AMD Ryzen (Summit Ridge) Benchmarks Thread (use new thread)

[StinkyPinky]

3.6 is fantastic for 8 core. It really makes you wonder what speeds they can get on their hex core cpus. Can they get 4?

 

[krumme]

3.6 is fantastic for 8 core. It really makes you wonder what speeds they can get on their hex core cpus. Can they get 4?

Who dares answer that?
In 20 minutes we get a new tweet from Canard or Mathias and they pull another rabbit out the hat.

 

[lolfail9001]

Who dares answer that?
In 20 minutes we get a new tweet from Canard or Mathias and they pull another rabbit out the hat.

I dare to claim there won't be 6 cores either.

 

[KTE]

It seems like 3.6 is flattening out for baseclocks, I wouldnt give it more than 3.7 for final.. Turbo on the other hand

From what I'm seeing, I would not put 3.8GHz past them

I know, I know, I still find it very mysterious, but we'll soon manage to know how they've managed this.

Sent from HTC 10
(Opinions are own)

 

[Doom2pro]

I love how the mood has swung from what can't AMD do to what can AMD do... It seems like it was yesterday the mood was that AMD is going to over hype, under perform and disappoint. Now look around, someone suggests another 200Mhz base at launch and instead of getting laughed at people are like "I could see that".

What a wild ride this has been...

 

[bakyt115]

http://www.hardware.fr/news/14924/tous-amd-ryzen-seront-overclockables.html

sorry if someone post this earlier

 

[lifeblood]

According to AMD, the better your cooling, the faster Ryzen will run. This kinda makes boost clocks irrelevant, doesn't it? Base is the minimum speed the CPU will run, and (on a normal CPU) boost is the fastest your CPU will run if cooling allows. But with Ryzen, if you put exotic cooling (H2O or something) it will boost even higher. So that implies their really isn't a max boost except what your cooling solution or motherboard power allows.

Or am I reading that wrong?

 

[cytg111]

I love how the mood has swung from what can't AMD do to what can AMD do... It seems like it was yesterday the mood was that AMD is going to over hype, under perform and disappoint. Now look around, someone suggests another 200Mhz base at launch and instead of getting laughed at people are like "I could see that".

What a wild ride this has been...

I know it looks good though I still reserve judgement.. Havent seen conclusive evidence for the ST performance yet.
We do know, now, that AMD will be presenting a full stack of Ryzen CPU's so whatever they can clock a hex and a quad at... we're soon to find out!

 

[KTE]

I know it looks good though I still reserve judgement.. Havent seen conclusive evidence for the ST performance yet.
We do know, now, that AMD will be presenting a full stack of Ryzen CPU's so whatever they can clock a hex and a quad at... we're soon to find out!

It's better to underhype than overhype

We don't want a repeat of the past 10 years.

So far things are looking extremely positive. I can't wait to see some data!

Sent from HTC 10
(Opinions are own)

 

[lolfail9001]

I love how the mood has swung from what can't AMD do to what can AMD do... It seems like it was yesterday the mood was that AMD is going to over hype, under perform and disappoint. Now look around, someone suggests another 200Mhz base at launch and instead of getting laughed at people are like "I could see that".

What a wild ride this has been...

I suppose it's time for me to spout more doom and gloom, because so far it's been working excellently.

Okay, you got it, Zen will probably match Broadwell in most stuff, few tasks here and there where they differ significantly. But will Zen have memory controller to pull off Skylake DDR4 frequencies?

 

[CatMerc]

I suppose it's time for me to spout more doom and gloom, because so far it's been working excellently.

Okay, you got it, Zen will probably match Broadwell in most stuff, few tasks here and there where they differ significantly. But will Zen have memory controller to pull off Skylake DDR4 frequencies?

The AM4 motherboards are supporting 4000MHz+, so VoV

 

[BeepBeep2]

The AM4 motherboards are supporting 4000MHz+, so VoV

I haven't seen any evidence suggesting that.

 

[lolfail9001]

The AM4 motherboards are supporting 4000MHz+, so VoV

I wonder why MSI only lists up to DDR4-2666 with OC tag in the promo for the Titanium board, then.

 

[cytg111]

I wonder why MSI only lists up to DDR4-2666 with OC tag in the promo for the Titanium board, then.

Same with skylake at launch, ddr4 speeds was mediocre and it got a mixed rating in reviews.. later when ddr4 speeds picked up the platform shined.

 

[nismotigerwvu]

It's better to underhype than overhype

We don't want a repeat of the past 10 years.

So far things are looking extremely positive. I can't wait to see some data!

Sent from HTC 10
(Opinions are own)

10 Years is a bit of a stretch. Conroe was certainly a game changer but it isn't like everything from that point on was as bad as it has been the last few years. Anand titled his Phenom II launch review A True Return to Competition and the very first line read "The AMD we used to know and love is back". 15 months later with the hex-core launch he started off with "A very smart man once told me that absolute performance doesn’t matter, it’s performance at a given price point that makes a product successful. While AMD hasn’t held the absolute performance crown for several years now, that doesn’t mean the company’s products haven’t been successful". I mean even at the Bulldozer launch he concluded "In many cases, AMD's FX-8150 is able to close the gap between the Phenom II X6 and Intel's Core i5 2500K. Given the right workload, Bulldozer is actually able to hang with Intel's fastest Sandy Bridge parts. ... AMD has released a part that is generally more competitive than its predecessor, but not consistently so. AMD also makes you choose between good single or good multithreaded performance, a tradeoff that we honestly shouldn't have to make in the era of power gating and turbo cores". Not exactly high praise, but not the LOLFaildozer point of view most people look back with. AMD doesn't need to recreate the Athlon 64 obliterating the Pentium 4 type situation again, nor does it need the Athlon besting the Pentium III across the board by a small margin (though that would be great for us), really all they need is a return to competition in the meat of the lineup a la the Phenom II. Chasing the absolute performance crown is nice and all, but the $1000 CPU market isn't the most necessary niche. The scary part for Intel will be Raven Ridge, as it looks like the CPU bottleneck of AMD APUs will finally be alleviated and there likely won't be a better all around chip on the market for majority of users.

 

[The Stilt]

The AM4 motherboards are supporting 4000MHz+, so VoV

Sure, if you really want to tamper with the BCLK...
Personally I appreciate reliability more, than the few additional MHz that in most cases gain you nothing but bigger figures on the screen.

 

[lolfail9001]

Same with skylake at launch, ddr4 speeds was mediocre and it got a mixed rating in reviews.. later when ddr4 speeds picked up the platform shined.

First review i picked up for 6700k: DDR4 3600Mhz. Next few did not mention issues with memory overclocking or did not bother with it at all.
So, not really.

 

[itsmydamnation]

Sure, if you really want to tamper with the BCLK...
Personally I appreciate reliability more, than the few additional MHz that in most cases gain you nothing but bigger figures on the screen.

so long as i can run low timers if i cant run really high clocks im still happy

 

[Insomniator]

10 Years is a bit of a stretch. Conroe was certainly a game changer but it isn't like everything from that point on was as bad as it has been the last few years. Anand titled his Phenom II launch review A True Return to Competition and the very first line read "The AMD we used to know and love is back". 15 months later with the hex-core launch he started off with "A very smart man once told me that absolute performance doesn’t matter, it’s performance at a given price point that makes a product successful. While AMD hasn’t held the absolute performance crown for several years now, that doesn’t mean the company’s products haven’t been successful". I mean even at the Bulldozer launch he concluded "In many cases, AMD's FX-8150 is able to close the gap between the Phenom II X6 and Intel's Core i5 2500K. Given the right workload, Bulldozer is actually able to hang with Intel's fastest Sandy Bridge parts. ... AMD has released a part that is generally more competitive than its predecessor, but not consistently so. AMD also makes you choose between good single or good multithreaded performance, a tradeoff that we honestly shouldn't have to make in the era of power gating and turbo cores". Not exactly high praise, but not the LOLFaildozer point of view most people look back with. AMD doesn't need to recreate the Athlon 64 obliterating the Pentium 4 type situation again, nor does it need the Athlon besting the Pentium III across the board by a small margin (though that would be great for us), really all they need is a return to competition in the meat of the lineup a la the Phenom II. Chasing the absolute performance crown is nice and all, but the $1000 CPU market isn't the most necessary niche. The scary part for Intel will be Raven Ridge, as it looks like the CPU bottleneck of AMD APUs will finally be alleviated and there likely won't be a better all around chip on the market for majority of users.

A single title or line does not a review make -- I looked through those benchmarks for Phenom II and they are getting crushed by the new i7's and Anand is happy that the Phenom II can compete with the 2 year old (at the time) Core 2 Quads, though even the 9550 is still faster. With Bulldozer its also still slower and using 2x the power. They haven't released anything useful for mid-high end in 10 years.

 

[Abwx]

10 . Conroe was certainly a game changer

A True Return to Competition .

The actual game changer was the use of Sysmark, some Excel test optimised by and for Intel, and a huge marketing campaign that overhyped what was after all a small progress despite one node advantage.

If we look at the link you provided the 2.2GHz Core 2 is not that much better than the Athlon 64 X2 2.4GHz in the encoding tests, Povray, 3DS Max, Blender, and of course Cinebench, but wait, how wasnt CB the thermometer of IPC at the time.???.
Or was it Sysmark..?.

Anyway once the A64X2 was shrinked to the same node as the Core 2 it got back the perf/Watt crown...

 

[majord]

Sure, if you really want to tamper with the BCLK...
Personally I appreciate reliability more, than the few additional MHz that in most cases gain you nothing but bigger figures on the screen.

So I take it 2666 the max memory multi?

 

[The Stilt]

so long as i can run low timers if i cant run really high clocks im still happy

So I take it 2666 the max memory multi?

Let's put it this way: Ryzen won't be memory bound

 

[DrMrLordX]

Sure, if you really want to tamper with the BCLK...

So long as we don't have a return to the FM2+ fiasco, bclk OC is going to be fine.

Let's put it this way: Ryzen won't be memory bound

And Raven Ridge?

 

[The Stilt]

So long as we don't have a return to the FM2+ fiasco, bclk OC is going to be fine.



And Raven Ridge?

There should be no need to touch the BCLK in the first place.

The thrust is nominal.

 

[BeepBeep2]

There should be no need to touch the BCLK in the first place.

The thrust is nominal.

DRAM frequency WR or bust