Same behavior from Intel, using MBA tricks instead of innovating.<p>[1] Intel "'Forgot' to Mention 28-Core, 5-GHz CPU Demo Was Overclocked to such an extreme that it required a one-horsepower industrial water chiller" <a href="https://www.tomshardware.com/news/intel-28-core-cpu-5ghz,37244.html" rel="nofollow">https://www.tomshardware.com/news/intel-28-core-cpu-5ghz,372...</a><p>[2] Intel decides Cinebench "which has a really niche usefulness" in their Tiger Lake presentation <a href="https://www.youtube.com/watch?v=aFHBgb9SY1Y" rel="nofollow">https://www.youtube.com/watch?v=aFHBgb9SY1Y</a><p>[3] Intel allegedly paid manufacturers "rebates" to limit their purchases of AMD, ended up paying $1.25B to AMD and $1.45B more to the EU for the antitrust practices. <a href="https://en.wikipedia.org/wiki/Advanced_Micro_Devices,_Inc._v._Intel_Corp" rel="nofollow">https://en.wikipedia.org/wiki/Advanced_Micro_Devices,_Inc._v...</a>.<p>From the article:<p><pre><code> Intel’s explanation for why AMD CPUs lose so much performance
on battery is that the systems wait for 7-10 seconds before
engaging turbo mode
... the settings that control the amount of time before turbo
modes engage and the overall performance delta between AC and
DC power are settings that the OEM controls, not AMD.
... Intel’s five comparison systems for itself came from MSI,
Lenovo, Intel itself (in the form of a laptop kit), and two
from HP. Intel is drawing on a much wider range of manufacturers
for its own systems. I don’t know anything about the NUC laptop
kit - haven't had the opportunity to test one - but I would have
preferred the fifth system be a standard commercial comparison,
and the AMD systems should have been drawn from an equally diverse
pool of hardware as the Intel ones were. There are four
manufacturers represented for Intel, and two for AMD.
...
When Intel gave its presentation, it made a point of calling
out the fact that Cinebench R20 doesn’t show the same behavior
as the other benchmarks it had chosen to highlight.
The "oddly" is straight-up FUD. Cinebench R23 also doesn’t
show the 30-48 percent pattern of decline Intel claims. Neither
does Corona Render. Neither does Handbrake. Neither does
JetStream 2. Neither does Blender 2.90. Neither does the
Blender 1.0Beta2 benchmark (not shown, but I ran it).</code></pre>
My 4750u (in T14 thinkpad) doesn't go to 4GHz clock in the first 10s of load when on battery. After 10s it jumps to 4GHz+. Which means that for my bursty workloads like running unit tests in python, linters, etc. I get 60% of performance. To circumvent that I often use external powerbank just to make it 'plugged in'. Running kernel 5.9 btw. Annoying AF.
One of the things that sucked about working for Intel is that you just knew you were working for a company that had the institutional personality of a complete raging arsehole. HR people would explain to you that whilst yes, those floating point units did demonstrably produce the wrong answers, Intel as an organisation doesn't accept that it did anything wrong, customer expectations were simply misplaced.<p>Geopolitically Intel is probably going to need to get bailed out, but it's a toxic company that could do with disappearing. I won't be mourning their Sales & Marketing teams.
<a href="https://www.extremetech.com/wp-content/uploads/2020/11/Performance-Comparison-Combined.png" rel="nofollow">https://www.extremetech.com/wp-content/uploads/2020/11/Perfo...</a><p>oh yes, I totally see this performance drop on battery, Intel simply switched laptops around. Its i7 that drops like a rock on battery.
Very happy to see Apple roll out their own processors.<p>Intel is well know for these tricks.<p>Quotable from the article.<p>>is an overreach that recalls Intel’s behavior from the early 2000s in the most unflattering of ways. If I want to know whether the company building the fastest CPU core on a per-clock, per-watt basis thinks AMD’s product stack is valid on the basis of its on-battery performance, I’ll ask Apple.
Walking a fine line here:<p>I'm not saying it's okay for manufacturers to present misleading data like this—they really shouldn't—but, this has basically been standard practice since the beginning of time, hasn't it? Journalists shouldn't be taking a competitor's claims at face value, and I expect the vast majority are smart enough to know this.