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
Casecutter
I see it as TheMailMan78 posting yesterday said "initial testing of the upcoming Windows 8 operating system, we’ve seen performance improvements of up to 10% in some applications, when compared to Windows 7". Are these "patches" actually able to replicating what a complete and final Win8 architecture improvments offer? Are these just a rehash of what Beta Win8 has, and as AMD and Microsoft collaborate furthure they will find 10% here and there.

Then today btarunr finds one site that ran a few tests (obviously not all the software AMD has at their disposal) and then claim is "Still No Improvement"... typical misleading banter.

First AMD should conduct a complete battery of tests and provide results and work in partnership with Microsoft to say within the confines of Win7 this is what such patches can impart. Nothing wrong with that, while just shut-up about Win8, and keep that in their back pocket till Win8 is really relevant.
Posted on Reply
#2
Deadlyraver
I think there needs to be more patching done with this, Bulldozer is still a nice solution for its clock speed and overclocking headroom however fails to maintain purpose in performance solutions. I guess the problem here is that AMD gets too focused on trying to lead an idea, which eventually compromises their marketing goals. Perhaps too early release to counter Sandy-Bridge?
Posted on Reply
#3
Dent1
Deadlyraver said:
I think there needs to be more patching done with this, Bulldozer is still a nice solution for its clock speed and overclocking headroom however fails to maintain purpose in performance solutions. I guess the problem here is that AMD gets too focused on trying to lead an idea, which eventually compromises their marketing goals. Perhaps too early release to counter Sandy-Bridge?
As far as single threaded applications go. I think we Piledriver will be enough to counter Sandybridge. Because, in TPU's 7970 review Bulldozer seems on par with the 920 Nelham for the most part. After Bulldozer's B3 stepping, Piledriver offers 20-30% performance increase ontop (AMD's estimate). This should be enough to close the Sandy Bridge gap whilst continuing to nullify Sandy in multithreading too.

Although, it might be too late as Ivy Bridge is around the corner and is likely to close the gap again. AMD will have to release Piledriver same price or cheaper.
Posted on Reply
#4
trickson
OH, I have such a headache
Deadlyraver said:
I think there needs to be more patching done with this, Bulldozer is still a nice solution for its clock speed and overclocking headroom however fails to maintain purpose in performance solutions. I guess the problem here is that AMD gets too focused on trying to lead an idea, which eventually compromises their marketing goals. Perhaps too early release to counter Sandy-Bridge?
You can not just patch performance into a CPU ! Jesus , If it was just an issue as a patch then we wouldn't need to have new CPU's they could just patch the performance into them ! This just makes no sense to me at all . :confused::twitch::banghead:
Posted on Reply
#5
Syborfical
Bulldozer one of the biggest Epic fails in PC history.
Posted on Reply
#6
trickson
OH, I have such a headache
Syborfical said:
Bulldozer one of the biggest Epic fails in PC history.
No 2nd did you forget about netburst and P4 ?
Posted on Reply
#7
Suhidu
trickson said:
You can not just patch performance into a CPU ! Jesus , If it was just an issue as a patch then we wouldn't need to have new CPU's they could just patch the performance into them ! This just makes no sense to me at all . :confused::twitch::banghead:
I understand it would break the way the market for x86 CPUs currently works, but consider that they can release occasional patches, and it still wouldn't prevent them from selling upgrades. Imagine a "Service Pack" paradigm, like Microsoft has with its Operating Systems. We'd get a few significant updates over the life of the product, and a new product in no more than a half a decade.

It'd shatter the way CPUs have been sold for decades, but AMD needs to help Bulldozer from every angle it can integrate into its VISION.
Posted on Reply
#8
trickson
OH, I have such a headache
Suhidu said:
AMD needs to help Bulldozer from every angle it can integrate into its VISION.
They should then start over . This is just not going to get fixed by patching the OS . It would seem to me the lack of performance that AMD users are having is not due to an OS but hardware . Though there is a 10% increase in performance with the patch , I truly think that it is not going to get any better than that . Sad that AMD could not beat sandy bridge as every one so wanted it to do but this is a fact so again no patch will fix that !
Posted on Reply
#9
ensabrenoir
Wow....people are really passionate about the intel must fall thing..... Bd cant go core for core with intel.....and with whats coming.......its over. Amd knows where its strength lies.... Gpus and low poweed apus. Thats amds fututer thats where the rule....for now.
Posted on Reply
#10
BeepBeep2
The low level of intelligence of a lot of people posting in these threads here is worrying.

The patch puts 1 thread on its own module, up to 4 threads. You get the same effect as shutting off every other core in BIOS leaving 1 FPU (BD has 4) to 1 thread instead of making it work on 2.

Here are my test results on my own system from Dec 16th when the first patch (KB2645594 only, then was removed)came out:
As you can see, 8 thread performance was lowered a few percent, so the patch was removed and now two patches are coupled.

Test System:
AMD Eight Core FX-8150 @ 4.69Ghz / 2.51Ghz CPU-NB
2x2GB DDR3-2133 CAS 7-10-7-27 160ns 1T
ASUS Crosshair V Formula
2x Western Digital Caviar Black 640GB WD6401AALS in RAID 0
XFX Black Edition 850w (Seasonic 850w M12D) 80 Plus Silver
2x AMD HD5770
Windows 7 Professional 64-bit SP1

Core Parking ON

wPrime 32M v1.55 -

1 Thread: 44.896 sec
2 Thread: 22.586 sec
3 Thread: 15.114 sec
4 Thread: 11.684 sec
5 Thread: 10.017 sec
6 Thread: 8.815 sec
7 Thread: 7.938 sec
8 Thread: 7.673 sec

1 to 4 Thread Ratio: 3.842x
2 to 4 Thread Ratio: 1.933x

1 to 8 Thread Ratio: 5.851x
4 to 8 Thread Ratio: 1.523x

Non-patched wPrime 32M v1.55:
1 Thread: 45.116 sec
2 Thread: 22.869 sec
3 Thread: 15.725 sec
4 Thread: 12.098 sec
5 Thread: 10.640 sec
6 Thread: 8.924 sec
7 Thread: 7.831 sec
8 Thread: 7.410 sec

1 to 4 Thread Ratio: 3.729x
2 to 4 Thread Ratio: 1.890x

4 to 8: 1.632x


Cinebench R11.5 -

1 Thread: 1.16 pts
2 Thread: 2.30 pts
3 Thread: 3.42 pts
4 Thread: 4.44 pts
5 Thread: 5.31 pts
6 Thread: 6.14 pts
7 Thread: 6.93 pts
8 Thread: 7.68 pts

1 to 4 Thread Ratio: 3.82x
2 to 4 Thread Ratio: 1.93x

1 to 8 Thread Ratio: 6.62x
4 to 8 Thread Ratio: 1.72x

4 thread Cinebench R11.5 unpatched:
4.30 pts

Patched:
4.44 pts

7-Zip 9.20 - AES-256 Encrypted 10 Char. Password - 1003MB 200 File JPEG deflate to .ZIP

1 Thread: 8:14s (494s) 2030 KB/s
2 Thread: 4:12s (252s) 3980 KB/s
3 Thread: 2:46s (166s) 6040 KB/s
4 Thread: 2:15s (135s) 7430 KB/s
5 Thread: 1:52s (112s) 8955 KB/s
6 Thread: 1:38s (98s) 10234 KB/s
7 Thread: 1:29s (89s) 11270 KB/s
8 Thread: 1:21s (81s) 12382 KB/s

1 to 4 Thread Ratio: 3.65x
2 to 4 Thread Ratio: 1.86x

1 to 8 Thread Ratio: 6.09x
4 to 8 Thread Ratio: 1.66x

4 thread Unpatched 7-Zip 9.20:
2:20

Patched:
2:15
Posted on Reply
#11
Disruptor4
The patch appears to be more of a stability fix which enables the CPU to handle the threads better as it was previously putting cores to sleep when it shouldn't etc, which in turn, allows for a more stable FPS count which means a boost to your performance.
I personally would be happy with that, if I had BD. The performance of the processor is still good, especially considering the hardware I currently have. IIRC, they never said it was going to be the best CPU on the market, just they were going to compete better than before, and they are. With this patch, they are making it more stable and giving a slight boost here and there.
Posted on Reply
#12
seronx
Dent1 said:
As far as single threaded applications go. I think we Piledriver will be enough to counter Sandybridge. Because, in TPU's 7970 review Bulldozer seems on par with the 920 Nelham for the most part. After Bulldozer's B3 stepping, Piledriver offers 20-30% performance increase ontop (AMD's estimate). This should be enough to close the Sandy Bridge gap whilst continuing to nullify Sandy in multithreading too.

Although, it might be too late as Ivy Bridge is around the corner and is likely to close the gap again. AMD will have to release Piledriver same price or cheaper.
Orochi-B2 and Orochi-B3 competes with Sandy Bridge-E(294mm² vs 315mm²)
Viperfish-C2 competes with Ivy Bridge-E

Trinity is the one that will compete with Ivy Bridge
Posted on Reply
#13
Damn_Smooth
seronx said:
Orochi-B2 and Orochi-B3 competes with Sandy Bridge-E(294mm² vs 315mm²)
Viperfish-C2 competes with Ivy Bridge-E

Trinity is the one that will compete with Ivy Bridge
Trinity will beat Ivy with IGP, but it's CPU performance will fail hard. I'm not in the market for an IGP right now.
Posted on Reply
#14
seronx
Damn_Smooth said:
Trinity will beat Ivy with IGP, but it's CPU performance will fail hard. I'm not in the market for an IGP right now.
CPU performance won't fail hard...in reality it is pretty much the same minus AVX which will be dependent on the applications then you have case of it being "optimized" for Windows 8...C++ AMP Support and Forced Auto-Vectorization comes with Windows 8(IGP kicks in with C++ AMP and FAV will make FMA3/FMA4 be used more)

IGP performance is true Trinity is about 5x-8x faster than Ivy Bridges IGP
Posted on Reply
#15
tigger
I'm the only one
Syborfical said:
Bulldozer one of the biggest Epic fails in PC history.
And the biggest win is Core 2 Duo, Intel realized what they were doing wrong with netburst, and fixed it in spectacular fashion. Amd need to do the same now.
Posted on Reply
#16
seronx
tigger said:
AMD needs to do the same now.
Not really, Bulldozer has potential just like Netburst....luckily Bulldozer isn't actually aimed at what Netburst was really aimed at

Bulldozer is aiming for a Hetrogeneous design
Netburst was aiming for a Homogeneous design

Netburst will make it's return by Skylake since Haswell still has a 14 stage pipeline

Intel needs Netburst to beat Bulldozer in the later stages...
Posted on Reply
#17
Damn_Smooth
seronx said:
CPU performance won't fail hard...in reality it is pretty much the same minus AVX which will be dependent on the applications then you have case of it being "optimized" for Windows 8...C++ AMP Support and Forced Auto-Vectorization comes with Windows 8(IGP kicks in with C++ AMP and FAV will make FMA3/FMA4 be used more)

IGP performance is true Trinity is about 5x-8x faster than Ivy Bridges IGP
A few months ago, I would have agreed with you. Obviously though, instruction sets don't make up for a lack of per core performance. Then again, I'm only really interested in gaming. AMD does have one hell of a server based architecture.
Posted on Reply
#18
eidairaman1
Deadlyraver said:
I think there needs to be more patching done with this, Bulldozer is still a nice solution for its clock speed and overclocking headroom however fails to maintain purpose in performance solutions. I guess the problem here is that AMD gets too focused on trying to lead an idea, which eventually compromises their marketing goals. Perhaps too early release to counter Sandy-Bridge?
This just means improvements Piledriver will have over First Gen Bulldozer
Posted on Reply
#19
seronx
Damn_Smooth said:
Obviously though, instruction sets don't make up for a lack of per core performance.
You need to look for applications that actually use the ISAs....a lot of people are using older versions of applications which distorts actual performance

Damn_Smooth said:

Then again, I'm only really interested in gaming. AMD does have one hell of a server based architecture.
The gaming partition of everything is majority all our fault and the OEMs/Partners

The Chipset is the limiting factor on Gaming Performance not the architecture
Posted on Reply
#20
eidairaman1
seronx said:
Not really, Bulldozer has potential just like Netburst....luckily Bulldozer isn't actually aimed at what Netburst was really aimed at

Bulldozer is aiming for a Hetrogeneous design
Netburst was aiming for a Homogeneous design

Netburst will make it's return by Skylake since Haswell still has a 14 stage pipeline

Intel needs Netburst to beat Bulldozer in the later stages...
Netburst is what Core i3-7 is.
Posted on Reply
#21
seronx
eidairaman1 said:
Netburst is what Core i3-7 is.
No that is a fusion with 80% Core 20% Netburst

Intel needs 100% Netburst to beat Bulldozer after Excavator

AMD releasing Bulldozer with no optimizations should have been a huge warning to everyone...about the future versions of Bulldozer
(They pretty much ported Sandtiger to 32nm and called it Orochi)
Posted on Reply
#22
ensabrenoir
All sounds familar......can smell the fail from here.
Posted on Reply
#23
erocker
seronx said:
The Chipset is the limiting factor on Gaming Performance not the architecture
Wrong. The architecture of the chip plus its IMC are the limiting factor with gaming performance, not the chipset.
Posted on Reply
#24
trickson
OH, I have such a headache
I think you all need to get back on topic here . The fact is that BD finally has a patch did it improver things for BD YES it did . Did the patch fix the issues BD was having sure . Stability is now corrected , I heard the problem was scheduling that windows was shutting off the cores of the CPU because they were not being used and since this was happening then the CPU would become unstable as it really can only do what it is told to . Now is there the huge performance gain from this No not really are people pissed because they did not get the CPU performance of the Intel sandy bridge ? I do not care ! Thing is the patch works and the CPU is now fixed move on , Nothing to see here now time to move on .
Posted on Reply
#25
seronx
erocker said:
Wrong. The architecture of the chip plus its IMC are the limiting factor with gaming performance, not the chipset.
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



Vishera has 4 64bit Memory Controllers meaning it will compete with Ivy Bridge-E and Sandy Bridge-E
Posted on Reply
Add your own comment