Friday, January 13th 2012

AMD FX-8150 Tested with Latest Windows Hotfixes, Still No Improvement

German tech website TweakPC did a before-after comparison of applying Microsoft's recently-released KB2645594 + KB2646060 Windows updates, which intend to improve performance of systems running AMD FX processors, by improving the way in which the OS deals with Bulldozer cores, using a top-of-the-line FX-8150 processor. The reviewer put FX-8150 through synthetic tests such as AIDA64 (CPU benchmarks, FPU benchmarks), Cinebench 11.5, MaxxPi (multi-threaded PI calculations), WPrime, Twofish AES, 3DMark (Vantage and 11), ComputeMark; and some real-world tests such as WinRAR, Resident Evil 5, and Battleforge. Barring Resident Evil 5, where the patched FX-8150 produced 4% higher performance and WinRAR, where it produced 3% higher performance, there were no significant performance gains noticed. The review can be accessed at the source.

Source: TweakPC.de
Add your own comment

165 Comments on AMD FX-8150 Tested with Latest Windows Hotfixes, Still No Improvement

#1
erocker
seronx said:
http://www.cray.com/Home.aspx

No, I am talking about super computing

K15 is bred from a long heritage of super computers
I understand your point however thats not what most members, including myslelf are concerned with or talking about.
Posted on Reply
#2
BeepBeep2
Did seronx claim the chipset was the limiting factor in gaming performance earlier?
I spewed OJ all over my keyboard. That's stupidity (no, not ignorance!) at it's best.

"Bulldozer has a faster architecture" - are you serious? So because it has more jiggahurtz it is a faster architecture and the chipset is the problem? Because it has an IMC that pulls more bandwidth, the chipset is the problem? Get real...

Attain knowledge.

AMD has an extremely robust platform since 790FX, which 890 and 990 are evolutions of. NVIDIA had the crown in the AM2 era with nforce 500 series.

Furthermore, rasing HT clock to 3GHz + doesn't gain you any performance except in IGP scenarios (think 790GX/890GX), in which case AMD now has Hudson FCH for their APUs and elimated on-board GPU from their 9-series chipsets.
Posted on Reply
#3
seronx
Damn_Smooth said:
Can I have some of what you're smoking? I don't know what it is, but it's obviously a pretty good departure from reality. I don't care about instruction sets, integers, clock speeds or anything. I care about what CPU drives games better. Can you find a game that is better serviced by BD? I'll wait here.
Any game that doesn't use x87 code
Avoid Havok, Physx(CPU), and Bullet

You might ask why Bullet? Well the benchmarks that use it compile it with ICC

Also, Any game that uses 64bit

So, go find a game that uses 64bit...I bet you'll have a hard time...do to the Blueness

brandonwh64 said:
HMM doesn't seem like they would be good for super computing seen that they fail in mathematical computing.

http://www.bit-tech.net/hardware/cpus/2011/11/14/intel-sandy-bridge-e-review/4
Intel C++ Compiler for both

You are going to have to use SPEC for benchmarks when talking about actual performance in Supercomputing

erocker said:
I understand your point however thats not what most members, including myslelf are concerned with or talking about.
Well, Supercomputers usually have the fastest processor and there is a reason Bulldozer is slightly still based on Alpha

BeepBeep2 said:
Did seronx claim the chipset was the limiting factor in gaming performance on this page?
I spewed OJ all over my keyboard. That's stupidity (no, not ignorance!) at it's best.

"Bulldozer has a faster architecture" - are you serious? So because it has more jiggahurtz it is a faster architecture and the chipset is the problem? Because it has an IMC that pulls more bandwidth, the chipset is the problem? Get real...

Attain knowledge.

AMD has an extremely robust platform since 790FX, which 890 and 990 are evolutions of.

Furthermore, rasing HT clock to 3GHz + doesn't gain you any performance except in IGP scenarios (think 790GX/890GX), in which case AMD now has Hudson FCH.
Oh GOD BeepBeep I've been waiting for you I've been seeing your retarded posts at xtremesystems oh my...

You have no idea what you are talking about....

HT Clock is still below 4.4GHz, learn to read

Every time I read your posts at xtremesystems I regurgitate a little

I bet you have an awful sense of what IPC is as well oh wait I already saw your IPC tree of wrongliness when going from K8 to K15...IPC didn't decrease with Bulldozer, broski
Posted on Reply
#4
Super XP
seronx said:
Well February 2nd will prove everything

If Bulldozer is still in the roadmaps I am right if it isn't in the roadmaps I am wrong

But, I have a four out of five chance of being correct

http://ir.amd.com/phoenix.zhtml?c=74093&p=irol-EventDetails&EventId=4203026

Regardless, Bulldozer has won
brandonwh64 said:
Just admit it seronx.... Bulldozer failed... Its ok, the first step to recovery is acceptance!
Your opinion of course. Bulldozer may not have lived up to the hype, but in no its a fail.
Was the P4 a fail? Absolutely not because Intel sold a dump load of them, just like AMD selling its FX line very well.

Does Bulldozer need some work? Absolutely. But calling it fail is short sited. Price/Performance currently is great for FX CPU's.
Posted on Reply
#5
eidairaman1
Ya know People should respect eachother here regardless if they are wrong or not and not insult one another.
Posted on Reply
#6
TheLaughingMan
seronx said:
False erocker

It's the chipset

You simply don't know what you are talking about anymore

Bulldozer has a faster architecture and a faster IMC than Sandy Bridge

http://www.extremetech.com/wp-content/uploads/2011/11/SandraMemory.png

Vishera has 4 64bit Memory Controllers meaning it will compete with Ivy Bridge-E and Sandy Bridge-E
There seems to be something very wrong with your chart. As I recall it should look more like this:

Posted on Reply
#7
seronx
eidairaman1 said:
Ya know People should respect eachother here regardless if they are wrong or not and not insult one another.
I'm just repaying BeepBeep because I had to go through his awful factoids about what he thinks Bulldozer is

http://www.xtremesystems.org/forums/showthread.php?277474-NaySa...BeepBeep-s-FX-8150-has-arrived!-Box-photos...

*holds it in*

TheLaughingMan said:
There seems to be something very wrong with your chart. As I recall it should look more like this:
The Sandy Bridge processor isn't using 1866MHz RAM 20GB/s-24GB/s is impossible on Dual Channel unless you use 2400+ MHz Ram
Posted on Reply
#8
BeepBeep2
seronx said:

Oh GOD BeepBeep I've been waiting for you I've been seeing your retarded posts at xtremesystems oh my...

You have no idea what you are talking about....

HT Clock is still below 4.4GHz, learn to read

Every time I read your posts at xtremesystems I regurgitate a little

I bet you have an awful sense of what IPC is as well oh wait I already saw your IPC tree of wrongliness when going from K8 to K15...IPC didn't decrease with Bulldozer, broski
HT Clock? On BD it is 2200 MHz, 4400 MT/s. The chipset is not the limitation. Raising the bus speed doesn't change performance.

I'll again pull up this diagram:


Where is the chipset bottleneck? Why does a Phenom II X6 CPU on 790/890990FX @ 4.2 GHz play games faster than AMD FX-8150 @ 4.6 GHz on 990FX? Must be the chipset, because the architecture is "faster".

Instructions per clock decreased with Bulldozer.

IPC increased from K8 > Bulldozer.
IPC decreased from Family 10h > Bulldozer.

You are the one which can not read.

Acquire knowledge.

EDIT:
I see you revised your post. Too bad I'd already replied to the original.

seronx said:
I'm just repaying BeepBeep because I had to go through his awful factoids about what he thinks Bulldozer is

http://www.xtremesystems.org/forums/showthread.php?277474-NaySa...BeepBeep-s-FX-8150-has-arrived!-Box-photos...

*holds it in*




The Sandy Bridge processor isn't using 1866MHz RAM 20GB/s-24GB/s is impossible on Dual Channel unless you use 2400+ MHz Ram
My CPU
A. Overclocked poorly, was buggy
B. Did not run stock settings on stock cooler with normal vdroop

I RMA'ed and now have a CPU that actually does. I quite like it, to be honest.
Posted on Reply
#9
seronx
BeepBeep2 said:

Instructions per clock decreased with Bulldozer.

IPC increased from K8 > Bulldozer.
IPC decreased from Family 10h > Bulldozer.

You are the one which can not read.

Acquire knowledge.
Nope it is still the same K8 = K10 = K15 there is no drops and with K15 20h-2Fh you will have K8 = K10 < K15

Acquire knowledge. Thou who canst read!
Posted on Reply
#10
brandonwh64
Addicted to Bacon and StarCrunches!!!


Can we please close this thread, It already served it purpose and Its obviously getting deep in here

Super XP said:
Your opinion of course. Bulldozer may not have lived up to the hype, but in no its a fail.
Was the P4 a fail? Absolutely not because Intel sold a dump load of them, just like AMD selling its FX line very well.

Does Bulldozer need some work? Absolutely. But calling it fail is short sited. Price/Performance currently is great for FX CPU's.
I just had to troll him due to his crazy posts throughout this thread.
Posted on Reply
#12
TheLaughingMan
seronx said:
The Sandy Bridge processor isn't using 1866MHz RAM 20GB/s-24GB/s is impossible on Dual Channel unless you use 2400+ MHz Ram
To believe your bullshit or my tests??? That is a hard decision. You are a mad man and need get back your medication soon.

I am done. I am going to go play some games on my Bulldozer.
Posted on Reply
#13
seronx
eidairaman1 said:
im not singling out no one as this applies to everyone in this thread. There is no need for insulting eachother in this forum n when people do it makes them seem unprofessional and extremely uncouth.
There is no way to be professional about this subject it pretty much is politics

You have Bulldozer and Sandy Bridge performance in a margin of 5% of each other in benchmarks

The argument will always end up in a way talking about how Republicans are better than democrats
Posted on Reply
#14
trickson
OH, I have such a headache
brandonwh64 said:
http://dl.dropbox.com/u/34835733/Programming/Untitled.png

Can we please close this thread, It already served it purpose and Its obviously getting deep in here



I just had to troll him due to his crazy posts throughout this thread.
I just about pissed myself !!! :roll: That is just too funny !!!
Posted on Reply
#15
BeepBeep2
seronx said:
Nope it is still the same K8 = K10 = K15 there is no drops and with K15 20h-2Fh you will have K8 = K10 < K15

Acquire knowledge. Thou who canst read!
Per clock, per thread, K15 services less instructions every clock cycle than K8 and 10h. This is the reason for lower gaming performance. Instructions per clock has decreased, however over time has increased 10% over K8 + a lot of clock speed.

Have a jolly day, and I apologize for telling you to read and acquire knowledge.
:toast:

seronx said:
There is no way to be professional about this subject it pretty much is politics

You have Bulldozer and Sandy Bridge performance in a margin of 5% of each other in benchmarks

The argument will always end up in a way talking about how Republicans are better than democrats
In some benchmarks, the difference is up to 80%.
Posted on Reply
#16
brandonwh64
Addicted to Bacon and StarCrunches!!!
seronx said:
The Sandy Bridge processor isn't using 1866MHz RAM 20GB/s-24GB/s is impossible on Dual Channel unless you use 2400+ MHz Ram
Posted on Reply
#17
trickson
OH, I have such a headache
seronx man you need to chill out you are getting no were man ! BD is just not what you think or want to make it out to be face it man . The patch worked so it was not the best fix for a shitty CPU !
Posted on Reply
#18
seronx
BeepBeep2 said:
Per clock, per thread, K15 services less instructions every clock cycle than K8 and 10h.

Have a jolly day, and I apologize for telling you to read and acquire knowledge. :toast:
Now you are using the broad definition of instruction great...

K15 has 4 IPC per core it has 4 Execution units to process those instructions so 4 IPC 4 x 3.9 GHz = 15.6 IPS

K10 has 6 IPC per core it has 3 Executions units per clock to process those instructions so 3 IPC 3 x 3.7GHz = 11.7 IPS

Well good riddance retard

You can only have high IPS when you have a good clock rate and good IPC

BeepBeep2 said:

In some benchmarks, the difference is up to 80%.
Which is because of ICC

brandonwh64 said:
http://img.techpowerup.org/111217/maxxmem.jpg
That is MaxxMem not SiSoft
Posted on Reply
#19
trickson
OH, I have such a headache
seronx said:
Now you are using the broad definition of instruction great...

K15 has 4 IPC per core it has 4 Execution units to process those instructions so 4 IPC 4 x 3.9 GHz = 15.6 IPS

K10 has 6 IPC per core it has 3 Executions units per clock to process those instructions so 3 IPC 3 x 3.7GHz = 11.7 IPS

Well good riddance retard

You can only have high IPS when you have a good clock rate and good IPC



Which is because of ICC
DUDE really ? You brought this on yourself !
Posted on Reply
#20
eidairaman1
seronx said:
There is no way to be professional about this subject it pretty much is politics

You have Bulldozer and Sandy Bridge performance in a margin of 5% of each other in benchmarks

The argument will always end up in a way talking about how Republicans are better than democrats
Im already at the point of not giving a flying fuck who is better than the other. I stick to my guns n no one can change me just like i cant change no one here. I cant fore anything on anyone like several members of this website try to do. I can only provide suggestions/solutions and problem solving techniques. This same shit is what made me disappear for a year.
Posted on Reply
#21
BeepBeep2
seronx said:
Now you are using the broad definition of instruction great...

K15 has 4 IPC per core it has 4 Execution units to process those instructions so 4 IPC 4 x 3.9 GHz = 15.6 IPS

K10 has 6 IPC per core it has 3 Executions units per clock to process those instructions so 3 IPC 3 x 3.7GHz = 11.7 IPS

Well good riddance retard

You can only have high IPS when you have a good clock rate and good IPC



Which is because of ICC

That is MaxxMem not SiSoft
We've been discussing Instructions Per Cycle, not Instructions Per Second. Furthermore, my "idiot wrongliness" chart on XS defined real world performance to achieve performance differences in Instructions Per Cycle.

The amount of "execution units" you are talking about (FPU units), 15h has four 256-bit FPU and 10h has six 128bit. BD has essentially 8 128-bit FPU units through Flex-FP however they service less Instructions Per Cycle than 10h. FX-6100 never really wins in the real world vs 1100T does it?

"Good riddance retard"? Nice one. Your calculations are wrong and you don't know what you are talking about.

By the way, most people measure bandwidth with AIDA Extreme Edition (Used to be Lavalys Everest.).

Sisoftware Sandra reads up to 20GB/s on Phenom II depending on overclocks and Everest will only read 12GB/s.

Again:
K15 has 4 IPC per core it has 4 Execution units to process those instructions so 4 IPC 4 x 3.9 GHz = 15.6 IPS

K10 has 6 IPC per core it has 3 Executions units per clock to process those instructions so 3 IPC 3 x 3.7GHz = 11.7 IPS

Well good riddance retard
FPU decode width:
Phenom II - 3 wide in single thread
Bulldozer - 4 wide 256bit, 2 wide 128 bit

4 256-bit IPC (select programs like 256-bit AVX) / clock on BD, 2 128-bit IPC / clock
3 128-bit IPC / clock on Phenom II

8 "cores" threads * 2 FMAC = 16
6 cores * 3 FMAC = 18

BD can only execute 4 256-bit FMAC at once, so 4 "cores" / threads * 4 FMAC = 16. For 256-bit FMAC, BD is essentially a quad core CPU. Integer and normal 128-bit FMAC however BD acts as an 8 core and is marketed as such.

So you need 12.5% extra clockspeed over Phenom II to make it's 8 128-bit FMAC threads = 6 Phenom II FPU threads, and 50% extra clockspeed over Phenom II to make its 6 = 6. I'm not sure if you noticed, but Phenom II's turbo never works for one, and applies to only 1 thread. Turbo on BD is 3.9 up to all cores and 4.2 on one. In benchmarks with Turbo enabled, BD spends 80% of its time at 3.9 while X6 is stuck at 3.3. That's an 18% difference, so BD's performance often wins when all 8 cores are used. Congrats! ...right?

On BD, IPC decreases. This translates to real world performance, which only increases in applications that use 256-bit FMAC (ie. 256-bit AVX)

Then you have integer calculations...which also play into real world performance.
Posted on Reply
#22
brandonwh64
Addicted to Bacon and StarCrunches!!!
seronx said:
The Sandy Bridge processor isn't using 1866MHz RAM 20GB/s-24GB/s is impossible on Dual Channel unless you use 2400+ MHz Ram
seronx said:
That is MaxxMem not SiSoft
better for you?

Posted on Reply
#23
Damn_Smooth
seronx said:
Any game that doesn't use x87 code
Avoid Havok, Physx(CPU), and Bullet

You might ask why Bullet? Well the benchmarks that use it compile it with ICC

Also, Any game that uses 64bit

So, go find a game that uses 64bit...I bet you'll have a hard time...do to the Blueness
So basically, don't play any games that are out or in development and BD will be a great CPU. Well, since I already acknowledged that earlier, that's not really a point.

My point is that Intel is clearly a far superior solution for gaming right now, and will be for quite some time. If not indefinitely.
Posted on Reply
#24
Dent1
brandonwh64 said:
From any benchmarks I have seen, sandy bridge beats bulldozer and thuban in every gaming bench I have seen. Unless your talking AMD the GPU side then you must be mistaken.
Think that is a little farfetched. I can dig out a couple of benchmarks where Bulldozer beats out the Sandy, Battlefield 3. I've even seen the Phenom II X6 Thubans beat the Sandy in that gaming benchmark.

Damn_Smooth said:
So basically, don't play any games that are out or in development and BD will be a great CPU. Well, since I already acknowledged that earlier, that's not really a point.

My point is that Intel is clearly a far superior solution for gaming right now, and will be for quite some time. If not indefinitely.
I agree with your overall statement, but disagree where you say "any". You are basically implying that bulldozer is incapable of playing games, which is false.

If somebody does 80% encoding, and 20% gaming. Bulldozer is still a good choice. So that contracticts your "any" statement.
Posted on Reply
#25
Damn_Smooth
Dent1 said:
Think that is a little farfetched. I can dig out a couple of benchmarks where Bulldozer beats out the Sandy, Battlefield 3. I've even seen the Phenom II X6 Thubans beat the Sandy in that gaming benchmark.



I agree with your overall statement, but disagree where you say "any". You are basically implying that bulldozer is incapable of playing games, which is false.

If somebody does 80% encoding, and 20% gaming. Bulldozer is still a good choice. So that contracticts your "any" statement.
True, it can handle games fine, but price/performance against Intel in gaming is a sure loss for AMD.
Posted on Reply
Add your own comment