Intel Announces 13th Gen "Raptor Lake" - Linux Benchmarks To Come

[coder]

You know PL2 limits (and stuff like "Multi core enhancment") are set by motherboard manufacturers?

Then Intel's product literature for their desktop CPUs needs to specify the range, like they do for their mobile parts. Anything else would be misleading, especially if common practice is to set them higher.

Gen 13 will be another chance for Intel. Let's hope they don't embarrass themselves, but I wouldn't count on it.

And again Package power is power of CPU, GPU, chipset related stuff in chip and I/O. Intel power limits are only towards CPU, package power is all of those together.

That's not true. Package power refers to the CPU package, which is what they specify and regulate. I think you're confusing it with "system power"?

[piotrj3]

Then Intel's product literature for their desktop CPUs needs to specify the range, like they do for their mobile parts. Anything else would be misleading, especially if common practice is to set them higher.

Gen 13 will be another chance for Intel. Let's hope they don't embarrass themselves, but I wouldn't count on it.


That's not true. Package power refers to the CPU package, which is what they specify and regulate. I think you're confusing it with "system power"?

You lack some knowdlege.

On intel most of chipset is not literally chipset, it is inside CPU. Majority of PCI-E lanes, SATA, USB ports are wired directly to CPU, not chipset. Not to mention Intel CPUs commonly also have iGPU which is also part of CPU package. PL1/PL2 applies only to processor unit itself, I/O and iGPU is outside of it.

Note: The System on Chip processor integrates multiple compute cores and I/O on a
single package. Platform support for specific usage experiences may require additional
concurrency power to be considered when designing the power delivery and thermal
sustained system capability.

This is issue with measurements from those tests. For example people forget how most motherboards of AMD X470 had literal fan on top of chipset and that chipset was consuming often up to 15W of power while Amd CPUs still do a lot of I/O by itself.

But again that is OK. Intel maximum spiking 271W instead of 241W (and most of time being 250-255W for very big stress test) seems reasonable for how much stuff is on Intel CPU. AMD 5950X going 120W with declared TDP of 105W is also ok. Going 80W over on average long term without OC and without messed up setup from motherboard is NOT.

And Intel's product literature exactly specify that. There are 2 public volumes specifically about information like that and GamersNexus was pointing it out in the past that Intel's has own recommendations that motherboards do not have to comply with and very often don't. A lot of motherboards loved:

- pushing BCLK 1-5% higher (and 5% in some edge cases could make stability issues),
- enable multi-core-enhancment aka remove Intel's turbo limits for multi-core workload (Intel's recommendations (and default) were that all-core was boosting less then single core and that had big efficiency diffrence, but motherboards often allowed all cores at once to boost to max speed what eaten efficiency in multi-core workloads alive),
- remove turbo limit times by default - doesn't matter anymore with 12th gen Alder lake K CPUs, but did matter a ton in 11th gen and older,

[coder]

You lack some knowdlege.

We'll see. Really, don't we all?

On intel most of chipset is not literally chipset, it is inside CPU. Majority of PCI-E lanes, SATA, USB ports are wired directly to CPU, not chipset.

Well, if that's what you mean, then don't call it a "chipset". More to the point, it does fall in the definition of what Intel means by "package power". If they didn't mean power to the entire CPU package, they wouldn't call it "package power" - they'd call it "cores power" or some such thing!

What you're describing used to be known as "North Bridge", before the CPUs absorbed the memory controller and PCIe lanes. Lower-bandwidth peripherals would be connected via the "Southbridge", which (in desktop platforms) is still a separate physical package on the motherboard. In mobile (BGA) CPUs, you'll see it as a separate die inside the CPU package.

So, I thought you meant the Southbridge, when you said "chipset".

PL1/PL2 applies only to processor unit itself, I/O and iGPU is outside of it.

I think your quote doesn't support that claim, nor did you cite a source.

One piece of evidence to the contrary are the KS-series CPUs. Their iGPU is disabled, which allows the CPU to have a tiny bit more power budget. Hence, they tend to be pretty popular with overclockers.

people forget how most motherboards of AMD X470 had literal fan on top of chipset and that chipset was consuming often up to 15W of power while Amd CPUs still do a lot of I/O by itself.

I remember that being true of the X570, but maybe you're right about the X470, also. One reason they used a lot of power is that they were made on a 14 nm GF process node and had to support PCIe 4.0.

Intel maximum spiking 271W instead of 241W (and most of time being 250-255W for very big stress test) seems reasonable for how much stuff is on Intel CPU.

If the stress test wasn't hitting any of those peripherals or the iGPU, then they're irrelevant. Idling them uses just a few Watts, at most.