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
The Jedi - Monday, April 7, 2008 - link
I'm pretty much with you, but just to comment on this part:"As for price the q6600 is dropping all over the place... Frys had it for 180 yesterday, Microcenter has it for 200."
It's a common misnomer to see a sale price on something and then get it locked into your head that that price you saw one time is the price you should expect to pay for something from then on. For example if the company that rhymes with hell is advertising a PC with monitor for $299, even if it's THREE DAYS ONLY in the fine print, or like after rebate, people tend to get it stuck in their head that "a new computer" can be had for a mere $300, when a wiser person would know something that cheap would be like 3-year old tech/speed, likely with dead pixels and a 6-bit analog LCD panel, Windows Basic, stuff like that.
Companies sometimes have a sale on one thing hoping you'll buy items with it, which allows them to make money. Just wanted to throw that out there.
bigboxes - Thursday, March 27, 2008 - link
How old are you? What's with all this "ownage" crap you are spewing? Do you really tie in your self worth to the cpu you use (feel free to substitute car, house, salary)? Most of us mature individuals who have actually reached adulthood just want the best performance for our dollar, not ownage just to inflate our e-penis.Nice article.
RamarC - Thursday, March 27, 2008 - link
it's "funny" that anand forgot that the e6750 is $180 (not $266) and that the 3ghz oem e8400 (sans cooler) is in-stock and available for $200. the e8400 would certainly push a couple of phenoms lower on the chart.and it's also "funny" that anand's comparing projected phenom prices (since they aren't available yet) with real street prices. wait until you can get street prices before claiming a better price/performance ration.
Margalus - Thursday, March 27, 2008 - link
apparently you didn't read the article. The amd chip is not as good as intel currently, but they aren't crap.And if you read the article you would have seen that they still recommended and intel cpu for a new system, so it definately wasn't written with payola in mind from amd.
ap90033 - Thursday, March 27, 2008 - link
We read it, cmon you didnt see any slant towards AMD? Come on, be honest :)And it sounded like they were about to cry when they recommended Intel (plus the long in the tooth comments geez, I mean really, Intels old crap sucks and should die but AMDs latest and greatest ALMOST beats Intels crap wow what logic, LOL). Hey I wish AMD were top dog again. I loved the Athlon XP's & 64's. But facts are facts....
hooflung - Thursday, March 27, 2008 - link
Well look at it this way. Enthusiasts do not drive the market. System builders and servers do. AMD is able to bring competitive prices to the OEM channels and that will also translate to the server markets for the Phenom Opteron lineup.AMD is still largely competitive with Intel at the server level with the Phenom where TLB, the now strong point of the Phenom, is implemented better.
To keep your servers sponsored with a healthy company, IT departments will purchase desktop parts when refreshing hardware. It would be nice for AMD to be able to boast the crown but their company is still profitable, ie in business, by offering parts that sell well.
Also, its not wise to accuse Anand to being bribed. He's been saying this for a long time and he's enthusiastic that AMD is finally making good on their goals. Fanboi squat somewhere else.
michal1980 - Thursday, March 27, 2008 - link
How is this NOT a fluff piece? A 'new' cpu (Thats only new because the first time around it had a bug) thats 4+ months late to the party.Is being beaten by processor that was launch over a YEAR ago.
In gaming the new processor has even been beaten by a X2 6400+!!!.
Thats CRAP. How old is that cpu?
and yet we get conclusions that this is more like the "Amd we're used to seing.. a competitive AMD"? Competitive excatly how? I'll grant you this will push intel to release there 45nm cpu's... But its not like intel is sweeting.
Futhermore, How can you come out and say the Q6600 is long in the tooth, when its better then the new stuff amd has on the market?
Long in the tooth because 12+ months after being released its faster then a brand new amd chip? long in the tooth because its easy to find one for 250, and on sale for less? Or just long in the tooth because It just beats the AMD right now, and doesn't whoop them by 20%+?
I'm standing by my claim this article is fluff/ BS . its written in a postive spin for amd.. When the AMD processor has clearly been beaten again/still.
Goty - Thursday, March 27, 2008 - link
I love how fanboys like to conveniently "forget" about the few years that AMD was dominating Intel in pretty much every benchmark when it was the Pentium 4 against the Athlon64.VashHT - Thursday, March 27, 2008 - link
I don't get what you're saying, are you implying that phenom is competitive because A64 dominated the P4? Funny how you can call someone a fanboy when you're bringing up 2 processors that don't matter in the current market.Goty - Thursday, March 27, 2008 - link
You kind of have to read the previous post wherein the author implies that AMD has never been competitive, which it has been numerous times. My example was merely the latest and had no bearing on the current generation of products.