Jump to content

Why does the base clock of a CPU even exist?

Go to solution Solved by YoungBlade,

The base clock can be reached in certain scenarios under stock conditions. The most common is intensive AVX workloads that push a CPU past its power envelope and thus force it to clock lower to compensate.

 

Basically, the base clock is a guarantee by Intel and AMD that, under stock conditions, you will never see a lower clockspeed than that under load, and the reason it's that low is that they found some situation in their testing that caused it to drop that low at stock.

 

It might be an incredibly rare situation that normal users will never encounter, but it might happen.

No, I am not talking about that 100 MHz base clock, I am talking about the 4.5 GHz base clock on the 7950X. Why do they exist? I've never seen them come in any calculation or any scenario. The boost clock is what the actual speed of the CPU is, so what is that base clock?

Microsoft owns my soul.

 

Also, Dell is evil, but HP kinda nice.

Link to comment
Share on other sites

Link to post
Share on other sites

The base clock can be reached in certain scenarios under stock conditions. The most common is intensive AVX workloads that push a CPU past its power envelope and thus force it to clock lower to compensate.

 

Basically, the base clock is a guarantee by Intel and AMD that, under stock conditions, you will never see a lower clockspeed than that under load, and the reason it's that low is that they found some situation in their testing that caused it to drop that low at stock.

 

It might be an incredibly rare situation that normal users will never encounter, but it might happen.

Link to comment
Share on other sites

Link to post
Share on other sites

With Intel, I believe it is the clock that is guaranteed to be achievable with the stock cooler (or equivalent) and will not exceed the TDP (while the boost clock can, if it has enough headroom thermally), so probably more insurance for their bins than for you. With AMD, I'm not sure how they define it.

Link to comment
Share on other sites

Link to post
Share on other sites

26 minutes ago, Hensen Juang said:

The boost clock is what the actual speed of the CPU is

The boost clock is the speed it will (try to) boost up to if conditions permit it.
Intel:

Quote

Max Turbo Frequency

Max Turbo Frequency is the maximum single-core frequency at which the processor is capable of operating using Intel® Turbo Boost Technology and, if present, Intel® Turbo Boost Max Technology 3.0 and Intel® Thermal Velocity Boost. Frequency is typically measured in gigahertz (GHz), or billion cycles per second.


AMD:

Quote

Max boost for AMD processors is the maximum frequency achievable by a single core on the processor running a bursty single-threaded workload. Max boost will vary based on several factors, including, but not limited to: thermal paste; system cooling; motherboard design and BIOS; the latest AMD chipset driver; and the latest OS updates. GD-150. Learn More.


 

26 minutes ago, Hensen Juang said:

so what is that base clock?

The minimum frequency that it will reach on all cores without throttling. Intel's definition from their Ark page for example:

Quote

Processor Base Frequency

Processor Base Frequency describes the rate at which the processor's transistors open and close. The processor base frequency is the operating point where TDP is defined. Frequency is typically measured in gigahertz (GHz), or billion cycles per second.

 

or AMD's from their FAQ:

Quote

https://www.amd.com/en/support/kb/faq/pibrmats3
The base clock can be defined as the sustainable speed across all cores in a running processor with adequate cooling. Whereas the maximum boost clock is the peak frequency achievable by a single core on the processor running a bursty single-threaded workload1.

 

In that sense not seeing it is a good thing, because that means conditions are good enough for it to boost higher than base clock.

 

Crystal: CPU: i7 7700K | Motherboard: Asus ROG Strix Z270F | RAM: GSkill 16 GB@3200MHz | GPU: Nvidia GTX 1080 Ti FE | Case: Corsair Crystal 570X (black) | PSU: EVGA Supernova G2 1000W | Monitor: Asus VG248QE 24"

Laptop: Dell XPS 13 9370 | CPU: i5 10510U | RAM: 16 GB

Server: CPU: i5 4690k | RAM: 16 GB | Case: Corsair Graphite 760T White | Storage: 19 TB

Link to comment
Share on other sites

Link to post
Share on other sites

28 minutes ago, Hensen Juang said:

No, I am not talking about that 100 MHz base clock, I am talking about the 4.5 GHz base clock on the 7950X. Why do they exist? I've never seen them come in any calculation or any scenario. The boost clock is what the actual speed of the CPU is, so what is that base clock?

Its a synchronized clock across the bus. Each component having their own multipliers and internal clocks, but for them to communicate effectively, there has to be a constant 'tick' that they can all negotiate to.

 

Regarding 'base clock' for a multiplier clock, it doesn't really matter and is arbitrary. Intel/AMD set arbitrary expectations for a given bin of silicon and probably determines what the 'base clock' is theoretically then experimentally with first samples of a production.

Ryzen 7950x3D PBO +200MHz / -15mV curve CPPC in 'prefer cache'

RTX 4090 @133%/+230/+1000

Builder/Enthusiast/Overclocker since 2012  //  Professional since 2017

Link to comment
Share on other sites

Link to post
Share on other sites

On 9/22/2023 at 12:47 PM, W1zarDdd said:

Energy Saving: Increasing the processor frequency consumes more power and creates more heat. However, in some operating scenarios the processor may not require maximum performance.

While this is true base clock (BCLK) is really what Intel came up with years ago for their chips as a standard.

Used to be systems ran FSB which was anything from 100Mhz to 200Mhz, depending on what gen you refer to but FSB is normally thought of as being 200MHz default on the board's bus.

That means a CPU didn't have to run as high of a multiplier to get the same system speed, for example to get 4.0GHz from a system you either run 40x/100 BCLK or 20x/200 FSB to get the same system speed (4.0GHz).
FSB has the CPU running at a lower clock (multiplier) to get the same system speed but what Intel did was to shift it to a default 100MHz and letting the CPU do all the work getting it up to speed.

AMD didn't follow suit right away but with Sockets AM1/FM2 onward, they changed from the FSB standard to the BCLK standard.
BTW it's been proven BCLK chips CAN run up on the system bus like older chips do but Intel's standard is enforced by them to all board manufacturers so they have to play along with it.

One thing BCLK takes away is RAM tweakability.
If using FSB you can run a mix of CPU multiplier and bus speed to zero in on what performs best, that also giving greater flexibility for RAM tuning. 
Since you can't vary bus speed much by using BCLK, your options for finding the "Right" RAM speed are limited since you can't really overlap RAM speeds achieved based on RAM MHz vs the RAM divider used but with FSB you can do that. 

To that end, all I can say is I don't make 'em, I just run 'em.

Hope this helps to clear up some of the confusion.

"If you ever need anything please don't hesitate to ask someone else first"..... Nirvana
"Whadda ya mean I ain't kind? Just not your kind"..... Megadeth
Speaking of things being "All Inclusive", Hell itself is too.

 

Link to comment
Share on other sites

Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now

×