Apple M1 vs Intel i7: Cherry-picked benchmarks and shifting Tiger Lake SKUs leave Intel looking revolutionary rather than evolutionary

[mrfroid]

Apple was actually right here.
Okay, notebookcheck might have testet it with different brightness. But then Intel's claim of Acer's battery life is a lie.

Notebookcheck mentions benchmark numbers, Intel tells you what they did: Netflix stream + tabs in a browser (real world usage).

[Jonny 5]

Team Notebookcheck may have missed a beat here though. Instead of focusing on generating revenue for their themselves by trying to bring a Source down a few pegs, it would have been better for Notebookcheck to simply a) make judicious attempts at impartiality or, b) wear their bias with grace and not choose to couch their glaringly obvious clickbait articles in pseudo ethical journalism. Since Honesty's introduction by hopefully their parents, this is the path Adults have taken -- evolving and improving rather than resorting to taking pot-shots at Titans of an Industry that support their website.

[Friendo]

Team Notebookcheck may have missed a beat here though. Instead of focusing on generating revenue for their themselves by trying to bring a Source down a few pegs, it would have been better for Notebookcheck to simply a) make judicious attempts at impartiality or, b) wear their bias with grace and not choose to couch their glaringly obvious clickbait articles in pseudo ethical journalism. Since Honesty's introduction by hopefully their parents, this is the path Adults have taken -- evolving and improving rather than resorting to taking pot-shots at Titans of an Industry that support their website.

Nerd

[JohnS]

Apple has an advantage with its own customized ARM chip and I mean they really customized their M series to the MacOS and Mac hardware. By no means is this an off the shelf ARM series chip and I doubt if it was placed in a non Mac notebook it could perform as well. Sort of why Windows even though it has a ARM release may never actually work natively on an Apple ARM CPU. Personally, I would rather have a ARM chip in a notebook not tied specifically to Apple but rather one that could run a ARM based OS like Linux or something else. I don't want to be tied down to Apple's whims on Mac's with their customized ARM chips.

[Alexandro]

hello, Intel.
first of all, just have a look spec for swift5 - resolution is 1080p (1920 x 1080) only while Apple M1 AIR has 2560 x 1080 - you should know what i mean,, second - i7 has 10-15nm silicon technology VS 5nm Apple M1 - nothing to say how we can compare powerconsumption.. and in the end - last - battery: Apple M1 has onboard 49.9‑watt battery while Acer has 56watt. and in the end - to be honest - if you switch M1 to 1080p resolution same as Acer Swift - you will be very surpriced, Intel, just try and compare, common! :) LOL

[Stephan E]

What would the battery life have been like if they used their own edge browser?

[Kenkor]

You are buffons if you believe the m1 comes close. You are losing decades of software that will run extremely slow on the m1 emulated layer. Decades. And its moronic to argue that the m is customised for the hardware. Escuse me, does intel not help oems with their designs? Are you implying that intel is somehow sacrificing performance with their drivers? You cant program a game really. On the m1. You need intel.

[Shirubax]

I am all for competition, and while I have no love for Intel, I do want to see them and other vendors come out with something that can challenge the m1.  But the current chips aren't even close.  They have faster chips (through virtue of multiple cores), and they have lower power chips with nowhere near the performance.  They have nothing in the same power class with even class with even remotely the same performance.

If I were them, I would own up to it and lower prices while I develop something new.

As for the "extremely slow emulation", they is where the m1 is most surprising.  For example, I have a top of the line 16 inch macbook of the most recent model with the highest speed i9 chip available, and I also have a top of the line thinkpad x1.  The m1 easily beats most of them on almost all tasks and benchmarks, Under Emulation.  And it does that while consuming much, much less per.  That is pretty much unheard of in the history of computing.   Not to mention, this is apple's lowest end chip!  If Intel is playing catchup now, what will happen when Apple releases chips with a core count of 12 or more?

Now, it isn't all roses.  I don't want Apple to be the only choice, so I do want competitive chips from other vendors, whether that means Intel, and, qualicom, Samsung, Toshiba, or whomever.

But at the moment, there is no contest.

[slws]

Well, my Intel laptop is actually good enough for my use - it doesn´t need to be updated now.
At the same time:  M1 is so promising - I am waiting what is comming next! LOL!

[pdx]

The Tiger Lake comparisons show what the M1 laptops are  sacrificing by using a mobile phone chip.

Now we know why Apple's PR compares vs Comet Lake chips.

Implying Tigerlake can possibly match Apple silicon in power efficiency.  You are 100% delusional.

[Astar]

You know what is pathetic? Notebookchat being such blatant hypocrites now that Intel is basically using the age old tricks against CrApple ... which CrApple copied from Intel! Cherry picked benchmarks!

What else is pathetic? The i-Stupids & i-Diots crying foul when what Intel did is merely point out the strengths of the x86/x64 architecture over ARM - CPU intensive real world workloads! Basic things that CrApple conveniently IGNORED when they harped on & on ad nauseum about single core scores and power efficiency of ARM based M1.

Wow... we know Intel is crap. I have no sympathy for Intel at all given how they have screwed consumers for decades. But they merely used the trite same crappy single-core single-thread benchmark scores trick when they couldn't compete against AMD when Zen first launched. They still do that because even though AMD is now superior even in single-threaded scores, Intel looks "less bad" compared to their hopeless multi-core scores.

Do realise that CrApple merely copied this Intel playbook by flogging the same lame old single core score trick against x86. We know ARM does well in low CPU usage simple application scenarios - big deal! The ARM M1 of course will do well given it has 4 "smartphone" efficiency ARM cores. Duh...

But nobody gives a damn about power efficiency when running really heavy workloads. Time is money when crunching compute intensive tasks - that's the whole bloody point of x86!

How is it that when CrApple can use CHERRY-PICKED synthetic benchmarks like Geekbench 5 (not even the x86 version but using theM1 optimised native version, mind you!) but the i-Stupids don't realise that they are biased scores?

Intel used real world benchmarks like Cinebench and real world workloads here, like games & Topaz image editing software - areas where M1 always struggles at because it is essentially a 5W ARM CPU overclocked-overvolted to its limit to run at 20-22W.

Real world workloads are the only true way to show performance because its essentially like a 100m sprint timed with a stopwatch.
We don't care what it takes, finish it as fast as you can!

The i-Diots & i-Stupids here clearly don't even know why Geekbench is synthetic test garbage. Its a suite of tests measuring different aspects of a CPU's capabilities, like AI, machine learning, certain types of calculations like floating point etc. etc. and then creates an AVERAGE score of all the various scores. Obviously if you pay them enough "marketing dollars" they will assign higher weightage to the scores that your CPU does well in vis-a-vis other competitors! Intel & CrApple, with their well known huge marketing dollars always come out top with their bribes.

I won't bother to explain further except cut & paste what other experts have said. EEtimes and PC Perspectives, among many others have stated time and again how Geekbench is basically biased and hence useless (see
https://www.eetimes.com/new-geekbench-5-improves-tests-but-adds-bias/

"In a review of some of the results posted for the same platforms on both
Geekbench 4 and Geekbench 5, we found that the change in performance numbers was higher on the Android OS and AMD processor than on Apple's operating systems or Intel processors (the table provides a sample of these results). The Apple OSs and Intel processors appear to have benefitted most from the benchmark changes, much of which is likely attributed to the elimination of the memory and battery test that benefit the AMD processors and Android OS.

PC Perspective did a similar comparison both versions of the benchmark on a pair Intel and AMD-based PCs and the differences are rather drastic — showing a much higher relative performance of the Intel-based platforms than the AMD platforms."

Hilarious how the i-Stupids don't understand that all these Geekbench scores CrApple cherry picked are obtained through marketing dollars to skew performance scores?

AMD and Android as a whole do not do well in these synthetic scores because they simply don't pay Geekbench any money. (1) in AMD's case they do not wish to enter into a marketing pissing contest knowing that Intel will simply p*** more money down marketing drains than them; (2) Android as a whole have already conquered the mobile market with 90% marketshare with a variety of ARM CPUs. The individual players, like Samsung, don't see the need to waste money promoting Android for their competitors like Huawei or Qualcomm. Not to mention the fact that the richest player, Google, doesn't sell ARM CPUs!

This is really about 2 s*** companies slinging crap at each other. Its hilarious how the hypocrite i-Sheeps cry foul when Intel twists their panties!

Really only AMD comes out looking great in this! Absolutely destroys Intel and M1 garbage in all-core multi-core tests. After all, who the hell buys modern 8 core CPUs for single-core scores? Oh wait... Apparently the Intel-tards & iSheep do... ...