Ryzen2 may well hit 5GHz on 7nm says GF CTO

Good news:

http://www.guru3d.com/news-story/amd-ryzen-3000-globalfoundries-expects-5-ghz-in-the-7nm-process.html

Intel, you better prepare more cores ! If AMD comes along at the same speed, more Lanes, better prices...oh oh..I can see bad times coming for Intel if they don't throw in some goodies, like many more lanes, more cores, SOLDER, L3 cache, yeah...AMD has some advantages already, believe it or not, my 1600X outperforms my 8700k in mining by 50% ! with 1.2G less it makes 300 vs 200 Hs/sec in cryptonight algo. That thing literally pays for itself.

Ryzen2-3000_5G bring it on Lisa :)

I am having a hard time believing that even considering the source. Things never pan out as planned this much in advance.

I can see more cores and 4.7 Ghz, because silicon is not the only limiting factor, architecture is also. And I think its great anyway.

According to leaks, the 2700x has a factory boost clock of 4.35GHz, there are also some 4.8GHz results up. 5.0 GHz for the top end 3000 series seems very reasonable if the leaks are true.

If they can hit 4.8 in oc now with 12nm, you can bet that they run well beyond 5.0 with 7nm.

That or they have more cores to use the benefits, or a bit of both. 5G on 10c/20T 24MB L3 was cool hehe

Not trying to rain on the AMD parade, but Intel have easily had the lead for the last 5 years.

I wouldn't be surprised if they already have the roadmap available and ready to rock and roll for the next 2-3. If I were them, I'd be waiting until AMD are getting close, THEN drop the next bombshell of performance change.

Don't get me wrong, I think it's great that AMD are again providing genuine competition, as it'll always be good for consumers. However, I don't see Intel taking this without a fight.

Not trying to rain on the AMD parade, but Intel have easily had the lead for the last 5 years.

I wouldn't be surprised if they already have the roadmap available and ready to rock and roll for the next 2-3. If I were them, I'd be waiting until AMD are getting close, THEN drop the next bombshell of performance change.

Don't get me wrong, I think it's great that AMD are again providing genuine competition, as it'll always be good for consumers. However, I don't see Intel taking this without a fight.

With the Spectre and Meltdown issues, I think any road plan Intel might have had has taken a knock.

Intel is stuck to the current IPC until 2020 when they finally have a new uarch to go for the next leap, until then they'll just keep on refreshing their lineup. RYZEN 2000 are already all over the i5 and i7 chips in single core and better in multi for the same price. There will be few reasons to buy Intel unless you prefer the automation these chips offer for overclocking since AMD right now is very much an old school manual approach.

Not trying to rain on the AMD parade, but Intel have easily had the lead for the last 5 years.

I wouldn't be surprised if they already have the roadmap available and ready to rock and roll for the next 2-3. If I were them, I'd be waiting until AMD are getting close, THEN drop the next bombshell of performance change.

Don't get me wrong, I think it's great that AMD are again providing genuine competition, as it'll always be good for consumers. However, I don't see Intel taking this without a fight.

And they Cheated to get that lead...

It all Started w/ the Socket 7 Sabotage, and continued since then,

waiting to see how Intel sabotages Ryzen....

Intel is stuck to the current IPC until 2020 when they finally have a new uarch to go for the next leap, until then they'll just keep on refreshing their lineup. RYZEN 2000 are already all over the i5 and i7 chips in single core and better in multi for the same price. There will be few reasons to buy Intel unless you prefer the automation these chips offer for overclocking since AMD right now is very much an old school manual approach.

Intel has a huge advantage over AMD in single-threaded performance. In certain games, this is very important.

The small improvement with the new AMD parts will not close the gap. For the best gaming performance, Intel will still be the only option.

Of course, this doesn't diminish the great value of Ryzen for gamers outside these marginal situations.

Single core performance is losing importance as DX11 is fades from the norm. Intel's lead there is eroding quickly as the following graphs show. We could see the situation reverse with DX12 and Vulkan because those will be multicore capable API's. DCS happens to be one such future example. :)

Note: these benches were obtained with sub spec memory (2400MHz VS 2933 supported) on Ryzen 2700X. We should expect better performance with retail units.

I got 11% more performance from overclocking both the CPU and memory. (3.9 and 3.2 Ghz respectively).

The new CPU's are expected to match that on stock and likely another step of the same size further up when overclocked.

According to leaks, the 2700x has a factory boost clock of 4.35GHz, there are also some 4.8GHz results up. 5.0 GHz for the top end 3000 series seems very reasonable if the leaks are true.

4.25 Ghz is what I expect the 2700x to max at with all cores (most ryzen 1000's top out at a speed equivalent to the single core XFR frequency)

where did you see 4.8?

More cores will eventually count more than ultra high clocks on a few cores only.

Convenient to mention: thats liquid Nitrogen, Not for 24/7 use.

I do have to wonder if anyone has successfully built a liquid nitrogen loop for 24/7 use and what kind of stable overclock they were able to achieve.

In any case, that 4.8 GHz I mentioned previously seems to be unconfirmed and more rumor than fact. I expect 4.3 GHz will be the brick wall we hit with most Ryzen 2xxx chips. That's a decent bump by itself. I think the more interesting part is in stock settings though. My Ryzen 5 1600x system does 4.1 GHz on 1 core when completely idle, but the instant I have so much as a browser window open on a blank page, it drops to 3.7 GHz. The reason is it has only 2 boost states, 4.1 single core and 3.7 all core. There is nothing in between.

The Ryzen 2xxx's use a new system which, from AMD charts, suggests it will scale more like the current Intel chips. So on a 2600x, it will hold that top boost speed with 2-3 cores active instead of only 1, and it will drop only slightly as core usage goes up. This isn't important to those of us who overclock the snot out of everything, but for the other 99% of the world, that's a big change.

Regardless, the 8700k and 8600k look to remain the top DCS chips for the short term. When DCS moves from DX11 to Vulkan, that may change but it will depend on how ED codes it.

Is there any word on Vulkan? Are we a couple of years off? While that may...and I stress may tip the scales in AMD's favor but the 8700K won't be far behind if at all...They'll also be gaining a ton of power if we take away the CPU bottleneck we currently face in DCS...

I do have to wonder if anyone has successfully built a liquid nitrogen loop for 24/7 use and what kind of stable overclock they were able to achieve.

 

In any case, that 4.8 GHz I mentioned previously seems to be unconfirmed and more rumor than fact. I expect 4.3 GHz will be the brick wall we hit with most Ryzen 2xxx chips. That's a decent bump by itself. I think the more interesting part is in stock settings though. My Ryzen 5 1600x system does 4.1 GHz on 1 core when completely idle, but the instant I have so much as a browser window open on a blank page, it drops to 3.7 GHz. The reason is it has only 2 boost states, 4.1 single core and 3.7 all core. There is nothing in between.

 

The Ryzen 2xxx's use a new system which, from AMD charts, suggests it will scale more like the current Intel chips. So on a 2600x, it will hold that top boost speed with 2-3 cores active instead of only 1, and it will drop only slightly as core usage goes up. This isn't important to those of us who overclock the snot out of everything, but for the other 99% of the world, that's a big change.

 

Regardless, the 8700k and 8600k look to remain the top DCS chips for the short term. When DCS moves from DX11 to Vulkan, that may change but it will depend on how ED codes it.

A liquid nitrogen loop would be insanely expensive, it's only used (as far as I know) for crazy scientific applications since it expands like crazy as a gas and needs to be constantly turned back into a liquid.

LoL...Yeah...

Jesus & Maria !

4.5 maybe on a decent chip, but 5ghz no

It looks like the best you can possibly get is around 4.3Ghz in the testing that's coming out. Looks like the 8700K is still going to be king in DCS...till the 9700K maybe.

Our studio overclocked a 2700x to 4.8 Ghz on Custom Loop liquid cooling,

We can prolly get 4.9/5.0 if we deep cool the liquid in the loop via cooler unit.

So Price of Custom Loop ($500~), and Cost of a Chiller to cool water to pre-specified temp, $1200

SkateZilla, just because I'm curious, what core voltage was used ? (I bet pretty higher than 1.4...?)

There you go !!!!!!!!!!!!!!!!!!!!!!!!!

Goodbye Intel

I need to redo the title ! Ryzen+ may hit 5G on good dies..how bout that ?

I need to redo the title ! Ryzen+ may hit 5G on good dies..how bout that ?

Skatezilla's results are definitely impressive but still not a practical application for all but a very rare few(an extra $1700 of worth of hardware to cool it). I would still think DCS will run faster on Intel. Mining maybe not but that is a small relatively unimportant segment of the market. As I'm sure you know Bitmaster every 8700K will hit 5Ghz pretty easily.