not worked out the size, but it looks more GK110 than GK104 sized to me.
I hope I never see that power configuration on the 880. They proved Maxwell uses little power and pumps out a lot, so why an 8+6+6?
"Nothing is safer than a giant snowball whipping through space...at a million miles an hour"
Actually they only proved Maxwell does great with a small core. It could be the same issue AMD is facing with Kaveri, which having been designed for modest power consumption the difference between < 65w parts and the 95w one is much much less than what the 50% increase in TDP suggests.
Frankly 8+6+6 is clearly an engineering sample thing, but they could well be back to the 250w ceiling if the performance/power scaling is not that good.
Its the lower power draw from Maxwell that interests me most.. Also less power = less heat = more overclocking potential. :-)
That's a huge over-simplification. Just for example, lower power may be due to using a different process which may not facilitate higher clocks.
New processors are very frequently more energy efficient than their predecessors - this does not necessarily imply better OC headroom, quite on the contrary in many cases.
Last edited by watercooled; 12-08-2014 at 03:55 PM.
There are currently 1 users browsing this thread. (0 members and 1 guests)