[OBR] AMD FX-8300/6300 family-Piledrive or Not - Page 4

Originally Posted by Fuell 

Even if you were to take this
Clock speed increase from 3.6 to 4.0 while lowering rated TDP from 124 to 94.

Originally Posted by Demonkev666 

the ES shown here is 95 watts and 3.3ghz 4.2ghz Turbo.

Originally Posted by Homeles 

No, it definitely isn't. Performance in different applications can vary wildly based on a variety of factors, such as how frequently a cache miss occurs. Cache misses in particular are what I'm getting at — if code executed with very few relative misses, the branch prediction improvements of Piledriver wouldn't translate to much performance improvement.
There are perhaps hundreds of factors that play into how well a CPU performs in one cycle — Piledriver only improves a handful of them. If the bottleneck lies in a region where Piledriver didn't improve over Bulldozer, say the L1 and L2 cache latencies, then you're not going to see a noteworthy performance improvement.
Also, it turns out that my memory has failed me — Trinity was more than 15% faster clock for clock in two applications in the THG review, not one. Still, Piledriver is definitely not a flat 15% improvement over Bulldozer per clock. There's also the potential that the cores used in Trinity may not be the same ones showing up in Vishera.
It's just him, generally. The rest of the AMD shills generally keep their circlejerk to themselves down in the CPU section.

Originally Posted by Warrax22 

Take a look at the screenshot again, the "piledriver" on the screenshot is a 6 cores, hence the 94w.
Also where did you get the 3.3ghz base with 4.2ghz turbo?

Originally Posted by Warrax22 

Take a look at the screenshot again, the "piledriver" on the screenshot is a 6 cores, hence the 94w.

Originally Posted by 2010rig 

Why do people hate OBR so much? Is it because he releases info you are not prepared to handle?

I get that he puts out shady stuff also, and laughed at Bulldozer, but if you go back and compare his Bulldozer "leaks" vs Bulldozer's real performance, he was putting out real numbers most of the time.
I remember some AMD fans worshipped JF-AMD, and talked smack about OBR, and in the end, we all know how that turned out.

Originally Posted by Mr Frosty 

JF-AMD.... I remember him....what ever happened as I wasn't around back then? Did he get banned?

Originally Posted by JF AMD 
So here's the story on IPC from my perspective.

The original design goal was higher IPC. Back before we had taped out the first processors the discussion came up. I am not allowed to say anything in public that hasn't been vetted past engineering. I specifically asked the engineering team about IPC and they replied that they expected higher IPC and I was cleared on that statement.

In my estimation, I made the IPC stament on XS and I don't recall making it other places (but I am sure that my comments were reposted.)

This is not a case of me lying, this is a case of me being wrong. And that happens to all of us. There is no way that I would intentionally say something that I did not believe to be true because a.) the interenet is a permanent record and b.) eventually you'll have to answer to those comments.

In these different forums that I would frequent, I have made thousands of posts about the product, always trying to help people understand the technology. Everything was done with the intention of being informative. I never made client performance predictions and was very clear on correcting people who took server benchmarks and tried to correlate client performance, because it just doesn't work like that.

Since the launch I haven't really been in any forums because I was in Seattle all week with MSFT. Once the product launched, I started receiving lots of hate mail. If I had a dollar for every message that used the word f*** I would have enough money to buy myself a bulldozer server.

Early on there were a lot of people that said I was crazy for trying to talk to the enthusiast community, but I persisted, the occasional idiot is something that everyone has to put up with from time to time. But the volume of hate messages that I received has unfortunately convinced me that I was wrong.

I was doing this on my own time, it was not part of my job. And because of that, I don't really feel compelled to take any more abuse.

All of the statements that I have made at the time were statements that I believed to be true. I am no more a liar than Paul Otellini when he said IB would ship in Q4. He is not a liar, he is giving the best information he has at the time and things change. If you are going to extend courtesy to others when their statements don't pan out, you should do that with everyone.

Thanks to exarkun and some of the others that have had a reasonable response in all of this. Too many people were waiting to attack, it's almost like they don't really care, maybe they just like to fight.
__________________

Originally Posted by Demonkev666 


I'm pretty sure the author of cpu-z can get a chip earlier then most of us to get he raw values.
The program reads raw registry data in the cpu anyways

Originally Posted by Schmuckley 


ORLY? Best cpu line AMD has produced to date was just a "stepping stone"? To date..They have not produced a cpu with better performance than Thuban.
I'll gain faith in AMD when they produce something that outdoes Thuban.It may happen.

Originally Posted by Homeles 


No, it definitely isn't. Performance in different applications can vary wildly based on a variety of factors, such as how frequently a cache miss occurs. Cache misses in particular are what I'm getting at — if code executed with very few relative misses, the branch prediction improvements of Piledriver wouldn't translate to much performance improvement.

There are perhaps hundreds of factors that play into how well a CPU performs in one cycle — Piledriver only improves a handful of them. If the bottleneck lies in a region where Piledriver didn't improve over Bulldozer, say the L1 and L2 cache latencies, then you're not going to see a noteworthy performance improvement.

Also, it turns out that my memory has failed me — Trinity was more than 15% faster clock for clock in two applications in the THG review, not one. Still, Piledriver is definitely not a flat 15% improvement over Bulldozer per clock. There's also the potential that the cores used in Trinity may not be the same ones showing up in Vishera.

Originally Posted by Homeles 


Yeah. If we assume that alleged picture of Vishera is legitimate, then it's quite clear that not all of the changes that went into Trintiy are going into Vishera (and vice versa). In particular, there's the SRAM issue that I think I've pointed out to your before. If I had to guess, that would mean Vishera doesn't feature the larger L1 TLB mentioned here: http://images.anandtech.com/doci/5831/Screen%20Shot%202012-05-14%20at%2010.38.42%20PM.png

Complete speculation on my part, though. That's also if we're giving OBR any credit, which I'd rather not do.

Originally Posted by 2010rig 

Why do people hate OBR so much? Is it because he releases info you are not prepared to handle?

I get that he puts out shady stuff also, and laughed at Bulldozer, but if you go back and compare his Bulldozer "leaks" vs Bulldozer's real performance, he was putting out real numbers most of the time.

I remember some AMD fans worshipped JF-AMD, and talked smack about OBR, and in the end, we all know how that turned out.

Originally Posted by Brutuz 

Get real, Bulldozer overclocks much higher than Thuban and matches it, Thuban had the same IPC as Deneb and I can guarantee my quad core FX and quad core PhIIs are all within the margin of error to each other.