AMD RyZen CPU Architecture for 2017

Anyone knows if the supposed turbo core speed for the leaked specs is for 1, 4, 8 or maybe a dynamic mix?

 

EU prices listed - AMD Ryzen 7 1800X To Cost 628 EUR

http://www.guru3d.com/news-story/eu-prices-listed-amd-ryzen-7-1800x-to-cost-628-eur.html

 

386 EUR is looking great for the 65w 8 core.

 

Yes.

 

Spoiler

http://www.pcgamer.com/new-amd-ryzen-details-and-pricing-leaks/
Results are incredibly inconsistent, it's very workload specific, plus, i'm talking about real-world performance(since that matters the most to most consumers), which we don't really know about yet, but it likely will only be worse than bench's avg.

FX to this day scores high, even very high, in some benchmarks, before its release it was also looking better than Sandy Bridge, but it's not even as good as trade-off, is it? AMD CPUs have some really low lows, compared to Intel's, it's definitely not going away completely with Zen, and market share is not helping it.

They all stand no chance against current Intel line-up. None of these products are desirable.

You have got to be kidding, not only it's worse in every possible way: performance, power consumption, heat, efficiency, outdated dead platform; it's also more expensive.

I would prefer G4560 over ANY current AMD cpu right now, and i am sure i'm in vast majority, their current products are not competitive in the slightest, and it would be even cheaper to switch to Zen from Pentium(since you would have DRR4 already).

http://www.techspot.com/review/1325-intel-pentium-g4560/

 

So don't look at these dumb graph's, go look at the raw scores (anyone can) in the app. Then look at the config of that Zen host note that it has DDR4 2400 17-17-17 memory ( terrible) then look at the workloads that are most effected by crap slow memory. Shock horror they are physics and prime numbers sub tests. On my machine (ivb@4.3) going from 13ns to 9-10ns see's a big increase in the performance of both of those benchmarks, Zen is running in that benchmark with memory access speed of 14ns. So if i get a 76% increase in Physics test and a 74% increase in the prime numbers test going from 13ns to 9ns what do you think Zen will get going from crap memory to middle of the road DDR4 ( say 3200 16-16-16 (10ns)) memory? If it scales like my ivb then its 1263 and 64.

oh look those are right near the top, So how about "No Scott" /dr evil.

Code:

##1066 10-11-10 (18.7ns)
CPU Mark This Computer 9230
Integer Math This Computer 19408
Floating Point Math This Computer 8121
Prime Numbers This Computer 19.8
Extended Instructions (SSE) This Computer 225.8
Compression This Computer 14193
Encryption This Computer 2024
Physics This Computer 359.7
Sorting This Computer 8723
CPU Single Threaded This Computer 2370




##1066 7-7-7 (13ns)
CPU Mark This Computer    9932
Integer Math This Computer    19862
Floating Point Math This Computer    8305
Prime Numbers This Computer    25.5
Extended Instructions (SSE) This Computer    227.5
Compression This Computer    15206
Encryption This Computer    2078
Physics This Computer    413.9
Sorting This Computer    8589
CPU Single Threaded This Computer    2327

###1333 8-8-8 (12ns)
CPU Mark This Computer    10140
Integer Math This Computer    17076
Floating Point Math This Computer    8182
Prime Numbers This Computer    29.1
Extended Instructions (SSE) This Computer    220.0
Compression This Computer    14959
Encryption This Computer    2040
Physics This Computer    476.2
Sorting This Computer    8557
CPU Single Threaded This Computer    2367

###1333 7-7-7 (10.5ns)
CPU Mark This Computer    10516
Integer Math This Computer    19445
Floating Point Math This Computer    8457
Prime Numbers This Computer    29.9
Extended Instructions (SSE) This Computer    228.5
Compression This Computer    15119
Encryption This Computer    2074
Physics This Computer    503
Sorting This Computer    8761
CPU Single Threaded This Computer    2375

##2000 10-11-10 (10ns)
CPU Mark 10673
Integer Math 19504
Floating Point Math 8336
Prime Numbers 31.5
Extended Instructions (SSE) 219.1
Compression 14806
Encryption 1944
Physics 597
Sorting 8577
CPU Single Threaded 2358

##2133 mhz 13-14-13 CR T3 ....lol ( 12ns)
CPU Mark This Computer    10749
Integer Math This Computer    19761
Floating Point Math This Computer    8384
Prime Numbers This Computer    31.1
Extended Instructions (SSE) This Computer    226.9359
Compression This Computer    15186
Encryption This Computer    2134
Physics This Computer    538
Sorting This Computer    8811
CPU Single Threaded This Computer    2377

###2000mhz 9-11-10 (9ns!)
CPU Mark This Computer    11094
Integer Math This Computer    19519
Floating Point Math This Computer    8436
Prime Numbers This Computer    34.6
Extended Instructions (SSE) This Computer    225.8
Compression This Computer    15175
Encryption This Computer    2124
Physics This Computer    634
Sorting This Computer    8839
CPU Single Threaded This Computer    2379

 

Looks good I might be in for one during the summer. 8 core 16 threads would be a nice upgrade

 

Tell me about it, still on a 3GHz Core 2 Duo here…

 

Wow... upgrade often?

 

https://forum.beyond3d.com/posts/1965222/

Honestly again, the only 2 scores on Passmark that are incredibly bad are thoses 2.... its not what i call as you have write, totally inconstitent. .... In fact if you know the nature of prime and physics test, you should know that you cant get good result on the 5 other and abnormal test on thoses one due to the cpu being inconsitent.. ( more likely a bad memory setup )...

 

Well, I've got some 80 games in my Steam library, about 70 of which I have yet to play. Many of them are old enough to run very comfortably on my current rig, so I figure that I don't really need to upgrade until I've played all the old games and I move on to newer ones. That said, my 4GBs of RAM are getting small for a number of non-gaming use cases.

 

79.90$ AMD FX-4350 versus Skylake i3 6100 (dual core, 3.7 GHz with hyperthreading):
http://www.anandtech.com/bench/product/1682?vs=1273

i3 6100 is 200 MHz faster (3.7 GHz) than Pentium G4560 (3.5 GHz). Pentium doesn't have hyperthreading, meaning that it is significantly slower in some multi-threaded tests. The FX-4350 beats the i3 in many benchmarks. It would beat the 3.5 GHz Pentium in most benchmarks (as Kaby has same IPC as Skylake). AMD FX-4350 is definitely not "worse in every possible way" compared to the Pentium G4560. FX-4350 beat the Pentium especially bad in integer heavy multi-threaded tasks.

I don't think power consumption and heat are top concerns when you are building on budget. You want most performance out of the buck. AMD FX delivers very compatible performance at 79.90$.

If you are building on tight budget, you don't upgrade your computer that often. IMHO, you are not a budget oriented consumer if you own a DDR4 based system and are already looking to upgrade it. If you are upgrading your Haswell/Skylake DDR4 based system, a dual core (no HT) 3.5 GHz Pentium wouldn't be a noticeable improvement over anything you'd already have. Neither would be a cheap dual core Zen (if that existed) or AMD FX. Budget consumers would likely be upgrading from Core 2 Quad, Phenom X6 or Nehalem/Sandy (slower quad or faster dual). You'd have to buy a new mobo and new memory in any case.

 

I imagine that if and when AMD makes a "real" quad-core, i.e. a specific die with only 4 cores present, very affordable Ryzens would be doable, perhaps with half the normal amount of L3 per CCX.

Incidentally, we have yet to hear anything about that, but I wonder whether AMD intends to release 45W SKUs. Based on the rumored clock speeds for the 95W, 8-core SKUs, I think AMD should be able to come up with some pretty compelling stuff. The small form factor crowd might really like it, especially since the southbridge is optional, which enables really tiny motherboards. But that would make more sense with APUs.

 

Hopefully AMD is able clock their small quad core dies higher. People have been complaining that Intel no more makes 95W+ desktop quad cores. Desktop CPUs could have higher TDP with no problem. Nobody cares about +30W on desktop CPU as modern GPUs are taking 200W+. Servers and laptops are obviously a completely different matter.

 

Consumers seem reluctant to embrace power-hungry CPUs, beyond 95~125W, and I think a big reason for that is just diminishing returns, as high clocks tend to lead to much higher power consumption.

As for AMD's quads, I suppose higher base clocks would be possible (perhaps 3.8GHz instead of 3.5~3.6, assuming AMD isn't averse to this for marketing reasons) but I don't see how Turbo clocks could be significantly higher at 95W.

 

It's like you're ignoring Raven Ridge on purpose

 

Intel's K-series are still 91W+ TDP

 

I for one think Raven Ridge is a much more exciting product than all the CPU-only products coming in two weeks, but I understand AMD's need to strike at the high-end.
Raven Ridge in raw CPU performance is probably going to stand between the higher-end i3 and i5, so they might get mediocre reviews despite the iGPU being on a whole different level.

 

There are Xeons based on Broadwell EP that are cut down to 4 cores with a 140W TDP. Single-core turbo can get to 4 GHz.
A design targets a certain level of power delivery and dissipation per core, and turbo already allows a single core to act a lot like it is nearly alone or in a low-count chip--with some added dissipation area for good measure. I'm not sure if single-core turbo can max out at 140W on a sustained basis like having all cores running.

The gains may be somewhat limited due to this, and getting more out of it may require designing a core or CCX for an increasingly niche level of power delivery/density that raises the question of who buys a value-oriented 4-core that needs a custom water loop. In that regard, modern GPUs take advantage of parallelism (area, pins, units) and specialization (dedicated cooler, own VRMs) to eat up the extra TDP over a physically smaller CPU.

The power density problem can be acute enough that it can be a question of whether a core's expected performance can suffer if measures are taken to combat it. A core's thermal density can drop if it has more area, but there's a limit to how much heat can be transferred to neighboring power-gated silicon (having an inactive GPU or CCX can actually help), and a smaller native quad has less. Having more dissipation area in the core increases wire length--which counters clock or power scaling.

 

I dont know for the performance, you have 2 versions for what i have understand FP5 and AM4, both up to 4 cores / 8threads.. and coupled with Vega ( 12 and 16CU ). respectively 4-35W and up to 95W for the AM4 version. the AM4 version have HBM2+DDR4 ..

For the latter version ( AM4 ), i really think review will try exhaustively to check how >GPU performance are affected. And if the perf of the CPU parts are good ( all will depend what clock can be achieved in this 95W enveloppe ), i dont see why it could have mediocre review.