News Leaked Lunar Lake's Ultra 7 chip debuts in Geekbench database — impressive performance from low-power chips

Toggle sidebar Toggle sidebar
Why do you judge them impressive?

They seem to be really along the same lines as the competition on single, less impressive on multi, but that's because they are designed for the ultra low power classs.
 
  • Like
Reactions: KnightShadey
abufrejoval said:
Why do you judge them impressive?

They seem to be really along the same lines as the competition on single, less impressive on multi, but that's because they are designed for the ultra low power classs.
Click to expand...
Disagree completely on the multithreaded not being impressive as it's much more impressive than single threaded. We're talking 4P/4E/8T, E-cores that don't have L3 access, P-cores that don't have HT about matching the performance of a 13400 (ADL specs even in the RPL version) at 6P/4E/16T. This configuration matching a 65W SKU in a package designed to not go past 30W with a steady of 17W (assuming the leaks are accurate) is extremely impressive.
 
  • Like
Reactions: vongole, 35below0, JTWrenn and 3 others
I totally welcome good performance on a low-power chips.
Not even thin-and-light, I want a fanless workstation.
Real performance now I worry about only in the cloud on much bigger machines than I'm likely to run IRL.
 
abufrejoval said:
Why do you judge them impressive?

They seem to be really along the same lines as the competition on single, less impressive on multi, but that's because they are designed for the ultra low power classs.
Click to expand...
The article explains why they call them impressive in the last paragraph.

"so it still impresses in the multi-threaded tests if you take into account the comparative thread counts and target TDPs (reported default of 17W for most models, with 30W peak). In contrast, Meteor Lake processors are designed to scale to higher TDPs. Intel has yet to introduce its successor for the higher-powered 45W/115W Meteor Lake chips."
 
  • Like
Reactions: vongole
OK, so I guess potato / tomato regarding 'impressive'.

But even on multi-threaded performance, is it "impressive" or "not" to y'all?
Article says one thing, and most here are arguing the opposite.

Quick look on NBC multi- core performance of 9,972 is way below an equally low TDP QualcommX1P-64 which scores 13,278 running 10 cores @ 3.4Ghz max, vs the LNL 4/4 @ 3.9/4.7/49Ghz. And Single & multi-core performance is right near the similar TDP 15W Ryzen 8840U's score for something with similar TDP but far more threads. Both below the Z1 extreme in MC.

IMG-4751.jpg


It's definitely 'good' for efficiency & power from 4+4 cores, but is it 'impressive' , or.... what you would expect from a node update, freq/memory bump, and cutting down extra cores/multi-threaded performance to focus on TDP and single threaded performance ala Apple/Qc?

All seems pretty inline to me, and it's only impressive versus particularly bad previous generation efficiency. However, whether TDP or cores, there's existing product all around it, above and below and beside. 🤔

By impressive I was expecting Apple intel -> M1 change in single core - efficiency. Especially after all the wild early claims from Qualcomm, AMD, and intel. These seem like more down to earth improvements.

BTW, I wonder about that 155H result in the article, seems like a throttled version, 155U or 165 U would've been a better choice, especially if TDP is the selling point of 'impressive' in this case. 🤷🏻‍♂️
 
Last edited:
JRStern said:
I totally welcome good performance on a low-power chips.
Not even thin-and-light, I want a fanless workstation.
Real performance now I worry about only in the cloud on much bigger machines than I'm likely to run IRL.
Click to expand...
I understand the desire, but I've learned that some of the things I want can't be had.
Among them is workstation performance on a phone power budget, which would make fanless a snap.

And in the mean-time I've settled for unoticeable noise.

That's worked out pretty well with clunky and noisy HDDs transitioning to silent NVMes, which allowed for big heat sinks and large slow moving fans to fill the tower chassis I don't keep next to my ear.

Of course an 800 Watt GPU can't really keep silent, nor can CPU eating 300 Watts. But systems designed to manage such peak loads, can be rather unnoticable when running below maximum.

Which is why I try to avoid running at peak, when the results aren't actually all that critical or the extra performance doesn't deliver real benefits (e.g. frame rates above monitor capabilities).

That's often not as trivial to control as it should be, perhaps some type of decibel regulator should be integrated into PCs on top of variable TDP. But when the annoyance level is high enough, I usually find a solution.
 
KnightShadey said:
By impressive I was expecting Apple intel -> M1 change in single core - efficiency. Especially after all the wild early claims from Qualcomm, AMD, and intel. These seem like more down to earth improvements.
Click to expand...
We tend to overlook that that Intel to M1 gain came at a somewhat singular moment, when x86 evolution had basically stopped going into new silicon because Intel had fab troubles and AMD was still going through the Zen redesign.

There simply isn't as much all-around magic in the x86 to ARM transition as people infer from that one point in time.

And there won't be, if the entire focus remains on top Geekbench CPU scores, because there is no way to raise those except with either lots of transistors or Wattage or both, while efficiency suffers.

All of these vendors tried to sidestep the limits of CPU performance scaling by telling us how much faster these devices would be running AIs on NPUs intead of CPUs or GPUs. But that requires that actually being thing and is now under the active threat of paradigm shifts in LLM hardware implementations (e.g. reduction of MatMul effort in transformers).
 
  • Like
Reactions: KnightShadey
thestryker said:
Disagree completely on the multithreaded not being impressive as it's much more impressive than single threaded. We're talking 4P/4E/8T, E-cores that don't have L3 access, P-cores that don't have HT about matching the performance of a 13400 (ADL specs even in the RPL version) at 6P/4E/16T. This configuration matching a 65W SKU in a package designed to not go past 30W with a steady of 17W (assuming the leaks are accurate) is extremely impressive.
Click to expand...
I can’t really speak to the 13400 but the 13600k doubles those multithreaded scores so I’m pretty sure the 13400 should be higher than you claim.
 
Just my personal opinion here but the era of x86 for mobile computer is darn near over.

I wouldnt invest in anything x86 for a personal mobile computer.
Heck I'm counting the months until even mobile gaming machines, like my Steam Deck, ditch the x86 processors and move over to Arm chips.
 
cknobman said:
Just my personal opinion here but the era of x86 for mobile computer is darn near over.
Click to expand...

Even if true, the existing install base is enough to keep it going for at least a decade.

cknobman said:
I wouldnt invest in anything x86 for a personal mobile computer.
Click to expand...

Until the alternatives reach the power and options of the X86 ecosystem, they aren't worth 'investing in' either, especially with all the near-term shortcomings tradeoffs, they are just another valid alternative, as is RISC-V for some too.

However for the vast majority, they don't currently know or care that it is x86, and they likely will go on being oblivious when they change to the alternatives, as long as it works, meets their needs, is easy to use, and is at the price they like for the features they get.

We're the minority that know the difference, and if the performance vs price is compelling enough most of us will go with the one that gets it done too.... unless they are RISC averse. 😜
 
I'm running a ten year old i5 workstation that idles at 1ghz and has a nicely quiet box fan and there's hardly a way to do better unless both box and chip go fanless.

The other threat to need a fan I suppose would be the video, just have to see about that. Workstation could host a pretty good sized chunk of aluminum or even copper, if that would help. Maybe a low-speed fan on the box for good luck, in case I want to run it on a hot day, LOL.
 
Alvar Miles Udell said:
Beats the heck out my AMD 4700U (8C/8T) Lenovo laptop

1500 - Single-Core Score
5051 - Multi-Core Score


https://browser.geekbench.com/v6/cpu/6685914
Click to expand...
Which is based on Zen 2, so yeah, going to be a little bit of a difference. 😛 That's also a 15W normal, 28W max CPU ('U' suffix); the gap would close in with a Zen 2 'H' CPU, which I mention because they article's author compared Lunar Lake 'V' chips to Meteor Lake 'H' chips.
 
JRStern said:
I totally welcome good performance on a low-power chips.
Not even thin-and-light, I want a fanless workstation.
...
Click to expand...
Fanless USFF and NUC-sized desktops, yes, exactly.

I was bummed seeing HP having to use the chunkier 120W power bricks on 12th and 13th gen Intel Core mini desktops (Elite Mini 800 G9, for example.). Several generations of Ryzen-based counterparts -- from Ryzen (1) to Ryzen 3 and never had anything bigger than a 65W brick, even on the Ryzen 7 bad boyz. Sure, peak performance is substantially higher and perf-per-watt is good under low to medium load, but just felt like a step backwards and added to my setup time as I couldn't reuse the same power supplies. I say this to say good job, Intel -- thank you for not going even hotter than Raptor Lake!!
 
Pierce2623 said:
Mine, locked at 5.6p core/4.2e core scores just under 18K. That’s pretty close to doubling up a score in the 9k area.
Click to expand...
I feel like I shouldn't have to point out the stupidity of comparing a desktop CPU with a +500/300 overclock and the extra power consumption that comes with it as if that means anything. Think of it this way: you're comparing something that has 2 more P-cores, 4 more E-cores, 12 more threads with at least 6x the power consumption (for MT) and still can't double the score (and no 18k isn't "pretty close" to doubling scores that are no lower than 9.9k).
 
You must log in or register to reply here.

TRENDING THREADS

Latest posts

Moderators online

Share this page

COMPANY
RESOURCES
FOLLOW
Top Bottom