A leak on Weibo purportedly lists IPC and process node gains for Intel's upcoming Golden Cove and Ocean Cove architectures. The 7nm Ocean Cove, in particular, looks interesting, allegedly built on the 7nm process and offering upwards of 80 percent IPC gains.
https://www.notebookcheck.net/Intel-s-7nm-Ocean-Cove-architecture-might-deliver-80-percent-gains-to-IPC-and-higher-clocks-in-2022-enough-to-catch-up-with-5nm-AMD-Ryzen-6000-Raphael.467539.0.html
I think if intel keep 7nm the same fab quality it should have density on par with 5-6 nm TSMC.
Just a bit curious about 80% IPC that quite too high and that higher clock make it more unlikely to happen even in 10nm itself intel can't make higher clock I mean after 14nm it seem like lower nm make it harder to push higher clock speed.
80% IPC ... estimates ... stopped reading after that. Utter nonsense. Won't be enough anyway. My "estimates" see 8000% IPC improvement for 2022/2023 Ryzen processors.
Intel's 7nm is better than Foundry 5nm, and close to their 3nm. Foundry 5nm is more akin to a half node jump, and 3nm is another half node(little more) from 5nm. Intel 7nm is a full jump from 10nm.
The 80% over SKL guess is reasonable but I have doubts on the numbers being a genuine leak, rather its a guess.
They have backfired by they laziness. If they excute their plans as it should then they will have some buffer to reduce amd damage to them. Lisa su used to say "we will tock tock tock" when asked about they future plans in an interview a while ago. This is serious mesage. 80% ipc is imposible in single generation upgrade and it need at least 2 or 3 generation. Unless they compare it to older arch like haswell.
Somewhat ambitious but certainly not impossible, compared to Skylake. Ice Lake is...15%? increase in IPC already, so steady rate as such for 20-21-22, 3 years, would lead to ~80% over Skylake.
Considering how much heat anything over 5GHz will generate. A 7nm architecture may work and bring Intel back to competition. The question here is, will these operate long enough before electrons make them unusable. The same can be said about AMDs 5nm technology, though at lower cycle times (<5GH) they are considerably more reliable.
How long will these chips work, before they produce unreliable results? This remains to be seen. 7nm is as far down as I'll trust the tech currently.
Though Intel has another problem. Most of us that deploy develop technology on these servers and deploy 1000s of them a day, understand that Intel has major security holes. This means we need to spend additional resources or sacrifice performance to compensate for it
This is where switching to AMD is looking great economically in addition to lower operation costs. Furthermore or competition is already doing so, putting more pressure on us and on Intel.
Once we switch, going back to Intel will not be an option, at least fir a decade. Unfortunately for Intel, 2023 is too late.
I highly doubt Intel's first gen 7nm will reach 5.5 GHz. Intel's current node, the 10nm suffer from lower clock due to denser transistor. this is actually the same case with Intel's 14nm process, where only the best Skylake chip could overclock past 4.7 GHz. according to Wikichip, Intel then relaxed the poly pitch on 14nm++ to push past 5 GHz.
I don't see why people are so skeptical about this...
First of all, Intel has hired Jim Keller. He's not washing the toilets there you know...
Also, they had this long span of years to work on something like this and given the process doesn't allow them to make what AMD did with chiplets, then they are forced to do this, that is to increase the IPC massively.
Jim has been heard discussing about some upcoming core (Golden Cove or Ocean Cove) that it will support ~800+ instruction window which is some 3-4X the number that Zen 2 and Skylake support.
Another thing to note is that mobile has gained back the IPC difference during these years of stagnation from Intel so now Apple A13/A14 should be very similar in IPC to what a fully features desktop core can do, that is support some 200 instruction window.
So I think this is a good time for CISC cores to move on and get another leap in what they can do. Sure, many cores are nice and AMD has capitalized on that. But commonly used software (games, browsers even productivity apps) have yet to become highly parallel so more than 8 cores won't give you much for the next 5-10 years except for some specific cases where an entry level GPU will nevertheless do a better job than even a 3990x.
So IPC still stands as a very important metric and this is what AMD and Intel need to work on and improve. This is a metric which is much harder to improve and that is why AMD has yet to catch up with the best Intel core that is Ice Lake. Zen 2 is still some 10% worse than Ice Lake and next gen (Zen 3 and Tigerlake) might be more even with what comes beyond not being clear.
Anyway, if these rumours hold true than Alder Lake will be a big improvement and will pass Zen 3 by a big margin. And I don't see AMD being capable, technically to add more than 15-20% IPC in one generation for the same uArch.
Anyway, I hope these rumours are true.
80% better IPC? On an x64 architecture? Let me be the first to call BS.
I don't know how long will Intel keep that 5nm. May be it will keep refreshing it for a decade, while others will move towards using light instead of electrons.
Let me tell you a joke... Intel 80% IPC improvement in a generation......
hahahahahahahahhahahhahahahahahahahhahahahahhahahahhahahahahahahahahahahahahhahahhahahahahahahahhahahahahhahahahhahahahahahahahahahahahahhahahhahahahahahahahhahahahahhahahahhahahahahahahahahahahahahhahahhahahahahahahahhahahahahhahahahhahahahahahahahahahahahahhahahhahahahahahahahhahahahahhahahahhahahahahahahahahahahahahhahahhahahahahahahahhahahahahhahahahhahahahaha
with desktop market shining brightly, jim keller there and intels deep pocket that is minimum what is to be achieved.Don't know If Jim keller is working on MCM as well. Intel desperately needs alternative to infinity fabric, because its blessing for super computer or server. Intel taking on TSMC is never surprising to me, infact i believe that can happen early than expected. Intel can accelrate R&D and preponed like in case of c2d. Lets see how long TSMC will be able to stand tall. Any how i had always been telling AMD is bit struggling with IPC against intel since long is big pain, a particular field where they had been good earlier. Only reason they are competitive is because of TSMC. Any how DDR5 may change the case, who knows. But one thing for sure clash of titan is awaited intel plus jim keller vs AMD plus TSMC/samsung. competition is good and was missed for quite some time now.
I wonder who in weibo make this up... definitely not going hugh improvement rebuilding a cpu with that much gain.
they didn't abandon clock. it was just much easier to do cores.
Quote from: DavidC1 on June 01, 2020, 11:22:35Intel's 7nm is better than Foundry 5nm
No, it isn't. I wonder if it is at least close to 5nm+ that AMD is using for Zen 4. And even if, probably it will be available 1 or 2 years later.
80% increase isn't that much considering skylake will be 6/7 years old...
I enjoy a rumour as much as the next man, but 5.5Ghz is pie in the sky given Intel's issues with hitting high clock speeds on both 14nm (original, more dense variant) and 10nm (all variants, but especially the original more dense variant).
80% increase I could potentially believe - Skylake came out in 2015, so that increase over 7-8 years adds up to at least being plausible, if less remarkable. It's like comparing Zen 2 to Excavator.
I don't know why you guys find it so hard to believe the 80% IPC improvement over skylake, willow cove already has 25% IPC over skylake so that is about a 20% IPC every generation to reach 180% IPC of skylake. The frequency is defintely BS though since there is no way they can be sure of the frequency at such an early stage of developement, its probably a dream rather than fact. Just for comparison sake, zen 2 is already 110% IPC of skylake, zen 3 relasing at the end of the year is 130-135% IPC of skylake. AMD just need to maintain a 15% IPC per gen improvement and they would be able to keep up. I find this target quite reasonable for intel to catch up with AMD. Its going to be interesting to see the 2 of them fighting for the crown.
why are we stopping at only a measly 80 percent? a trillion percent increase would sound even more believable, never mind, Intel is now saying the industry should move away from benchmarking anyways, makes you wonder what Intel is trying to do, whatever it is it's getting sill at this point.
Quote from: fdsdsas on June 01, 2020, 13:43:49
I don't see why people are so skeptical about this...
First of all, Intel has hired Jim Keller. He's not washing the toilets there you know...
Also, they had this long span of years to work on something like this and given the process doesn't allow them to make what AMD did with chiplets, then they are forced to do this, that is to increase the IPC massively.
Jim has been heard discussing about some upcoming core (Golden Cove or Ocean Cove) that it will support ~800+ instruction window which is some 3-4X the number that Zen 2 and Skylake support.
Another thing to note is that mobile has gained back the IPC difference during these years of stagnation from Intel so now Apple A13/A14 should be very similar in IPC to what a fully features desktop core can do, that is support some 200 instruction window.
So I think this is a good time for CISC cores to move on and get another leap in what they can do. Sure, many cores are nice and AMD has capitalized on that. But commonly used software (games, browsers even productivity apps) have yet to become highly parallel so more than 8 cores won't give you much for the next 5-10 years except for some specific cases where an entry level GPU will nevertheless do a better job than even a 3990x.
So IPC still stands as a very important metric and this is what AMD and Intel need to work on and improve. This is a metric which is much harder to improve and that is why AMD has yet to catch up with the best Intel core that is Ice Lake. Zen 2 is still some 10% worse than Ice Lake and next gen (Zen 3 and Tigerlake) might be more even with what comes beyond not being clear.
Anyway, if these rumours hold true than Alder Lake will be a big improvement and will pass Zen 3 by a big margin. And I don't see AMD being capable, technically to add more than 15-20% IPC in one generation for the same uArch.
Anyway, I hope these rumours are true.
SW algorithms can be experimented, changed / implemented easier to take advantage of parallelism than hardware redesign. Even you are just one SW guy, there are millions SW there, by what qualificantion you can say that won't happen 5 to 10 years?