Wednesday, January 29th 2020

Intel Core i5-L16G7 is the first "Lakefield" SKU Appearance, Possible Prelude to New Nomenclature?

Intel Core i5-L16G7 is the first commercial SKU that implements Intel's "Lakefield" heterogenous x86 processor architecture. This 5-core chip features one high-performance "Sunny Cove" CPU core, and four smaller "Tremont" low-power cores, with an intelligent scheduler balancing workloads between the two core types. This is essentially similar to ARM big.LITTLE. The idea being that the device idles most of the time, when lower-powered CPU cores can hold the fort; performance cores kick in only when really needed, until which time they remain power-gated. Thai PC enthusiast TUM_APISAK discovered the first public appearance of the i5-L16G7 in an unreleased Samsung device that has the Userbenchmark device ID string "SAMSUNG_NP_767XCL."

Clock speeds of the processor are listed as "1.40 GHz base, with 1.75 GHz turbo," but it's possible that the two core types have different clock-speed bands, just like the cores on big.LITTLE SoCs. Other key components of "Lakefield" include an iGPU based on the Gen11 graphics architecture, and an LPDDR4X memory controller. "Lakefield" implements Foveros packaging, in which high-density component dies based on newer silicon fabrication nodes are integrated with silicon interposers based on older fabrication processes, which facilitate microscopic high-density wiring between the dies. In case of "Lakefield," the Foveros package features a 10 nm "compute field" die sitting atop a 22 nm "base field" interposer.
Intel's nomenclature for the Core i5-L16G7 is fascinating. It condenses Intel's lengthy "i9-10980XE" (7-character) model names down to 5, besides the main brand extension (i3, i5, i7, i9). The first character probably represents the product type, followed by a numerical model number, further followed by "G" denoting the presence of integrated graphics, and a numeral next to "G" denoting its tier. Here's hoping this nomenclature holds, because Intel now has three: the 10th gen "Comet Lake" mobile processors retain the classic nomenclature (eg: Core i7-10710U), while the 10th gen "Ice Lake" has a slightly improved nomenclature (eg: Core i7-1065G7), and now "Lakefield" brings in the shortest of the three (eg: Core i5-L16G7).
Source: TUM_APISAK (Twitter)
Add your own comment

33 Comments on Intel Core i5-L16G7 is the first "Lakefield" SKU Appearance, Possible Prelude to New Nomenclature?

#26
bug
R0H1TThat would necessitate a major overhaul of the kernel(?) & the OS scheduler, didn't we see how inefficient Windows is thanks to bouncing threaded workloads from core to core? What you're suggesting is not possible on Windows now, though I also believe this is the most interesting chip from Intel in a long, really long time!
I don't image that would be any different from trying to pin demanding tasks to "favorite cores".

Unfortunately big.LITTLE doesn't work like that. You can have either the big or the little core active, but not both at once. Of course, Intel doesn't have to copy what ARM did verbatim, but there's a TDP issue trying to run both cores at the same time.
Posted on Reply
#27
R0H1T
Yes & big Little has been superseded by DynamIQ for quite some time now. I'd imagine that would be more of the template Lakefield could follow, although it will still need an OS scheduler update at the very least as well as application support. You can't restrict programs to certain cores on Windows by default, & I don't believe favorite cores work that way. Process Lasso does that but it's more of a heavy handed approach & slightly inefficient at that.
Posted on Reply
#28
bug
R0H1TYes & big Little has been superseded by DynamIQ for quite some time now. I'd imagine that would be more of the template Lakefield could follow, although it will still need an OS scheduler update at the very least as well as application support. You can't restrict programs to certain cores on Windows by default, & I don't believe favorite cores work that way. Process Lasso does that but it's more of a heavy handed approach & slightly inefficient at that.
Don't worry about it, if we have "favored core" on the market, the academia is years away as far as ideas are concerned. I mean, you don't seriously think Intel would trouble themselves with a heterogeneous design and forgot all about scheduling.
Posted on Reply
#29
notb
R0H1TThat would necessitate a major overhaul of the kernel(?) & the OS scheduler, didn't we see how inefficient Windows is thanks to bouncing threaded workloads from core to core?
What you're suggesting is not possible on Windows now, though I also believe this is the most interesting chip from Intel in a long, really long time!
I don't see why Microsoft would include such a change if Intel decided to provide this kind of tech in mainstream CPUs. There's benefit for all.
It's already working well in the Windows 10 ARM. So it's not like they can't or are against the idea.

Also, I'm not entirely sure what you mean by Windows being inefficient. You mean that some exotic CPU architectures aren't properly designed for the OS that has 80% PC market share? It's not Microsoft's fault, is it? :D
Posted on Reply
#30
R0H1T
bugDon't worry about it, if we have "favored core" on the market, the academia is years away as far as ideas are concerned. I mean, you don't seriously think Intel would trouble themselves with a heterogeneous design and forgot all about scheduling.
The question isn't whether Intel's looking/working for this, it's whether MS can actually deliver it. At least to the extent we see it with linux (based OS) especially Android.
notbIt's already working well in the Windows 10 ARM.
Actually it's not, that's the reason why Snapdragon 8xx based devices aren't all that better in terms of battery life. I'll see if I can find a recent article about it but I do remember this point being mentioned specifically in regards to Windows on ARM.
Posted on Reply
#31
dont whant to set it"'
For anyone who needs Skylake core's I've got a pair of dual core chips >1000miles away. Free , postage not included. Intel need a bit of more than a trowing around as a ragdoll for the lack of innovation since Conroe/Nehalem and come to think of it without other knowledge from my part, those arch names are genuine.
Posted on Reply
#32
GlacierNine
notbAlso, I'm not entirely sure what you mean by Windows being inefficient. You mean that some exotic CPU architectures aren't properly designed for the OS that has 80% PC market share? It's not Microsoft's fault, is it? :D
What kind of bass-sackwards logic are you running on here? There was a time windows couldn't even see more than a single CPU core, let alone schedule multiple cores effectively. It was never AMD or Intel's responsibility to *not* develop better hardware in those circumstances - it was Microsoft's responsibility to react to superior hardware existing so that users could utilise it.

If the industry had worked on this argument then, we'd still not have multitasking.
Posted on Reply
#33
dont whant to set it"'
@GlacierNine , and probably more than 16/32threads for high-end mainstream, if Intel/AMD/Ms and the like's would of cooperated a lot better ,we'd be a heck of a lot closer to assimilating ourselves. Khala. Do you not?
Le:
Posted on Reply
Add your own comment
Dec 20th, 2024 01:10 EST change timezone

New Forum Posts

Popular Reviews

Controversial News Posts