Intel's 10nm only coming to servers in 2020 with Ice Lake

[cj09beira]

2 hours ago, AngryBeaver said:

People need to actually research why NM claims are not worth a damn atm. There is no standard to how one measures their manufacturing process... which means what might be considered a 7nm process to amd would be a 12nm for intel. This is why Intel has been pushing to have a standard put in place for how all manufacturing processes are gauged.

 

 

As an example. This is even before 14++. Intel has much better transistor density with their design. They also have number better Pitch lengths. Which is no different than how the 10nm process will work out with them. They are already claiming 2.4x more desisty with 10nm than what they curently have with 14++. Which will put their 10nm process ahead of the 7nm process AMD is leveraging. So until they standardize the system in place for determining the NM of a process you need to take things with a grain of salt.

 

It is like me saying that since a v8 has more cylinders than a v6 it is better.

But that v8 could be making only 300hp  while the v6 is making 450. Then again it could be the v8 is only 250ci and the V6 is 290ci.  So going off just one number when there is no standard is very deceptive and does not reflect all the needed information to gauge which one is superior.

you should have researched a bit more because we do know the specs of each node and global foundries 7nm is as dense or denser than intel's 10nm and its also a high performance node (14nm is a low power node) so although there was a big difference at 14nm intel is in big trouble at 10nm as theirs is late and the other guys have it figured out

 

2 minutes ago, D13H4RD2L1V3 said:

Isn't AMD's 7nm competing directly against Intel's 10nm?

 

They shouldn't be much different aside from the nm number

intel's problem is that their 10nm is late so amds 7nm will be going against intel's 14nm

[Mira Yurizaki]

4 minutes ago, D13H4RD2L1V3 said:

Isn't AMD's 7nm competing directly against Intel's 10nm?

And if it is, so what? People are fixated on the number that they forget the number doesn't really matter in the end. The end result is what matters.

[CTR640]

Good, good, very good! Let Intel lose for once. Always charging us for exorbitant prices and bribing companies to only sell Intel CPU's.

[The Benjamins]

10 minutes ago, cj09beira said:

you should have researched a bit more because we do know the specs of each node and global foundries 7nm is as dense or denser than intel's 10nm and its also a high performance node (14nm is a low power node) so although there was a big difference at 14nm intel is in big trouble at 10nm as theirs is late and the other guys have it figured out

 

intel's problem is that their 10nm is late so amds 7nm will be going against intel's 14nm

And at this point TSMC have started working on 5nm.

https://www.anandtech.com/show/12727/tsmc-details-5-nm-process-tech-aggressive-scaling-but-thin-power-and-performance-gains

[D13H4RD]

14 minutes ago, M.Yurizaki said:

And if it is, so what? People are fixated on the number that they forget the number doesn't really matter in the end. The end result is what matters.

We'll have to wait and see 

[iamdarkyoshi]

Anyone get the feeling ice lake is going to be hot ice?

[D13H4RD]

2 minutes ago, iamdarkyoshi said:

Anyone get the feeling ice lake is going to be hot ice?

That would've been horrifically ironic 

[AngryBeaver]

20 minutes ago, cj09beira said:

you should have researched a bit more because we do know the specs of each node and global foundries 7nm is as dense or denser than intel's 10nm and its also a high performance node (14nm is a low power node) so although there was a big difference at 14nm intel is in big trouble at 10nm as theirs is late and the other guys have it figured out

 

intel's problem is that their 10nm is late so amds 7nm will be going against intel's 14nm

This is somewhat true, but look at the clock speed lead intel already holds over amd at 14nm. That will be the biggest advantage AMD will see.. is they MIGHT be able to shrink a lot more of the gap in speed. So they might use less power and have higher clocks than current AMD products, but does that mean they will overtake the current lineup? Then they have to pray that the improvements intel see's don't blow them out of the water.

 

That is the problem with how things are now. Intels 14nm++ process is more dense than other manufacturers smaller processes like 10-12nm

 

So for the record intels 10nm process is closer to competitors 7nm process than that of other 10-12nm processes. The first deployment of intels 10nm will have a slight 3-6% disadvantage to the 7nm processes from the competitors, but they are expected to regain the lead in 1-3 years as they push for 10nm+ and 10nm++ etc.

 

Honestly, I just don't see intel losing the lead because of this 7nm ordeal. They don't need the benefits of a smaller process nearly as much as amd does atm.

[goodtofufriday]

10 hours ago, Master Disaster said:

Anybody ever thought Intel are playing the smart game?

 

Everybody knows 7nm is just about the limit of silicon transistors and without some new breakthrough, be it either a compound or new material, once we reach 7nm we're kind of stuck there.

 

It's possible Intel are sitting back and waiting for AMD to show all their playing cards to the group before they push forward with more node shrinks. At the end of the day all they have to do is beat AMD at 7nm and they've effectively won the silicon race forever.

I feel that the opposite happened. Amd bidded their time until they felt it was time to strike. 

[mynameisjuan]

4 minutes ago, goodtofufriday said:

Amd bidded their time until they felt it was time to strike.

So their strategy was, lets release shit, uncompetitive products for 7 years, force our competitor to raise their prices, almost go bankrupt all so they could wait for the right time to strike......

[Mira Yurizaki]

4 minutes ago, goodtofufriday said:

I feel that the opposite happened. Amd bidded their time until they felt it was time to strike. 

AMD is a fabless company. They're at the mercy of other manufacturers. So if anything, we should be crediting TSMC, GoFlo, or whoever.

[The Benjamins]

7 minutes ago, iamdarkyoshi said:

Anyone get the feeling ice lake is going to be hot ice?

Its called ice lake, because it will need ice water to keep cool.

[thorhammerz]

17 minutes ago, AngryBeaver said:

Honestly, I just don't see intel losing the lead because of this 7nm ordeal. They don't need the benefits of a smaller process nearly as much as amd does atm.

Shhhh, didn't you get the memo? Here, you gotta scream how Intel's big and bad and gonna burn down, and how AMD is gonna white-knight everyone to 9001-FPS gaming-while-streaming-while-encoding-while-compiling-while-server-hosting paradise !

[Biggerboot]

1 hour ago, M.Yurizaki said:

I feel like people are having a pissing contest over a number without understanding what that number actually means.

 

EDIT: When I say "people", I mean people who are not directly involved in the manufacturing process.

It's like the bit wars all over. 

[AngryBeaver]

10 minutes ago, thorhammerz said:

Shhhh, didn't you get the memo? Here, you gotta scream how Intel's big and bad and gonna burn down, and how AMD is gonna white-knight everyone to 9001-FPS gaming-while-streaming-while-encoding-while-compiling-while-server-hosting paradise !

Im calling it now. New ryzen 2 on 7nm.  More cores! OC Soft cap at 4.4-4.5ghz. I just wish they would have learned more from bulldozer. I feel they are going back to just throwing more cores at everything. What they need is higher clocks and much better IPC.

[Stefan Payne]

Just now, D13H4RD2L1V3 said:

Isn't AMD's 7nm competing directly against Intel's 10nm?

AMD doesn't have 7nm, they use TSMCs 7nm node, regardles of the fab.

 

1 hour ago, AngryBeaver said:

As an example. This is even before 14++.

Yes, you used that because the old numbers look better than the newer ones.

Because with the 14++ noe, Intel Increased the Transistor Gate Pitch to 84.

And here is the proof:

https://www.anandtech.com/show/11859/the-anandtech-coffee-lake-review-8700k-and-8400-initial-numbers/2

 

And what Anand says about that:

Quote

Increased gate pitch moves transistors further apart, forcing a lower current density. This allows for higher leakage transistors, meaning higher peak power and higher frequency at the expense of die area and idle power.

 

 

1 hour ago, AngryBeaver said:

 

It is like me saying that since a v8 has more cylinders than a v6 it is better.

But that v8 could be making only 300hp  while the v6 is making 450. Then again it could be the v8 is only 250ci and the V6 is 290ci.  So going off just one number when there is no standard is very deceptive and does not reflect all the needed information to gauge which one is superior.

In 9 out of 10 cases, Car Analogys are just bullshit as is the case here.

Because you need to be very knowledgable in Car Technology and also whatever you want to compare the car to.

The normal layman knowledge is not sufficient for this.

 

So it would be better to not do it.

Because you are missing RPM of the engine, natural aspired vs. Turbo or Supercharged, Diesel vs. Gasoline and a couple of other shit as well like the valves per cylinder or the cycle it works with (Normal Otto Cycle or Atkinson or the other one Mazda used in some of their vehicles and Toyota in one of the Prius)...

 

Just now, cj09beira said:

you should have researched a bit more because we do know the specs of each node and global foundries 7nm is as dense or denser than intel's 10nm and its also a high performance node (14nm is a low power node) so although there was a big difference at 14nm intel is in big trouble at 10nm as theirs is late and the other guys have it figured out

Yes and he also used the Infos about the old 14nm Intel node wich looked better on paper than the 14nm++ one wich increased clock at the cost of power consumption.

 

Just now, cj09beira said:

intel's problem is that their 10nm is late so amds 7nm will be going against intel's 14nm

Exactly. AMD has products on a better node than Intel has a tape out.

That is a huge deal.

 

Just now, iamdarkyoshi said:

Anyone get the feeling ice lake is going to be hot ice?

Well, brand new architecture vs a 10 year old one...

Probability that the old one is worse is pretty high.

[cj09beira]

26 minutes ago, AngryBeaver said:

Honestly, I just don't see intel losing the lead because of this 7nm ordeal. They don't need the benefits of a smaller process nearly as much as amd does atm.

oh they will, in the server market they will definitely loose as amd will launch a 48 core and maybe even a 64 core, on the consumer market it will be 12 cores from amd against 8 from intel add to that the power and frequency benefits of 7nm + the lattest rumors point to 10-15% ipc gains, it all points to a very bad year for intel

[Biggerboot]

I'll side comment that even if AMD's nm process isn't equivilent to Intel, a delay on the 10nm process this long still isn't what Intel wanted.  AMD is still going to be cutting their node process in half from a few years ago (I know, they just design the chip), and they probably anticipated intel would be further along by now.

Pretty big deal if you ask me.  We'll see where it goes.

[cj09beira]

5 minutes ago, AngryBeaver said:

Im calling it now. New ryzen 2 on 7nm.  More cores! OC Soft cap at 4.4-4.5ghz. I just wish they would have learned more from bulldozer. I feel they are going back to just throwing more cores at everything. What they need is higher clocks and much better IPC.

increasing ipc is extremely difficult, and clock speeds haven't improved much since the 32nm days, so the only way to improve performance significantly is to add more cores (one could add a l4 cache but those are pretty expensive and people dont want to pay for them)

[Stefan Payne]

Just now, AngryBeaver said:

Im calling it now. New ryzen 2 on 7nm.  More cores! OC Soft cap at 4.4-4.5ghz. I just wish they would have learned more from bulldozer. I feel they are going back to just throwing more cores at everything. What they need is higher clocks and much better IPC.

Oh you mean that Intel hasn't learned anything from the P4 as they go full on clockrate again, while AMD concentrates on smaller, more efficient cores and also has lower power consumption under load than Intel right now. How do you expect it to be when AMD has a node advantage?!

 

And BD cores were OK, they were just late and hindered by the garbage K10 Northbridge and shitty/slow Caches.

 

The thing is:

you can't increase the "IPC"

you can't increase the Clockrate of the CPU (much)

 

What else can you do but add more cores?!

 

I really don't get what you want. In one sentence you say you don't want a second Bulldozer but then you demand a second Bulldozer?! Can you decide what you want pls?!

Because AMD decided to NOT go high Clockrate (again)...

[Stefan Payne]

Just now, Biggerboot said:

I'll side comment that even if AMD's nm process isn't equivilent to Intel, a delay on the 10nm process this long still isn't what Intel wanted.  AMD is still going to be cutting their node process in half from a few years ago (I know, they just design the chip), and they probably anticipated intel would be further along by now.

Pretty big deal if you ask me.  We'll see where it goes.

As some Canadian Phsychiatrist once said on one of its bible lectures (forgot what it was):
Its not to big to fail.

its to big it has to fail.

And again, AMD does NOT have a Node, they are using the TSMC 7nm Process and not the IBM 7nm process.

[BuckGup]

11 hours ago, Master Disaster said:

Anybody ever thought Intel are playing the smart game?

 

Everybody knows 7nm is just about the limit of silicon transistors and without some new breakthrough, be it either a compound or new material, once we reach 7nm we're kind of stuck there.

 

It's possible Intel are sitting back and waiting for AMD to show all their playing cards to the group before they push forward with more node shrinks. At the end of the day all they have to do is beat AMD at 7nm and they've effectively won the silicon race forever.

Except it takes 7+ years to develop architectures and CPUs so I am pretty sure both companies have solutions already.

[AngryBeaver]

14 minutes ago, Stefan Payne said:

Oh you mean that Intel hasn't learned anything from the P4 as they go full on clockrate again, while AMD concentrates on smaller, more efficient cores and also has lower power consumption under load than Intel right now. How do you expect it to be when AMD has a node advantage?!

 

And BD cores were OK, they were just late and hindered by the garbage K10 Northbridge and shitty/slow Caches.

 

The thing is:

you can't increase the "IPC"

you can't increase the Clockrate of the CPU (much)

 

What else can you do but add more cores?!

 

I really don't get what you want. In one sentence you say you don't want a second Bulldozer but then you demand a second Bulldozer?! Can you decide what you want pls?!

Because AMD decided to NOT go high Clockrate (again)...

Yes intel doesn't have much wiggle room in core clocks atm, but you noticed they are producing an 8 core consumer cpu now right?

 

When it comes to clocks though the gap between intel and ryzen is still pretty big. You are now seeing more and more 5.2+ ghz intel chips, while Ryzen is pretty much soft-capped to 4.2-4.3 ghz. Also IPC has been steadily increasing even if slowly. Ryzen is due for a decent increase itself, but we will see how that goes.

 

The thing is just throwing more cores out there doesn't do much to help in ST demanding titles like games. Do you know what is hurting ryzen so much right now when it comes to games and fps? Draw calls. Draw calls are handled in most cases by a single core. So when you have lower ipc and clocks per core it becomes a problem.

 

So instead of focusing on squeezing as much power out of each core like intel, AMD is just throwing more cores at it. Quantity over quality. I mean look at the current situation. The intel 8700k performs on par with the 8 cores with only 6 cores. Also the 8700k is a 95w chip vs the 105w 2700x. So the 8700k is less power hungry.

[pas008]

21 minutes ago, BuckGup said:

Except it takes 7+ years to develop architectures and CPUs so I am pretty sure both companies have solutions already.

agreed like I stated before

1 hour ago, pas008 said:

I wonder this myself

considering graphene chips or graphene coated copper

and fact emib hasnt even been used by intel yet

 

plus this https://www.techspot.com/news/75020-intel-now-capable-producing-full-silicon-wafers-quantum.html

 

[cj09beira]

23 minutes ago, Stefan Payne said:

As some Canadian Phsychiatrist once said on one of its bible lectures (forgot what it was):
Its not to big to fail.

its to big it has to fail.

And again, AMD does NOT have a Node, they are using the TSMC 7nm Process and not the IBM 7nm process.

Dr. Jordan B. Peterson, you welcome 

4 minutes ago, AngryBeaver said:

Yes intel doesn't have much wiggle room in core clocks atm, but you noticed they are producing an 8 core consumer cpu now right?

 

When it comes to clocks though the gap between intel and ryzen is still pretty big. You are now seeing more and more 5.2+ ghz intel chips, while Ryzen is pretty much soft-capped to 4.2-4.3 ghz. Also IPC has been steadily increasing even if slowly. Ryzen is due for a decent increase itself, but we will see how that goes.

 

The thing is just throwing more cores out there doesn't do much to help in ST demanding titles like games. Do you know what is hurting ryzen so much right now when it comes to games and fps? Draw calls. Draw calls are handled in most cases by a single core. So when you have lower ipc and clocks per core it becomes a problem.

 

So instead of focusing on squeezing as much power out of each core like intel, AMD is just throwing more cores at it. Quantity over quality. I mean look at the current situation. The intel 8700k performs on par with the 8 cores with only 6 cores. Also the 8700k is a 95w chip vs the 105w 2700x. So the 8700k is less power hungry.

thats because right now its intel's 14nm vs an 20nm node using finfet optimized for low power, so of course it will clock lower and of course it will consume more power, right now the only problem that is actually amd's fault is the higher than normal latency, which should improve orver time as amd improves on IF