• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

"Steamroller" could crush "Haswell"?!

Page 3 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.
Status
Not open for further replies.
Sheep221 said:
Dude seriously read what you just wrote.
For first if FX 8350 has 220W TDP it means it has 220W TDP! Nothing else, TDP= max power draw on stock settings
The i5-3570k has 74W TDP which also means 74 not 180! Even if you would OC on nitrogen it still would not draw 180W there are not even boards for that.
This is not leasure center class where you can spread these false claims and your numbers are completely unreal.
Click to expand...

I'm not going to ask...
 
I very doubt it's going to match Haswell clock for clock. Even though it would've been kind of going against HSA and GPGPU, going with a split 512 bit FPU for each module would've instantly given it equal capabilities to quad Haswell in raw GFLOPS which is significant.
 
Intel17 said:
What makes you think that Steamroller will end up being faster than the i7?
Click to expand...

Multi threaded scenarios only, mainly as Piledriver trades blows with Ivybridge i7's in a few multitask related benchmarks. Haswell only brought small improvements over Ivybridge so it should be fairly easy for Steamroller to beat in certain benchmarks.
 
chernobog said:
TDP does not mean power consumption... Please look at this link:
http://www.bit-tech.net/hardware/2012/11/06/amd-fx-8350-review/7

i5 3570k on mini-atx motherboard consumes 160 watts while on a regular ATX motherboard it would consume 180 watts thus you fail my friend.
Click to expand...
That's system power at the wall. The difference between idle and load, and adjusted for PSU efficiency shows that as usual, Intel TDP is 25-25% higher than actual sustained power consumption for their high end parts.
 
If a certain member starting with G - stops activity posting wise.. well just saying.


@Chernobog:

Dear dis-illusioned AMD fan (because you are one, in my humble oppinion).

Remember Bulldozer?

Remember how estimating from internal slides went?

Remember how listening to a direct employee from within the Marketing Arm of AMD went?

What makes you think on a worse process too - that AMD can somehow increase ST\MT 20% on constrained budgets - after laying off a SIZEABLE chunk of they're talent.

Can somehow turn it around - on a uARCH that's been described as well nearly as bad as Netburst - within 2 small years?


Do you think this is "logicly fallable" within your own personal judgement?

Do you think it's probable given the scenario AMD is in?



If yes - please stop posting any pro AMD thread again - and wait til SR is released.
(especially the FX as you claim) - and then watch and enjoy rubbing it in all the "pro" intel people here.

Why would you (after twice in a row failing with uArch's upon released performance results vs pre-marketing slides) - not atleast say "Hey... it looks pretty good - but lets wait til we get actual results!" ?

Why?
 
I hope AMD crushes Nvidia/Intel. Nvidia/Intel need to be put back in line, theyre locking EVERYTHING down because they have a monopoly.
 
chernobog said:
Steamroller is 15 to 20% faster per core, Steamroller removes the bottleneck/penalty involving multi-threaded performance thus it more performance efficient in multi-threading.

IF Piledriver was to have the same fix as Steamroller involving multi-threading then per core it would be the same but in multi-threaded it would be 20% faster than current Piledriver.

Example:
Piledriver at 5ghz would have same single threaded performance as Steamroller, but in multi-threaded it would be 20% slower than Steamroller because it has the bottleneck/penalty compared to Steamroller that has none.

Bulldozer/Piledriver have a bottleneck, Steamroller has no bottleneck involving multi-threaded performance.
Click to expand...

This is all pure speculation. I would suggest not confusing predictions/assumptions with facts.
 
MisterMac said:
If a certain member starting with G - stops activity posting wise.. well just saying.


@Chernobog:

Dear dis-illusioned AMD fan (because you are one, in my humble oppinion).
(sadly for you I am neither, I am right now on netbook powered by Atom)

Remember Bulldozer?
(yes, it was a utter fail since it was rushed and partially done on a machine)

Remember how estimating from internal slides went?
(the old slides full of hope but the execution was a different story)

Remember how listening to a direct employee from within the Marketing Arm of AMD went?
(the old crew is gone, deal with it. It won't happen again)

What makes you think on a worse process too - that AMD can somehow increase ST\MT 20% on constrained budgets - after laying off a SIZEABLE chunk of they're talent. (yes they did, but in the end some most talented engineers that worked for Apple are now in AMD)

Can somehow turn it around - on a uARCH that's been described as well nearly as bad as Netburst - within 2 small years?(Bulldozer=/=Netburst, AMD old talents that worked on Athlon are now working on Steamroller)

Do you think this is "logicly fallable" within your own personal judgement?
(it depends from person to person, some will agree other will not)

Do you think it's probable given the scenario AMD is in?
(yes since AMD is recovering, look at Jaguar microarchitecture)



If yes - please stop posting any pro AMD thread again - and wait til SR is released. (because it puts a good light on SR and AMD it does not mean its pro-AMD compared to many pro-Intel threads)

(especially the FX as you claim) - and then watch and enjoy rubbing it in all the "pro" intel people here. (if they can make a 4 core steamroller APU then they can make an 8 core Steamroller FX, simple)

Why would you (after twice in a row failing with uArch's upon released performance results vs pre-marketing slides) - not atleast say "Hey... it looks pretty good - but lets wait til we get actual results!" ? (I wrote many times before but nobody reads, why bother explaining?)

Why?(you and your fellow bashers can't understand that this is collection of available data/information's thus it only shows what is known, not what will happen or how it will execute)
Click to expand...

I can't comprehend how you all can't understand that the old guard that screwed AMD is gone, if you can't understand what I am saying then you must be all braindead or have a extremely right winged mind...

@boxleitnerb

This whole thread is a speculation and you all take it seriously, what the hell is wrong with you people?

Knock off the insults.
Markfw900
Ananctech Moderator.
 
Last edited by a moderator:
Intel17 said:
Ivy Bridge-E will make short work of anything AMD could put out in the Enthusiast space.
Click to expand...

Maybe, but at what price? I'd rather not spend a grand on a mobo/CPU combo if I don't have to. If Steamroller ends up besting the 4770K, that might be enough for some people, since it's almost a given it won't cost even close to as much as Ivy-E.
 
boxleitnerb said:
1. Watch your tone!
2. If you want to speculate, then formulate your posts accordingly. What Steamroller "is" or "isn't" we don't know (yet).
Click to expand...

2. was already done, why watch my tone since with all responses from most members of this forum is acting just like that.
 
Last edited:
Then what's the beep point - if your going to speculate based on craptastic sources.

Your just creating a thread - that will attract tons of criticism because

A. You yourself know - it's unreleastic based on EVERY historic DATA point in the HISTORY of AMD.

B. The speculation loosely based on GOALS from AMD - MARKETING rather than specific first tape out tests as an example.

(AND it's from the SUPPOSED old "CRAP MARKETING" people - that aren't there anymore even. Hypocrisy much?)

Just grow up - and be better than the supposed Intel shills - you dislike.
 
MisterMac said:
Then what's the beep point - if your going to speculate based on craptastic sources. (you again fail)

Your just creating a thread - that will attract tons of criticism because

A. You yourself know - it's unreleastic based on EVERY historic DATA point in the HISTORY of AMD. (It is not unrealistic as you want to believe)

B. The speculation loosely based on GOALS from AMD - MARKETING rather than specific first tape out tests as an example. (Remember what Intel promised and they utterly failed, AMD is not even close to them)

(AND it's from the SUPPOSED old "CRAP MARKETING" people - that aren't there anymore even. Hypocrisy much?) (you are the hypocrite, oh the irony)

Just grow up - and be better than the supposed Intel shills - you dislike. (look who's talking, I am better. You believe that I am something that I am not, control your freaking imagination and get down on earth, fool)
Click to expand...

If you want keep failing then go ahead, don't drag me.
 
Just so you guys know...

Kyoto is the base number for performance numbers. The Berlin APU is 2x the performance of the Kyoto APU. Seattle is 2x the performance of the Kyoto APU, with the octo-core form. While, the Sedec-core form of Seattle is 4x the performance of the Kyoto APU.

http://www.anandtech.com/show/6974/amd-kabini-review/3
http://www.sweclockers.com/nyhet/16597-amd-temash-specifikationer-och-prestanda
It is safe to say Kyoto @ ~2 GHz would score around ~2 pts in Cinebench R11.5. To back this up Temash @ 1 GHz, scores ~1 pts/@ 1.4 GHz, scores ~1.4 pts. Kabini @ 1.5 GHz, scores ~1.5 pts.

Since, Jaguar and ARM cores don't have parts above 2.4 GHz, it is safe to guess that the performance is clock to clock.

In short, if all architectures could run Cinebench R11.5, multithreaded:
Kyoto 4C @ ~2 GHz = ~2 pts
Berlin 4C @ ~2 GHz = ~4 pts
Seattle 8C @ ~2 GHz = ~4 pts
Seattle 16C @ ~2 GHz = ~8 pts
 
Last edited:
Pandamonia said:
If AMD had any chance of beating haswell then AMD would be telling everyone about it.
Click to expand...

That's not a smart move, Kaveri and Steamroller FX are months away also you really don't want the competition to know what you have.

Secrecy is important.

@NostaSeronx

By your calculations, an 8 core Steamroller at 4Ghz should score 16 points...? o.0
 
Last edited:
chernobog said:
I can't comprehend how you all can't understand that the old guard that screwed AMD is gone, if you can't understand what I am saying then you must be all braindead or have a extremely right winged mind...

@boxleitnerb

This whole thread is a speculation and you all take it seriously, what the hell is wrong with you people?
Click to expand...
You are obvious troll, you act rude and can't speak with others accordingly.

I have verified that FX-8350 has 125W TDP instead of 220, but what I said is still valid. TDP is not power draw 1:1 but it is very similar, the higher the TDP the higher the power draw. The 220W is only possible on heavily overclocked FX, while overclocked 3570K won't ever draw 180, that's just ridiculous.
 
chernobog said:
By your calculations, an 8 core Steamroller at 4Ghz should score 16 points...? o.0
Click to expand...
That part would also have a ~300 watt TDP. I'm guessing around 320 to 360 watts, if you did calculations from the volt required with the amps provided.
 
Last edited:
chernobog said:
TDP does not mean power consumption... Please look at this link:
http://www.bit-tech.net/hardware/2012/11/06/amd-fx-8350-review/7

i5 3570k on mini-atx motherboard consumes 160 watts while on a regular ATX motherboard it would consume 180 watts thus you fail my friend.

FX 8350 has a TDP of 125 watts not 220 as you want to believe, fanboy.
Click to expand...

The current AMD cpus consume more power than their stated specs.
But AMD doesn't release full specs for piledriver/bulldozer so power consumption can't be ascertained. That is why MSI hamhandedly throttles down AMD cpus for some motherboards.

Here is the thread showing piledriver sucking in 200W at stock settings.
http://forums.anandtech.com/showthread.php?t=2289809

Some speculated that this is happening because AMD is close to the edge and is selling anything that closely resembles a product.
 
MisterMac said:
Then what's the beep point - if your going to speculate based on craptastic sources.

Your just creating a thread - that will attract tons of criticism because

A. You yourself know - it's unreleastic based on EVERY historic DATA point in the HISTORY of AMD.

B. The speculation loosely based on GOALS from AMD - MARKETING rather than specific first tape out tests as an example.

(AND it's from the SUPPOSED old "CRAP MARKETING" people - that aren't there anymore even. Hypocrisy much?)

Just grow up - and be better than the supposed Intel shills - you dislike.
Click to expand...

Maybe he wants to make it into your sig. 😉
 
This whole thread should really be closed. I see nothing but bickering and trolling over 'imaginary' numbers.

I read the whole thing and i actually feel dumber for even doing so. 🙂
 
Intel has set the bar SO LOW for 2 generations that its surprising AMD cannot catch up.. its almost as if Intel is purposefully slowing down IPC gains for some odd reason.
 
chernobog said:
Moderators, can you delete response 16 and 17, why? Offtopic.

Thank you, and delete this response also. I want a clean thread.

I understand sarcasm but I don't know if Galego is an member or its a thing, something other.
Click to expand...

OMG, I swear I work with you
 
Status
Not open for further replies.

TRENDING THREADS

Back
Top