AMD Demos Breakthrough Performance of the ZEN CPU Core

[$ReaPeR$]

I doubt it the last so called 'leaked' benchmark was ashes and we all know how much that (and I use this term very loosely)`game` favors lots of threads
theres been no superpi or luxmark single thread or cinbench

look, even marketing idiocy has its limits, there has to be some truth at least. i doubt that zen will be faster, but imo it will be within 10% of the corresponding intel counterpart. at this point that will have to do.

 

[TRWOV]

Well, this was pleasantly unexpected

The only drawbacks I think Zen will have is that the CPUs will sport a higher TDP; I'm thinking about 165w for a 8C/16T part at 3.2Ghz or so. I'm pretty sure AMD is brute forcing all of this performance for the time being and will later be refined. Maybe I'll pick up the revised Zen.

 

[OneMoar]

look, even marketing idiocy has its limits, there has to be some truth at least. i doubt that zen will be faster, but imo it will be within 10% of the corresponding intel counterpart. at this point that will have to do.

I hope so but don't count on it and certainly don't give anybody any money until you see numbers

 

[alucasa]

It's simple really.

Make judgement - after - it's released, not before.

 

[Jism]

Breakthrough Performance of Next-Generation “Zen”

"We are on par with our performance targets"

Sums about it. And if anyone has any doubts about that blender render, please count the time from the moment that button was pressed until that bench finished up. Compare results to other systems and do your own math.

 

[the54thvoid]

AMD Stocks are rising up to ~5% today! Glad I bought my shares cheap ^___^

Sell them before the review sites do their independent analysis. It'll be the best AMD CPU for a long time, no doubts but I think the people (evil speculators and shysters) who make the main play with stocks will not like it's performance.

 

[alucasa]

And if anyone has any doubts about that blender render, please count the time from the moment that button was pressed until that bench finished up. Compare results to other systems and do your own math.

As someone who uses Blender everyday, I can tell you that it's really easy to rig the rendering time. For a simple image like in the Youtube, 500 sample render will look identical to 5,000 sample render.

 

[evernessince]

Hmm, the Broadwell-e was clocked wayyy below it's normal clock speed, 3.0GHz versus what it's sold as, 3.7GHz. This tells me that Summit Ridge likely won't be clocked at a similar frequency to Broadwell-E, otherwise they would've shown that comparison, right? It's exciting, sure, but if it's not able to match the clock rate of Intel, I'm not exactly hyped...

We can't say for sure yet. I doubt AMD's current samples will be the final result. The last benchmark with Zen we saw was clocked at 2.8 Ghz so they obviously managed to increase the clock speed. Even without the same clock speed this would mean AMD is competitive again. All they need to do is release a successor to the quad core low end athlon and they win the biggest part of the market, the budget end. Intel's low end pentiums only have 2 cores and don't even have hyper-threading. An AMD quad-core of even remotely close IPC would make Intel's offerings look silly.

 

[rtwjunkie]

It's always never enough with you people. They go core to core thread to thread clock to clock, on a bench that is HIGLY reliant on all cores / threads. Outcome is that AMD finishes up that test FASTER then Intel's counterchip. I dont think they would be clocking down that intel chip by putting the bclk down, slower memory speeds and all but simply set for a 30x MP and not 37x.

Bottom point is is that AMD actually offers something with raw power that COMPETES with intel's 8c/16t CPU worth 1000$.

What you're ignoring, is that at their real speeds, running in the wild, the AMD will not be able to keep up unless (A) They can speed the clocks up, and (B) demonstrate its single core supremacy. By slowing down the Intel for the demonstration, they may be showing that the Intel is slower at completing instructions...at that speed. But real life speeds, which is where consumers will actually use them, and what consumers will judge on, the Broadwell will win because it is clocked higher, and people will buy accordingly.

Don't get me wrong, I want Zen to be great and succeed! Just don't read too much into this.

 

[Supercrit]

I really hope that will force i3 becoming quad cores or at least turbo enabled, with the whole line have less disabled features just because intel could with no competition.

 

[HD64G]

Couldn't care less about clock for clock comparison since they are 2 different architectures. Only metric that matters is performance per watt.

If we suppose linear performance to clocks for the Intel CPU in this comparison and we assume that this 8C/16T Zen is the one that is going to be sold as the 95W, with 140W for Intel's Zen is 20% better in Perf/W. Simple assumptions there. Future reviews will prove if this benchmark is accurate or not.

 

[Dimi]

I remember the AMD hype from back in the days of the FX processors.

I think i jumped from Intel to an AMD Athlon 64 4000 (San Diego) cpu while shortly after it got rendered useless compared to a cheaper intel core duo. I think i paid close to 400 euro for the AMD cpu while the i3 was like 120 ish.

I'm not falling for this hype again.

 

[cadaveca]

ROFL.

choo-choo! All aboard the hype train!

 

[the54thvoid]

ROFL.

choo-choo! All aboard the hype train!

What do you know about CPU's? /sarcasm.

 

[alexsubri]

ROFL.

choo-choo! All aboard the hype train!

That's right! You BETTER hop on that Zen train!

 

[cadaveca]

What do you know about CPU's? /sarcasm.

This is the sort of launch I can't miss. But I dunno... might be a bit late.

 

[OneMoar]

I think TPU should just refuse to cover anything AMD
I mean we are totally bias here right its not like we have been lied to time and time again or anything

 

[cadaveca]

I think TPU should just refuse to cover anything AMD
I mean we are totally bias here right its not like we have been lied to time and time again or anything

Meh. Put it in my hands and let me play with it, and I'll be honest. I wasn't one to buy into the hype in the past; you can find my posts denying it from the get go and even explaining why.

 

[Fx]

ROFL.

choo-choo! All aboard the hype train!

It isn't just hype that has some of us aboard the train. I am one of AMD's customers that continues to purchase their products to support them. Their processors have plenty of power needed for gaming. I use Xeons for my servers.

If Zen can improve its generational performance leap by 20-30% compared to the 40% it is claiming, I will be more than happy.

 

[cadaveca]

It isn't just hype that has some of us aboard the train. I am one of AMD's customers that continues to purchase their products to support them. Their processors have plenty of power needed for gaming. I use Xeons for my servers.

If Zen can improve its generational performance leap by 20-30% compared to the 40% it is claiming, I will be more than happy.

AMD does a great job of pricing their product accordingly for the most part, so they'll do well. But they are a tiny CPU company, so I just don't expect much. It just doesn't matter how fast Zen is; it'll be priced according to its true value anyway. Ultimately THAT is what matters.

 

[ensabrenoir]

 

[Frick]

Erm no, hate to tell you and about 10 000 other people on this forum will tell you just the same thing that AMD was cheaper on the 939 socket, the FX57 and 60 was around $1000-$1200 and the Pentium EE was around $1500 AUS, its just a fact

Anyone can post a pic like you did that is from god knows what source, and from even before launch date where in actual fact I never saw any CPU from AMD (price to performance comparison) be more then Intel.

Different continents. I am too quite sure that AMD was just as expensive as Intel when they were competitive. They often, iirc, offered a bit more punch for your money and often overclocked decently, but they weren't magical people giving stuff away if they could charge for it and get away with it, which they did.

Annywaay, real world test is nice. But I don't expect it to last if they perform different tests. Remember the goal was Haswell-ish performance, iirc.

 

[D007]

Lol and so the war of the fanboys ensues.. Like always.. Why can't people just be happy, that AMD may finally make a processor worth a shit? lol.
I'm happy for them.. I go with performance.. Idc about cost. If AMD can beat intel, I'll be looking at it. Anyone with sense would do the same thing.
But don't make huge assumptions based on half tests..

 

[dozenfury]

I'm excited and looking forward to Zen too. *However* AMD has also shown a strategy of embellishing in their marketing pretty extremely. Their problem is that real performance gains generally take big $ R&D, money which Intel has and AMD doesn't. It's far cheaper to market something as faster than to actually make a faster chip.

So I hope maybe AMD gets lucky and has a surprise performance breakthrough despite fighting an underdog battle without the huge R+D spend Intel has, because I would love to be able to go back to AMD and the competition is badly needed. But...I'll believe it when I see it, as in third-party real released product benchmarks. We've been hearing about your secret weapon Piledriver/Steamroller, etc. cpu for the past 10 years and have been let down every time, prove the doubters wrong this time AMD.

 

[slozomby]

I'm confused. so the zen chip at 3k outperforms an underclocked 6900k. I wonder if they turned off boostclock as well.