Core i9-10900K up to 30% Faster than i9-9900K: Intel

[Renald]

Software and workloads used in performance tests may have been optimized for performance only on Intel microprocessors

What a joke.

 

[HugsNotDrugs]

Intel should have added on four more cores for at least twelve cores instead of a measly two core bump.

Intel already looks be in second place compared to AMD's twelve, and sixteen core chips.

It's very costly to expand the size of an already-large monolithic die.

 

[Metroid]

almost 30% more cores, certainly 30% faster in multicore apps, now if is 30% in single thread then I shut off my mouth, which I'm sure is not the case.

 

[ppn]

almost 30% more cores, certainly 30% faster in multicore apps, now if is 30% in single thread then I shut off my mouth, which I'm sure is not the case.

meteor lake in 2021-22. ST+30% sunny cove +50% faster than SKL. what we have to do now is wait and boycott this 14++ ridiculous refresh cycle.

 

[londiste]

It's very costly to expand the size of an already-large monolithic die.

In this case I think adding two cores would be doable without any major issues. Running them at competitive clock speeds, however...

 

[trparky]

In this case I think adding two cores would be doable without any major issues.

Their yields must be hideous.

 

[londiste]

Their yields must be hideous.

Why? A 10-core 10900K die would be about 200mm^2. This is roughly the same size as Zen/Zen+ dies on the same type of mature manufacturing process.

When we are talking about monolithic, we are talking about many cores and large die sizes. Intel's 28-core is difficult/expensive enough as monolithic. To some degree, so is 18-core die. 10 cores and 200mm^2 or so is very much fine.

 

[efikkan]

As londiste was saying, ~200mm² is not a problem. Comet Lake is likely to have the same "bottlenecks" as Coffee Lake, where the limit will be energy density. 125W (and ~185W peak) on ~200mm² is the issue, not yields. 200mm² is still a "small" chip. If we're talking >500mm², then yields become a greater concern.

 

[biffzinker]

As londiste was saying, ~200mm² is not a problem. Comet Lake is likely to have the same "bottlenecks" as Coffee Lake, where the limit will be energy density. 125W (and ~185W peak) on ~200mm² is the issue, not yields. 200mm² is still a "small" chip. If we're talking >500mm², then yields become a greater concern.

Intel's problem being stuck on 14nm++ is how many dies per wafer they can get. Bigger die means less yield per wafer.

 

[efikkan]

Intel's problem being stuck on 14nm++ is how many dies per wafer they can get. Bigger die means less yield per wafer.

As I said; yields is not an issue for such small dies. Yields on 14nm++ is excellent. As we can see on their bigger dies, they have to sacrifice clock speeds due to heat and power long before yields become an issue.

 

[trparky]

Why? A 10-core 10900K die would be about 200mm^2. This is roughly the same size as Zen/Zen+ dies on the same type of mature manufacturing process.

When we are talking about monolithic, we are talking about many cores and large die sizes. Intel's 28-core is difficult/expensive enough as monolithic. To some degree, so is 18-core die. 10 cores and 200mm^2 or so is very much fine.

Yeah but I have to wonder how many of these 10-core chips can still be 10-core chips and not be down-binned to lesser models like i7s, i5s, and even worse... i3s.

 

[efikkan]

Yeah but I have to wonder how many of these 10-core chips can still be 10-core chips and not be down-binned to lesser models like i7s, i5s, and even worse... i3s.

Good enough that Intel plans to use the 10-core die for only 10 and 8 core models, and 6-core die for 6 core models and down.

 

[trparky]

Good enough that Intel plans to use the 10-core die for only 10 and 8 core models

I guess we'll see based upon how much Intel prices these things. If they're priced at some ungodly high amount then we'll know how (un)successful they are at making these things.

 

[DeathtoGnomes]

What a joke.

actually its not, Intel is known to do such things.

 

[Berfs1]

*adds 25% more cores* (1.25x)
*adds 6% more clock speed* (1.06x)
*acts surprised that there is a 30% improvement in multithreaded is huge when 1.25x1.06 is 1.325 and with losses is ~30% gain so IPC actually is not improved*
“125W TDP.” 125W my ass.

It’s funny how intel is the one that said adding more cores is bad, yet they GLORIFY this for their 10900K. Best joke of the new decade.

As I said; yields is not an issue for such small dies. Yields on 14nm++ is excellent. As we can see on their bigger dies, they have to sacrifice clock speeds due to heat and power long before yields become an issue.

Intel totally didn’t have any yield issues with their 9th generation.

 

[Tsukiyomi91]

Rather wait for reviewers to compare this chip against the R9 3900X & possibly Ryzen 4th gen (when it comes out later this year). Hoping this year Intel is taking things seriously...

 

[Berfs1]

Yo, Intel finally had the balls to come out and mention the actual power limit of the 9900K, 210W! Bravo Intel! So that means the 10900K is rated to do 250W. Ok. Consumer chips, doing 250W, no biggie. It's not like we won't have liquid nitrogen AIO coolers in 2020.

 

[biffzinker]

So that means the 10900K is rated to do 250W. Ok.

With or without AVX2 though?

 

[CyberBuddha]

Yes, even in gaming. With an AMD you lose how much? From 0%-10% in 1080p? Up to 5% in 1440p? Up to 2% in 4K? And those differences with a 2080Ti probably.

So you go out and buy an Intel processor because reviews show you that the top Intel CPU, under the best cooling solution, on an expensive high end motherboard in a case with plenty of air flow, while paired with an RTX 2080 Ti is 5%-10% on average faster than the 3900X at 1080p? And that's while ignoring power consumption because power consumption is important only when AMD CPUs are less efficient.

What about a typical system with a mid range motherboard, mid range air cooling, probably an RTX 2070S or 5700XT at best, in a case with mediocre air flow running games at 1440p? What is the difference in games there? And can you really see it and feel it in games?


Yes they will see it and they will say "10 cores much faster than 8 cores"...... IN EVERYTHING.

you nailed it !

 

[phanbuey]

cant wait for my 4700x from amd

 

[Renald]

actually its not, Intel is known to do such things.

I know, and that's why these numbers are ridiculous !

Very often they do it in "secret". This time it's "We are bullshiting you, it's just for shareholders"

 

[mechtech]

Sysmark overall says 1.10x, but the wattage says 125W/250W over the i9s 95W/210W. Wattage % increase outdoes performance, is this cause on 14nm or pushing it too far out of the happy curve?

 

[cygnus_1]

Oh boy, 33% more power usage and 25% more cores... and it ONLY gets 30% better performance??

 

[Steevo]

Now 30% faster with 30% more cores 30% more power consumption and 30% more winter heating!

 

[Tsukiyomi91]

funny replies aside, I wanna know does Intel's claim can be legit when it comes out? what if the 30% gain is with all the hardware mitigations & AVX-adjusted clocks thrown into the mix? Will it be at the heels of AMD's R7 & R9 when it comes to heavy workloads? Will Intel finally add more PCIe lanes for their mainstream platform? All these questions; I want it to be answered.