Power Consumption Figures for AMD Fiji XT Flagship GPU and Nvidia GTX 980 Ti Leak Out - Bermuda XT Analysed - badgerspitied

Today's send wish be about two things; first, the supposed ability consumption figures for flagship GPUs of both sides; which leaked out from the usual Chiphell forums by the agency. And secondly, something that has been bugging me about the "Bermuda Einsteinium" try spotted in yesterday's leak. This something is the fact that we suddenly bear benchmarks for a buffalo chip that didn't even live a hebdomad past.

A cool looking featured image. @Wccftech, AMD, Nvidia

AMD and Nvidia flagships develop their direct magnate numbers game leaked - and what's up with the Bermuda XT GPU?

Lets start with the power consumption first. Great power consumption is a same important aspect of some commercial GPU and get down power ingestion with decent execution (Beaver State power efficiency) is the ideal target. However, since we are talking about the ultra high final stage segment here, wattage of upto 250W is permissible. Guardianship that in mind, I Don River't really expect any side by side gen GPU to exceed or flatbottomed go up this limit. We can tell that the GM200 GPU mentioned here is actually the cut die and not the grumbling fat one. This is because the difference between the Fiji ES taste and GM200 is negligible, allowing U.S. to identify it as the cut die thanks to the benchmarks leaked before.  Anyways, hither are the power figures:

WCCFTech	Geforce GTX 980 Ti (GM200 cut)	Radeon R9 390X/380X (Fiji ES)	Geforce GTX 980	Geforce GTX 780 Ti	Radeon R9 290X	Geforce GTX 970	Radeon R9 285
Relative Performance Ordered series	199%	195%	169%	154%	148%	144%	100%
Power Consumption	225W	215W	180W	256W	286W	158W	169W
Arbitrary Efficiency	0.884	0.906	0.939	0.602	0.517	0.911	0.592
Relative Efficiency	171%	175.2%	181.6%	116.4%	100%	176.2%	114.5%

To turn over deeper into the power image I have also calculated king efficiency based on the numbers provided and using an arbitrary efficiency total (Relative Performance Scale/Power Consumption) and then plotting it into a relative scale with the almost uneconomical GPU as the baseborn unit. The GM200 die will most probably be called the GTX 980 Ti (operating theatre equivalent) simply as usual I want to make it clear that we don't really lie with what IT will actually live called. It beatniks the Fiji ES sample away approximately 2%. Non really a all-inclusive gap by any standard. You will note that neither the full fat GM200 or the Bermuda XT are mentioned in the wetting. We get it on certainly that the GM200 exists because its papertrail can be traced all the way back to its prototyping (anyone think of the circuit loadboard?).

Today here's the affair, we leaked the AMD Next Gen language a very very years ago, but to comprise honest, I am not riant with this ontogeny. I had accepted the fact that Fiji XT is the main die and everything made sense, Zauba merchant marine data enclosed, but now we have a bench mark with the Bermudas ES smiling for the world. I have double checked and triple chequered and there is still no signs of Bermuda happening Zauba - the only authentic information rootage on the leak scene. So does that mean AMD managed to get an entire CORE past Zauba someways? masked nether another name?. Maybe. In my opinion, any of triplet things has happened: 1) there is no Bermuda ES center and the benches are completely misrepresent (highly improbable), 2) AMD managed to disguise information technology past the leak scene (no comment) or 3) Something very unusual is occurring.

As the archetypal two are beautiful obvious, lets discuss the last. The first thing that comes to mind is that AMD might be playing with nomenclature, that the Republic of Fiji XT GPU spotted on Zauba is the 4096 SP one and will be renamed to Bermuda XT. Which suggests that a cut down random variable testament then be called Fiji XT. If we were to go a young further then I guess it is besides practicable (article skimmers, beware, this is speculation on my part) that the R9 380X is manufactured on the 28nm node (from TSMC) patc R9 390X is manufactured on the 20nm node from GloFo. Since the testing channels would be other, this would explain its absence from Zauba, which lists silicon shipped to India. Apart from that, I don't really bon what to suppose along this one. Chiphell has been a reliable source of benchmarks in the by (the ones that are styled alike this at any rate) but this time, I would impulse our readers to absorb this with a pinch of salt anyway.

[socialpoll ID="2238653"]

Source: https://wccftech.com/power-consumption-amd-fiji-xt-gpu-nvidia-gtx-980-ti-bermuda/

Posted by: badgerspitied.blogspot.com

Share this post