AMD FX-8150 Bulldozer finally tested

Printable View

Show 100 post(s) from this thread on one page

10-09-2011, 12:26 PM
Brice MJ

http://img69.imageshack.us/img69/1236/bd2007.png

Yeah, right...
10-09-2011, 12:27 PM
PerryR

Yeah, fastest back in 2008.
10-09-2011, 12:28 PM
Brice MJ

Quote:

Originally Posted by PerryR

Yeah, fastest back in 2008.

We had Nehalem back in 2008.
10-09-2011, 12:29 PM
Cecil

Quote:

Originally Posted by BeepBeep2

The problem is, they would have been much more competitive with Sandy Bridge if they had shrunk X6 (I'm not sure why guys keep saying "add two cores!"), added 4-6MB between L2 and L3 caches, and sped stock speeds up to 3.6-4.0 single thread. I'm fairly certain that is doable within a 95-125w TDP on 32nm, and they should have been able to figure out some way to gain clockspeed...intel has had no problems with it, and AMD did it well from transition to 65nm to 45.

X6's that would OC on water 4.6-4.7 Ghz on 32nm +3% IPC boost from extra cache or adopted Llano's STARS core + L3, would have gained ~5-10% IPC over current gen and would have been a lot better than this.

Thats definitly what they should have done, to get them selves in a better situation for right now. They could have saved BD a little longer to work on it more.

But, its AMD, and they didnt. They want to try to change the game too much when they need to focus on playing it better.
10-09-2011, 12:31 PM
PerryR

Quote:

Originally Posted by Brice MJ

We had Nehalem back in 2008.

This beats that......Barely. At least the original models, and non-enhanced editions.
10-09-2011, 12:32 PM
Cecil

Quote:

Originally Posted by PerryR

This beats that......Barely. At least the original models, and non-enhanced editions.

Uh, 920 is faster then Deneb/Thuban, this is slower then Deneb and Thuban.
10-09-2011, 12:33 PM
Brice MJ

Quote:

Originally Posted by PerryR

This beats that......Barely. At least the original models, and non-enhanced editions.

FX8150 can barely come close to Phenom II X6 1100T in low-threaded apps, so no, comparing it to 2008's Core i7 965 3.2GHz is not even funny.
10-09-2011, 12:40 PM
radaja

Quote:

Originally Posted by Cecil

Thats definitly what they should have done, to get them selves in a better situation for right now. They could have saved BD a little longer to work on it more.

But, its AMD, and they didnt. They want to try to change the game too much when they need to focus on playing it better.

yep,i think they just got sideswiped doing the new uarch and unmature node shrink simultaneously(very risky).and now we are seeing the salvaged product(the best AMD could make of the situation)
hopefully we will see Big improvements upcoming with this new uarch:D
10-09-2011, 12:40 PM
Hornet331

Seems another guy snaged a 8120:
http://forums.anandtech.com/showpost...&postcount=192

Is currently putting the rig together.
10-09-2011, 12:50 PM
BeepBeep2

Quote:

Originally Posted by Cecil

Uh, 920 is faster then Deneb/Thuban, this is slower then Deneb and Thuban.

And an X6 @ 3.6 with 6-7% IPC increase average from extra L2,L3 + Llano's "STARS" core in 95/125ww TDP envelope would beat Nelahem in single thread and smash it in multithread workloads...

I'm pretty sure that would have made a lot of us more than happy enough.
10-09-2011, 12:50 PM
PerryR

Quote:

Originally Posted by Cecil

Uh, 920 is faster then Deneb/Thuban, this is slower then Deneb and Thuban.

I thought 1090t was essentially even with 920?

http://www.anandtech.com/bench/Product/146?vs=47

Also, I thought the 8150 was marginally faster than the 1090t?

Quote:

Originally Posted by Brice MJ

FX8150 can barely come close to Phenom II X6 1100T in low-threaded apps, so no, comparing it to 2008's Core i7 965 3.2GHz is not even funny.

A 965 is an extreme edition processor, which I said it doesn't beat. I think you mean the 940?
10-09-2011, 12:52 PM
Oliverda

Quote:

Originally Posted by xdan

Anyway for AMD it's clear now that they should have done a new socket from 0.
May be to fit and work better with BD arhitecture.

http://prohardver.hu/dl/upc/2011-06/...ce-palm_av.jpg
10-09-2011, 01:08 PM
AliG

Quote:

Originally Posted by BeepBeep2

And an X6 @ 3.6 with 6-7% IPC increase average from extra L2,L3 + Llano's "STARS" core in 95/125ww TDP envelope would beat Nelahem in single thread and smash it in multithread workloads...

I'm pretty sure that would have made a lot of us more than happy enough.

See that's what makes me question these results a bit. If anything, isn't BD an augmented version of Llano? So shouldn't at the very least the multithreaded performance be drastically better due to CMT?
10-09-2011, 01:09 PM
ice_chill

On the other hand, lets be greatfull we still have someone who competes with Intel.
10-09-2011, 01:11 PM
AliG

Quote:

Originally Posted by ice_chill

On the other hand, lets be greatfull we still have someone who competes with Intel.

Perhaps, but I personally find that to be a losing attitude. As the consumer we should never settle for what the industry hands us, that's the whole point of supply and demand
10-09-2011, 01:12 PM
PerryR

Where's JF?
10-09-2011, 01:17 PM
xBanzai89

Quote:

Originally Posted by PerryR

Where's JF?

Likely responding to all the emails he is getting about this or went on a vacation where there is no internet till the 12th.
10-09-2011, 01:18 PM
radaja

Quote:

Originally Posted by PerryR

Where's JF?

this is what he said yesterday at ocn

Quote:

Originally Posted by JF-AMD

A. I could never comment on that.

B. ESPECIALLY during quiet period.

so im sure he wont comment on this due to quiet period
10-09-2011, 01:20 PM
Iconyu

Quote:

Originally Posted by PerryR

Where's JF?

If these numbers are true, I think he's getting drunk.
10-09-2011, 01:24 PM
celerity

Quote:

Originally Posted by gosh

If Lab501 is right then this is fake:
http://img.ozeros.com/noticias/2011/...150_slide4.jpg
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

Hold on... there is something really weird with the graphs:

(1) http://img.ozeros.com/noticias/2011/...500K_2600K.jpg

(2) http://img.ozeros.com/noticias/2011/...150_slide3.jpg

In the first Bulldozer is ~20% faster than 2600K in wPrime 32M. However, in the second it's 20% slower than 2600K. Same for other graphs, e.g. in the first 2600K is faster @ Winrar 4, second shows Bulldozer being faster. How come? :confused:
10-09-2011, 01:24 PM
PerryR

I just realized that slide from 2007 said fastest cpu core in "history!" I thought it said mainstream cpu core.

LOL. What was AMD smoking back then?
10-09-2011, 01:30 PM
Cecil

Quote:

Originally Posted by PerryR

I thought 1090t was essentially even with 920?

http://www.anandtech.com/bench/Product/146?vs=47

Also, I thought the 8150 was marginally faster than the 1090t?

A 965 is an extreme edition processor, which I said it doesn't beat. I think you mean the 940?

A 920 is faster then a Thuban in ST apps, Thuban catches up in really MT stuff. But thats at stock clocks with the 920 at 2.6 and the Thuabn at 3.2. With both at 4Ghz the 920 is much faster. Also, most 920s will continue on to clock higher.
10-09-2011, 01:30 PM
AffenJack

Quote:

Originally Posted by PerryR

Where's JF?

Look at AliG's Signature and at the Benches so far, looks like he might have a lot to do tellin customers where BDs IPC increase went.

Was the donaminhaber video test already here?
http://www.donanimhaber.com/islemci/...o-inceleme.htm
10-09-2011, 01:37 PM
PerryR

Quote:

Originally Posted by Cecil

A 920 is faster then a Thuban in ST apps, Thuban catches up in really MT stuff. But thats at stock clocks with the 920 at 2.6 and the Thuabn at 3.2. With both at 4Ghz the 920 is much faster. Also, most 920s will continue on to clock higher.

I was mostly referencing to stock clocks, I already knew that the 920 will win in most apps when over clocked.
10-09-2011, 01:41 PM
Hornet331

Quote:

Originally Posted by AffenJack

Look at AliG's Signature and at the Benches so far, looks like he might have a lot to do tellin customers where BDs IPC increase went.

Was the donaminhaber video test already here?
http://www.donanimhaber.com/islemci/...o-inceleme.htm

Haven't seen it... but the graphs in the vid basically show the same thing again... 8150 slower then X6 or barly beating it... (gona make a few screen caps)
10-09-2011, 01:42 PM
BeepBeep2

Quote:

Originally Posted by Cecil

A 920 is faster then a Thuban in ST apps, Thuban catches up in really MT stuff. But thats at stock clocks with the 920 at 2.6 and the Thuabn at 3.2. With both at 4Ghz the 920 is much faster. Also, most 920s will continue on to clock higher.

Correction:
With both at 4 Ghz, the 920 is much faster in ST. In MT, Thuban is still very competitive, trailing slightly in some apps.
10-09-2011, 01:59 PM
Baam

Why don't AMD just call it a quad-core with AMD's version of HT. Then it wouldn't look so bad. bad but not like it looks as a so called 8 core.
10-09-2011, 02:00 PM
Tha Last Meal

so Finally We can say the Bulldozer is A big fail ?
10-09-2011, 02:05 PM
Chickenfeed

For the sake of objectivity, I wouldn't make any such claims until the 12th.
10-09-2011, 02:11 PM
PerryR

http://www.justin.tv/bassbench#/w/1883595104
10-09-2011, 02:19 PM
PerryR

This is actually better:

https://join.me/743-658-418
10-09-2011, 02:24 PM
Dainas

Quote:

Originally Posted by ryan92084

i take everything with a big ol' grain of salt until proper nda lifted reviews.

Amen, although the review seems more legit than most early early ones... it wouldn't be the first time for a relaunch review with completely flubbed results that were massively skewed against or for the product.

Only reason I'm not screaming right now is I do not get the vibe the reviewer is out to get AMD, at the same time I want an actual consensus from multiple reviews with far more benchmarks.
10-09-2011, 02:25 PM
Iconyu

Quote:

Originally Posted by jimbo75

If AMD are calling people tomorrow they are probably trying to ensure this low-res gaming skullduggery isn't happening, which imo is their right as they are simply ensuring that the gaming benchmarks are representative of the cpu's while gaming. Also, if BD is strong in minimum framerates then AMD would want that message to be getting across, which is also well within their rights.

Any site using low res gaming benchmarks has an axe to grind with AMD, or an intel shill. Why do you think the unnamed blogger benchmarked Unigine at low res to "prove" his point? I've never seen anyone else do that, like ever. But even at that BD was massively better in minimum framerates.

I actually think that's a difference in PCI-E controller rather than CPU performance. When AMD bought ATI they also gained their chipset guys, while Intel have been eroding into their chipsets to place more on the CPU. So I would certainly place more faith in chipset performance causing these strange results at higher resolutions over CPU performance. It doesn't make much sense otherwise, if the CPU has proven superior in almost every way under artificially high loads that real world high loads shouldn't cause such drops unless there is a factor everyone is ignoring.

Right now I'd say AMD is definitely running a stronger PCI-E controller, it's the only logical thing I can think of, as AMD's memory controller is obviously weaker than Intel's right now.
10-09-2011, 02:29 PM
Hornet331

As promised the screen caps:

3Dmark:
http://img210.imageshack.us/img210/7...ark2001.th.jpg http://img687.imageshack.us/img687/8...ark2006.th.jpg http://img219.imageshack.us/img219/5...2006cpu.th.jpg http://img143.imageshack.us/img143/5...extreme.th.jpg http://img196.imageshack.us/img196/7...011phys.th.jpg

CinebenchR11.5:
http://img714.imageshack.us/img714/1...nchr115.th.jpg

Aida:
http://img195.imageshack.us/img195/4...iafpuv8.th.jpg http://img641.imageshack.us/img641/4...acpuase.th.jpg http://img855.imageshack.us/img855/8...fpujuia.th.jpg http://img249.imageshack.us/img249/5...umendel.th.jpg http://img684.imageshack.us/img684/3...injulia.th.jpg

SPI:
http://img844.imageshack.us/img844/9779/dnispi.th.jpg

Other Benches:
http://img543.imageshack.us/img543/3...umark99.th.jpg http://img846.imageshack.us/img846/3835/dnifritz.th.jpg http://img23.imageshack.us/img23/9290/dnipcmark7.th.jpg http://img805.imageshack.us/img805/2...iwinrar.th.jpg

Games:
http://img851.imageshack.us/img851/7...naa1050.th.jpg http://img844.imageshack.us/img844/8...naa1080.th.jpg http://img525.imageshack.us/img525/4...iv51050.th.jpg http://img28.imageshack.us/img28/922/dniciv51080.th.jpg http://img716.imageshack.us/img716/6...se21050.th.jpg http://img824.imageshack.us/img824/9...se21080.th.jpg

Ram compare:
http://img819.imageshack.us/img819/7...6cpuram.th.jpg http://img846.imageshack.us/img846/3...2006ram.th.jpg http://img708.imageshack.us/img708/7...enchram.th.jpg

OC:
http://img262.imageshack.us/img262/3...06cpuoc.th.jpg http://img809.imageshack.us/img809/3...k2006oc.th.jpg http://img3.imageshack.us/img3/9867/...benchoc.th.jpg http://img802.imageshack.us/img802/6301/dnispioc.th.jpg
10-09-2011, 02:33 PM
accord99

Quote:

Originally Posted by celerity

In the first Bulldozer is ~20% faster than 2600K in wPrime 32M. However, in the second it's 20% slower than 2600K. Same for other graphs, e.g. in the first 2600K is faster @ Winrar 4, second shows Bulldozer being faster. How come? :confused:

For some reason, the 8150 and 2600K were switched. Whether it was accidental or incidental on the part of AMD, who knows.
10-09-2011, 02:35 PM
Tha Last Meal

Quote:

As promised the screen caps:

Source ?
10-09-2011, 02:37 PM
PerryR

Quote:

Originally Posted by Tha Last Meal

Source ?

Donanim.
10-09-2011, 02:37 PM
cold2010

16801060 and 1920.1080 and aa8 lol :down:
10-09-2011, 02:41 PM
Final8ty

Quote:

Originally Posted by Hornet331

As promised the screen caps:

The scaling on the graphs takes the cake.

3dmark2011extreme: 1857 v 1757 but looks more than twice as much.
10-09-2011, 02:42 PM
Tha Last Meal

Quote:

Donanim.

thx

Quote:

16801060 and 1920.1080 and aa8 lol

yeah man this Review Not professional
10-09-2011, 02:42 PM
eXa

Seemes to be running into other limitations, hard to judge the gaming performance.
10-09-2011, 02:44 PM
Hornet331

Well game benchmarks are fail.. they show exactly what many others and me where saying -> gpu limitation @ that high res... regardless what cpu is used all perform the same... a difference of 1-2fps is laughable... and yes the scailing in the graphs is also bad.. but well I just made the screen caps.. blame donanimhaber. ;)
10-09-2011, 02:50 PM
Maxforces

Quote:

Originally Posted by BeepBeep2

Correction:
With both at 4 Ghz, the 920 is much faster in ST. In MT, Thuban is still very competitive, trailing slightly in some apps.

for sure??
http://maxforces.com/articles.php?ar...38&rowstart=12
Comparison 4Ghz (920) vs 4.2Ghz Thurban
Use google translator Polish-English
games are the worst
10-09-2011, 02:50 PM
Cecil

Quote:

Originally Posted by BeepBeep2

Correction:
With both at 4 Ghz, the 920 is much faster in ST. In MT, Thuban is still very competitive, trailing slightly in some apps.

The Thuban at 3.2 clocked to 4Ghz is a 25% increase, while clocking a 2.6 920 to 4Ghz is a 54% increase. Thuban's MT performance is not 30% faster then a 920.
Ive had many of both, i7 is just faster.
10-09-2011, 02:50 PM
Tha Last Meal

Quote:

Well game benchmarks are fail.. they show exactly what I and many others where saying -> gpu limitation and that high res... regardless what cpu is used all perform the same... a difference of 1-2fps is laughable...

1+

Did you know man this game benchmarks Settings Remember Me with AMD Slices :down:
10-09-2011, 02:53 PM
Hornet331

Well maybe its in the offical amd review kit guidelines how to bench games?... :D
10-09-2011, 02:57 PM
JumpingJack

Quote:

Originally Posted by Hornet331

As promised the screen caps: <snip>

They commit the unpardonable sin of not starting the graphs a zero (0)....
10-09-2011, 02:57 PM
Tha Last Meal

Quote:

Well maybe its in the offical amd review kit guidelines how to bench games?...

:Dlol

AMD This is wrong :shakes:

http://www.youtube.com/watch?v=Wrjwa...eature=related
10-09-2011, 02:59 PM
JumpingJack

Quote:

Originally Posted by Tha Last Meal

Source ?

http://www.donanimhaber.com/islemci/...o-inceleme.htm
10-09-2011, 03:14 PM
Frodin

This game's benchmark settings must have a strong memory then, I would have forgotten you with AMD slices right away.
10-09-2011, 03:14 PM
jimbo75

Quote:

Originally Posted by cold2010

16801060 and 1920.1080 and aa8 lol :down:

Would you rather see 1024x768 0xAA and 400fps on the intel cpu and 300 fps on the AMD cpu?
10-09-2011, 03:19 PM
eXa

Yes, because that actually says something. (all settings maxed ofc)
10-09-2011, 03:20 PM
Maxforces

I would like to see the cpu test and not gpu built-in benchmark
10-09-2011, 03:22 PM
looncraz

Thought the same thing....

Quote:

Originally Posted by Kobaltrock

I suppose there is also a small chance that all the final BIOS updates for the BD won't be released until the day of the launch.
They still could have disabled a few things to see who is breaking the NDA...:shrug:
If AMD is doing this, then, they really got some devious people there. :rofl:

I was thinking the same thing, but JF-AMD stated outright (to me, IIRC) that no such thing was happening, but that the BIOS updates could make a considerable performance difference do to the CPU initialization code. Also, Windows and Linux need kernel scheduler changes and memory alignment changes due to the share L1 cache causing excessive cross invalidations and subsequent reloads.

The cache memory has significantly more latency, but about a third more reading performance. Writes are also slower, which explains the presence of an L2 WCC (write coalescing cache). The very existence of the WCC and the cache details made available long ago made me wary... 18-20 cycle access times vs 12 cycles on Phenom II seemed like a BAD idea... that, and they kept the specialization of the ALUs instead of making them more capable, then removed one... but added an extra pipeline... that didn't seem too bright either, unless you can use the ALUs across the whole module to make a fat core (which should have been done before releasing this product).

If this is indicative of Bulldozer's performance, I will be building Intel machines almost across the board because the 1155 upgrade path is strong, but AM3+ is weak... a few of the lowest end machines will be AMD... but Athlon IIs.

My media machine upstairs is being prepped for an $800 upgrade and I was hoping Bulldozer would be the core, but it looks like an i2600k will be there instead - which sucks, because I have to pay a premium for the other features I need... but the performance is what matters for HD video.

--The loon
10-09-2011, 03:23 PM
gosh

Quote:

Originally Posted by Hornet331

Well game benchmarks are fail.. they show exactly what many others and me where saying -> gpu limitation @ that high res... regardless what cpu is used all perform the same... a difference of 1-2fps is laughable... and yes the scailing in the graphs is also bad.. but well I just made the screen caps.. blame donanimhaber. ;)

Dont think so, this is good for a cpu that focus on scaling. 2MB L2 cache and 8MB L3 cache 64 way set associative isn't as fast as cache on 2600K but it scales better
10-09-2011, 03:24 PM
Hornet331

Quote:

Originally Posted by gosh

Dont think so, this is good for a cpu that focus on scaling. 2MB L2 cache and 8MB L3 cache 64 way set associative isn't as fast as cache on 2600K but it scales better

Yes a good thing we bench the gpu in a cpu review... and I have a very bad deja vu about a thread form 2008... :rolleyes:
10-09-2011, 03:26 PM
-=DVS=-

Some dude is doing live stream benching Bulldozer , with 8 threads he got 24 GFLOPs :shakes: in LinX 0.6.4
10-09-2011, 03:26 PM
gosh

bulldozer online: https://join.me/573-962-519
10-09-2011, 03:27 PM
eXa

In what?
10-09-2011, 03:28 PM
Aberration

Wow. I sure hope there is just something wrong in the BIOS, or maybe a new stepping is needed.

I was really hoping to change camps.
10-09-2011, 03:30 PM
jimbo75

Quote:

Originally Posted by eXa

Yes, because that actually says something. (all settings maxed ofc)

Yes it would tell you how the chip handles gaming at settings you'll never play it.

In these 6 tests the BD cpu averaged 130 fps with AA. The i7 averaged 131.5 fps with AA.

Answer me this - if that BD chip was $50 would you even consider buying anything else for gaming? What about $100? How much is that 1.5 extra fps worth? This is the reality of enthusiast gaming, not ridiculous 600x480 resolutions.
10-09-2011, 03:32 PM
gosh

Quote:

Originally Posted by Hornet331

Yes a good thing we bench the gpu in a cpu review... and I have a very bad deja vu about a thread form 2008... :rolleyes:

No! It is important that it runs games at normal resolutions as fast as the fastest phenom as long as it wins in BF3. BF3 is the key because that is using new technology. It seems that it wins over phenom in all games and in some games it wins over 2600K, this is very good.
10-09-2011, 03:33 PM
Hornet331

10 Attachment(s)

All credit geos to black96ws6 on Overclock.net
http://www.overclock.net/amd-general...s-benches.html

Screencaps so far:

Attachment 121031 Attachment 121032

Attachment 121030
Attachment 121028
Attachment 121027
Attachment 121026
Attachment 121023
Attachment 121024
Attachment 121025
Attachment 121029

hes installing vantage now.
10-09-2011, 03:42 PM
richierich

Why does the task manager not show 100% utilization?
10-09-2011, 03:44 PM
radaja

dont forget this video someone made right after that FX-8120 CB run was done,its mean but funny as hell
http://youtu.be/CqTU4wVvZL0
10-09-2011, 03:47 PM
cold2010

Quote:

Originally Posted by jimbo75

Would you rather see 1024x768 0xAA and 400fps on the intel cpu and 300 fps on the AMD cpu?

NO
1680x1080 without AA And AF

Quote:

Originally Posted by radaja

dont forget this video someone made right after that FX-8120 CB run was done,its mean but funny as hell
http://youtu.be/CqTU4wVvZL0

:rofl:
10-09-2011, 03:47 PM
Hornet331

Quote:

Originally Posted by radaja

dont forget this video someone made right after that FX-8120 CB run was done,its mean but funny as hell
http://youtu.be/CqTU4wVvZL0

omg.. im laughing hard right now... damn you... :rofl:
10-09-2011, 03:48 PM
Brice MJ

Quote:

Originally Posted by radaja

dont forget this video someone made right after that FX-8120 CB run was done,its mean but funny as hell
http://youtu.be/CqTU4wVvZL0

:rofl: Tragicomic.
10-09-2011, 03:50 PM
radaja

Quote:

Originally Posted by Hornet331

omg.. im laughing hard right now... damn you... :rofl:

Quote:

Originally Posted by Brice MJ

:rofl: Tragicomic.

i told you,its funny as hell whether your pro or anti amd,it is what it is,you just cant help to chuckle:D
10-09-2011, 03:51 PM
eXa

Quote:

Originally Posted by jimbo75

Yes it would tell you how the chip handles gaming at settings you'll never play it.

In these 6 tests the BD cpu averaged 130 fps with AA. The i7 averaged 131.5 fps with AA.

Answer me this - if that BD chip was $50 would you even consider buying anything else for gaming? What about $100? How much is that 1.5 extra fps worth? This is the reality of enthusiast gaming, not ridiculous 600x480 resolutions.

Why are you arguing cpu performance with gpu performance?

The cpu does the same amount of work regardless of resolution (as long as all the other settings are the same)
Yes, a game wich has 3-400fps with 1024 resolution is rather pointless, since you obviously dont need much cpu performance for it to run great. But what if you get a game that runs with 100fps, or 50fps @ 1024?
Thoose 300 and 400fps would tell me SOMETHING about what to expect, while those 130 gpu limited fps you want to see wouldnt tell me a daam thing about cpu performance in that game.
All that 130fps shows me is that both cpu is enough for that game(but nothing about newer/more cpu dependant games).
10-09-2011, 03:51 PM
Hornet331

Wait till the "hittler got told" stuff pops up...

Quote:

Originally Posted by eXa

Why are you arguing cpu performance with gpu performance?

The cpu does the same amount of work regardless of resolution (as long as all the other settings are the same)
Yes, a game wich has 3-400fps with 1024 resolution is rather pointless, since you obviously dont need much cpu performance for it to run great. But what if you get a game that runs with 100fps, or 50fps @ 1024?
Thoose 300 and 400fps would tell me SOMETHING about what to expect, while those 130 gpu limited fps you want to see wouldnt tell me a daam thing about cpu performance in that game.
All that 130fps shows me is that both cpu is enough for that game(but nothing about newer/more cpu dependant games).

Exactly, it just tells you right now the cpu is "good enough" what happens when you buy half a year later another gpu and run cf/sli, or when a game finnaly starts to be more cpu dependent (like SC2).

With lower res benches you see what potential the cpu has, with caped max res benches it all looks the same.
10-09-2011, 03:52 PM
Hondacity

thats awesome :rofl:
10-09-2011, 03:53 PM
Tha Last Meal

Quote:

Originally Posted by radaja

dont forget this video someone made right after that FX-8120 CB run was done,its mean but funny as hell
http://youtu.be/CqTU4wVvZL0

LOL :rofl::rofl::rofl:
10-09-2011, 03:55 PM
PerryR

Indeed funny.

BTW, anyone know why the CPU is hardly strained in some of these CPU intensive benches?
10-09-2011, 03:58 PM
eXa

hahahah, that clip made me laugh alot too :D
10-09-2011, 04:02 PM
highoctane

Quote:

Originally Posted by radaja

dont forget this video someone made right after that FX-8120 CB run was done,its mean but funny as hell
http://youtu.be/CqTU4wVvZL0

:rofl: Pretty good!
10-09-2011, 04:04 PM
Hornet331

Quote:

Originally Posted by PerryR

BTW, anyone know why the CPU is hardly strained in some of these CPU intensive benches?

because what you see is actually idle, the bench is already done. The 10% utilisation is the the teamviewer running (remote access). This of course can hamper the test quite a bit. I wouldn't take this resultt real serious without the RDT you probably see 10-20% increase in scores.
10-09-2011, 04:10 PM
Pantsu

Quote:

Originally Posted by radaja

dont forget this video someone made right after that FX-8120 CB run was done,its mean but funny as hell
http://youtu.be/CqTU4wVvZL0

After having seen the benchmark results I wasn't sure whether to laugh or cry, but after seeing this vid I was certainly laughing. :ROTF: Unfortunately I'm sure that laugh will turn into tears when we get to see Ivy Bridge price tags. What a sad time for desktop enthusiasts :(
10-09-2011, 04:13 PM
Hornet331

ACtually I doubt we see much of a price increase in the mainstream parts, the thing i can see is, that the remove the K parts and only let them live in the premium price segment.
10-09-2011, 04:23 PM
Brice MJ

Quote:

Originally Posted by Hornet331

ACtually I doubt we see much of a price increase in the mainstream parts, the thing i can see is, that the remove the K parts and only let them live in the premium price segment.

They might even keep unclocked chips in the mainstream segment, but they probably wont push IB stock clocks much over what we have today if they dont need too (3.6-3.8GHz 4C/8T with 5-10% IPC boost).
10-09-2011, 04:25 PM
gosh

Quote:

Originally Posted by Hornet331

With lower res benches you see what potential the cpu has, with caped max res benches it all looks the same.

You don't!
10-09-2011, 04:27 PM
jimbo75

Quote:

Originally Posted by eXa

Yes, a game wich has 3-400fps with 1024 resolution is rather pointless, since you obviously dont need much cpu performance for it to run great. But what if you get a game that runs with 100fps, or 50fps @ 1024? Thoose 300 and 400fps would tell me SOMETHING about what to expect, while those 130 gpu limited fps you want to see wouldnt tell me a daam thing about cpu performance in that game.
All that 130fps shows me is that both cpu is enough for that game(but nothing about newer/more cpu dependant games).

What games do you know that run at 50 fps @ 1024? You are using low res benchmarks as some kind of proof of lastability but it's a total fallacy. Any enthusiast who isn't gaming at his gpu's bottleneck needs to go out and buy a new gpu, not a new cpu.
10-09-2011, 04:31 PM
jjj

Quote:

Originally Posted by Pantsu

Unfortunately I'm sure that laugh will turn into tears when we get to see Ivy Bridge price tags. What a sad time for desktop enthusiasts :(

The sad part is that we won't see more than 4 cores at reasonable prices from Intel anytime soon.
10-09-2011, 05:17 PM
BababooeyHTJ

Quote:

Originally Posted by gosh

You don't!

You are talking to a guy who thinks that canned benchmarks like the small ranch loop that he posted are supposed to somehow be representative of real world performance.

There aren't too many sites out there that do a proper cpu gaming comparison. Anandtech, Techpowerup, Hardware Canucks, [H], and Guru3d all do awful cpu reviews. You can't treat a cpu review like its a video card review with a super pi bench.
10-09-2011, 05:29 PM
Sparky

Part of me still hopes it might be a Radeon 9700 pro deal, where it was released and was sucky due to some serious stability issues (my brother had one at the time and experienced this), then they realized that the card hated AGP fast writes for some reason (which they did fix with the 9800). Disable fast writes in the system BIOS and the card turned into a monster that completely caught nvidia off guard.

Not likely, but I'm still sort of hoping there is some flaw in the BIOS coding or whatever that is easily fixed, turning the CPU into a monster.

Vain hope? Probably.
10-09-2011, 05:33 PM
highoctane

Quote:

Originally Posted by BababooeyHTJ

There aren't too many sites out there that do a proper cpu gaming comparison. Anandtech, Techpowerup, Hardware Canucks, [H], and Guru3d all do awful cpu reviews. You can't treat a cpu review like its a video card review with a super pi bench.

Since you're calling out some of the major players what do you consider a proper cpu gaming comparison, where are they lacking, what are you looking for in a proper cpu gaming comparison?
10-09-2011, 05:34 PM
G0ldBr1ck

It has to be better than this preview eludes. If this is all there is than $250 will never work. They would be lucky to sell any at $200 so I'm expecting there is something we are missing here.
10-09-2011, 05:38 PM
eric66

if i was amd i would quickly acquire arm license cause they can't even touch intel lol bulldozer my ass sorry must say that ...
10-09-2011, 05:38 PM
highoctane

Quote:

Originally Posted by G0ldBr1ck

It has to be better than this preview eludes. If this is all there is than $250 will never work. They would be lucky to sell any at $200 so I'm expecting there is something we are missing here.

Well considering launch prices are always the highest, unless things change after NDA lifts I'm sure we can expect some price drops soon after in retail.
10-09-2011, 05:45 PM
Pantsu

Quote:

It has to be better than this preview eludes. If this is all there is than $250 will never work. They would be lucky to sell any at $200 so I'm expecting there is something we are missing here.

You forget it's AMD's flagship. It will always be priced as high as it possibly can, like Intel does with Xtreme Edition cpus. The next lower model might be 100$ cheaper while being barely any slower.

The leaked AMD slides already showed that even in PR slides FX could only barely compete with 2500K in cherry picked tests which are supposed to justify the 245$ price for that small subset of users. Lab501 benches just reveal the flip side, that it sucks for everyone else.
10-09-2011, 05:54 PM
PerryR

Quote:

Originally Posted by Pantsu

The leaked AMD slides already showed that even in PR slides FX could only barely compete with 2500K in cherry picked tests which are supposed to justify the 245$ price for that small subset of users. Lab501 benches just reveal the flip side, that it sucks for everyone else.

Which slides are you talking about? The ones I saw recently showed it beating a 2500k pretty handily in picked benches.

http://i.imgur.com/EG4cN.jpg
10-09-2011, 05:57 PM
G0ldBr1ck

Well then Piledriver cant get here soon enough.
10-09-2011, 06:01 PM
geo

give AMD a break lol...
10-09-2011, 06:03 PM
CrazyNutz

WOW! This looks bad. Hurry get a 1100t while you still can!!!
10-09-2011, 06:09 PM
The Coolest

Quote:

Originally Posted by G0ldBr1ck

Well then Piledriver cant get here soon enough.

My thoughts exactly. Maybe that's why AMD's putting the rush on getting the new APUs, and subsequently BD II out the door ASAP?
I'm pretty disappointed at this point, especially after more than 5 years that the codename Bulldozer was floating around and all of the unofficial delays it encountered this year.
I still think that we got to give AMD the benefit of the doubt until the 12th, when all the other official reviews either confirm or refute this preview.
10-09-2011, 06:10 PM
LightSpeed

If the benches are indeed true, which i seriously hope are not, Phenom II at 32nm with some uarch improvements would easily be >20% better. I love AMD but I want what their CPU division are smoking. Now.
10-09-2011, 06:16 PM
Toysoldier

Quote:

Originally Posted by mav2000

If there are no major changes in the bios or whatever and there is no significant performance gain, I am not going to buy this chip. I will stick to my 1090T and wait for the next revision....

I was also planning on getting a BD, but like you I will stick to my 1100T.
(edit : I personally never expected BD to beat Intel's i2600K, but to be close to or on par with it)
10-09-2011, 06:18 PM
haylui

Quote:

Originally Posted by LightSpeed

If the benches are indeed true, which i seriously hope are not, Phenom II at 32nm with some uarch improvements would easily be >20% better. I love AMD but I want what their CPU division are smoking. Now.

from the design alone, BD suppose to be very good in FPU since it has 4 x 256bit FMAC units and not too much improvements on INT unit.
But the greatest disappoint here is that both INT and FPU are not better than Deneb, no?
If AMD just die shrink Deneb, they could have a lot of trouble competing in the future. Perhaps, there would be FMAC optimization after BD is launched.
10-09-2011, 06:29 PM
G0ldBr1ck

I have no doubt that Bulldozer will be useful in select niche markets but they need to go ahead and extend the life of thuban. A shrink would be great and some more Mhz to stay aimed at the mainstream and/or gamers.
10-09-2011, 07:03 PM
clayton

The prophet terrace215 is laughing somewhere.

Show 100 post(s) from this thread on one page

All times are GMT -8. The time now is 05:34 AM.

XtremeSystems