News for hackers. Stuff that matters.
Re:Apple M2 Ultra Isn't Faster Than Last Gen AMD&Intel Deskt... by peoplefromibiza on Saturday June 10, 2023 @12:49PM (#36272184)
> Economically and environmentally it's absolutely a problem.

[citation needed]

Economically the Intel CPU of the 90s that had a very bad perf/watt compared to today's standards have been awesomely worth it

Environmentally, CPU have been getting better and better, the difference of a few 10s of watts doesn't really make any difference, unless you have numbers to back up your very strong claim.

Re:Apple M2 Ultra Isn't Faster Than Last Gen AMD&Intel Deskt... by daneel_w on Saturday June 10, 2023 @12:53PM (#36272220)
Citation needed? Do you live in some alternate reality?

> "... the difference of a few 10s of watts doesn't really make any difference, unless you have numbers to back up your very strong claim."

We have a billion power-hungry PCs running on the planet. Power-efficiency matters for economy and for environment, because power isn't free and only a tiny speck of the world runs on clean energy. It always mattered.

Re:Apple M2 Ultra Isn't Faster Than Last Gen AMD&Intel Deskt... by locustous on Saturday June 10, 2023 @01:47PM (#36272810)
Most of those systems sit at idle, when they are on at all. Idle power is not the same as TDP. The idle difference is not so great that it's a big deal.
Re:Apple M2 Ultra Isn't Faster Than Last Gen AMD&Intel Deskt... by daneel_w on Saturday June 10, 2023 @02:14PM (#36273183)
Whataboutism.
Re:Apple M2 Ultra Isn't Faster Than Last Gen AMD&Intel Deskt... by tester756 on Saturday June 10, 2023 @07:14PM (#36276277)
Yea, sure you can argue for the sake of arguing

but yea it makes difference if the difference is

0.001% 0.01% 0.1% 1% 10% 1000%

Re:Apple M2 Ultra Isn't Faster Than Last Gen AMD&Intel Deskt... by MBCook on Saturday June 10, 2023 @04:18PM (#36274646)
Do you have a source showing idle numbers? I’ve never seen a comparison. The ones I’ve seen are always about max power.
Re:Apple M2 Ultra Isn't Faster Than Last Gen AMD&Intel Deskt... by locustous on Sunday June 11, 2023 @07:32AM (#36280366)
It's not apples vs apples. Literally and figuratively. The I/O or board features on PC boards will eat power. So you will end up with a 15-30 W idle vs probably <5 for the Mac because they are effectively laptop board equivalents. I doubt the PCIe does much to the power, you need active chips to eat power. That is vs Intel.

AMD will add a bunch more watts to the idle number as their multi CCX CPUs just eat more power at idle. You'll be closer to 30-45 W idle.

AMD monolithic dies are more in line with Intel. IE the laptop/mini PC line will be nice and low.

The difference is vastly diminished when you add the display that's using 80 Ws. So that's 85 vs 100 W total system power? It just blows out total system power at idle and makes arguing over numbers less than 20 pretty meaningless.

Apple numbers are better in pretty much every way on power. But we're talking a handful of watts. Even at really high power rates it isn't going to add to up much.

Sources: I have a Mac mini and an Intel raptor lake desktop. I take measurements. And I have read various sources. This is my best information.

Re:Apple M2 Ultra Isn't Faster Than Last Gen AMD&Intel Deskt... by peoplefromibiza on Monday June 12, 2023 @09:14AM (#36292894)
> We have a billion power-hungry PCs running

Let's do some math.

According to [1] Human production of energy is even lower at an estimated 160,000 TW-hr for all of year 2019 (a COVID year)

Let's hypothesize the difference is on average 10watt/hour (rather large for the average device), the difference for a billion devices would be 10GW/hour.

Which is exactly 1/16,000,000th of the total.

Assuming every Apple computer consumes 100watts less than the equivalent non Apple, assuming there are 20 million new low power Apple computers (probably there are much less), assuming the CPU are 100% of the time in sustained mode (of course on average CPU do not run at 100% of the power all the time continuously, but let's assume they all do in this example) it would mean 2GW/hour saved, which corresponds to a 1/80,000,000th of the total.

It would allow, maybe, to shutdown an average power plant (the largest one produces 23GW/hour)

Unfortunately there are over 65,000 power plants in the World, 2,500 of which run on coal.

Unfortunately the energy saved could come from renewables, so the difference on emissions would be even less relevant than it already is.

Economically those 2GW even at the Denmark prices ($0.50/KW) would cost one million dollars (2GW = 2,000,000KW). AKA nothing.

As you can see the difference must be quite large to make a real measurable difference.

[1] https://en.wikipedia.org/wiki/Earth%27s_energy_budget