Higher Clock Speeds, No TLB Issues and Better Pricing: The New Phenom
by Anand Lal Shimpi on March 27, 2008 12:00 AM EST- Posted in
- CPUs
The Test
| CPU: | AMD Phenom 9850 (2.5GHz) AMD Phenom 9750 (2.4GHz) AMD Phenom 9550 (2.2GHz) AMD Phenom 9600 (2.3GHz) AMD Phenom 9500 (2.2GHz) Intel Core 2 Quad Q9300 (2.50GHz/1333MHz) Intel Core 2 Quad Q6600 (2.40GHz/1066MHz) Intel Core 2 Duo E8200 (2.66GHz/1333MHz) Intel Core 2 Duo E6750 (2.66GHz/1333MHz) |
| Motherboard: | ASUS P5E3 Deluxe (X38) MSI K9A2 Platinum (790FX) |
| Chipset: | Intel X38 AMD 790FX |
| Chipset Drivers: | Intel 8.1.1.1010 (Intel) AMD Catalyst 8.3 |
| Hard Disk: | Western Digital Raptor 150GB |
| Memory: | Corsair XMS2 DDR2-800 4-4-4-12 (1GB x 2) Corsair XMS3 DDR3-1066 7-7-7-20 (1GB x 2) |
| Video Card: | eVGA GeForce 8800 GT SSC |
| Video Drivers: | NVIDIA ForceWare 169.25 |
| Desktop Resolution: | 1920 x 1200 |
| OS: | Windows Vista Ultimate 32-bit |
Our Stance on Testing with the TLB Bug
The B2 stepping Phenoms suffer from the infamous TLB erratum which, if left unpatched, could potentially result in system instability or silent data corruption. Thus far AMD has only seen negative after effects from unpatched B2 processors in very isolated cases, described to AnandTech as the following:
1) Windows Vista 64-bit running SPEC CPU 2006
2) Xen Hypervisor running Windows XP and an unknown configuration of applications
While these are both isolated cases, they are by no means the only scenarios in which the TLB bug could rear its ugly head. All of the latest Socket-AM2+ motherboards have been updated to fix the TLB bug, at the expense of sometimes significant performance degradation. The table below summarizes our findings in our initial B3 stepping article:
| SYSMark 2007 | DivX | CineBench R10 | 3dsmax 9 | WinRAR | |
| AMD Phenom 9600 (B2 Stepping) - TLB Fix Disabled | 117 | 74.3 fps | 7396 | 7.20 | 1348 KB/s |
| AMD Phenom 9600 (B2 Stepping) - TLB Fix Enabled | 105 | 72.0 fps | 7031 | 6.47 | 367 KB/s |
| Performance Impact | -10.3% | -3.1% | -4.9% | -10.1% | -72.8% |
Since the bug could prove to be a problem in usage scenarios that haven't yet been discovered, we feel that it's best to test these B2 stepping chips with the TLB fix enabled (the default state on all motherboards now). Obviously this doesn't impact the new xx50 CPUs since they aren't plagued by the TLB erratum.
Facebook
Twitter
RSS
65 Comments
View All Comments
ap90033 - Thursday, March 27, 2008 - link
Amen brother, I had the Athlon 64 when it ruled, but now i have E8400 since it smokes AMD's best...So I guess I am an AMD/Intel Fan BOY!!!
No offense but this artlicle had a very strong slant towards AMD, even though Intel destroys their newest and best with a 1+ year old chip. Dont you find that the least bit odd....? If anyone is sounding like a "Fanboy" I would say it would have to be you Mr. Crusader for AMD. LOL
Dude when you get to where I am you will see, it doesnt matter what the fluff is, get the FACTS and decide with your dollars there... Sheesh...
AssBall - Thursday, March 27, 2008 - link
I thought it was a very well written article. I didn't get any OMGAMDFTW out of it like you apparently did. Your "Man" would not be up already if AMD wasn't still churning these new procs out. Good luck finding those special Intel prices then.Olaf van der Spek - Thursday, March 27, 2008 - link
> We get the impression that there are some speed paths that could be optimized on the current B2 and B3 Phenoms that simply aren't because of a very sensible thought process.I'm wondering why those speed paths haven't been fixed before the first launch. Certainly it wasn't good for AMD to only introduce them at low clock frequencies.
Visual - Thursday, March 27, 2008 - link
It's really disheartening for a "fanboy" like me to see AMD beaten all over the board again.I may very well build a system or two with AMD parts because of the 780G chipset and its great budget video performance, but for a full-blown performance system i'll certainly go with Intel now.
AMD better hurry up with their 45nm tech, its way overdue.
Griswold - Thursday, March 27, 2008 - link
"AMD better hurry up with their 45nm tech, its way overdue."You're right, Intel has been selling 45nm parts for like a year now... oh wait, no they havent.
If you meant overdue as in they need it to (hopefully) achieve higher clock speeds and lower power consumption in addition to lower production cost, then you got that right.
If they keep their schedule with 45nm, they will have narrowed the gap between process shrinks vs. intel a bit again - which is good. But things like that dont happen overnight.
MoonRocket - Thursday, March 27, 2008 - link
Can anyone identify the case on the 3ghz where are you page?Looks interesting.
AmberClad - Thursday, March 27, 2008 - link
It looks like the CoolerMaster Stacker 830 to me.dnz - Thursday, March 27, 2008 - link
We musn't forget how great an overclocker the Q6600 is. My system is running at 3.2GHz (8x400) and I'm using cheap DDR2-800 RAM. The Q9300 may have some advantages but overclocking it is going to require some VERY expensive RAM.Griswold - Thursday, March 27, 2008 - link
First you'll need an good mobo that can deliver high FSB for these 45nm quads. RAM is secondary (can always use a divider if needed).ui5200 - Thursday, March 27, 2008 - link
Maybe this will cause intel to finally release the latest Dual and Quad core chips (oh like the E8400 that's been 'out of stock' for months)? Or is this another paper launch ?