Why does Intel care less about power-saving on the desktop than mobile?

[Lepton87]

Likewise, the "UnCore" part of the CPU (L3 cache, memory controller, etc) will draw a fixed amount of juice anyway independently of SpeedStep, so halving freq won't exactly halve power consumption (core gets pulled off of VCore, uncore feeds off of VTT). Same is true of running the iGPU (another fixed minimum load within the CPU), which is partly why dual-cores are 55w TDP not 42w (exactly half of quad's 84w)).

Edit: Likewise for load power, a maxed out 4-core x264 encode draws only 33% more juice vs 2-core (on my rig anyway), yet provides over 80% higher fps.

From what I remember this UnCore thing is only true for Nehalem and HW. SB and IB have cache running at the core clock with HW they changed it to the way it was in Nehalem. You are probably right about the memory controller etc. though but cache is clocked at the same frequency as the core clock in SB and IB.
UPDATE: Yes, the memory controller sits on a separate voltage plane. VCCIO is the memory controller voltage, default at 1.05V so much less then Vcore. And VCCSA system agent voltage default at 0.95V involved in keeping BCLK at 100MHz.

 

[piasabird]

You can save more money by buying a low-energy smaller monitor. There are 2 or 3 main sectors in the desktop area.

Power users who want to do things fast like at work for big business.

Gamers and others who use video cards. Might also include some casual photoshop and light video editor users.

Casual home users who want e-mail and cat videos who use integrated video. A sub-category might be the home theater crowd that stream video to their HDTV.

The exception to these are the super power users who want expensive high-end workstations.

So Intel kind of missed the boat on the Mobile users when all these tablets and smartphones came to market. However, for years customers have been moving away from desktops to phones and tablets and set top boxes and video extenders, video game consoles that do much more, etc. In this day and age people want it all and they want to take it with them.

As an example, When I go to Church, I like having access to things like the Bible, and other religious texts like hymn books, lesson manuals, Magazines, and religious videos all on my tablet. Tablets have so many uses.

 

[VirtualLarry]

This is pretty much true. I just tested 800MHz vs 1600MHz on an Ivy Bridge via ThrottleStop - voltage doesn't go any lower automatically, and can't really be forced much lower below 0.65v via offset undervolt without experiencing instability at higher Speedstep freqs. With a kill-a-watt plugged in there was literally zero difference in 800MHz vs 1.6GHz idle power consumption both at any one time and over time, but the forced 800MHz often idle'd at 1000-1100MHz with a web browser running in the background whereas the 1.6GHz stayed at 1.6GHz. So overall, it's already as low as it can go. Likewise, the "UnCore" part of the CPU (L3 cache, memory controller, etc) will draw a fixed amount of juice anyway independently of SpeedStep, so halving freq won't exactly halve power consumption (core gets pulled off of VCore, uncore feeds off of VTT). Same is true of running the iGPU (another fixed minimum load within the CPU), which is partly why dual-cores are 55w TDP not 42w (exactly half of quad's 84w)).

Edit: Likewise for load power, a maxed out 4-core x264 encode draws only 33% more juice vs 2-core (on my rig anyway), yet provides over 80% higher fps.

Thanks for testing. So apparently, there is a method to Intel's madness?

 

[DrMrLordX]

There are benefits that the IVR brings to overclocking, like the extremely clean power being supplied, but they're significantly outweighed by the fact that there's more power and heat being released, and at close proximity to the CPU cores. Unless these can be built with near 100% efficiency... these IVRs are probably always going to hold back max overclocks. Still, there is a long way to go in the realm of integrating power supply components on die.

Maybe they can use strontium titanate or something. Granted, exposing the IVRs to light under those conditions would be a little strange.

A more-practical solution might be some metal traces along with an insulator layer between the IVRs and the die so that heat can effectively be piped away from the IVRs and into a part of the IHS that receives less heat from the die than other parts. Or micro-heatpipes . . . or something.

 

[SlickR12345]

Because mobile needs to last at least few days before you are bothered to recharge it for several hours just to use it, while desktops are plugged in in the power socket and don't need to be recharged.

Plus you also have options, you could go for an atom PC or whatever and have that low power consumption on desktop as well.

 

[witeken]

Why does Intel care less about power-saving on the desktop than mobile? This should answer your question.