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
165 Comments on AMD FX-8150 Tested with Latest Windows Hotfixes, Still No Improvement
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.
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.
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.
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
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.
Viperfish-C2 competes with Ivy Bridge-E
Trinity is the one that will compete with Ivy Bridge
IGP performance is true Trinity is about 5x-8x faster than Ivy Bridges IGP
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...
The Chipset is the limiting factor on Gaming Performance not the architecture
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)
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