Bulldozer Review! Legit?

[StrangerGuy]

I agree it gets eaten, but for most gamers min FPS means everything!

I guess you're not a gamer?

You can have a million fps for 99.99% of the time and still can get a 1 in minimum fps just because of that one errant microsecond of sudden fps drop.

 

[lOl_lol_lOl]

I looked at the prices of the 8150 again and found something interesting:

[CB 10 MT] - 22615/20615 = 1.097
[CB 11.5 MT] - 6.75/6.01 = 1.123
[3DM V CPU] - 22500/19119 = 1.177
[3DM V TOT] - 25500 /21949 = 1.162
[3DM 11 TOT] - 7385/6616 = 1.116
------------------------------------
Total diff in perf = 5.675/5 = 1.135
Perf acc to price = 1.135 x $283 = $321.20

Diff in price = Diff in perf = 1.135 = 13.5%

According to prices, the perf should be:
2600K = 113.5%
8150 = 100.0%
8120 = 83.75%
6100 = 71%
4100 = 42.76 - 66.78% depending on price

I hope this was a good first post .

 

[Gikaseixas]

I would suggest to wait for the official reviews

I would advise the same. Intel fanboy's don't be so quick to dismiss BD, we haven't seen a proper review yet. If it doens't live up to expectations then so be it, bad for future cpu prices and game over AMD... maybe

 

[Schmide]

You can have a million fps for 99.99% of the time and still can get a 1 in minimum fps just because of that one errant microsecond of sudden fps drop.

One possible extreme scenario. Regardless you don't notice the high frame rates, it's the drops that get ya killed.

 

[3DVagabond]

Not really a good review; not enough benchmarks.

But I'll say it again: FX-8120 will be ~10% faster than i5-2500K in multi-threaded, ~25-30% slower in single-threaded.

Reviews will be here in very little time, so you'll see.

Are you talking stock configured chips? Or, adjusted clock for clock?

 

[Arkaign]

I would advise the same. Intel fanboy's don't be so quick to dismiss BD, we haven't seen a proper review yet. If it doens't live up to expectations then so be it, bad for future cpu prices and game over AMD... maybe

Yeah I'm a fanboy of neither company, though I feel the best likely scenario is that some midrange BD chips can OC and become a much better value than locked chips like the 2-core 2100 and 4-core 2400. Really with Intel the glory begins with the 2500k, and $220ish is a lot for some people. If one can get a BD for $150ish and do an easy OC to hit roughly stock 2500k levels, I think that's a win.

I think people should be crazy to expect even the top BD to be able to match 2500k/2600k gaming scores when both are overclocked to common speeds (~4.5ghz is nearly a lock for decent air cooling and stock volts for the Ks, probably about the same or a shade more for the BD?).

The ultimate lesson has always been to wait for the pros like Anand to get the real story out though.

 

[Arkaign]

Are you talking stock configured chips? Or, adjusted clock for clock?

Given that both are likely to OC in the same neighborhood, it's likely that that range will be true both of stock vs. stock and OC vs. OC benches. This would mean that at least BD should be able to closely approximate stock 2500 or 2600k performance after OC in gaming, and be a decent choice for users that need tons of "cores". Who knows.

 

[grimpr]

Yeah I'm a fanboy of neither company, though I feel the best likely scenario is that some midrange BD chips can OC and become a much better value than locked chips like the 2-core 2100 and 4-core 2400. Really with Intel the glory begins with the 2500k, and $220ish is a lot for some people. If one can get a BD for $150ish and do an easy OC to hit roughly stock 2500k levels, I think that's a win.

I think people should be crazy to expect even the top BD to be able to match 2500k/2600k gaming scores when both are overclocked to common speeds (~4.5ghz is nearly a lock for decent air cooling and stock volts for the Ks, probably about the same or a shade more for the BD?).

The ultimate lesson has always been to wait for the pros like Anand to get the real story out though.

Review samples are running at 4.9ghz stable.

 

[Arkaign]

Review samples are running at 4.9ghz stable.

I might believe that, but at what voltage? If stock, then that's awesome and will help AMD a bit more. If it's raised by any real level (like getting close to 1.5v), then I'm a little more hesitant to get excited unless they prove to be reasonable at that speed in terms of heat/speed/stability. After all, SB can hit 4.8 and higher, but those kinds of volts/heat don't really make me count that type of OC as a legitimately recommended target like 4.5 is with stock volts and a $20 tower cooler.

 

[mosox]

However, the Intel CPU dispatcher does not only check which instruction set is supported by the CPU, it also checks the vendor ID string," Fog details, "If the vendor string says 'GenuineIntel' then it uses the optimal code path. If the CPU is not from Intel then, in most cases, it will run the slowest possible version of the code, even if the CPU is fully compatible with a better version

http://www.osnews.com/story/22683/In...from_Compiler_

However, Intel is definitely detecting 3DMark Vantage and changing the behavior of its drivers in order to improve performance, which would appear to be a direct contravention of Futuremark's guidelines.

http://techreport.com/articles.x/17732/2

AMD has for some time been a member of BAPCo, an industry organization that promotes, among other things, a benchmark known as SYSmark. In the past year or so AMD, with openness and transparency, has tried to explain why we believe this benchmark is misleading with respect to today’s commonplace applications − about a year ago I published a blog designed to explore this. If you work for a company that believes in transparency and integrity – and I do – then you have to take a stand and speak up when something is wrong.
BAPCo’s response to this blog was a threat to expel AMD from the consortium.
The heart of our complaint is this: the SYSmark benchmark is not only comprised of unrepresentative workloads (workloads that ignore the importance of heterogeneous computing and, frankly, favor our competitor’s designs), but it actually generates misleading results that can lead to very poor purchasing decisions, causing governments worldwide to historically overspend somewhere in the area of approximately $8B!

http://blogs.amd.com/nigel-dessau/2011/06/21/1006/

A new Intel C++ compiler version 12 has now been released as part of the new "Intel Parallel Composer 2011". The CPU dispatching methods are unchanged from version 11. Apparently, all that has come out of the legal battles over CPU dispatching is a notice on Intel's website that the compiler does not optimize equally for non-Intel microprocessors

The settlement with AMD requires that Intel shall not include any Artificial Performance Impairment in any Intel product. I cannot find any change in the new compiler version that reflects this requirement.
While the wording of the AMD settlement with regard to CPU dispatching is much more far-reaching than the FTC settlement, it has had no apparent effect so far, perhaps because it is subject to interpretation. Likewise, the FTC have not succeeded in making Intel change their compiler and libraries - maybe because they don't have the power to do so, or maybe because they don't have sufficient specialized knowledge to counter the technical arguments of Intel's experts.

http://www.agner.org/optimize/blog/read.php?i=49#127

 

[zlejedi]

I would advise the same. Intel fanboy's don't be so quick to dismiss BD, we haven't seen a proper review yet. If it doens't live up to expectations then so be it, bad for future cpu prices and game over AMD... maybe

Forum guide how to recornize fake benchmark:

If AMD performs badly it must be fake.



But It looks like I won't have any regrets from buying 2500K 2 weeks ago.

 

[psolord]

I agree it gets eaten, but for most gamers min FPS means everything!

I guess you're not a gamer?

I am a gamer since the Amstrad CPC 6128 and after all these years of gaming evolution, I have come to the conclusion that the min framerate means jack nothing.

The explanation is exactly this.....vv

You can have a million fps for 99.99% of the time and still can get a 1 in minimum fps just because of that one errant microsecond of sudden fps drop.

Min fps is a split second value that cannot possibly affect the whole gameplay experience. The same holds true for max framerate values. The average is what matters.

The best way to evaluate framerate, is to have an analytical result of what percentage of the total time was from 0-15fps, what percetange was from 15-30fps etc.

Obviously everything above 60fps is of little importance for real life gameplay, but the fact of the matter is, that large differences in cpu performance, even in low res benchmarks, do show the potential of the cpu. So when the time comes that a super heavy game comes along, that puts three times the workload on the cpu, compared to Unigine heaven, the cpu that was giving 180fps, will be able to give 60fps. The cpu that was giving 120fps, will give 40fps, which just plain sucks.

That being said, this Unigine score got me really disappointed. OK Unigine heaven barely features any multithreading, quite possibly much less than any game out there, but still the potential shown there is too bad.

P.S. Does BD support SSE5 as that shot shows?

 

[Gaz550]

Forum guide how to recornize fake benchmark:

If AMD performs badly it must be fake.



But It looks like I won't have any regrets from buying 2500K 2 weeks ago.

No no. Not even funny. Benchmarking is science. And all the rules that apply to scientific study apply here too.

So far the benches have hard time to fulfil even the basics.

 

[Arkadrel]

Given that both are likely to OC in the same neighborhood, it's likely that that range will be true both of stock vs. stock and OC vs. OC benches. This would mean that at least BD should be able to closely approximate stock 2500 or 2600k performance after OC in gaming, and be a decent choice for users that need tons of "cores". Who knows.

I think your right.

And:

Looks like it ll be faster than the 2500k atleast, in most apps, and faster than the Corei7 980x for gameing.

 

[3DVagabond]

Given that both are likely to OC in the same neighborhood, it's likely that that range will be true both of stock vs. stock and OC vs. OC benches. This would mean that at least BD should be able to closely approximate stock 2500 or 2600k performance after OC in gaming, and be a decent choice for users that need tons of "cores". Who knows.

If I understand correctly, BD w/turbo will run 4.1GHz stock single thread, SB 3.8GHz. So, is the estimate for both chips running the same speeds or at stock clocks where BD has a clock advantage?

 

[grimpr]

I might believe that, but at what voltage? If stock, then that's awesome and will help AMD a bit more. If it's raised by any real level (like getting close to 1.5v), then I'm a little more hesitant to get excited unless they prove to be reasonable at that speed in terms of heat/speed/stability. After all, SB can hit 4.8 and higher, but those kinds of volts/heat don't really make me count that type of OC as a legitimately recommended target like 4.5 is with stock volts and a $20 tower cooler.

Close to 1.450v, funky chip, i dont know, but i'm certain that 4.5ghz is a piece of cake in BD, just like in SB, with 4.8 to 5.0ghz doable on the majority of the retail chips. Couple that with great temps and we will see how it goes.

 

[Gikaseixas]

Forum guide how to recornize fake benchmark:

If AMD performs badly it must be fake.



But It looks like I won't have any regrets from buying 2500K 2 weeks ago.

what benchmarks??? Have they been officially launched? Congrats for the 2500K, great for you

 

[AtenRa]

I think your right.

And:

Looks like it ll be faster than the 2500k atleast, in most apps, and faster than the Corei7 980x for gameing.

Can you please give me the source of the slides ??

 

[Arkadrel]

Can you please give me the source of the slides ??

Found them in bulldozer thread, from semi accurate forums.
They probably found them somewhere else ect ect.

I just re posted them here.

 

[inf64]

One very interesting post from SA. We now have a new slide deck which is different from the one leaked earlier. Especially the slide covering FX vs i5 and i7.

Has anyone noticed that between this slide:

And this slide:

The 2600K and FX have been swapped around showing the same difference in numbers? The second slide makes more sense with the results being order of the key. Whoever made the first slides decided it would be a good idea to swap 2600K and FX performance...

Let's see what the latest slide shows us:
8 tests in total.
We can say that Zambezi FX wins hands down in at least 4 or even 5 of them (Handbrake is a win for FX but by a few percents;still a win).
It looses in one test(7 zip) by a small margin (few percents again).
It loses by a decent/big margin in 1 benchmark (wprime) and it loses by a smaller margin in also one benchmark which is Bibble (by 5 to 7% tops).
New slide deck shows us that in following benchmarks FX is NOW faster than 2600K,instead of being slower as depicted in earlier version: Winrar4.x264 pass2,pov ray,abbyy OCR. In wprime FX is NOW slower than 2600K and this is the only case where new slide deck shows FX being slower versus the old one.

All summed up:According to AMD's newest slide deck, FX XXXX @ XXGhz is overall somewhat faster than 2600K. This is not what all the leaked benchmarks are showing us though.

 

[Idontcare]

All summed up:According to AMD's newest slide deck, FX XXXX @ XXGhz is overall somewhat faster than 2600K. This is not what all the leaked benchmarks are showing us though.

The problem with slide-decks is they are always made from cherry-picking the absolute best-case results to maximize the marketing aspects behind the creation of the deck itself.

In other words sure they win 5 out of 8, but what that really tells you is they searched and searched and could not find a 6th case where it also beat out the 2600K.

So they show you the 5 out of 8 cases rather than the 5 out of 10, or 5 out of 11, or 5 out of 20 cases where now you begin to get a more realistic view of where the product is performing at as you add more applications into the test suite.

If they could have shown you 6 out of 8 then they would have.

 

[aphelion02]

The problem with slide-decks is they are always made from cherry-picking the absolute best-case results to maximize the marketing aspects behind the creation of the deck itself.

In other words sure they win 5 out of 8, but what that really tells you is they searched and searched and could not find a 6th case where it also beat out the 2600K.

So they show you the 5 out of 8 cases rather than the 5 out of 10, or 5 out of 11, or 5 out of 20 cases where now you begin to get a more realistic view of where the product is performing at as you add more applications into the test suite.

If they could have shown you 6 out of 8 then they would have.

You are a cruel and unkind character with a depressing personality.

 

[lOl_lol_lOl]

The problem with slide-decks is they are always made from cherry-picking the absolute best-case results to maximize the marketing aspects behind the creation of the deck itself.

In other words sure they win 5 out of 8, but what that really tells you is they searched and searched and could not find a 6th case where it also beat out the 2600K.

So they show you the 5 out of 8 cases rather than the 5 out of 10, or 5 out of 11, or 5 out of 20 cases where now you begin to get a more realistic view of where the product is performing at as you add more applications into the test suite.

If they could have shown you 6 out of 8 then they would have.

...not to mention the testing methodology is entirely dependent on the credibility of AMD...

 

[LOL_Wut_Axel]

Are you talking stock configured chips? Or, adjusted clock for clock?

Stock.

 

[lOl_lol_lOl]

The slides present the same benchmarks with the main difference being the reversal of results b/w 2600k and 8150..and the same graphics...Could one of the attendees have the nerve to produce false results like that? What kind of people do AMD accept at such presentations?