I wonder how it will behave in real world workloads on all cores. Because if Cores were originally designed as 4C/8T to work with dual channel and high end platform 8C/16T working with quad... there may be quite some bottleneck outside of synthetic benchmark workloads.

The intel "unicorn" was finally spotted? Even if it's just a tail but still... :P

As much as I want one, I rather save my kidneys for later.

Probably just two dies glued together. 😀

Srsbsns:

Probably just two dies glued together. 😀

OUCH! Right in intels nut sack!

Srsbsns:

Probably just two dies glued together. 😀

Pentium D anyone? Q6600 anyone? HAHA though.

Agonist:

Pentium D anyone? Q6600 anyone? HAHA though.

Q6600 was superb I used it to replaced my E7200@4GHz (super low voltage) Ran it at 3.2GHz i think... 3.6GHz was not fully stable. 8700K incoming...I'm slightly worried that ACIV backplate in 1st PCIEe will clash with Noctua NH-D15 (Asus Hero X)

Tempting, but no. Will see what's up with 9th gen IceLake (@10nm+), apparently also due in 2018, they've split CannonLake to laptops and IceLike will be using its improved 10nm process, kind of like what KabbyLake is to Skylake. I've also read somewhere that this IceLake and improved 10nm++ TigerLake will have next-gen x86, dropping older SIMID for newer executions and more of them, older will be emulated. https://s18.postimg.org/gk165vbp5/Screenshot-2018-3-21_Tick_tock_model_-_Wikipedia.png

Noisiv:

Q6600 was superb I used it to replaced my E7200@4GHz (super low voltage) Ran it at 3.2GHz i think... 3.6GHz was not fully stable. 8700K incoming...I'm slightly worried that ACIV backplate in 1st PCIEe will clash with Noctua NH-D15 (Asus Hero X)

I had a q6600 @ 3.75 with 1.4v, it would do 4GHZ @ 1.52v. I had that rig for almost 4 years. Q6600@ 3.75 MSI P35 Neo2 4GB Wintec AMP X DDR2 800 @ 1000 OCZ 850w HiS HD 5770 1GB ICEQ Turbo 5 EVGA 9800GTX + 512mb for Physx Ultra X Blaster Case 160GB OS 320GB steam drive 1TB storage drive. It was a good chip but it was not a true quadcore. No 775 quads were.

well, when it does arrive, it will be nice to see what watts and heat it will produce at the same frequency as a the ryzen. And I think in that area the ryzen will win, because intel's 6 coffee cupper is a hottish chip already

Fox2232:

I wonder how it will behave in real world workloads on all cores. Because if Cores were originally designed as 4C/8T to work with dual channel and high end platform 8C/16T working with quad... there may be quite some bottleneck outside of synthetic benchmark workloads.

So Ryzens are severely limited by the dual channel as well, is that the thing you wanted to propose?

So once again, only with new MB and chipset, even for same 8xxx line?

ruthan:

So once again, only with new MB and chipset, even for same 8xxx line?

Yes something like that, hey' gotta milk it to the max before moving on to 9000 series. Imo 9000 series is worth waiting. It will be the first with a new architecture, no more SandyBridge roots.. Second half 2018, probably Q3, is the release date. This is also that new hw fixed meltdown and spectre processor.

SaLaDiN666:

So Ryzens are severely limited by the dual channel as well, is that the thing you wanted to propose?

Ryzen was not developed to be sold as 4C/8T. Its IMC behaves differently (read AMD's IMC is now better than intel's) as can be seen on comparison of EPYC vs intel's workstation solutions.

Koniakki:

The intel "unicorn" was finally spotted? Even if it's just a tail but still... 😛

At 2.2ghz it better be super highly optimised cpu, or it gona have some shitty unicorn performance

Fox2232:

Ryzen was not developed to be sold as 4C/8T. Its IMC behaves differently (read AMD's IMC is now better than intel's) as can be seen on comparison of EPYC vs intel's workstation solutions.

Ryzen and Epyc are different platforms, so stop comparing apples and oranges to get your points across. /benchmarks I saw tells the different story, depends on a number of threads, sometimes AMD is better, sometimes Intel, one AMD CCX /4cores/ can access only up to 30GB/s / 8700k and 1800x have pretty much same memory bandwith while 8700k having 3x lower latencies, also i7 8700k's cache manages higher bandwith, so not really. OC 8700k is almost as quick or even faster as an 8 core Ryzen in cpu heavy tasks such as rendering etc. Intel also generally handles and supports higher RAM clocks and lower latencies better. None of current Intel cpus were developed as quad cores, all cores all native and the ringbus is scalable, the culprit is that at a certain point you start encountering higher latencies due to a higher number of cycles, so Intel is upgrading to the mesh. If anything, AMD current cpus were designed mainly as quadcores which are interconnected together in order to be scaled, look at their latencies and their gaming performance being heavily affected by RAM clocks/timings. So stop with this projecting towards Intel. So I really don't get it were are you getting your assumptions from because by your logic, even 8700k should be somehow underpeforming and suffering from "the quad core design" and "missing the quad channel". But the reality is different and 8700k is riping everything apart in games and contests with 8cores when OC-ed at rendering.

SaLaDiN666:

Ryzen and Epyc are different platforms, so stop comparing apples and oranges to get your points across. /benchmarks I saw tells the different story, depends on a number of threads, sometimes AMD is better, sometimes Intel, one AMD CCX /4cores/ can access only up to 30GB/s / 8700k and 1800x have pretty much same memory bandwith while 8700k having 3x lower latencies, also i7 8700k's cache manages higher bandwith, so not really. OC 8700k is almost as quick or even faster as an 8 core Ryzen in cpu heavy tasks such as rendering etc. Intel also generally handles and supports higher RAM clocks and lower latencies better. None of current Intel cpus were developed as quad cores, all cores all native and the ringbus is scalable, the culprit is that at a certain point you start encountering higher latencies due to a higher number of cycles, so Intel is upgrading to the mesh. If anything, AMD current cpus were designed mainly as quadcores which are interconnected together in order to be scaled, look at their latencies and their gaming performance being heavily affected by RAM clocks/timings. So stop with this projecting towards Intel. So I really don't get it were are you getting your assumptions from because by your logic, even 8700k should be somehow underpeforming and suffering from "the quad core design" and "missing the quad channel". But the reality is different and 8700k is riping everything apart in games and contests with 8cores when OC-ed at rendering.

Isn't it funny when you look at it, but can't see it. You even wrote it down: "8700k and 1800x have pretty much same memory bandwith" What you do not get is Bandwidth scaling. Ryzen AM4 has 20~35% bandwidth scaling when you move from ST to MT workloads. Coffee Lake 7~13% bandwidth Scaling from ST to MT. Those Higher end platforms with Quad channel have much better bandwidth scaling. So, now Intel brings 8C/16T chip with dual channel which does not scale bandwidth with increased number of cores used. For those who will not want to have this chip bandwidth starved at certain workloads, it will be very cheap chip. Because cost of the top OC memory kit will make it look that way. Want to see if it will be memory starved? Ask someone with Coffee 6C/12T to reduce memory clock from 3200MHz to 2400MHz. Why, because 6C/12T is 25% less cores than 8C/16T. And 2400MHz is 25% lower clock than 3200MHz. (But I think you are already starting to get it, right?)

Yeah but Intel use a Special glue not just your average Amd el-cheepo one. What a bunch of Haters these guys are I swear to god.

Fox2232:

...... Want to see if it will be memory starved? Ask someone with Coffee 6C/12T to reduce memory clock from 3200MHz to 2400MHz. Why, because 6C/12T is 25% less cores than 8C/16T. And 2400MHz is 25% lower clock than 3200MHz. (But I think you are already starting to get it, right?)

I can help with that. Any specific tests to run?

Koniakki:

I can help with that. Any specific tests to run?

Usual Suspects 🙂 Geekbench 3/4, Luxmark, Cinebench r15, 3D Mark FS Standard. And if you have some game with Benchmark built-in. I sorted them out based on expected ability to show difference.