Wednesday, January 1st 2020

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

Intel's upcoming Core i9-10900K desktop processor is up to 30 percent faster than the Core i9-9900K according to the company, which put out a performance guidance slide that got leaked to the web. Based on the 14 nm "Comet Lake-S" silicon and built for the new LGA1200 platform (Intel 400-series chipset motherboards); the i9-10900K is a 10-core/20-thread processor that leverages increased TDP headroom of 125 W to sustain higher clock-speeds than 9th generation "Coffee Lake Refresh," while also offering a 25% increase in processing muscle over the i9-9900K, thanks to the two additional CPU cores.

In its performance guidance slide, Intel shows the i9-10900K scoring 30% more than the i9-9900K in SPECint_rate_base2006_IC16.0. There's also a 25% boost in floating-point performance, in SPECfp_rate_base2006_IC16.0, which roughly aligns with the additional core count, as both these tests are multi-threaded. Other noteworthy results include a 26% gain in Cinebench R15, and 10% in SYSMark 2014 SE. In tests that don't scale with cores, Intel appears to rely entirely on the increased clock-speeds and improved boosting algorithm to eke out performance gains in the low-to-mid single-digit percentages. Intel is introducing a new clock-speed boosting technology called Thermal Velocity Boost, which can dial up clock-speeds of the i9-10900K up to 5.30 GHz.
Sources: ITHome, Tom's Hardware
Add your own comment

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

#51
Bones
R-T-B
And AMD is using better glue? What is your point here? This is just as valid a criticism as Intel calling Ryzen "glued together."
AMD is using this glue to make good processors.
Intel is just sniffing it.
Posted on Reply
#52
EarthDog
W00t, more cores? lol

XL-R8R
Intel do have some funny press announcements recently.
You think only intel markets that way?
Posted on Reply
#53
Tomorrow
londiste
There are two somewhat different implementations of IF in Zen, one inside the CPU between CCXs is different from the one used between dies. IF in the implementation it is used between dies in Zen CPUs it seems to be roughly on par with UPI.

Intel's counterpart to IF is UPI. By the way, both are used in pretty much the same way in multi-socket/CPU systems. There is a reason EPYCs top out at 2 socket configurations and while marketing says this is market optimization and best most optimal section of the market, the actual reason is purely technical - with the amount of dies EPYCs use there are not enough to facilitate the links between separate CPUs in optimal manner.
Based on what i found UPI tops out at ~30GB/s (3 links per CPU) where as IF is quoted to much more scaleable between 30-250GB/s. Intel prefers to do as much as possible in silicon and use UPI only when needed where as IF is used much more.

The reason why EPYC tops out at 2S is TCO. Since a single EPYC CPU can replace a 4S Intel system (typically a 2S system, and still cost less) there is little incentive to go to 4S systems due to cost and complexity reasons.

So no i don't see any scalability issues with IF. If Intel were more competetive in server space i have no doubt AMD would push 4S systems.
But any of this is way beyond the current topic. We are talking abount mainstream enthusiast CPU's here. The fact that Intel might have some benefit in some rare server scenario has little bearing on mainstream.
Posted on Reply
#54
heflys20
R-T-B
No, it doesn't.

It has less latency which is better for gaming yes. But it is actaully worse in ST IPC.
I stopped taking him seriously long ago. just Lol when he post...Anyway, I would hope it would be 25%-30% faster, since it possesses two more cores. I think I'll just get a 3700x to replace my 4670k and call it a day.
Posted on Reply
#55
londiste
Tomorrow
Based on what i found UPI tops out at ~30GB/s (3 links per CPU) where as IF is quoted to much more scaleable between 30-250GB/s. Intel prefers to do as much as possible in silicon and use UPI only when needed where as IF is used much more.
There are some advantages and disadvantages to both interconnects but overall they are pretty close to parity.
- Current UPI is 41.6GB/s bi-directional.
- IF as implemented in Zen/Zen+ was 38GB/s bi-directional at 1333MHz memory clock (so, usually a bit more than that). Zen2 upped it a bit but I'd have to look up how much.
Tomorrow
The reason why EPYC tops out at 2S is TCO. Since a single EPYC CPU can replace a 4S Intel system (typically a 2S system, and still cost less) there is little incentive to go to 4S systems due to cost and complexity reasons.
Not sure about Zen2 EPYCs but in case of Zen/Zen+ EPYCs the reason it tops out at 2S is 4 IF links per die.
Posted on Reply
#56
Durvelle27
cucker tarlson
same number of upgrades as ryzen 3000 owners at this point.
and same type too.tweaked 14nm vs tweaked 7nm.
more for amd to squeeze out from 7nm+ than for Intel to gain from another 14nm revision,same as a better IMC on ryzen 4000 would benefit IF speeds.
Still,the path is mostly the same.


was that developed for core+vega apus only ? seems wasteful.
You can't just say Ryzen 3000 owners as AM4 has been around for a few years now and alot of those users are still on Ryzen 1000

So for those they have the option of upgrading to Zen+, Zen 2, and Zen 3 without the need of having to change anything but the BIOs

Hell i went from Ryzen 1000 to Ryzen 3000 and still have the option of Ryzen 4000 once it launches. I say that's a win win considering I've had my board now close to 3 years
Posted on Reply
#57
chfrcoghlan
biffzinker
Intel should of 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.
*should have
Posted on Reply
#58
B-Real
fancucker
Cooper-Lake will arrive MCM with 48/56 cores H2 2020. As for this, Skylake at two nodes behind still manages to have greater ST than AMD's tweaked Ryzen. Zen 3 will arrive to find backported Willow Cove on 14nm++ or 10nm/7nm, Zen 4 will probably be the first to equal WC clock-for-clock in IPC. So Intel has winning cards in all battles here.
"So Intel has winning cards in all battles here."

Absolutely! That's why AMD is outselling Intel CPUs in nearly every market by 70/80% to 20/30%. :) So bad troll you are.

cucker tarlson
I think they're slightly ahead,though for single thread gaming intel still beats them due to lower latency of the ring design and clocks.

This looks like same old same old core,only 10th gen locked skus will match 9th gen k-series on stock clocks and there's HT on every cpu + a 10 core.

will probably end up really competitive against ryzen 3000/4000,imagine stock 9900k rivalling 3700x/3800x not 3900x,but intel has no new core design still.
Yes, beats Ryzen in gaming by 4-5% when you pair it with a $1100 2080Ti and test it on FHD. :D Which is not a real life situation. When you move to 1440p with a 2080Ti, difference is 2-3%. When you switch to lower tier GPUs, difference is near 0 on FHD.
Posted on Reply
#59
ZeroFM
JackCarver
That's nature of Benchmarks, isn't it? Can you feel the few ms a Ryzen 3900X compresses a file faster than an Intel 9900K?

You can look at the 3900X Review, it got beaten over all games relative Performance by my old 8700K. But when it comes to pricing a german Hardware dealer asks the following Prices:

- Ryzen 3700X 325,90€/Intel i7 9700K 379,90€
- Asrock Taichi X570 305,90€/Asrock Z390 Taichi 232,45€

The Ryzen System costs you 631,80€/The Intel System costs you 612,35€
So the Intel System is cheaper and it beats the Ryzen System in games by nearly 10%. So if your System is a gaming rig, what would you choose?


You can cool it with a good air cooler or an AiO, no custom Loop or similar necessary here. 10% gaming benefit over all cards
Okey budged 900$ cpu , mb , gpu
9700K 426[B][B]€ [/B]+ asus strix h370-f 137.20€ + cooler 212 evo 30€ + gigabyte 1650 super 189.39[B]€ =[/B] 782.59€ / 874.51$
2700 160.19+ strix b450-f 119.69[B]€ + [/B]sapphire pulse 5700xt 447[B]€[/B] = 726.88[B]€[/B] / 812.25$[/B]
In most games 5700xt is at least 80%+ faster , wolfenstein 2 1440p is 160% faster .
For gaming and is only choice .
Posted on Reply
#60
cucker tarlson
B-Real
AMD is outselling Intel CPUs in nearly every market by 70/80% to 20/30%.
proof ?

:) So bad troll you are.
Posted on Reply
#61
B-Real
JackCarver
There is no clear answer which cpu is better, Intel or AMD. Before Ryzen the answer was clear Intel but now it depends on use case. For gamer I think Intel is the best choice and 10c/20t are more than enough for this use case. For Productivity I would choose AMD.
It isn't clear? :D Gaming performance is equal. If you want to use your 2080 Ti on a 1080p monitor, yes, you get 4-5% better fps on average on Intel. On the "other" part, AMD has reached Intel in IPC. Not to speak about programs that make use of the cores.

cucker tarlson
proof ?

:) So bad troll you are.
https://www.extremetech.com/computing/281741-new-retail-data-shows-amd-outselling-intel-21
https://wccftech.com/amd-outselling-intel-by-more-than-double-analyzing-5-year-historical-sales-at-mindfactory-de/
https://www.techradar.com/news/amd-ryzen-7-3700x-is-such-a-hit-it-almost-outsold-intels-entire-cpu-range
https://www.techpowerup.com/257755/japanese-diy-market-goes-big-on-ryzen-68-6-market-share-for-amd

Gamersnexus made a survey, where 85 or 90% of its users bought Ryzen.
Posted on Reply
#62
Tomorrow
cucker tarlson
proof ?
Germany, Japan and South Korea have been in the news for Ryzen significantly outselling Intel. Individually Gamers Nexus say most of their audience now buys Ryzen.
There's little reason to doubt other markets do not have the same trends.
Posted on Reply
#63
cucker tarlson
B-Real
Yes, beats Ryzen in gaming by 4-5% when you pair it with a $1100 2080Ti and test it on FHD. :D Which is not a real life situation. When you move to 1440p with a 2080Ti, difference is 2-3%. When you switch to lower tier GPUs, difference is near 0 on FHD.
15-20% between 9900k and 3900x in gaming
https://www.purepc.pl/procesory/test_procesora_amd_ryzen_9_3900x_jeszcze_wincyj_rdzyniuf?page=0,50
https://www.purepc.pl/procesory/test_procesora_amd_ryzen_9_3900x_jeszcze_wincyj_rdzyniuf?page=0,42
https://www.purepc.pl/procesory/test_procesora_amd_ryzen_9_3900x_jeszcze_wincyj_rdzyniuf?page=0,43
https://www.purepc.pl/procesory/test_procesora_amd_ryzen_9_3900x_jeszcze_wincyj_rdzyniuf?page=0,45

also,how 1440p is a test for CPU's performance to guys like you I still can't understand.
framerates are framerates,if it takes 2080Ti to show the difference then after ampere/rdna2 enter the market that's gonna be a $500-600 card,what a vast portion of this forum is running.2080 super after OC is already close to 2080Ti.

Tomorrow
Germany, Japan and South Korea have been in the news for Ryzen significantly outselling Intel. Individually Gamers Nexus say most of their audience now buys Ryzen.
There's little reason to doubt other markets do not have the same trends.
I take your and B-real's point,but your data is anecdotal.That's not Germany,that's minfactory.If you analyzed their prices for amd and intel you'd see why.
Posted on Reply
#64
trparky
I'm really surprised nobody is talking about the 250 Watt TDP value that Intel is saying the chip will have when hitting all-core boost speeds. On one hand, I'm glad that Intel is finally advertising something that comes close to real-world TDP values; but on the other hand, it's showing just how inefficient their chips really are and just how badly they need to get off the aging 14nm process node. Too bad Intel doesn't have an answer to that issue until sometime in 2023 if you ask some people.

In other words, get ready for some really hot running chips from here on out from Intel until they can somehow fix their smaller process nodes. Good luck people. Meanwhile, I'm really looking more and more at AMD as the winner for the next few years.
Posted on Reply
#65
B-Real
JackCarver
That's nature of Benchmarks, isn't it? Can you feel the few ms a Ryzen 3900X compresses a file faster than an Intel 9900K?

You can look at the 3900X Review, it got beaten over all games relative Performance by my old 8700K. But when it comes to pricing a german Hardware dealer asks the following Prices:

- Ryzen 3700X 325,90€/Intel i7 9700K 379,90€
- Asrock Taichi X570 305,90€/Asrock Z390 Taichi 232,45€

The Ryzen System costs you 631,80€/The Intel System costs you 612,35€
So the Intel System is cheaper and it beats the Ryzen System in games by nearly 10%. So if your System is a gaming rig, what would you choose?


You can cool it with a good air cooler or an AiO, no custom Loop or similar necessary here. 10% gaming benefit over all cards
Why are you counting an X570 when an X470 or B450 is absolutely enough for a 3700X? Or why are you checking the same model? Cheapest X570 is $140, cheapest Z390 is $115. That's a $25 difference. Yours is $73. Of course it sounds better for you, Intel fanboy.

Where did your 8700K beat the 3700X by nearly 10% in games? It's 4% with a 2080Ti in FHD. Is lying lucrative for you?

https://tpucdn.com/review/amd-ryzen-7-3700x/images/relative-performance-games-1920-1080.png

"You can cool it with a good air cooler or an AiO"

Hope you counted its price when comparing prices. :) :)

cucker tarlson
15-20% between 9900k and 3900x in gaming
https://www.purepc.pl/procesory/test_procesora_amd_ryzen_9_3900x_jeszcze_wincyj_rdzyniuf?page=0,50
https://www.purepc.pl/procesory/test_procesora_amd_ryzen_9_3900x_jeszcze_wincyj_rdzyniuf?page=0,42
https://www.purepc.pl/procesory/test_procesora_amd_ryzen_9_3900x_jeszcze_wincyj_rdzyniuf?page=0,43
https://www.purepc.pl/procesory/test_procesora_amd_ryzen_9_3900x_jeszcze_wincyj_rdzyniuf?page=0,45

also,how 1440p is a test for CPU's performance to guys like you I still can't understand.
framerates are framerates,if it takes 2080Ti to show the difference then after ampere/rdna2 enter the market that's gonna be a $500-600 card,what a vast portion of this forum is running.2080 super after OC is already close to 2080Ti.


I take your and B-real's point,but your data is anecdotal.That's not Germany,that's minfactory.If you analyzed their prices for amd and intel you'd see why.
1. So it takes a $1100 card to show that Intel has a 4-5% advantage in gaming. A card that is never used in FHD, but 1440P or more likely in 4K, where you nearly won't get measurable difference. Anyway, how do you see a 4-5% difference in real life? :D

2. You believe a Polish site but you won't to Techpowerup? :D https://tpucdn.com/review/amd-ryzen-9-3900x/images/relative-performance-games-1920-1080.png And you link one result but won't link something like Watch Dogs 2, where the difference is 4%? Or Civilization VI where Ryzen beats Intel?

3. "That's not Germany,that's minfactory" Mindfactory is Germany's BIGGEST retailer. Also, there is the link from Japanese retailers. You can believe what you want, I don't really care. I care for the numbers that are shown for current sales. Check Techpowerup's survey for future CPU purchases and current CPU owners. For the former, the majority is willing to buy Ryzen, for the latter, about 40% of them have CPUs of Haswell or older models (myself too). Most of these owners will switch to AMD in some years.
Posted on Reply
#66
cucker tarlson
B-Real
Where did your 8700K beat the 3700X by nearly 10% in games? It's 4% with a 2080Ti in FHD. Is lying lucrative for you?
7-15% is a correct estimate

https://ithardware.pl/testyirecenzje/test_amd_ryzen_7_3800x_najszybsze_osiem_rdzeni_na_rynku-10186.html




it's 12% faster than 3800x OC,on 1080ti

for a guy with that nickname you surely talk surprisingly little facts and surprisingly lot propaganda


B-Real
So it takes a $1100 card to show that Intel has a 4-5% advantage in gaming. A card that is never used in FHD, but 1440P or more likely in 4K, where you nearly won't get measurable difference. Anyway, how do you see a 4-5% difference in real life? :D
this is how measuring performance works.
you think all other tests,e.g. video or rendering,are setup differently cause that way they favor amd ?
fhd at ultra runs same or worse than 1440p on custom high/v.high settings
it's the numbers the tests focuses on,not resolutions.
Posted on Reply
#67
Tomorrow
cucker tarlson
15-20% between 9900k and 3900x in gaming
https://www.purepc.pl/procesory/test_procesora_amd_ryzen_9_3900x_jeszcze_wincyj_rdzyniuf?page=0,50
https://www.purepc.pl/procesory/test_procesora_amd_ryzen_9_3900x_jeszcze_wincyj_rdzyniuf?page=0,42
https://www.purepc.pl/procesory/test_procesora_amd_ryzen_9_3900x_jeszcze_wincyj_rdzyniuf?page=0,43
https://www.purepc.pl/procesory/test_procesora_amd_ryzen_9_3900x_jeszcze_wincyj_rdzyniuf?page=0,45
15-20% edge cases. Not the norm:


Source:
Posted on Reply
#68
cucker tarlson
Tomorrow
15-20% edge cases. Not the norm:


Source:

certainly not the norm.
but then again,9900k is not for normal people,is it :laugh:

btw their numbers are BS,like 1% in witcher 3.easy to find videos disproving it.they're testing 3600 cl14 too.
but then they're a youtube channel,they will pander to whoever prevails in their comment section.just the way it has to be.
Posted on Reply
#69
trparky
Yes, Intel will indeed beat AMD in gaming when you pair each of their high-end chips with the best nVidia GPU that can be had (RTX 2080Ti). However, can I ask a really stupid question? Outside of benchmarks and people who just have more money than they know what to do with... Who really builds a system like that? Most of us mere mortals don't, we're lucky we're going to be pairing these chips with something closer to that of an RTX 2060 or something that's far more affordable than that.

With that being said... if you pair an Intel or AMD chip with a more affordable GPU then the performance gap starts to not look as big. Some might say that it's hardly noticeable at that point.
Posted on Reply
#70
cucker tarlson
trparky
Yes, Intel will indeed beat AMD in gaming when you pair each of their high-end chips with the best nVidia GPU that can be had (RTX 2080Ti). However, can I ask a really stupid question? Outside of benchmarks and people who just have more money than they know what to do with... Who really builds a system like that? Most of us mere mortals don't, we're lucky we're going to be pairing these chips with something closer to that of an RTX 2060 or something that's far more affordable than that.

With that being said... if you pair an Intel or AMD chip with a more affordable GPU then the performance gap starts to not look as big. Some might say that it's hardly noticeable at that point.
the "floor" on current cpu gaming performace is good enough to buy a 3500x/9400f and easily pair it with a 2080 for pleasurable +70-80 fps experience with everything cranked up at 1440p
with 4c/8t i3s running +4GHz on locked skus it's gonna get even better.

people who buy 9900k's for that extra 10-20% are just like those who buy 3900x over 3700x to save seconds on rendering.cause they can.

noticeable - yes,easily.
the real question is necessary,not noticeable.
Posted on Reply
#71
trparky
The point I'm driving at is the fact that when you ask most benchmarkers they refer to the fact that they use the RTX2080Ti graphics card to eliminate all possible forms of GPU-bound performance limitations. However, when you pair any one of these chips that's we're talking about with more affordable graphics cards you start bumping up against situations in which you're no longer limited by the CPU but instead by the GPU.

For instance, if I were to build two systems with my GPU which is an older GTX1060 6 GB card. One system with the best Intel offers and one with the best AMD offers. Would you be able to tell the difference? Probably not even close.
Posted on Reply
#72
cucker tarlson
trparky
The point I'm driving at is the fact that when you ask most benchmarkers they refer to the fact that they use the RTX2080Ti graphics card to eliminate all possible forms of GPU-bound performance limitations. However, when you pair any one of these chips that's we're talking about with more affordable graphics cards you start bumping up against situations in which you're no longer limited by the CPU but instead by the GPU.
it's the testing location that matters just as much imo,not just the card.
it all depends on what your upgrade path is,too.
I went from 980Ti to 2070 super on my current z97.that's 1.6x on average.If your way is to keep the gpu for longer you may look at it from another perspective.BTW it's an interesting topic to ask ppl ion a poll.how much has your gpu performance increased on your current platform (socket) and did you have to upgrade the cpu in the process too.

Posted on Reply
#73
SrKag


View this on Intel's self boosting marketing. Y'all are falling in the same pit again. :banghead::banghead::banghead:
Posted on Reply
#74
trparky
I guess that the point I'm driving at is that 95% of users out there with modest hardware configurations aren't going to be able to tell the difference between AMD and Intel other than having about $200 more in the bank when buying AMD. It's only the top 5% of users that just have to have the best GPU that money can buy that will be able to tell the difference.

Do you see where I'm going with this? Benchmarks are nice and all, yes; I'm not denying that at all. It's cool to be looking at these numbers but in reality, they only really matter to 5% of the market that just must have the best of the best of the best just to say that they have it.
Posted on Reply
#75
cucker tarlson
trparky
I guess that the point I'm driving at is that 95% of users out there with modest hardware configurations aren't going to be able to tell the difference between AMD and Intel other than having about $200 more in the bank when buying AMD.
sorry,but which Intel equivalent costs $200 more than amd's option ?

9600k(f) is priced between 3600 and 3600x
9700k(f) is priced between 3700x and 3800x


of course you buy what you need,but that does not change the facts.
most of us would not notice 3600 vs 3700x in video creation nor gaming too.and you're paying a 60% premium.so yeah,saving ..... the more cores,the more saved.
Posted on Reply
Add your own comment