Definitely. This will be a card to get me by until 20nm. Still disappointed about 28nm still being here, but you have to give credit to both NV/AMD for the performance that has been squeezed out of this node.
Impressive set of cards. I absolutely cant wait to see what this arch can do on 20nm.
Well, it's always fun to get new stuff.
No, you ll need a high power PSU because power peaks reach close to 300W, good article from THG, that s not habitual, good analysis as how they get better "power efficency"...
http://www.tomshardware.com/reviews/nvidia-geforce-gtx-980-970-maxwell,3941-11.html
Nvidia's newest architecture presents us with a whole new set of challenges for measuring power consumption. If the maximum of all four possible rails are to be measured exactly (to find out Maxwells power consumption reduction secrets), then a total of eight analog oscilloscope channels are needed. This is because voltage and current need to be recorded concurrently at each rail in real-time. If the voltages are measured and then used later, the result may be inaccurate. So, how did we solve this problem?
We enlisted the help of HAMEG (Rohde & Schwarz) to search for a solution with us. In the end, we had to use two oscilloscopes in parallel (a master-slave triggered setup), allowing us to accurately measure and record a total of eight voltages or currents at the same time with a temporal resolution down to the microsecond.
To illustrate, lets take a look at how Maxwell behaves in the space of just 1 ms. Its power consumption jumps up and down repeatedly within this time frame, hitting a minimum of 100 W and a maximum of 290 W. Even though the average power consumption is only 176 W, the GPU draws almost 300 W when it's necessary. Above that, the GPU slows down.
Roughly twice as fast as my 7970 at my resolution. This fall may be time to switch back to nVidia.
Just called Microcenter and they should be on the shelf this afternoon, so if all goes according to plan, I'll have a nice new gtx970 in my hands this evening.
Finally upgrading these 560ti's that ive had for 3.5 years- should be a decent bump in performance hopefully!
Thanks for sharing that and props for Toms for starting a new power measurement standard. :thumbsup:
I'd be curious what the 290x consumption looks like in a similar measurement. I have a watt reader but it's so slow that I wouldn't have guessed the peaks are so high and often.
Pretty interesting..
To illustrate, let’s take a look at how Maxwell behaves in the space of just 1 ms. Its power consumption jumps up and down repeatedly within this time frame, hitting a minimum of 100 W and a maximum of 290 W. Even though the average power consumption is only 176 W, the GPU draws almost 300 W when it's necessary. Above that, the GPU slows down.
Stress Test Power Consumption
If the load is held constant, then the lower power consumption measurements vanish immediately. There’s nothing for GPU Boost to adjust, since the highest possible voltage is needed continuously. Nvidia's stated TDP becomes a distant dream. In fact, if you compare the GeForce GTX 980’s power consumption to an overclocked GeForce GTX Titan Black, there really aren’t any differences between them. This is further evidence supporting our assertion that the new graphics card’s increased efficiency is largely attributable to better load adjustment and matching.
Power Consumption Under Max. Load
Gigabyte GTX 980
Windforce OC
GeForce GTX 980
Reference
GeForce GTX 970
Reference (Emulated)
Gigabyte GTX 970
Windforce OC
PCIe Total 237.63 W
233.64 W
188.96 W
192.46 W
Motherboard 3.3 V 0.98 W 2.63 W 2.16 W 2.15 W
Motherboard 12 V 41.07 W 48.35 W
48.38 W 48.36 W
VGA Card Total 279.68 W 284.62 W 239.50 W 242.97 W
The values above have potential consequences for the everyday operation of these graphics cards, as they represent what can be expected when running performance-hungry compute-oriented applications optimized for CUDA and OpenCL. The reference card’s two 6-pin PCIe power connectors start looking a bit out of place in this context, as they might just not be enough.
Thanks for sharing that and props for Toms for starting a new power measurement standard. :thumbsup:
I'd be curious what the 290x consumption looks like in a similar measurement. I have a watt reader but it's so slow that I wouldn't have guessed the peaks are so high and often.
Pretty interesting..
http://www.tomshardware.com/reviews/nvidia-geforce-gtx-980-970-maxwell,3941-14.htmlnew graphics card’s increased efficiency is largely attributable to better load adjustment and matching
AMD’s issue is not absolute performance or the efficiency of its architecture, but rather that PowerTune technology can’t adjust the power consumption quickly or finely enough depending on the actual load. This is exactly where Nvidia scores most of its points with Maxwell.
Interesting info Abwx. So the efficiency isn't so much Maxwell's architecture so much as a more intelligent way of managing power on demand. Either way, good results for Nvidia.
Interesting info Abwx. So the efficiency isn't so much Maxwell's architecture so much as a more intelligent way of managing power on demand. Either way, good results for Nvidia.
It's both. Even if their power management is flat out better, that accounts for the consumption but not the performance.
It's absolutely insane how they can feed those 64 ROPs:
It would be interesting to dig into this more. I might venture a guess it is actually both. Likely NV engineered this from the ground-up to be managed dynamically from small applications (phone/tablet, etc.) all the way up to a Quardo -type application. Hopefully AT or TH digs into this more in-depth soon. Would love to see this investigated.
I'd assume given the clocked nature of these devices that consumption will fluctuate wildly. But the avg power consumption is what an avg user is ultimately interested in over a given time.