Intel: AMD Weak On Battery-Powered Laptop Performance - But DPTF On Linux Still Suck

[phoronix]

Phoronix: Intel: AMD Gimps On Battery-Powered Laptop Performance - But DPTF On Linux Still Sucks

Intel held a virtual event last week to basically plead their case that AMD Ryzen laptops are gimping on battery-powered performance compared to their own offerings. It was all Windows focused, but at least given their emphasis now on battery performance gave me another opportunity to prod over the lackluster state of Intel DPTF support on Linux with it not being pleasant out-of-the-box and one of the few areas encumbered by blobs or lack of public documentation...

http://www.phoronix.com/scan.php?pag...ry-Performance

[skeevy420]

I'm curious if there's something in regards to a more aggressive battery scheduler mode in use by AMD's firmware or simply unoptimized CPU schedulers for AMD in general.

I dunno, something just seems off about those numbers and my first instinct is they compared a power-saving mode with a performance mode. That's just what it looks like. Whether by accident or on purpose to fluff Intel numbers is another matter.

[GruenSein]

I'm curious if there's something in regards to a more aggressive battery scheduler mode in use by AMD's firmware or simply unoptimized CPU schedulers for AMD in general.

I dunno, something just seems off about those numbers and my first instinct is they compared a power-saving mode with a performance mode. That's just what it looks like. Whether by accident or on purpose to fluff Intel numbers is another matter.

This also seems highly suspicious to me. I haven't read a single review mentioning this "issue". Overall, AMD's process technology and somewhat lower clocks actually suggest better battery performance on paper. As always, it is a first party benchmark and we all know the stunts Intel have pulled recently like for example comparing mobile gaming performance with completely different GPUs. Beyond that, presenting "Outlook Mail Merge" as a performance indicator just seems desperate to me. They must have search a long time to actually find anything that suits their story.

[ms178]

Mimimi, Renoir gets all the buzz in the press, mimimi.

[MadCatX]

It looks like Intel's R&D has shifted gears towards identifying that handful of benchmarks where they can still look competitive. At least until Zen 3 laptop chips come out, not to mention that Apple's M1 completely destroys anything Intel in this exact kind of benchmark.

Since all of the tests they had done were web-based, I wonder how much could WiFi performance affect the results. It could be that the Realtek chips found on most AMD laptops don't perform as well in power saving modes as Intel's. As a happy T14 Gen1 with 4750U owner I can't say I noticed any performance degradation at all on battery power and I tend to use all of its 8 cores a lot.

[Flaburgan]

I don't get those numbers. To me they mean nothing if you don't actually show the watt consumed during the test. I mean I can easily set my CPU so it will be as powerful when unplugged than when plugged, but the battery will not last a long time. So what is Intel saying there? If they are powerful but consuming a lot of power, I don't see the point...

[kgardas]

Am I that blind or has Intel really forgotten to mention battery live at the end of test? You know, there is one thing about running hot as on AC power and completely another is how long I'll stay alive while working in this style... Somehow I miss that line in Intel thinking here...

[EvilHowl]

Well, I wasn't expecting Intel to say AMD CPUs are better either.

[Spacefish]

Looks like Intel marketing grabbing every Straw they can catch..
b.t.w. the Intel CPUs have a configurable TDP of 12-28W where the AMD CPUs have a TDP of 10-25W, so the Intel CPU has a larger power budget potentially.

If i just look at the first laptop, for intel it´s a
MSI Prestige 14 Evo for AMD it´s a Lenovo Xiaoxin 13

So the Intel is larger and performance targeted, so potentially it has a better cooling solution, thereby allowing a higher TDP..

So potentially:
- Comparing Apples to Oranges
- Very specific configuration (like choosing "high performance" profile or having a stupid default profile which drains the battery faster)

Furtheremore: 11th Gen Intel will be up against Zen 3 (Cezanne) not Zen 2 so comparing last years platform to your current year platform, yeahh marketing!

[microcode]

This is an extremely disingenuous marketing campaign from Intel, just like usual. Normalizing for power, there is no point where Intel's most comparable chips perform better this time around.