Nuvia: don’t hold your breath

[Cmaier]

I just asked the author and he confirmed that the X Elite allows you to target the NPU on Windows whereas the M3 doesn’t and so the results for the M3 are NPU plus CPU, which would account for the energy difference I would imagine.

Macos really needs an api to target the NPU exclusively.

they tend to avoid that when they think that their own solution is a stopgap until Arm adopts an equivalent functionality.

 

[Artemis]

i still say it does. whether you choose to take advantage of it is another matter. Depending on your package strategy, the RAM is located either right above the CPU, or adjacent to it. Call it 10 mm away. That means the time of flight is 60ps. Put the memory in DIMMS nearby on the motherboard instead. Call that 10cm away, That’s 600ps. So let’s call it 500ps difference. Assume your CPU runs at 4GHz. That means your CPU cycle time is 250ps. So it takes 2 extra cycles to address the RAM, and 2 extra cycles to read the RAM. Boo.

That’s assuming you optimize your design to take advantage of all that.

Yeah, all else equal I would guess it does, by a few nanoseconds.

 

[Jimmyjames]

LOL

Andrei used powermetrics — the old one that was better than we have today that still included DRAM — to show that it sucked. So weird you keep coming back to “he used it”. Dude he used it and thinks it sucks and that was why he published about it.



And he did that before they removed DRAM measurements too, so even if it were accurate it’d still have that issue. Mind you, the accuracy issue both ways.


Geekerwan only recently started using Apple’s internal modeling tool, which may also include other things PowerMetrics modifies.

And regardless, Andrei also called out those same 3.6W/7W A17/M4 measurements you posted here or elsewhere as “nonsense” (or bullshit, I can’t remember) in the Chips n Cheese discord and he would actually know. I happen to agree, the A17 especially is very unlikely.

The 11W M4? He says that’s reasonable.

Btw, notebookcheck does a skimmed powermetrics but their main measurements are via the wall, with an external monitor these days.

And second of all, that’s fine! RE: MS funded research, but I’d rather have it from the VRMs there too and compare to Apple. You can get directional ideas such as that an NPU might be more efficient than a CPU, I’m just not a huge fan of using first party APIs and firmware tools to compare two SoCs on power when we can do other ways and when the horse’s races are close.

Battery rundown quite frankly is probably one of the best ways to do things, and use multiple suites to do so.

You keep stating this and yet show zero proof.

Where did Andrew say it sucked? Show it. Where did he say 11 watts for the cpu alone is reasonable?

You are obsessed with dram power usage when we are discussing he cpu usage alone.

I’m sure you know better than MS. Maybe they said powermetrics sucked too!

All methods have their pros and cons, pretending that power metrics is worse than wall power for a measurement like cpu is nonsense.

 

[Cmaier]

Microsoft's Snapdragon X Elite-powered Surface Laptop and Surface Pro start at $999

Microsoft just launched its new Surface Laptop and Surface Pro, the first Surface devices powered by Snapdragon X Elite which...

9to5google.com

Remember how people whined about pricing? Starts at $999.

why would you buy that instead of a mac? because you like start menu ads?

 

[Artemis]

they tend to avoid that when they think that their own solution is a stopgap until Arm adopts an equivalent functionality.

Yeah. For one side case, I’m glad AMX is dying in favor of SME for instance.

 

[Cmaier]

Yeah, all else equal I would guess it does, by a few nanoseconds.

When i was busy shaving time off of opteron critical paths, a nanosecond was more than my entire cycle time If apple had the manpower to spend on it, they’d take advantage of that and gain the tiny latency advantage. But they don’t. (At AMD we would have. We were pretty relentless back then. Though, to be fair, keeping track of every one of millions of transistors in your part of the chip did tend to make us a little bit insane.

But I got better.

I swear.

 

[Artemis]

You keep stating this and yet show zero proof.

Where did Andrew say it sucked? Show it. Where did he say 11 watts for the cpu alone is reasonable?

You are obsessed with dram power usage when we are discussing he cpu usage alone.

I’m sure you know better than MS. Maybe they said powermetrics sucked too!

All methods have their pros and cons, pretending that power metrics is worse than wall power for a measurement like cpu is nonsense.

The Chips n Cheese discord has his comments. I’m not obsessed with DRAM, but DRAM is part of the power draw, that’s also how Apple keeps power down and is part of the system. If you want to know the CPU power, don’t be surprised when AMD and Intel guys quote implausibly low numbers relative to what you expect, and then you’ll balk and I’ll laugh and say “told you” because crappy PD and smaller cache on the CPU influences that.

And RE; software: other tools are more accurate than Apple’s.

RE: Apple and Powermetrics

I’m going to take Andrei on this, lmao.

 

[Artemis]

When i was busy shaving time off of opteron critical paths, a nanosecond was more than my entire cycle time If apple had the manpower to spend on it, they’d take advantage of that and gain the tiny latency advantage. But they don’t. (At AMD we would have. We were pretty relentless back then. Though, to be fair, keeping track of every one of millions of transistors in your part of the chip did tend to make us a little bit insane.

But I got better.

I swear.

Haha. Cliff it’s been a while since I remember you talking about adiabatic logic - did you ever work with any of that? This is random, but I feel like I remember you mentioning this.

 

[Cmaier]

Haha. Cliff it’s been a while since I remember you talking about adiabatic logic - did you ever work with any of that? This is random, but I feel like I remember you mentioning this.

No No sane person actually did that outside a university. Except maybe Intel - I seem to recall they had some ALU they published about in JSSC and the press went crazy and it never came to anything. I did do other weird stuff (like fully-differential current mode logic with bipolar transistors) (which i even did again at exponential). But nothing as crazy as that stuff.

 

[Artemis]

No No sane person actually did that outside a university. Except maybe Intel - I seem to recall they had some ALU they published about in JSSC and the press went crazy and it never came to anything. I did do other weird stuff (like fully-differential current mode logic with bipolar transistors) (which i even did again at exponential). But nothing as crazy as that stuff.

Ahh it might’ve been bipolar transistors I was thinking about . Yeah, reversible computing is more out there.

I need to go back and read some of your dissertation again which is above my head but still enjoyable. Caching is just an incredibly fun topic. Everything’s a tradeoff and there is no free lunch, but you might find a cheap date here and there is how I see it.

 

[Jimmyjames]

The Chips n Cheese discord has his comments. I’m not obsessed with DRAM, but DRAM is part of the power draw, that’s also how Apple keeps power down and is part of the system. If you want to know the CPU power, don’t be surprised when AMD and Intel guys quote implausibly low numbers relative to what you expect, and then you’ll balk and I’ll laugh and say “told you” because crappy PD and smaller cache on the CPU influences that.

And RE; software: other tools are more accurate than Apple’s.






View attachment 29537
View attachment 29538


RE: Apple and PowermetricsView attachment 29539

View attachment 29540
I’m going to take Andrei on this, lmao.

When it suits you I’m sure you do cherry pick. All methods have errors involved. if he said it then fair enough. I only know his Twitter account. We’ll see how accurate he is when the M4 reaches the Mac.

It’s worth remembering he compiled the initial data which quoted the +3200 gb score. A number which was used despite it being due to a lack of fan control on Linux. Before he worked for Apple’s competitor, he used powermetrics, now he works for Qualcomm he doubts it’s accurate. That is not to say he is wrong, but as with everything else, it has to be proved. Especially when battery life seems better on the M4 iPad Pro vs the M2.

To be clear, we’re expected to believe that the M3 which used about 15 watts multi core according to the terrible chart they show here

https://images.anandtech.com/doci/21116/M3-CPU_Curve.jpg

And now they are using 66% of that on single core performance in the M4, without losing battery life?

 

[Artemis]

When it suits you I’m sure you do cherry pick.

You just lobbed a hypothetical after being blown out. You are the one who cherrypicked here and were in total denial even after I told you the truth without reserve. This is embarrassing and unbecoming.

All methods have errors involved. if he said it then fair enough. I only know his Twitter account.

He’s said this there too, years ago.

We’ll see how accurate he is when the M4 reaches the Mac.

I mean, I wouldn’t let you be the judge of that considering the previous convo but I’ll keep the place posted on what he says. He doesn’t do reviews anymore — the man is professionally employed doing this stuff.

And I already explained to you exactly what he would say, at least 4 different times now and even explained to you that he himself used these same methods even for the phones and you were a belligerent dickhead to me over it on a high horse over something you don’t understand RE: measuring power.

Andrei has always tried to get DRAM in there and for a reason, because DRAM draw is a partially dependent variable of your CPU. And power delivery systems are a part of the CPU power draw in literally any practical context.

And on top of that, software modeling sucks. It just does. He said it too. Give me wall power any day minus idle over this bs.

It’s worth remembering he compiled the initial data which quoted the +3200 gb score. A number which was used despite it being due to a lack of fan control on Linux.

That was valid, it was Qualcomm’s marketing that wanted it and I’m not a fan of it either, but it’s a legitimate score.

Before he worked for Apple’s competitor, he used powermetrics, now he works for Qualcomm he doubts it’s accurate. That is not to say he is wrong, but as with everything else, it has to be proved. Especially when battery life seems better on the M4 iPad Pro vs the M2.

Jimmy come on. HE USED powermetrics one time. Lmao. To show that it sucked. His positions have never changed.

A13 review? From the wall or PMICs
M1 reciew? From the wall
M1 Pro/M1 Max? From the wall and powermetrics to show powermetrics was inaccurate. That was before he worked at QC.
A15 review? From the wall or PMICs

You are at this point just fundamentally dishonest. He “used it” one time to show it sucked. He said in the review it was inaccurate. And now? Apple doesn’t even measure DRAM, so it’s even worse.

 

[Artemis]

.

 

[Artemis]

M4 vs M2 battery life: idle power is a bigger issue as are the e cores, and those are still good. Further, that M4 in an iPad will throttle a lot anyways (which is fine tbc) and the tip of that curve is always the most inefficient. ST performance has improved enough to where pumping the power isn’t hugely bad. They’ve got a ways to go before pumping power will kill them in mobile, none of this is surprising.

Compare an M4 at 3.2GHz to an M1, and the M4 will be much more efficient. They’re still amazing chips.

 

[Jimmyjames]

You just lobbed a hypothetical after being blown out. You are the one who cherrypicked here and were in total denial even after I told you the truth without reserve. This is embarrassing and unbecoming.

Good lord you are insufferable. I never said he didn’t say it. I said you hadn’t proved he said it. Now you did. Kudos. I am really not bothered by what embarrasses you. I don’t know you and what I do know is obnoxious.

He’s said this there too, years ago.

I mean, I wouldn’t let you be the judge of that considering the previous convo but I’ll keep the place posted on what he says. He doesn’t do reviews anymore — the man is professionally employed doing this stuff.

Awesome. The feeling is mutual. You keep insisting you are in possession of the “truth” while denying the fundamental truth that without a known good measurement of power, you can’t be certain of which is more accurate. Your position is as follows:

Wall power is better because it’s better, and it’s better because it must be better because powermetrics is wrong because it gives a different answer to wall power.

And I already explained to you exactly what he would say, at least 4 different times now and even explained to you that he himself used these same methods even for the phones and you were a belligerent dickhead to me over it on a high horse over something you don’t understand RE: measuring power.

Yes you did say he would say it, but you never showed any evidence, which is what I asked you to show.

Andrei has always tried to get DRAM in there and for a reason, because DRAM draw is a partially dependent variable of your CPU. And power delivery systems are a part of the CPU power draw in literally any practical context.

And on top of that, software modeling sucks. It just does. He said it too. Give me wall power any day minus idle over this bs.

More proof. See above. It sucks because it does. Genius with a fetish for ad hominems.

That was valid, it was Qualcomm’s marketing that wanted it and I’m not a fan of it either, but it’s a legitimate score.

It was valid to show scores that are unachievable? Lol.

Jimmy come on. HE USED powermetrics one time. Lmao. To show that it sucked. His positions have never changed.

A13 review? From the wall or PMICs

Before he knew about powermetrics, as evidenced by the review:

Apple's M1 Pro, M1 Max SoCs Investigated: New Performance and Efficiency Heights

www.anandtech.com

M1 reciew? From the wall

Before he knew about it. You can’t just pretend his ignorance is a choice in favour of wall power measurements.

M1 Pro/M1 Max? From the wall and powermetrics to show powermetrics was inaccurate.

No it didn’t show that. It showed there was a difference, as there obviously would be.

That was before he worked at QC.

Yes, a direct competitor.

A15 review? From the wall or PMICs

You can’t use powermetrics on iOS or iPados

You are at this point just fundamentally dishonest.

Stunning. Pretending ignorance of the tool and an inability to run it in the case of iOS is an educated choice. No idea how you have the gall to talk about dishonesty.

He “used it” one time to show it sucked.

Straight up lie. He used it on the one device he could before leaving for Apple’s direct competitor. He never showed it sucked

He said in the review it was inaccurate. And now? Apple doesn’t even measure DRAM, so it’s even worse.

Jesus, shut the f up about dram.

Stop this bullcrap. How old are you? This is seriously bizarre, take the loss.

I mean, talk about the pot and the kettle. If your brain was anywhere as big as your ego, you wouldn’t be wasting your time on this tautologous guff.

 

[Jimmyjames]

.

More stunning wit.

 

[Artemis]

Good lord you are insufferable. I never said he didn’t say it. I said you hadn’t proved he said it. Now you did. Kudos. I am really not bothered by what embarrasses you. I don’t know you and what I do know is obnoxious.

Awesome. The feeling is mutual. You keep insisting you are in possession of the “truth” while denying the fundamental truth that without a known good measurement of power, you can’t be certain of which is more accurate. Your position is as follows:

Wall power is better because it’s better, and it’s better because it must be better because powermetrics is wrong because it gives a different answer to wall power.

Yes you did say he would say it, but you never showed any evidence, which is what I asked you to show.

More proof. See above. It sucks because it does. Genius with a fetish for ad hominems.

I’m not a genius? I’m just not going to lie about this, if you’re going to post on a forum about this at least get it right.

And it sucks because it’s not accurate to wall power and he’s measured VRMs too on his own. You ate the only one who doesn’t get this. Even the other Twitter repliers got this, and you went full narcissist and blocked them.

It was valid to show scores that are unachievable? Lol.

They are valid scores for the chip itself and it is actually possible to run Linux, yes.

Before he knew about powermetrics, as evidenced by the review:

Apple's M1 Pro, M1 Max SoCs Investigated: New Performance and Efficiency Heights

www.anandtech.com

Before he knew about it. You can’t just pretend his ignorance is a choice in favour of wall power measurements.

That’s not the point. The point is the previous measurements were not borne of powermetrics.

“Choice in favor of wall measurements” actually it was because in the M1 Max review he tacitly accepts the wall measurements as more accurate;

“In single-threaded workloads, such as CineBench r23 and SPEC 502.gcc_r, both which are more mixed in terms of pure computation vs also memory demanding, we see the chip report 11W package power, however we’re just measuring a 8.5-8.7W difference at the wall when under use. It’s possible the software is over-reporting things here.”

Notice he never said the wall was under-reporting things here. I’ll rely on his intuition.

No it didn’t show that. It showed there was a difference, as there obviously would be.

See above.

Yes, a direct competitor.

Doesn’t matter.

You can’t use powermetrics on iOS or iPados

Stunning. Pretending ignorance of the tool and an inability to run it in the case of iOS is an educated choice. No idea how you have the gall to talk about dishonesty.

You are dishonest. Looking at British GDP growth or lack thereof (you are poorer than we are) I’m starting to piece together why you people are the way that you are. The absolute indignity. So funny.

Straight up lie. He used it on the one device he could before leaving for Apple’s direct competitor. He never showed it sucked

Not a lie, the truth. He directly later implied it was inaccurate on his Twitter and he still says it’s bad today.

Jesus, shut the f up about dram.

Lmao, I think we had a selected exodus of the people with brains to the new world. You just don’t know what you’re talking about

I mean, talk about the pot and the kettle. If your brain was anywhere as big as your ego, you wouldn’t be wasting your time on this tautologous guff.

I’m actually impressed with how slow you are. You’ve probably been on these places longer than I have and yet it produced so little understanding.

 

[Artemis]

More stunning wit.

yep.

 

[Artemis]

I’m done with this on my end (sorry Cliff et. Al) but will note James is basically reaching the Andy guy in a mirror at this point. This is just ridiculous, but at any rate there are multiple ways to measure power, software shouldn’t be our first choice when battery rundowns and the wall exist or ideally VRMs.

 

[Cmaier]

Ok guys. Please, I beg you. Attack each other’s ideas all you want, but let’s avoid name calling or personal attacks. I don’t want to be the first mod to have to take action here.