News for hackers. Stuff that matters.
Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by wtallis on Monday January 16, 2023 @02:54PM (#34404757)
The article's title says "at 35W", but the article text says "the T-series chip is rated at up to 106 Watts". That appears to refer to the chip's short-term turbo power limit (PL2 in Intel parlance), typically effective for a default of 28 seconds if thermal limits don't kick in—but the time parameter can be adjusted by the end user (and this benchmark run has unknown provenance, so who knows what power management settings were in effect).

Since the benchmark in question (Geekbench 5) only runs for a minute or two, it does most of its work before the chip even attempts to throttle down to anywhere near 35W. An actual power measurement averaged over the entire benchmark run would yield a significantly higher value than 35W.

Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by htk on Monday January 16, 2023 @03:09PM (#34404920)
That's disappointing, I thought they were closer to Apple Silicon's performance/watt ratio.

The deceptive nature of such benchmarks is also troubling.

Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by runnerup on Monday January 16, 2023 @03:55PM (#34405360)
The benchmarks themselves aren't really deceptive, but wccftech's reporting on them is misleading. These aren't claims being made by Intel, but just random user benchmarks that appeared online.

For all benchmarks, context matters. These days, most in-depth reviewers understand how to work with transient power and thermal limits with respect to time. For example, measuring the MacBook Air M1's peak speed/time vs. its lower sustained speed after it hits thermal throttling around the 5-7 minute mark.

Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by toast0 on Monday January 16, 2023 @05:37PM (#34406415)
It's kind of hard to compare performance/watt meaningfully when the wattages aren't at all similar.

If you limit power on current generation Intel/AMD processors, the perf/watt is pretty good; depending on the specific load, sometimes better, sometimes worse than M2. When you allow more watts, perf goes up, but perf/watt goes down as you see diminishing returns. (With some loads, you may also have a point where more watts reduces performance, whoops)

Geekbench isn't great as it doesn't even attempt to capture power usage, but that may not be available or accurate on all systems anyway.

Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by bee_rider on Monday January 16, 2023 @04:08PM (#34405487)
It is a shame these kind of knobs are rarely exposed on a laptop. Sometimes I throttle my laptop cpu down to like 800MHz-1.2GHz to save power/prevent the fan from going. But this makes Vim less responsive for certain events. What I’d actually like is normal behavior but with the turbo clock limited to like… I dunno, a second.
Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by MikusR on Monday January 16, 2023 @04:18PM (#34405621)
Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by jeffbee on Monday January 16, 2023 @04:29PM (#34405733)
In Linux you want powercap tools. You can tune all three parameters in terms of power and time constant, so you can do exactly what you suggest. You can change it on the fly without rebooting so you could have a ridiculous setup like mine where I have the power limits wired up to two unused buttons on my mouse.
Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by bee_rider on Monday January 16, 2023 @05:26PM (#34406288)
Cunningham’d. Awesome, I’ll look into it, thanks.
Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by bee_rider on Tuesday January 17, 2023 @01:50AM (#34409794)
Seems to work pretty well. I was initially confused — it seems the default on my system had the “long term” limit set to some very high value, which made my changes to the short term moot. Seems like an odd default but I’ll blame ASUS for that I guess.

Still slightly confused as to what exactly the “time window” means physically. With mine set to 1000us I still seem to get multiple seconds at full power. But it bumps down before the fan spins up so that seems good enough!

Looking forward to the inevitable realization tomorrow that this is going to make my computer unusable in zoom calls.

Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by tambourine_man on Monday January 16, 2023 @06:28PM (#34406992)
If Vim isn’t responsive in a machine with hundreds of MHz something is very wrong with your setup. Vim was fast on machines with dozens of MHz. Either a bad terminal emulator or some plugin making it slow, I’d guess.
Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by pmontra on Monday January 16, 2023 @06:36PM (#34407057)
Not vim but vi, it was fast enough for me on machines with less than a dozen MHz, probably high single digit.

However we have many more layers now. I had a 80x24 serial tty exchanging ASCII characters with the computer back then.

Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by gonzo on Monday January 16, 2023 @11:31PM (#34409158)
Yes, but at what baud?
Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by pmontra on Tuesday January 17, 2023 @03:35AM (#34410373)
Probably 4 digits. I was young and not a very fast typer yet. Zenith green phosphor terminals with a repeat key. This one or very similar https://commons.wikimedia.org/wiki/File:Zenith_Z-19_Terminal...

According to https://vt100.net/heath/z19-om.pdf it can do 110 to 9600 baud. It was connected to some Z8000 based Onyx server. It was generally good but incredibly slow when more than four or five of us were compiling code for the tests at university class. Pascal, Berkeley p system or something with a similar name.

Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by pclmulqdq on Monday January 16, 2023 @06:34PM (#34407041)
It's probably a plugin. A lot of them are very slow.
Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by 3np on Tuesday January 17, 2023 @04:18AM (#34410586)
As far as I understand, neovim has multithreading where vim doesn't here, making heavy and bad plugins have less impact.
Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by bee_rider on Monday January 16, 2023 @07:04PM (#34407304)
So there are two problems I guess, user-based and technical.

User problem: since I use Vim for everything, my expectations as far as responsiveness goes are probably not calibrated correctly. It is almost always very good, so the moments of badness are noticeable. The user (me) is unreasonably picky.

Technical: LaTeX syntax highlighting. It is I’m pretty sure, generally known to be a bit of a pain. Lots of nested environments that can go back dozens of lines and change how commands are interpreted. It is happy in a decent (not huge or anything) sized Fortran code, so I think config is mostly OK. Maybe I should look around and see if there’s a nice LaTeX plugin out there.

Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by tambourine_man on Monday January 16, 2023 @07:21PM (#34407465)
I think you found the culprit. Syntax highlighters are notoriously slow.

You have every right to have high expectations for performance with Vim

Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by celrod on Tuesday January 17, 2023 @04:29AM (#34410644)
Perhaps tree sitter can help the syntax highlighting? https://github.com/latex-lsp/tree-sitter-latex
Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by lhl on Tuesday January 17, 2023 @12:15PM (#34415278)
Related, but Neovim has experimental treesitter support (w/ Latex) built in these days: https://github.com/nvim-treesitter/nvim-treesitter

Depending on how hard you push it, Neovim can also be noticeably faster than Vim (notably Lua/LuaJIT being much faster than VimScript)

Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by pletnes on Tuesday January 17, 2023 @05:51AM (#34411096)
Some vim plugins are slow. Fortran highlighting used to be super slow for certain use cases 10 years ago. I think there were some bad regexes. Latex documents are often long (cf other code) and the syntax rules are complex.
Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by ObscureScience on Monday January 16, 2023 @07:05PM (#34407310)
It's not vim, but the OS/graphical system that you are most likely using underneath. While having Firefox/Chromium open for reference to what you are working on.
Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by 3np on Tuesday January 17, 2023 @04:16AM (#34410577)
Specifically worth comparing terminal emulator performance. I noticed that for example (not surprisingly I guess) alacritty has been both the worst and the best depending on the setup.
Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by pengaru on Tuesday January 17, 2023 @02:38AM (#34410052)
There are definitely some pathological situations where vim becomes unresponsive even on a beefy box. Usually there's exceptionally long lines of text involved.

Furthermore there's the whole intentional delay on ESC exit from modes like an aborted search query... that can make it feel unresponsive but it's just a timeout. Try it, hit '/' in vim, then ESC to abort the search, count a full second of unresponsiveness.

Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by lhl on Tuesday January 17, 2023 @12:39AM (#34409498)
If you're running on Linux, almost all of this is completely configurable using ryzenadj for AMD laptops or powercap and thermald for Intel chips. Here's a document on how you might go about adjusting this w/ powercap: https://github.com/junaruga/framework-laptop-config/wiki/Imp...

For anyone looking for a good summary of the knobs available for AMD: https://github.com/FlyGoat/RyzenAdj/wiki/Renoir-Tuning-Guide

Or for Intel: https://github.com/lhl/linuxlaptops/wiki/2022-Framework-Lapt...

Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by bayindirh on Tuesday January 17, 2023 @04:09AM (#34410544)
Or you can always fine tune the on-demand governor to gracefully speed up the processor as the load increases and keep it there for a second or so and bring it down.
Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by lhl on Tuesday January 17, 2023 @11:59AM (#34415019)
Modern Linux kernels load the `intel_pstate` frequency driver by default these days which has it's own governors that don't quite act the same way as generic ones, but you can control scaling for them w/ the EPB/EPP hints.

* https://www.kernel.org/doc/html/v4.12/admin-guide/pm/intel_p...

* https://manpages.ubuntu.com/manpages/kinetic/en/man8/x86_ene...

* https://wiki.archlinux.org/title/CPU_frequency_scaling

Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by ajross on Monday January 16, 2023 @04:35PM (#34405799)
> Since the benchmark in question (Geekbench 5) only runs for a minute or two, it does most of its work before the chip even attempts to throttle down to anywhere near 35W.

That doesn't sound right at all. Nothing in a PC system (absent water systems with huge reservoirs I guess) is going to buffer excess heat on minute-long timescales, not even close. There's literally nowhere for that energy to go; 125W for a minute would be melting the solder joints.

CPU throttling works on at most small-integer-second scales.

Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by wtallis on Monday January 16, 2023 @04:42PM (#34405866)
CPU throttling happens on many different timescales. That's why Intel processors have multiple power limits (PL1, PL2, PL3, PL4), in addition to current and temperature-based throttling mechanisms. The time constant for PL2 is usually either 28 seconds or 56 seconds. At those timescales, the concern is usually not with power delivery or CPU die temperature but rather with exterior case temperatures that the user may be directly touching.

Based on the reported benchmark performance, it seems very unlikely that temperature-based throttling kicked in, and it's clear that the chip was operating well above 35W for at least a large portion of the benchmark run. So the PL1 and PL2 turbo power limits are the relevant controls at play here.

Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by ajross on Monday January 16, 2023 @04:46PM (#34405894)
Yeah yeah, I know. I'm just saying that there's zero chance that throttling is affecting this measurement. The idea that an Intel machine is significantly faster for 2-3 minutes after the start of a benchmark is just silly, that's not the way these things work. Go start a benchmark of your own to see.

Again, the thermodynamic argument is fundamental here. You're saying that a "35W" CPU is "actually" drawing power equivalent to a 125W CPU for exactly the time of a benchmark, which is several minutes. That excess would have nowhere to go! There's no reservoir to store it. (Obviously the cooling system could take it away, but part of your argument is that the cooling system is only good for 35W!).

Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by adrian_b on Monday January 16, 2023 @05:26PM (#34406289)
Even if the configuration may be different from motherboard to motherboard and from laptop to laptop, exactly as wtallis said, most Intel CPUs are configured by default to consume during the first 28 seconds a power 2 to 3 times greater than the nominal TDP, e.g. 105 W for a 35 W CPU.

Most, if not all, subtests of GeekBench need less than 28 seconds, so it is quite possible for the entire benchmark to be run at an 105 W power consumption. Whenever a subtest finishes, the power consumption momentarily drops, which resets the 28 second timer.

If the computer has poor cooling, it may happen that when the CPU spends too much time and too frequently at an 105 W power consumption the junction temperature limit is reached, which triggers thermal throttling and the power consumption is reduced. This is a different mechanism, independent of the one that reduces the power consumption down to the nominal TDP after 28 seconds, or after another configured time.

Thermal throttling reduces the power consumption only enough to keep the temperature under the limit, so the power consumption may remain greater than the TDP until the 28 seconds pass.

Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by wtallis on Monday January 16, 2023 @04:48PM (#34405917)
> The idea that an Intel machine is significantly faster for 2-3 minutes after the start of a benchmark is just silly, that's not the way these things work. Go start a benchmark of your own to see.

I've done so, on many occasions, with actual power meters rather than trusting software power estimates. You really do commonly see a laptop's power consumption drop significantly ~28 seconds into a multithreaded CPU benchmark.

> (Obviously the cooling system could take it away, but part of your argument is that the cooling system is only good for 35W!).

I make no such claim that the cooling system is limited to 35W. I only claim that the default platform power management settings from Intel impose a 35W long-term power limit, unless the system builder has adjusted the defaults to account for whatever form factor and cooling choices they've made.

Perhaps you haven't realized that the turbo power limits will still kick in even if the CPU die temperature is not too hot—because they're not actually a temperature-based control mechanism?

Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by ajross on Monday January 16, 2023 @05:13PM (#34406147)
Uh... this is a socketed CPU: https://www.intel.com/content/www/us/en/products/sku/230498/...

Now I see where the disconnect was. You're right, if this was a laptop that could happen. It isn't, and it didn't.

Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by ribit on Monday January 16, 2023 @05:25PM (#34406275)
Even in a laptop CPUs regularly draw more power than the TDP for non-trivial amounts of time.
Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by wtallis on Monday January 16, 2023 @05:49PM (#34406563)
It's a socketed CPU intended for low-power small form factor systems and thus will usually be running with Intel-recommended power limits or lower, for all the same reasons that laptop CPUs are usually running with low power limits. The control mechanisms don't actually function any differently between their laptop and desktop CPUs, they just have different default parameters (the various turbo limits).

The only relevance of the socketed nature of this part is that it is easy to put it in a normal desktop form factor where a big heatsink and possibly tweaked turbo limit settings can be used to generate misleading benchmark results. But it's not actually certain that this is what's happening; the Intel-recommended default behavior for this chip can plausibly produce the reported results—just not in any way that could be reasonably described as "35W".

Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by neilmovva on Monday January 16, 2023 @06:07PM (#34406758)
I was curious about exactly how much burst heat could be absorbed, so I asked WolframAlpha [0]. In a 15" workstation laptop, I think the CPU could quite reasonably pull +100 watts over steady-state TDP for 30 seconds. (100-gram aluminum heatsink absorbing 100W * 30sec -> ∆T = +33ºC)

[0] https://www.wolframalpha.com/input?i=%28100w+*+30+sec%29+%2F...

Re:Intel Core i9-13900T 35W CPU Outperforms 125W i9-12900K by mise_en_place on Monday January 16, 2023 @07:40PM (#34407640)
I always get confused with Intel’s clock speeds and power draw now. Because depending on the p-state or c-state it’s in, it can be severely underclocked. Even trying to set “performance” p-state doesn’t work all the time, at least on my Ice Lake Xeon.