What If The NX Console Is Portable Too?

[JustBeingReal]

Soundwave said:

JustBeingReal said:

This level of performance isn't even remotely possible yet when using the comparisons between PS4 and XB1, dude you really need to stop using Flops to compare different company's technologies, it's a pointless comparison.

The various companies making different processing technologies do not use the same standard for measuring Floating Point Operations, so trying to compare Apple's tech to IBM or whoever else Nintendo may use for their processors makes your points about flops per watt moot.

Comparing like for like, like AMD's last generation to this one is way more fitting, TBH AMD are most likely who Nintendo are going to partner with for various reasons, mainly because they've been ATI/AMD partners on their GPU for years and a single SOC for everything processor related in your device makes manufacturing much simpler and cheaper.

Hell we even have AMD saying they've partnered with a company to make a processor for a new console and we know Nintendo are announcing NX next year, it may be a slight reach to say it's definitely AMD, but it's not a reach in the slightest to say that AMD are the most likely partner for this.

Pretty sure that is what AMD is aiming for with the 14nm FinFET process that starts next year. 

The Tegra X1 gets 500 GFLOPS at roughly 10 watts, but that's at 20nm, the rumor is they are moving to 14nm FinFET later this year, which will allow the X1 to be put into a mini-tablet form factor. 

The Power VR GT 7900 also gets 800 GFLOPS at about 10-12 watts and that's at 14nm/16nm. 

I think what Nintendo will be using will more akin to these new advances in mobile tech, not based on AMD's existing desktop/laptop processors. Those just don't have anywhere close to the power efficiency to reasonably power a portable, which is essential to the NX concept. 

IMO if AMD cannot give Nintendo similar performance/watt that Nvidia and PowerVR (Apple) is getting, then they've made a huge mistake in choosing AMD again. 

You're doing it again, using Flop ratings to compare multiple different manufacturer's technology, when Floating Point calculations are not an industry standard measuring metric.

No company measures them in the same way, so you using them like they are is completely disingenuous.

No AMD are not aiming for 70GFlops per watt, going by the way AMD measures FLOPs, at 28nm's they've achieved 819Flops over 35watts, that's taking everything together into account across a Carrizo APU/SOC, which means they've achieved 23.4GFlops per watt, if that architecture can be shrunk to 14nm it would achieve 46.8GFlops per watt.

Perhaps they can optimize their design to gain more performance, but that would take time, 2016 probably isn't going to be when they can achieve 70GFlops per watt at 14nm, maybe they'll get close to 60GFlops, but this is based on how AMD measures floating point performance.

GFlops are not a standard for measuring total processor performance, you using PowerVR, Nvidia's Tegra or anyone else's tech as a comparison, with GFlops as a metric makes absolutely no sense, ratings are not comparable.

 

Flops are a marketing buzzterm, a fake figure to make it seem like you have X amount performance, but it's not accurate or a figure that is commonly always used in exactly the same way, nor does it cover total processor performance.

Flops don't tell you Instructions Per Second (IPS), cache size, cache amount, Bandwidth, latency between components inside a chip or between chips.