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
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.
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 BluenessIntel C++ Compiler for both
You are going to have to use SPEC for benchmarks when talking about actual performance in SupercomputingWell, Supercomputers usually have the fastest processor and there is a reason Bulldozer is slightly still based on AlphaOh 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
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.
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
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.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.
Acquire knowledge. Thou who canst read!
Can we please close this thread, It already served it purpose and Its obviously getting deep in hereI just had to troll him due to his crazy posts throughout this thread.
I am done. I am going to go play some games on my Bulldozer.
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
Have a jolly day, and I apologize for telling you to read and acquire knowledge. :toast:In some benchmarks, the difference is up to 80%.
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 IPCWhich is because of ICCThat is MaxxMem not SiSoft
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: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.
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.
If somebody does 80% encoding, and 20% gaming. Bulldozer is still a good choice. So that contracticts your "any" statement.