AMD FX-8150 Bulldozer finally tested

Printable View

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

10-09-2011, 07:03 PM
sin0822

Quote:

Originally Posted by Brice MJ

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).

ivy bridge will have a 63x max Intel multi instead of 57x so i am guessing w will see like 65x
10-09-2011, 07:32 PM
SKYMTL

The reactions of some people really get me laughing.

People wanted to see results posted so Lab501 did that. Unfortunately, some of us are bound by NDA so we can't comment on the accuracy of said numbers but....

Since they weren't anywhere near what some people expected, small details are picked and prodded until we get the "impossible", "BS!" and "biased" words thrown around for heaven knows what reason.

So if these numbers are accurate, will those same people post again saying "we were wrong!"? Methinks not. They'll go sulk in a corner for 5 minutes, find another thread to pick apart and then ultimately go buy an Intel processor. On the flip side of that coin, if the numbers are inaccurate or wrong, Lab501 has pretty much burned every possible bridge with a major manufacturer and will be the butt end of communal jokes until Theo or Charlie screw up again.

So which one will it be? Man, the next few days will be interesting to say the least..... :)
10-09-2011, 07:36 PM
Sparky

Quote:

Originally Posted by SKYMTL

So if these numbers are accurate, will those same people post again saying "we were wrong!"? Methinks not. They'll go sulk in a corner for 5 minutes, find another thread to pick apart and then ultimately go buy an Intel processor.

I disagree. I'll go sulk in a corner for 5 minutes, pick apart another thread, then continue using my current CPU :p:
10-09-2011, 07:45 PM
PerryR

Quote:

Originally Posted by SKYMTL

Since they weren't anywhere near what some people expected, small details are picked and prodded until we get the "impossible", "BS!" and "biased" words thrown around for heaven knows what reason.

This line makes me think you know it's bad, since the same could be asked of people who know that'll it suck based on this one review :p:

Regardless, I still find it strange that AMD is willing to charge around $280 for a failed processor. The price came from this microcenter employee.

http://www.overclock.net/amd-general...ate-specs.html
10-09-2011, 07:49 PM
xVeinx

AMD stated nothing over $250 during the live event, so I imagine that pricing will change (eventually).
10-09-2011, 07:54 PM
SKYMTL

Quote:

Originally Posted by PerryR

This line makes me think you know it's bad, since the same could be asked of people who know that'll it suck based on this one review :p:

I will repeat what others said: never, ever base your purchasing decisions or opinion about a certain product off of:

A) Rumors

B) A single review / preview

At this time everyone wants to know how this thing does so let's all wait until we see a large cross section of results before flinging crap around. :)
10-09-2011, 08:00 PM
qurious63ss

IIRC the PII 1090 and 1100 where both around 290 when first released but dropped down to 190 pretty fast so you will probably see this for these proc price drop as well. Supply and demand will dictate the price. Now if current results hold true I guess I should be glad Amd screwed up but I feel a bit a little bad for them since I know how much hard work it takes to get these things out successfully. Well if it helps I can talk to the big shots and see if we can fab those bulldozers on a proper 32nm process:)
10-09-2011, 08:06 PM
PerryR

Quote:

Originally Posted by SKYMTL

I will repeat what others said: never, ever base your purchasing decisions or opinion about a certain product off of:

A) Rumors

B) A single review / preview

At this time everyone wants to know how this thing does so let's all wait until we see a large cross section of results before flinging crap around. :)

I was just joshing tis all.:p:

Quote:

AMD stated nothing over $250 during the live event, so I imagine that pricing will change (eventually).

I've heard about this event, but can't tell which one it is.
10-09-2011, 08:07 PM
Gener_AL (UK)

I have been lurking, waiting, and I have to say.
It's the strangest build up to a CPU launch I have experienced so far.
Although I am full of a fever at the moment so everything is a little odd.
Can anyone remember AMD being so tight lipped on figures prior to launch?
Just about anything bulldozer related.
I have spent the day testing various BIOS on AMD chips > compatible code > optimised > non-optimised.
The results that have leaked so far give indication that the real performance is yet to be unleashed, the previews I'm seeing here sort of confirm this data pattern.
I think first of all BIOS is the key here, followed by OS updates and then software optimisation.
if this is raw performance on a compatible but non optimised BIOS I am quite happy then.
10-09-2011, 08:12 PM
Kobaltrock

If all these benchmarks are legit (and, at this point there is very little reason to doubt them since multiple people got pretty much the same results), the the only thing we are going to see the next few days is lots of spin control.

JF-AMD will have his work cut out for him, going into full damage control mode.

Nobody wants to only have one player in the mid to high end field, and at this time, it looks like that intel doesn't have anything to worry about, and they will continue to charge a premium for what they offer.

I still think AMD will do OK with the BD, they just need to adjust the price down, and hurry up and tape out pile driver.
10-09-2011, 08:40 PM
M.Beier

Quote:

Originally Posted by BababooeyHTJ

Here is what I saw in actual gameplay with the settings that I actually use not some :banana::banana::banana::banana:ty canned bench like what Hornet just posted like thats supposed mean something to me.

This is what I would expect from a "professional review" I should have left out the maximum framerate though.

This is an i5 750 at 4ghz and an i5 2500k at 4.7ghz.

http://i308.photobucket.com/albums/k...0vsi52500k.png

And here is what I would have expected from you....
Preview, review, do you know the difference? I think you do, do you need glasses then?
10-09-2011, 08:56 PM
M.Beier

Quote:

Originally Posted by SKYMTL

The reactions of some people really get me laughing.

People wanted to see results posted so Lab501 did that. Unfortunately, some of us are bound by NDA so we can't comment on the accuracy of said numbers but....

Since they weren't anywhere near what some people expected, small details are picked and prodded until we get the "impossible", "BS!" and "biased" words thrown around for heaven knows what reason.

So if these numbers are accurate, will those same people post again saying "we were wrong!"? Methinks not. They'll go sulk in a corner for 5 minutes, find another thread to pick apart and then ultimately go buy an Intel processor. On the flip side of that coin, if the numbers are inaccurate or wrong, Lab501 has pretty much burned every possible bridge with a major manufacturer and will be the butt end of communal jokes until Theo or Charlie screw up again.

So which one will it be? Man, the next few days will be interesting to say the least..... :)

True, double true. :)
We want results, but fanboyism gets in the way for some..... Making Lab501 the bad guys for serving the enthuciasts..
10-09-2011, 09:14 PM
Ice009

Quote:

Originally Posted by Viking1962

Monstru, I hope you not playing with us and the benchmark are true or not paid by Intel to do this. If its fake you desserve a big punch in your face from everyone who uses a AMD in this forum. Im not the happiest man in the world right now

Maybe he's been paid by AMD to leak it so if the actual performance is very close to the 2600K people will be ecstatic, rather than mildly disappointed if they hadn't seen these benchmarks ;).
10-09-2011, 09:14 PM
Viking1962

Monstru, I hope you not playing with us and the benchmark are true or not paid by Intel to do this. If its fake you desserve a big punch in your face from everyone who uses a AMD in this forum. Im not the happiest man in the world right now http://www.nordichardware.se/swforum...s/icon_cry.gif
10-09-2011, 09:41 PM
god_43

...lol wtf how did your comment end up quoted before you made it? who here is versed in temporal mechanics? :p:
10-09-2011, 09:52 PM
mAJORD

all the conspiracy theories are messing up spacetime
10-09-2011, 10:06 PM
Ice009

I don't know how how my post ended up above his, the quote was done before the edit too ;).
10-09-2011, 10:14 PM
thebluemeanie1

Lab501.ro +1 :)

At least they left plenty of numbers for them to upgrade to.

The rest of you guys just remind me why I stopped visiting this site...
10-09-2011, 11:09 PM
Russian

Quote:

Originally Posted by SKYMTL

The reactions of some people really get me laughing.

People wanted to see results posted so Lab501 did that. Unfortunately, some of us are bound by NDA so we can't comment on the accuracy of said numbers but....

Since they weren't anywhere near what some people expected, small details are picked and prodded until we get the "impossible", "BS!" and "biased" words thrown around for heaven knows what reason.

So if these numbers are accurate, will those same people post again saying "we were wrong!"? Methinks not. They'll go sulk in a corner for 5 minutes, find another thread to pick apart and then ultimately go buy an Intel processor. On the flip side of that coin, if the numbers are inaccurate or wrong, Lab501 has pretty much burned every possible bridge with a major manufacturer and will be the butt end of communal jokes until Theo or Charlie screw up again.

So which one will it be? Man, the next few days will be interesting to say the least..... :)

I've been tempted to comment on some of this that's been going on but I'm in the same boat as you. Oh well.
10-09-2011, 11:28 PM
zalbard

Quote:

Originally Posted by Russian

I've been tempted to comment on some of this that's been going on but I'm in the same boat as you. Oh well.

You could give us a hint! :D
10-09-2011, 11:38 PM
kuroikenshi

:horse::bsod:
10-09-2011, 11:39 PM
mongoled

Quote:

Originally Posted by zalbard

You could give us a hint! :D

Yes, please do,

would like to know if their is any light at the end of the 5 year tunnel!
10-09-2011, 11:39 PM
looncraz

Quote:

Originally Posted by 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.

Actually, we already have such an issue known for Bulldozer, and NO bench-marked system has the patch installed!

The shared L1 cache is causing cross invalidations across threads so that the prefetch data is incorrect in too many cases and data must be fetched again. The fix is a "simple" memory alignment and (possible)tagging system in the kernel of Windows/Linux.

I reviewed the code for the Linux patch and was astonished by just how little I know of the Linux kernel... lol! In any event, it could easily cost 10% in terms of single threaded performance, possibly more than double that in multi-threaded loads on the same module due to the increased contention and randomness of accesses.

Not sure if ordained reviewers have been given access to the MS patch, but I'd imagine (and hope) so! Last I saw, the Linux kernel patch was still being worked on by AMD (publicly) and Linus was showing some distaste for the method used to address the issue. One comment questioned the performance cost but had received no replies... but you don't go re-working kernel memory mapping for anything less than 5-10%... just not worth it!
10-09-2011, 11:40 PM
haylui

Quote:

Originally Posted by zalbard

You could give us a hint! :D

don't!
later the hint goes against the fact...:mad::mad:
10-09-2011, 11:44 PM
Hondacity

Quote:

Originally Posted by looncraz

Actually, we already have such an issue known for Bulldozer, and NO bench-marked system has the patch installed!

The shared L1 cache is causing cross invalidations across threads so that the prefetch data is incorrect in too many cases and data must be fetched again. The fix is a "simple" memory alignment and (possible)tagging system in the kernel of Windows/Linux.

I reviewed the code for the Linux patch and was astonished by just how little I know of the Linux kernel... lol! In any event, it could easily cost 10% in terms of single threaded performance, possibly more than double that in multi-threaded loads on the same module due to the increased contention and randomness of accesses.

Not sure if ordained reviewers have been given access to the MS patch, but I'd imagine (and hope) so! Last I saw, the Linux kernel patch was still being worked on by AMD (publicly) and Linus was showing some distaste for the method used to address the issue. One comment questioned the performance cost but had received no replies... but you don't go re-working kernel memory mapping for anything less than 5-10%... just not worth it!

wow
10-09-2011, 11:44 PM
mongoled

Quote:

Originally Posted by looncraz

Actually, we already have such an issue known for Bulldozer, and NO bench-marked system has the patch installed!

The shared L1 cache is causing cross invalidations across threads so that the prefetch data is incorrect in too many cases and data must be fetched again. The fix is a "simple" memory alignment and (possible)tagging system in the kernel of Windows/Linux.

I reviewed the code for the Linux patch and was astonished by just how little I know of the Linux kernel... lol! In any event, it could easily cost 10% in terms of single threaded performance, possibly more than double that in multi-threaded loads on the same module due to the increased contention and randomness of accesses.

Not sure if ordained reviewers have been given access to the MS patch, but I'd imagine (and hope) so! Last I saw, the Linux kernel patch was still being worked on by AMD (publicly) and Linus was showing some distaste for the method used to address the issue. One comment questioned the performance cost but had received no replies... but you don't go re-working kernel memory mapping for anything less than 5-10%... just not worth it!

Thanks for this great post!

There is some light!

So, maybe we will see a 20% improvement across the board in a couple of months time.

Excited again

:)
10-09-2011, 11:51 PM
Olivon

Good to see that there's some light in the lavatory pan ! :eleph:

Somebody seen rintamarootta, 2good4you or even JF :confused:
10-09-2011, 11:52 PM
haylui

Quote:

Originally Posted by Olivon

Good to see that there's some light in the lavatory pan ! :eleph:

Somebody seen rintamarootta, 2good4you or even JF :confused:

no, not in Singapore.
10-10-2011, 12:05 AM
Michaelius

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.

You would think people on enthusiast forum should know that fast CPU is essential for gaming in 2011:

http://www.techspot.com/review/405-t...nce/page8.html
http://www.pcgameshardware.com/aid,7...efit/Practice/
http://www.bit-tech.net/hardware/cpu...rcraft-2-use/2
http://www.techspot.com/review/312-m...nce/page8.html

PS. 50-100$ seems like a reasonable price for AMD offering.
10-10-2011, 12:09 AM
zalbard

Quote:

Originally Posted by looncraz

Actually, we already have such an issue known for Bulldozer, and NO bench-marked system has the patch installed!

The shared L1 cache is causing cross invalidations across threads so that the prefetch data is incorrect in too many cases and data must be fetched again. The fix is a "simple" memory alignment and (possible)tagging system in the kernel of Windows/Linux.

I reviewed the code for the Linux patch and was astonished by just how little I know of the Linux kernel... lol! In any event, it could easily cost 10% in terms of single threaded performance, possibly more than double that in multi-threaded loads on the same module due to the increased contention and randomness of accesses.

Not sure if ordained reviewers have been given access to the MS patch, but I'd imagine (and hope) so! Last I saw, the Linux kernel patch was still being worked on by AMD (publicly) and Linus was showing some distaste for the method used to address the issue. One comment questioned the performance cost but had received no replies... but you don't go re-working kernel memory mapping for anything less than 5-10%... just not worth it!

Very interesting.
I suppose applications would not need any extra optimisations to benefit from this, then?
And if this is all true and this Windows patch is not ready then the launch will be a disaster. They should have waited some more.
10-10-2011, 12:15 AM
bamtan2

Quote:

Originally Posted by looncraz

Actually, we already have such an issue known for Bulldozer, and NO bench-marked system has the patch installed!

The shared L1 cache is causing cross invalidations across threads so that the prefetch data is incorrect in too many cases and data must be fetched again. The fix is a "simple" memory alignment and (possible)tagging system in the kernel of Windows/Linux.

I reviewed the code for the Linux patch and was astonished by just how little I know of the Linux kernel... lol! In any event, it could easily cost 10% in terms of single threaded performance, possibly more than double that in multi-threaded loads on the same module due to the increased contention and randomness of accesses.

Not sure if ordained reviewers have been given access to the MS patch, but I'd imagine (and hope) so! Last I saw, the Linux kernel patch was still being worked on by AMD (publicly) and Linus was showing some distaste for the method used to address the issue. One comment questioned the performance cost but had received no replies... but you don't go re-working kernel memory mapping for anything less than 5-10%... just not worth it!

link to these discussions? I don't see anything about bulldozer on lwn.net or lkml.org
10-10-2011, 12:23 AM
Olivon

http://tof.canardpc.com/view/065decc...1443c9a715.jpg

http://tof.canardpc.com/view/80689cb...a247b20725.jpg
10-10-2011, 12:25 AM
flyck

isn't this already known? and i thought they talked about 3% performance.. Seems to be about the same 'issue'.
10-10-2011, 12:28 AM
bamtan2

^^power usage (dont care)
10-10-2011, 12:40 AM
radier

Power usage is very important. My rig at IDLE is draining 87,5W yet at load I can use extreme CPU performance. This is how modern CPU should act.
10-10-2011, 01:08 AM
jimbo75

Quote:

Originally Posted by Michaelius

You would think people on enthusiast forum should know that fast CPU is essential for gaming in 2011:

http://www.techspot.com/review/405-t...nce/page8.html
http://www.pcgameshardware.com/aid,7...efit/Practice/
http://www.bit-tech.net/hardware/cpu...rcraft-2-use/2
http://www.techspot.com/review/312-m...nce/page8.html

PS. 50-100$ seems like a reasonable price for AMD offering.

Starcraft 2 - First link shows the Phenom II scoring 26.7 fps at 1024x768, no AA/AF, clicking on the 2nd resolution shows 26.1 fps at 1920x1080, 4xAA/16AF. What would you play at? Oh incidentally, that puts it 0.6 fps behind it's main competition, the i5-750.

Mafia II - An i7 920 and i5 750 with a massive 60% overclock beats a stock 965 by 12%. 4% normally. This is supposed to be what, a major victory?

You didn't really look very hard at the majority of those links, did you? Only Witcher 2 shows the Phenom's in a bad light, being 44% faster than the next-gen SB and 20% slower than the real competition. Congratulations, you finally got a game where the cpu could actually be said to matter at gaming settings, 2 and a half years after the "slow" cpu was released. :clap:
10-10-2011, 01:35 AM
naokaji

Quote:

Originally Posted by bamtan2

^^power usage (dont care)

There is a place called Europe, where electricity is extremely expensive. Power consumption is the only reason in the near future for me to throw out my i7 920 and get something else, SB-E is out of the question as it sucks just as much power, Sandy Bridge is not enough extra performance and Bulldozer? well, if you believe the numbers then it sucks just as much power as a 6 Core Phenom / any S1366 Cpu but the performance is only a improvement if you compare it to something ancient like a Phenom II x4 or a C2Q... which is why I have a hard time believing the numbers, I mean surely AMD would not be so dumb to release it's new Cpu with a performance that can only compete with its own Phenom II x4? just doesn't make sense especially as the price suggests its a Phenom II x6 successor, but unfortunately for AMD lab501 is one of the more reliable sites out there.
10-10-2011, 01:36 AM
gosh

Quote:

Originally Posted by bamtan2

link to these discussions? I don't see anything about bulldozer on lwn.net or lkml.org

this maybe? http://comments.gmane.org/gmane.linux.kernel/1170214

more: http://www.spinics.net/lists/linux-t.../msg13140.html
10-10-2011, 01:50 AM
Hondacity

Quote:

Out of curiosity, what's the performance impact if the workaround is
not enabled?

Up to 3% for a CPU-intensive style benchmark, and it can vary highly in
a microbenchmark depending on workload and compiler

this might be the ummm....
10-10-2011, 01:52 AM
R101

It seems to me that AMD just expected Bulldozer to clock higher.. If there was any significant penalty in OS kernel, AMD would be crazy not to have managed it long before the CPUs hit the shelves.
10-10-2011, 01:53 AM
AAbenson

power usage on the FX8150 is just horrible:eek::down:
...i dont see how big companies that have many servers running 24/7 will buy the FX...AMD are shooting themselves in the foot big time now--->bad power usage,bad computing power
10-10-2011, 02:28 AM
Chrono Detector

What, so it consumes higher power and isn't really that much powerful? And what I can see that it can't even keep up with 1100T in some benchmarks which is embarrassing. Bulldozer looks less appealing now.
10-10-2011, 02:28 AM
villa1n

Quote:

Originally Posted by looncraz

Actually, we already have such an issue known for Bulldozer, and NO bench-marked system has the patch installed!

The shared L1 cache is causing cross invalidations across threads so that the prefetch data is incorrect in too many cases and data must be fetched again. The fix is a "simple" memory alignment and (possible)tagging system in the kernel of Windows/Linux.

I reviewed the code for the Linux patch and was astonished by just how little I know of the Linux kernel... lol! In any event, it could easily cost 10% in terms of single threaded performance, possibly more than double that in multi-threaded loads on the same module due to the increased contention and randomness of accesses.

Not sure if ordained reviewers have been given access to the MS patch, but I'd imagine (and hope) so! Last I saw, the Linux kernel patch was still being worked on by AMD (publicly) and Linus was showing some distaste for the method used to address the issue. One comment questioned the performance cost but had received no replies... but you don't go re-working kernel memory mapping for anything less than 5-10%... just not worth it!

I guess we can expect the same issue on interlagos? That kind of glitch would seem pretty important in terms of a datacenter environment... kvm / vmware is pretty much all multi.
10-10-2011, 02:29 AM
donitsi

Quote:

Originally Posted by gosh

this maybe? http://comments.gmane.org/gmane.linux.kernel/1170214

more: http://www.spinics.net/lists/linux-t.../msg13140.html

So there really are some performance problems they try to solve.

But these fixes are coming too late. (too small too?) First impression is the thing that matters and bd seems crap at launch
Plus can these things be fixed in Windows?
10-10-2011, 02:36 AM
Viking1962

Quote:

Originally Posted by god_43

...lol wtf how did your comment end up quoted before you made it? who here is versed in temporal mechanics? :p:

hahaha, he used a Bulldozer. Thats why his post came before my
10-10-2011, 02:44 AM
mav2000

Something is not right here..I am confused about a few things:

1. How can a company make a new product which is lower/equal to the older product line. I dont see OCZ coming out with a Vertex 4 which is slower than the Vertex 3, unless there is some significant change in life of the said SSD

2. How are the planning to price it at 285 USD, if most reviews have shown it to be equal to or below PH II?

3. If the discussed performance is true, then should AMD have marketed this as a 4 core, 8 thread chip?

On 1, I have no answer, but I guess if anything changes then it will be on launch date ...maybe..

On 2, I have heard the number of chips available is going to be extremely low on launch...could this be the reason for the high prices? Low supply, normal to high demand??
10-10-2011, 02:55 AM
Hornet331

Quote:

Originally Posted by looncraz

Not sure if ordained reviewers have been given access to the MS patch, but I'd imagine (and hope) so! Last I saw, the Linux kernel patch was still being worked on by AMD (publicly) and Linus was showing some distaste for the method used to address the issue. One comment questioned the performance cost but had received no replies... but you don't go re-working kernel memory mapping for anything less than 5-10%... just not worth it!

the queston was answered, amd said ~3%

Quote:

On Wed, Jul 27, 2011 at 11:57:45AM -0400, Avi Kivity wrote:
> Out of curiosity, what's the performance impact if the workaround is
> not enabled?

Up to 3% for a CPU-intensive style benchmark, and it can vary highly in
a microbenchmark depending on workload and compiler.

http://permalink.gmane.org/gmane.linux.kernel/1172226
10-10-2011, 03:08 AM
M.Beier

3% isnt enough to save this.
10-10-2011, 03:19 AM
STaRGaZeR

Quote:

Originally Posted by kobaltrock

if all these benchmarks are legit (and, at this point there is very little reason to doubt them since multiple people got pretty much the same results), the the only thing we are going to see the next few days is lots of spin control.

Jf-amd will have his work cut out for him, going into full damage control mode.

Quote:

Originally Posted by olivon

good to see that there's some light in the lavatory pan ! :eleph:

Somebody seen rintamarootta, 2good4you or even jf :confused:

QFT :down:
10-10-2011, 03:50 AM
FlanK3r

Quote:

Originally Posted by -=DVS=-

Some dude is doing live stream benching Bulldozer , with 8 threads he got 24 GFLOPs :shakes: in LinX 0.6.4

because last LINX dont stress this CPU now;), u need PRIME
10-10-2011, 04:26 AM
Kuroimaho

The Brain rejects negative thoughts, this might explain what's going on in this thread. :D
10-10-2011, 05:06 AM
Pantsu

Quote:

Originally Posted by Kuroimaho

The Brain rejects negative thoughts, this might explain what's going on in this thread. :D

It's a natural shock reaction, first you try to deny it. Then you start trying to "fix" it, until you finally accept it and move on to Intel. :D
10-10-2011, 05:44 AM
SoF

when we were playing BD a week ago we were looking at each other like "omg this is it?" - 6500+ and the scores were still as ugly as dinos in his summer-suit -.-
Everybody went back to Sandy and GT systems like half an hour later :ROTF:
10-10-2011, 05:57 AM
liberato87

@ Monstru
does HPET was enabled or not in bios?

Quote:

Originally Posted by chew*

There are many bios options that can effect the outcome of benches.

HPET is 1 for example, it stops the cpu from throttling back in mulithreaded apps.

Running pi on a cluster, versus a core ( 2 threads ) versus being able to disable a single cluster in a core ( which 99% boards/bios's do not have implemented so resources are not shared ) can all influence the results in single threaded.

Knowing all this tells you one thing for sure, you can make it look worse or make it look better all depending on your knowledge of the chip and or your intentions.

As far as PI it's an antiquated bench and has not been AMD's strong point for quite some time.

Granted some results shown tend to lead to the fact that 1m times are bad but looking at the bigger picture we also know that in many cases you can validate 1000mhz higher in many cases with BD, which would point to the fact that you can run 1m at alot faster speeds than current AMD tech.

Things that make you go hmm like what kind of times will we see at 8 gig or even comparing BD to deneb/thuban when same cooling is used.
10-10-2011, 05:59 AM
AKM

Quote:

Originally Posted by Kuroimaho

The Brain rejects negative thoughts, this might explain what's going on in this thread. :D

"And despite how sophisticated these neural networks are, it is illuminating to see how the brain sometimes comes up with wrong and overly optimistic answers despite the evidence."

LOL reading this thread makes this painfully obvious.
10-10-2011, 06:08 AM
Gener_AL (UK)

1 Attachment(s)

Attachment 121051

mm just spotted this. There are also tests against the 2500k.
10-10-2011, 06:19 AM
Mad Pistol

Quote:

Originally Posted by Gener_AL (UK)

Attachment 121051

mm just spotted this. There are also tests against the 2500k.

If this is true, there is a tangible performance increase going to BD from an x6.
10-10-2011, 06:20 AM
matose

Quote:

Originally Posted by liberato87

@ Monstru
does HPET was enabled or not in bios?

It's me that made the review, so I will take the liberty in responding. I will also respond to some questions from earlier!

BIOS was 9905 which was significantly better in both OC and performance than the old ones. All settings in BIOS were left on default, the only thing I modified was the memory frequency / timings / voltage and turned off all the things I don't use (LAN, USB 3.0, etc).
CPU is the final retail version, revision B2 and the Turbo Core worked without any problem: 1.4GHz when IDLE, 3.6 - 3.9GHz when all cores were used and 4.2GHz in single-threaded applications

Have a nice day,
matose
10-10-2011, 06:23 AM
Manicdan

Quote:

Originally Posted by Gener_AL (UK)

Attachment 121051

mm just spotted this. There are also tests against the 2500k.

this might have already been pointed out for a week now, or there could have been newer 8150 results uploaded to their database
10-10-2011, 06:29 AM
Manicdan

Quote:

Originally Posted by matose

1.4GHz when IDLE

Have a nice day,
matose

are there multiplyers as low as 4 for 800mhz, or is 7 the lowest?
10-10-2011, 06:29 AM
Manicdan

double post
10-10-2011, 06:30 AM
haylui

Quote:

Originally Posted by Gener_AL (UK)

Attachment 121051

mm just spotted this. There are also tests against the 2500k.

could we see the source of this ?
10-10-2011, 06:31 AM
liberato87

edit
10-10-2011, 06:33 AM
flyck

Quote:

Originally Posted by Mad Pistol

If this is true, there is a tangible performance increase going to BD from an x6.

Well if they could gain 80% in integer compared to thuban... that would be contradicting every bench that was leaked since that woul make a new BD core immensly more efficient. So this score from the BD seems to be an overclocked model (if we assume the numbers popping up in previews to be correct).

The smallest difference is in fpu load, the biggest in integers.
10-10-2011, 06:35 AM
liberato87

Quote:

Originally Posted by matose

It's me that made the review, so I will take the liberty in responding. I will also respond to some questions from earlier!

BIOS was 9905 which was significantly better in both OC and performance than the old ones. All settings in BIOS were left on default, the only thing I modified was the memory frequency / timings / voltage and turned off all the things I don't use (LAN, USB 3.0, etc).
CPU is the final retail version, revision B2 and the Turbo Core worked without any problem: 1.4GHz when IDLE, 3.6 - 3.9GHz when all cores were used and 4.2GHz in single-threaded applications

Have a nice day,
matose

thank you for reply.
I thought Monstru did the review ;)

I red the "HPET thing" long time before, so I was curious to see if it matters or not.

I can ask you why you left northbridge clock at default (I saw that in the spi picture)?
I red of someone raised nb to 3200...
I can ask you if you will post a complete review when nda expires?
10-10-2011, 06:39 AM
Gener_AL (UK)

Quote:

Originally Posted by haylui

could we see the source of this ?

http://semiaccurate.com/forums/showp...&postcount=539

Just happened to come across this earlier, a few more benchies to look at there ;)
10-10-2011, 06:55 AM
Opteron146

Quote:

Originally Posted by looncraz

Actually, we already have such an issue known for Bulldozer, and NO bench-marked system has the patch installed!

The shared L1 cache is causing cross invalidations across threads so that the prefetch data is incorrect in too many cases and data must be fetched again. The fix is a "simple" memory alignment and (possible)tagging system in the kernel of Windows/Linux.

I reviewed the code for the Linux patch and was astonished by just how little I know of the Linux kernel... lol! In any event, it could easily cost 10% in terms of single threaded performance, possibly more than double that in multi-threaded loads on the same module due to the increased contention and randomness of accesses.

Not sure if ordained reviewers have been given access to the MS patch, but I'd imagine (and hope) so! Last I saw, the Linux kernel patch was still being worked on by AMD (publicly) and Linus was showing some distaste for the method used to address the issue. One comment questioned the performance cost but had received no replies... but you don't go re-working kernel memory mapping for anything less than 5-10%... just not worth it!

Hi,

are you sure about the numbers? I remember following the discussion on the message board, I think they talked about ~3% performance impact, much more for "micro" benchmarks. So you say now that it is more 10-20%?
10-10-2011, 07:05 AM
saint19

Are this results all true? I was waiting more from BD and AMD with all the long wait that we did for this CPUs. Hope see something different to this results.
10-10-2011, 07:09 AM
wez

Quote:

Originally Posted by liberato87

I red the "HPET thing" long time before, so I was curious to see if it matters or not.

If I understood chew correctly, modifying HPET will allow it to run 4.2ghz on all cores. Not exactly suitable for most reviews, But no doubt interesting for us :) Hope more boards will implement that feature, as long as they can handle the load without going *poff* :D

(I think AMD confirmed on facebook or something that nda lift on the 12th?)
10-10-2011, 07:14 AM
hokiealumnus

Quote:

Originally Posted by SKYMTL

The reactions of some people really get me laughing.

People wanted to see results posted so Lab501 did that. Unfortunately, some of us are bound by NDA so we can't comment on the accuracy of said numbers but....

Since they weren't anywhere near what some people expected, small details are picked and prodded until we get the "impossible", "BS!" and "biased" words thrown around for heaven knows what reason.

So if these numbers are accurate, will those same people post again saying "we were wrong!"? Methinks not. They'll go sulk in a corner for 5 minutes, find another thread to pick apart and then ultimately go buy an Intel processor. On the flip side of that coin, if the numbers are inaccurate or wrong, Lab501 has pretty much burned every possible bridge with a major manufacturer and will be the butt end of communal jokes until Theo or Charlie screw up again.

So which one will it be? Man, the next few days will be interesting to say the least..... :)

As I'm also bound by NDA, I just wanted to say - QFT. Well said SKYMTL.
10-10-2011, 07:25 AM
xXSebaSXx

Regardless of how BD performs vs SB; I will guarantee you one thing... FX-8150 will become one of the most popular chips at HWBot faster than you can type "Rev 4 Sucks". If for one reason only; it will be because of its high OC ceiling. I foresee the 7GHz+ and even the 8GHz+ clubs gaining a load of new members in the future weeks/months.
10-10-2011, 08:03 AM
Syn.

Quote:

Originally Posted by xXSebaSXx

Regardless of how BD performs vs SB; I will guarantee you one thing... FX-8150 will become one of the most popular chips at HWBot faster than you can type "Rev 4 Sucks". If for one reason only; it will be because of its high OC ceiling. I foresee the 7GHz+ and even the 8GHz+ clubs gaining a load of new members in the future weeks/months.

I will buy FX8 simply because it is better then my current CPU. As far as performance numbers unlike most people in this thread i am not expecting anything. I am awaiting the reviews with no expectations, just curiosity.
10-10-2011, 08:06 AM
tiborrr

Who cares about performance, I want jiggahertzs! :up:
10-10-2011, 08:07 AM
Kobaltrock

Quote:

Originally Posted by looncraz

Actually, we already have such an issue known for Bulldozer, and NO bench-marked system has the patch installed!

The shared L1 cache is causing cross invalidations across threads so that the prefetch data is incorrect in too many cases and data must be fetched again. The fix is a "simple" memory alignment and (possible)tagging system in the kernel of Windows/Linux.
!

Here is the patch in question:
http://thread.gmane.org/gmane.linux..../focus=1171713

Quote:

From: Borislav Petkov <bp <at> amd64.org>
Subject: [PATCH] x86, AMD: Correct F15h IC aliasing issue
Newsgroups: gmane.linux.kernel
Date: 2011-07-22 13:15:47 GMT (11 weeks, 3 days, 2 hours and 46 minutes ago)

From: Borislav Petkov <borislav.petkov <at> amd.com>

This patch provides performance tuning for the "Bulldozer" CPU. With its
shared instruction cache there is a chance of generating an excessive
number of cache cross-invalidates when running specific workloads on the
cores of a compute module.

This excessive amount of cross-invalidations can be observed if cache
lines backed by shared physical memory alias in bits [14:12] of their
virtual addresses, as those bits are used for the index generation.

This patch addresses the issue by zeroing out the slice [14:12] of
the file mapping's virtual address at generation time, thus forcing
those bits the same for all mappings of a single shared library across
processes and, in doing so, avoids instruction cache aliases.

It also adds the kernel command line option
"unalias_va_addr=(32|64|off)" with which virtual address unaliasing
can be enabled for 32-bit or 64-bit x86 individually, or be completely
disabled.

This change leaves virtual region address allocation on other families
and/or vendors unaffected.

and Linus' response http://article.gmane.org/gmane.linux.kernel/1170744

Quote:

From: Linus Torvalds <torvalds <at> linux-foundation.org>
Subject: Re: [PATCH] x86, AMD: Correct F15h IC aliasing issue
Newsgroups: gmane.linux.kernel
Date: 2011-07-24 16:04:27 GMT (11 weeks, 23 hours and 59 minutes ago)
Argh. This is a small disaster, you know that, right? Suddenly we have
user-visible allocation changes depending on which CPU you are running
on. I just hope that the address-space randomization has caught all
the code that depended on specific layouts.

And even with ASLR, I wouldn't be surprised if there are binaries out
there that "know" that they get dense virtual memory when they do
back-to-back allocations, even when they don't pass in the address
explicitly.

How much testing has AMD done with this change and various legacy
Linux distros? The 32-bit case in particular makes me nervous, that's
where I'd expect a higher likelihood of binaries that depend on the
layout.

You guys do realize that we had to disable ASLR on many machines?

So at a MINIMUM, I would say that this is acceptable only when the
process doing the allocation hasn't got ASLR disabled.
...
Anyway, I seriously think that this patch is completely unacceptable
in this form, and is quite possibly going to break real applications.
Maybe most of the applications that had problems with ASLR only had
trouble with anonymous memory, and the fact that you only do this for
file mappings might mean that it's ok. But I'd be really worried.
Changing address space layout is not a small decision.
10-10-2011, 08:37 AM
Iconyu

Quote:

Originally Posted by Kobaltrock

Here is the patch in question:
http://thread.gmane.org/gmane.linux..../focus=1171713

and Linus' response http://article.gmane.org/gmane.linux.kernel/1170744

So will Piledriver be 10% just because of a bug fix, or will it be 10% faster than a Bulldozer without a missfire?
10-10-2011, 08:55 AM
Kobaltrock

Quote:

Originally Posted by Iconyu

So will Piledriver be 10% just because of a bug fix, or will it be 10% faster than a Bulldozer without a missfire?

Pile driver's 10% gain will most like be optimizations, but since those pics were more leaks, I have no idea how true that 10% figure is.

What is being talked about in the (3%) patch is the way BD accesses memory. It needs to do a extra fetch when the data isn't aligned correctly, and that can get expensive (time wise) since it must clear the cache, and start over again.

They are not related.

The thing we are all hoping for is for PD to tape out quickly, since from all the leaked BD benchmarks show, a 3% gain is pretty trivial.
We need competition in the high end, not the low end.
10-10-2011, 09:13 AM
SKYMTL

I want to draw everyone's attention to the fact that the patch people are suddenly talking about is for Linux ONLY and it WILL NOT address Windows-based performance. In addition, the Linux community has determined the "patch" itself is pretty much a hack job that could negatively impact system stability and in-app performance. So, it should not even be discussed at length at this point in time.
10-10-2011, 09:17 AM
Hondacity

thanks Mr Skymtl

how many nailbiting hours before nda lifts? are we following eastern time or when oct12 hits one country?
10-10-2011, 09:22 AM
nyeah

Quote:

Originally Posted by Hondacity

thanks Mr Skymtl

how many nailbiting hours before nda lifts? are we following eastern time or when oct12 hits one country?

yea, can't wait till NDA lifted, too many speculation based on wild guessing :D
10-10-2011, 09:30 AM
Gilgamesh

Quote:

Originally Posted by SKYMTL

I want to draw everyone's attention to the fact that the patch people are suddenly talking about is for Linux ONLY and it WILL NOT address Windows-based performance. In addition, the Linux community has determined the "patch" itself is pretty much a hack job that could negatively impact system stability and in-app performance. So, it should not even be discussed at length at this point in time.

Just a little question: for Bulldozer you will adopt same metodolgy and programs of your last review here?
hardwarecanucks.com/forum/hardware-canucks-reviews/44339-intel-core-i3-2120-core-i5-2400-lga1155-processors-review-4.html

I like it.
10-10-2011, 09:40 AM
solofly

Two more days to Halloween, silver shamrock...;)
10-10-2011, 09:54 AM
Kuroimaho

Quote:

Originally Posted by SKYMTL

I want to draw everyone's attention to the fact that the patch people are suddenly talking about is for Linux ONLY and it WILL NOT address Windows-based performance. In addition, the Linux community has determined the "patch" itself is pretty much a hack job that could negatively impact system stability and in-app performance. So, it should not even be discussed at length at this point in time.

You MR are the reason in this madness. :up:
10-10-2011, 12:02 PM
AzureSky

Quote:

Originally Posted by SKYMTL

I want to draw everyone's attention to the fact that the patch people are suddenly talking about is for Linux ONLY and it WILL NOT address Windows-based performance. In addition, the Linux community has determined the "patch" itself is pretty much a hack job that could negatively impact system stability and in-app performance. So, it should not even be discussed at length at this point in time.

as I understand it, theres a patch for windows either incoming or already in the hands of some testers.

and I for one couldnt give less of a :banana::banana::banana::banana::banana: about what the Linux community "determined", I quit with desktop linux years back after I finnely realised that it wasnt going anywhere, they refuse to support a unified audio/sound fraimwork, linux lacks a stable driver abi/api and ties drivers closely with the kernal so a small kernal patch can break your drivers....I could go on and on, but no need, I gave up on linux as a desktop OS quite a while back and have been happier since, as I prefer to use my computer rather then having to recompile the kernal with patches added/removed for hours/days on end to find what broke my video/audio/nic drivers.
oh yeah, and on windows/osx/bsd no dependency hell to deal with, no needing 3 versions of gtk installed because some idiot app dev decided to tie his/her app to a specific gtk version and hasnt bothered to updated to support newer gtk....

bah!!!

I have to say a few things about other comments about marketing and how "normal people" will see 8 cores being slower then 4 cores as fail....

Normal "Joe Sixpack" type users have no bloody idea about how a chip preforms, they buy what appears to be the best value, having worked in PC sales over the years, most of them dont even really care if its intel/amd/via/wtfe they only care that it looks like a good deal, hence the p4 sold so well despite it being so HOT and SLOW.

the fact is, most users are FAR FAR different from the users of this and other tech forums, they got no idea whats really in their computer, they just know what the sales people told them.

example: I recently had a friend of the family ask me to look at his computer, he bought it a few months ago and was told it was "Really fast" I get over there and its low end i3 prebuild with a 1gb gf210 and 2gb of VERY slow ram, he thinks its fast, because thats what he was told, well i cleaned off the preinstalled crapware and tweaked what i could to get it to run better, told him he needed to order ram and a videocard minimum if he wanted to play WoW on the 27" screen they sold him (1080p), He actually got mad at me for telling him this because they guys at the store told him it would game great and was fast...

i got him to come over to my house and try my system, he was quite mad when he found my system to be like lightning to his systems turtles stampeding thru peanut butter in January....

note: this office system im on smokes his, and its just a 9650@2.7 and 8gb ddr2 with a 8800gts512......

so he ordered the ram and gpu (he got a great deal on a 5770, under 80bucks on sale), I installed it for him, he was shocked how much better windows ran, let alone wow, now hes talking about cpu upgrades....on a system thats less then a year old that some smuck at bestbuy sold him to play wow on...ROFL......(think im gonna tell him to just get a board/cpu combo and a psu, the case is nice, just really bad liteon psu and horrible motherboard...)

meh, long story short, most users are idiots you could give a system running windows 8 on arm and as long as they could run ms office and IE they would be happy and not know the dif between that and their x86 system....

as to this dozer situation, I will wait and see how things flush out, i mean its not that big a deal to wait a bit and see if the windows patch shows up and boosts perf and to see how BD actually preforms.

I have little to no use for cinbench, its compiled with ICC using commands that make it use the intel cpu dispatcher, meaning AMD chips automatically get slower code paths then intels.
10-10-2011, 12:58 PM
Pantsu

Quote:

Originally Posted by Hondacity

how many nailbiting hours before nda lifts? are we following eastern time or when oct12 hits one country?

It's noon EST.

I like how people take it as black or white depending on what one preview test result says and how it's suddenly what justifies the price tag. There's no doubt logic behind AMD's pricing. FX *will* perform in some cases at least between 2500K and 2600K. More than likely it's the 8 thread applications that take full advantage of the architecture. This and the fact that it's the brand new flagship is enough to justify the price at launch at least. FX-8120 might be much more reasonable in terms of price/performance for the avarage gamer/overclocker (compare for example 955BE and 980BE). The question is how AMD's single thread perfomance works (or doesn't) with module architecture and slightly upped clocks. If lab501 results are true, it looks like the extra clocks are nowhere high enough to compensate the loss in IPC. Either they missed the clocks due to power/temp/whanot issues and/or the architecture just takes a much bigger hit than what they expected compared to Stars.
10-10-2011, 01:26 PM
Dumo

Quote:

Originally Posted by SoF

when we were playing BD a week ago we were looking at each other like "omg this is it?" - 6500+ and the scores were still as ugly as dinos in his summer-suit -.-
Everybody went back to Sandy and GT systems like half an hour later :ROTF:

Lol....Dang, if 6.5Ghz 8C/8T Vantage and '06 runs suck then it will be very sad:(
10-10-2011, 01:31 PM
informal

I don't know what,but imo something just doesn't add up.
10-10-2011, 01:36 PM
Tha Last Meal

1 Attachment(s)

guys i have the First picture of the amd Bulldozer :eek:
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.

Attachment 121061

:rofl:
10-10-2011, 01:38 PM
radaja

Quote:

Originally Posted by informal

I don't know what,but imo something just doesn't add up.

what you talking about willis?
10-10-2011, 01:49 PM
vinta

Quote:

Originally Posted by Tha Last Meal

guys i have the First picture of the amd Bulldozer :eek:
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.

Attachment 121061

:rofl:

:rofl: :rofl: :rofl:
10-10-2011, 02:15 PM
Kuroimaho

Quote:

Originally Posted by Tha Last Meal

guys i have the First picture of the amd Bulldozer :eek:
:rofl:

:clap:But it plays smooth jazz so well, just wait and see everybody who will own it will praise it for the smoothness.
10-10-2011, 02:20 PM
radaja

is cpu-z just not updated correctly(maybe franck) forgot something?
codename still reads bulldozer,isnt that wrong?shouldnt it be zambezi?
10-10-2011, 02:30 PM
Oliverda

Quote:

Originally Posted by Hornet331

the queston was answered, amd said ~3%

It's more than 3%.
10-10-2011, 02:39 PM
FischOderAal

Quote:

Originally Posted by Oliverda

It's more than 3%.

AMD themselves said up to 3 percent...
http://permalink.gmane.org/gmane.linux.kernel/1172226
10-10-2011, 02:44 PM
Oliverda

Quote:

Originally Posted by FischOderAal

AMD themselves said up to 3 percent...
http://permalink.gmane.org/gmane.linux.kernel/1172226

I'm talking about Windows.;)

mod: Anyway you can try the patch easily becuase Win 8 already contains it.
10-10-2011, 02:52 PM
saint19

Quote:

Originally Posted by radaja

is cpu-z just not updated correctly(maybe franck) forgot something?
codename still reads bulldozer,isnt that wrong?shouldnt it be zambezi?

Maybe, if you look some current cpuz reports all the 9xx mobos are reported with 850sb

Sent from my Android using TapaTalk
10-10-2011, 02:53 PM
SKYMTL

Quote:

Originally Posted by Gilgamesh

Just a little question: for Bulldozer you will adopt same metodolgy and programs of your last review here?
hardwarecanucks.com/forum/hardware-canucks-reviews/44339-intel-core-i3-2120-core-i5-2400-lga1155-processors-review-4.html

I like it.

It has been substantially expanded actually. :)

Quote:

Originally Posted by AzureSky

as I understand it, theres a patch for windows either incoming or already in the hands of some testers.

If the "patch" would work without breaking a million other things, you can bet that AMD would be actively pushing it to reviewers. They aren't, which should say a LOT about its viability and its compatibility with Bulldozer rather than Piledriver...

People seem to forget that Boris posted these patches for Thurban as well: https://lkml.org/lkml/2010/3/22/336 Did any of these ever amount to anything substantial on the Windows platform? No and no.
10-10-2011, 03:16 PM
Oliverda

Quote:

Originally Posted by slaveondope

http://i53.tinypic.com/15hbodu.jpg

...
10-10-2011, 03:20 PM
Hornet331

Quote:

Originally Posted by Oliverda

I'm talking about Windows.;)

mod: Anyway you can try the patch easily becuase Win 8 already contains it.

We know nothing about windows (7) and you are talking about the rewritten task scheduler (which of course includes the patch but is also a lot different from the one in win7), but windows 7 wont get that scheduler.
10-10-2011, 03:26 PM
Oliverda

Quote:

Originally Posted by Hornet331

We know nothing about windows (7) and you are talking about the rewritten task scheduler (which of course includes the patch but is also a lot different from the one in win7), but windows 7 wont get that scheduler.

I hope that you didn't include me in your "we". :)
10-10-2011, 03:37 PM
Hornet331

So tell me do you know the performance increase the patch will give you on win7 vs an unpatched version?

And pls no NDA BS since a percentage from a unknown number is still unknown.

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

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

XtremeSystems