• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

Intel Cannonlake SoC will have 4-core, 6-core and 8-core versions

S

Sweepr

Diamond Member
For many years now, Intel (NASDAQ:INTC) has offered CPUs with between two and four CPU cores for its client CPUs. Typically, the low-power CPUs aimed at Ultrabooks and 2-in-1 convertibles have two CPU cores while the processors aimed at higher-performance laptops as well as mainstream desktops feature between two and four cores depending on the particular chip and power envelope.

That being said, there is substantial evidence that Intel's upcoming Cannonlake client processors, which will be built on the company's next generation 10-nanometer manufacturing technology, will come with between four and eight cores.

Here's the proof
Take a look at the following LinkedIn profile from an Intel engineer:

profile_large.png


The engineer claims to be working on a system-on-chip that integrates between four to eight cores. Now, we know that this is a client processor and not, say, a server processor because Intel already fields chips with much greater core counts in the server market.
Click to expand...

Full article: www.fool.com/investing/general/2015...e-upping-its-core.aspx?source=iedfolrf0000001

Edit: Skylake's version of Xeon-D will feature up to 10 cores so it's probably not Cannonlake Xeon-D.
 
Last edited:
Pretty sketchy. I thought you had a real source instead of some linked in post. Lets hope though, it is about time. But I will believe it when I see it. I still am not convinced this is for the mainstream platform either, since it mentions 8 cores, and I dont think there is any way Intel will go from 4 to 8 cores for the mainstream in one generation.

When is cannonlake supposed to come to desktop, late 2017?
 
frozentundra123456 said:
Pretty sketchy. I thought you had a real source instead of some linked in post. Lets hope though, it is about time. But I will believe it when I see it. I still am not convinced this is for the mainstream platform either, since it mentions 8 cores, and I dont think there is any way Intel will go from 4 to 8 cores for the mainstream in one generation.

When is cannonlake supposed to come to desktop, late 2017?
Click to expand...

Agreed. Honestly, there's not really any reason for the mainstream consumer to have 8 cores in a desktop. The entire industry has been pushing towards lower power/lower TDP parts because compute performance has be well beyond "good enough" for nearly a decade. Making 8 core mainstream processors is like giving every soccer mom a sports car.

More expensive parts for underutilized performance doesn't make business sense.
 
The engineer claims to be working on a system-on-chip that integrates between four to eight cores. Now, we know that this is a client processor and not, say, a server processor because Intel already fields chips with much greater core counts in the server market.
Click to expand...

The above is FALSE.

They seem to have forgotten about Broadwell-D server SoC. 8 cores (but much less than Broadwell-EP or -EX), and most decidedly NOT a "client" CPU (though I wish that it was).
 
frozentundra123456 said:
Pretty sketchy. I thought you had a real source instead of some linked in post. Lets hope though, it is about time. But I will believe it when I see it. I still am not convinced this is for the mainstream platform either, since it mentions 8 cores, and I dont think there is any way Intel will go from 4 to 8 cores for the mainstream in one generation.

When is cannonlake supposed to come to desktop, late 2017?
Click to expand...

Cannonlake is H2-2017.
Look at the 25W mobile quad-cores and small dies Intel is selling right now with Skylake, they could very well release 10nm 6-8 core SKUs two years from now. Just a rumour, but worth discussing.
 
Last edited:
frozentundra123456 said:
Pretty sketchy.
and I dont think there is any way Intel will go from 4 to 8 cores for the mainstream in one generation.
Click to expand...
This, too.

I mean, with an 8-core / 16-thread Zen on the horizon, would Intel hedge their bets against it, and release 6-core mainstream CPUs? Or would they simply use their HEDT line, and lower prices (if even necessary) to field a competitive CPU in the market?
 
So... We are seeing This?

Celeron - Dual Core with HT
Pentium - Real Quad Core without HT
Core i3 - Real Quad Core with HT
Core i5 - Hexa Core with HT
Core i7 - Octo Core with HT

But maybe prices will get the same increase.:V
 
VirtualLarry said:
The above is FALSE.

They seem to have forgotten about Broadwell-D server SoC. 8 cores (but much less than Broadwell-EP or -EX), and most decidedly NOT a "client" CPU (though I wish that it was).
Click to expand...

Bingo.

I would advice people not to believe anything like this before it happens. There isn't any incentive to put more than 4 cores on a client chip. Lets be honest, more IGP would be more beneficial than more cores.

More cores=HEDT line.
 
Still outraged at Intel for not releasing an i7 Skylake chip with the same eDRAM that i7 Broadwell had. Probably will come in Kaby Lake.
 
VirtualLarry said:
The above is FALSE.

They seem to have forgotten about Broadwell-D server SoC. 8 cores (but much less than Broadwell-EP or -EX), and most decidedly NOT a "client" CPU (though I wish that it was).
Click to expand...

Do you think that at the 10nm generation Xeon D will come in configurations that top out at 8 cores? I would think they will be at much higher core counts.
 
ShintaiDK said:
Bingo.

Snip. Lets be honest, more IGP would be more beneficial than more cores.

More cores=HEDT line.
Click to expand...

Seriously? Igp is more than good enough for everyday tasks, and you still need a discrete card, and IMO will for a long time, for any really intensive graphical tasks. (talking about desktop here).

I just dont understand why you keep defending intel for not bringing out a mainstream hex core for the desktop. I know it would be a limited market, but come on, it seems like Intel is more interested in artificially segmenting the market for more profit than in designing a product to fit an existing market segment. Especially since they seem unable to get more than 10% performance increase from even a tock now, I think this strategy will eventually come back to bite them. And no, I dont consider a generation or 2 old HEDT server reject a good alternative.
 
Mondozei said:
Still outraged at Intel for not releasing an i7 Skylake chip with the same eDRAM that i7 Broadwell had. Probably will come in Kaby Lake.
Click to expand...
Intel is doing the same errors IBM did on their time... Low supplies, low performance increase, MIA projects (Quark, Edinson, Galileo that were supposed to take down Vortex86 and SoFIA who was supposed to take the Phone market) and maintaning the same ammount of cores on desktop and a very low increase of cores on servers.

Consequences of being a monopoly... Eventually the CPU will bottleneck the newer games and despite AMD and nVIDIA efforts, it will be worthless..

Also if Intel wants, they can cancell Nvilink since they can annul any 3rd party improvements (Maybe they learned from ASUS and their own LGA)

And I am hoping that Kabylake becomes what people expect and not ends into another big ragefest. I say that because Zen won't make it in time and without AMD, nVIDIA will have a very hard time.
 
frozentundra123456 said:
Seriously? Igp is more than good enough for everyday tasks, and you still need a discrete card, and IMO will for a long time, for any really intensive graphical tasks. (talking about desktop here).

I just dont understand why you keep defending intel for not bringing out a mainstream hex core for the desktop. I know it would be a limited market, but come on, it seems like Intel is more interested in artificially segmenting the market for more profit than in designing a product to fit an existing market segment. Especially since they seem unable to get more than 10% performance increase from even a tock now, I think this strategy will eventually come back to bite them. And no, I dont consider a generation or 2 old HEDT server reject a good alternative.
Click to expand...

I am not defending anyone. But I look at it from a different perspective. What you ask or is that Intel makes a design, mask, production runs etc for a tiny niche of people who want a dual channel 6-8 core chip without IGP on a mainstream platform limited to 95W. See the issue?

Until software radically changes its not needed and serves no purpose for the 99.x% crowd. And they are better of with better IGP, more cache, EDRAM, integrated PCH or whatever.
 
If apple wanted to, I bet they could sack the server market overnight. They have two suppliers more than happy to produce $20 dies that match broadwell in performance. Apple could slap 8 or 16 of these dies onto a package and sell it for $400-$600 and it would destroy intel in a server of similar price and power. Of course they wouldnt do that since they could easily make a 250 sq mm chip that contains 32 A9 cores.
 
sm625 said:
If apple wanted to, I bet they could sack the server market overnight. They have two suppliers more than happy to produce $20 dies that match broadwell in performance. Apple could slap 8 or 16 of these dies onto a package and sell it for $400-$600 and it would destroy intel in a server of similar price and power. Of course they wouldnt do that since they could easily make a 200 sq mm chip that contains 32 A9 cores.
Click to expand...

We have to see some real compare benches first. Some with equal compilers. And I doubt they will be as positive.

I dont think Apple pays 20$. Plus you forget all the RAS features needed and increased interconnect in the chips, caches etc. Something Apple as such got close to zero experience with.
 
Intel is facing a toxic mix of stiff competition with their own 4+ year old chips, dwindling consumer PC sales and escalating fab costs. The last thing they want in the consumer segment is even more cores and larger die sizes.
 
ShintaiDK said:
What you ask or is that Intel makes a design, mask, production runs etc for a tiny niche of people who want a dual channel 6-8 core chip without IGP on a mainstream platform limited to 95W. See the issue?
Click to expand...

Not so tiny. See this:
http://www.bbc.com/news/technology-34117120

"Intel claims something like 10% of the PC market is extreme gamers."

And that's just the "extreme" gamers, whatever that means. But it is safe to assume they are enthusiasts with really high performance hardware, that likely will benefit from and desire more cores in the years ahead. Add to that other users that use their desktop for video editing, compiling code, etc.

ShintaiDK said:
Broadwell-C will get a successor next year it seems.
Click to expand...

Now there is a niche market... ! And yet Intel makes specialized SKUs for it.
 
dark zero said:
Also if Intel wants, they can cancell Nvilink since they can annul any 3rd party improvements (Maybe they learned from ASUS and their own LGA)
Click to expand...

That makes no sense, NVLink isn't implemented in Intel CPUs, and I don't see how it could be. It's an NV technology, how in the world would Intel have any say in it?
 
Mondozei said:
Still outraged at Intel for not releasing an i7 Skylake chip with the same eDRAM that i7 Broadwell had. Probably will come in Kaby Lake.
Click to expand...

Probably not enough space. Broadwell has 6mb cache, Skylake has 8mb of cache.

The IGP is also quite a bit different between the two.
 
You must log in or register to reply here.

TRENDING THREADS

Back
Top