AMD FX-8150 Bulldozer finally tested

**gosh** · 10-09-2011, 04:10 AM

Originally Posted by Warwian

I'm still skeptical. If they didn't sign the NDA, where is this CPU coming from?

If they really had the CPU and it works properly, they would have done a much better test. For example, they need to throw in more CPU's.

**undone** · 10-09-2011, 04:22 AM

Originally Posted by Warwian

I'm still skeptical. If they didn't sign the NDA, where is this CPU coming from?

Originally Posted by gosh

If they really had the CPU and it works properly, they would have done a much better test. For example, they need to throw in more CPU's.

They might have some chips in hand but doesn't make any sense. While these guys never sign an NDA, it means they wouldn't be well-informed by official.

Originally Posted by Monstru

From what I know, MSRP for 8150 should be 245 USD.

Yes we have known that, from slides which were exposed half of a month ago.

**gosh** · 10-09-2011, 04:24 AM

Originally Posted by undone

They might have some chips in hand but doesn't make any sense. While these guys never sign an NDA, it means they wouldn't be well-informed by official.

Also I think that getting right hardare is like a two (or three) stage process. Just sending packets to different compaanies that does reviews, no way.

**undone** · 10-09-2011, 04:34 AM

Originally Posted by gosh

Also I think that getting right hardare is like a two (or three) stage process. Just sending packets to different compaanies that does reviews, no way.

And a chip being announce means it'll be wildly-available, I still suspect it'll be at mid-Oct, although some packages are confirmed, but still not enough, unless they show us tons of packages or amd decide to make a paper launch.

If something doesn't have enough amount to be mading a shipment, why would be benchmark out earlier?

**FischOderAal** · 10-09-2011, 04:49 AM

Originally Posted by gosh

If they really had the CPU and it works properly, they would have done a much better test. For example, they need to throw in more CPU's.

Nope. If you want to have hits you have to be the first. They did a rather quick instead of a thorough test to be the first one. There's nothing wrong with that.

For thorough reviews wait until the NDA is lifted. Some guys probably already have Bulldozer and make thorough reviews with a comparison to tother processors.

**bamtan2** · 10-09-2011, 04:57 AM

Originally Posted by gosh

How can anyone believe that this test is accurate?

because all the other benchmarks from all the other leaks also sucked? how much smoke must there be before people believe there is fire.

**gosh** · 10-09-2011, 05:06 AM

Originally Posted by bamtan2

because all the other benchmarks from all the other leaks also sucked? how much smoke must there be before people believe there is fire.

All? I haven't seen any trustworthy benchmark. What I have seen are some very strange benchmarks against just one other CPU, apps used that differ to normal reviews, some with strange settings.
Match that with a company that need to be very secretive because the contender has so much more money.

**JohnJohn** · 10-09-2011, 05:10 AM

Monstru: is this cpu representative of what is going to be in stores next week, or maybe because you got hold of an *unofficial* cpu you got an early stepping bugged/stupid cpu?

From OBR maybe

**xdan** · 10-09-2011, 05:26 AM

Originally Posted by gosh

If they really had the CPU and it works properly, they would have done a much better test. For example, they need to throw in more CPU's.

The title of the article is AMD FX-8150 Bulldozer Preview, it is not clear enough?
That's way are just medium number of tests, and only 2 cpu's anyway.
The larger review it will be posted on 12 as the others.
JohnJohn, the cpu's are already at the retailers if it is to be sold on 12, so more than sure is a retail.
And they didn't sad that they don't have the cpu from AMD, Monstru only sad that they didn't have a NDA accord with AMD.

because all the other benchmarks from all the other leaks also sucked? how much smoke must there be before people believe there is fire.

+1 quote of the day.

**Kuroimaho** · 10-09-2011, 05:28 AM

Final BIOS ?

I am a still bit skeptical, this looks too bad to be true. Is it called denial ? ^^;;;
After all these delays I did not expect much but this might not even show a clear lead over their last gen not to mention what Intel has to offer.

Thanks for enlightening us Monstru, I really appreciate giving us something to read until the 12th.

**gallag** · 10-09-2011, 05:29 AM

Originally Posted by gosh

All? I haven't seen any trustworthy benchmark. What I have seen are some very strange benchmarks against just one other CPU, apps used that differ to normal reviews, some with strange settings.
Match that with a company that need to be very secretive because the contender has so much more money.

Just out of intrest, as you are, well let's just say a big AMD fan, if these results are true what is your opinion?

**informal** · 10-09-2011, 05:34 AM

Originally Posted by Kuroimaho

Final BIOS ?

I am a still bit skeptical, this looks too bad to be true. Is it called denial ? ^^;;;
After all these delays I did not expect much but this might not even show a clear lead over their last gen not to mention what Intel has to offer.

To beat Thuban overall,it would need +20% magic dust bios update.Not going to happen I'm afraid. The sad part is that even in single thread SIMD code,the "very powerful 256bit FPU" is failing against K10's (128bit FP) core. Very surprising but true.

**gosh** · 10-09-2011, 05:37 AM

Originally Posted by gallag

Just out of intrest, as you are, well let's just say a big AMD fan, if these results are true what is your opinion?

(not a fan, have both intel and amd)
they are out of the gaming desktop area.

But it is easy to see that results isn't logical. Just check HAWX performance (not just strange to use a game like HAWX in a cpu test....), if they have a bulldozer then prefetching is off. Only 16KB L1 cache needs prefething on L2 to get good numbers
EDIT: I think that nehalem had some early benchemarks that had the same problem, it showed bad performance because if that

**tosunermc** · 10-09-2011, 05:38 AM

Yesterday I had a change to play FX-8150 I could not find what I excepted with FX , The max Cinebench speed was 4,55 Ghz with medium performance air cooler. The score I got from Cinebench was lower than same speed amd x6 processor.

**BababooeyHTJ** · 10-09-2011, 06:00 AM

Do a lot of people game on a $300 cpu at 1280×1024?

**-Boris-** · 10-09-2011, 06:09 AM

Originally Posted by BababooeyHTJ

Do a lot of people game on a $300 cpu at 1280×1024?

They aren't gaming, they are measuring differences between processors. So they try to make the GPU a non limiting factor. If you only looked at benches at 1980x1200 32bit all settings maxed then an Athlon II would look as good as an i7 in many tests.

**gosh** · 10-09-2011, 06:19 AM

If Lab501 is right then this is fake:

http://www.ozeros.com/2011/10/nuevos...e-el-i7-2600k/

I don't think AMD present fake numbers to customers, they may select apps that runs well on the product that is presented but they can't fake it

**Alex-Ro** · 10-09-2011, 06:29 AM

They are right guys,12 will be a sad day to remember i'm afraid...

**Iconyu** · 10-09-2011, 06:31 AM

Originally Posted by informal

To beat Thuban overall,it would need +20% magic dust bios update.Not going to happen I'm afraid. The sad part is that even in single thread SIMD code,the "very powerful 256bit FPU" is failing against K10's (128bit FP) core. Very surprising but true.

Originally Posted by Hans de Vries

Our friend who goes by the name dougsf30/terrace215/chipper/chipdesigner/tatertot/justaview/gloo...
and 100 more names has a history of driving people nuts (and maybe himself as well...)

To recapitulate this thread:

AMD Architects : IPC increases (Anand article commenting on the 2 ALUs an 16KB L1)

terrace215 post: IPC decreases, because of the 2 ALUs..
terrace215 post: IPC decreases, because of the 16KB caches
terrace215 post: IPC decreases, AMD presentation sheet no.X tells us so.
terrace215 post: IPC decreases, AMD presentation sheet no.Y confesses this.

JF-AMD posting: IPC increases!! instead of getting worse.

terrace215 post: IPC decreases, the marketing guy isn't talking about IPC
terrace215 post: IPC decreases, don't trust marketing guys.
terrace215 post: IPC decreases, Bulldozer is only optimized for server workloads.
terrace215 post: IPC decreases, AMD presentation sheet no.Y confesses this.

JF-AMD posting: IPC increases!!!! You are spreading FUD

terrace215 post: IPC decreases, AMD presentation sheet no.X tells us so.
terrace215 post: IPC decreases, The AMD architect says it decreases by 5%
terrace215 post: IPC decreases, because of the 2 ALUs..
terrace215 post: IPC decreases, AMD has given up improving IPC.

JF-AMD posting: IPC increases!!!!!!! How many times did I tell you!!!

forever{
terrace215 post: IPC decreases, because .....
terrace215 post: IPC decreases, says .... of AMD
terrace215 post: IPC decreases, according to AMD's presentation.
terrace215 post: IPC decreases, don't trust marketing guys.
terrace215 post: IPC decreases, because of the 2 ALUs..
terrace215 post: IPC decreases, the marketing guy isn't talking about IPC
terrace215 post: IPC decreases, because of the 16KB caches
terrace215 post: IPC decreases, AMD has given up improving IPC.
terrace215 post: IPC decreases, The AMD architect says it decreases by 5%
terrace215 post: IPC decreases, Bulldozer is only optimized for server workloads.
terrace215 post: IPC decreases, AMD presentation sheet no.X tells us so.
terrace215 post: IPC decreases, The more I post the more it decreases.
terrace215 post: IPC decreases, The more I post the more it decreases.
terrace215 post: IPC decreases, The more I post the more it decreases.
.....}
until (interrupt by Movieman)

Regards, Hans

I'm sure I just posted this a minute ago and it never made it on screen. Anyway, I'll just leave this here.

**FlanK3r** · 10-09-2011, 06:39 AM

Originally Posted by gosh

If Lab501 is right then this is fake:

http://www.ozeros.com/2011/10/nuevos...e-el-i7-2600k/

I don't think AMD present fake numbers to customers, they may select apps that runs well on the product that is presented but they can't fake it

but LAB501 dont test gaming performance! They tested in old 1280x1024! And this is the diference

**sholvaco** · 10-09-2011, 06:43 AM

Regarding benchmark scores being lower than Thuban's:

Could this come from current benchmarking programs not properly utilizing the floating point units, only issuing a single 128bit instruction per clock since there's only 1 FP scheduler per module (feeding two FMA execution units)?

In this case it would be a comparison between 4 zambezi vs 6 thuban cores.

**gosh** · 10-09-2011, 06:44 AM

Originally Posted by FlanK3r

but LAB501 dont test gaming performance! They tested in old 1280x1024! And this is the diference

They got 50% more fps on hawx for 2600K. That is way to much compared to the test on the slide even if they used a faster gpu and lower resolution.

**Kuroimaho** · 10-09-2011, 06:44 AM

Originally Posted by FlanK3r

but LAB501 dont test gaming performance! They tested in old 1280x1024! And this is the diference

You don't seem to get it. They tested it in 1280 to show a cpu bottlenecked situation, they did a cpu test. AMD slide shows they did a whole system test, probably high res game benches where gpu bottleneck would mask their cpu performance.

**FlanK3r** · 10-09-2011, 06:49 AM

Kuriimaho:yes, but who cares 1280x1024 in practice? Is the same as for Quadcores will be running superpi as main CPU benchmark

...Most gamers playing at 1680x1020 or higher resolutions, so if I have problem with games in higher resolution = problem. Example some strategy games etc are very hard with good CPUs and gaming resolutions.

**Maxforces** · 10-09-2011, 06:52 AM

even in high resolution you will see the same thing in places dependent on cpu
example all the tests depend on the cpu 1920x1200
http://nvision.pl/Intel-Core-i7-2600...details-5.html
must know how to distinguish a test from the gpu and cpu.
AMD shows GPU test.

Thread: AMD FX-8150 Bulldozer finally tested

Thread Tools

Search Thread

Rate This Thread

Display

Bookmarks

Bookmarks

Posting Permissions