Socket-AM2 Performance Preview
Without major architectural changes to the new AM2 CPUs, we wanted a quick and easy way to showcase the performance differences between AM2 and Socket-939. What we've got is a massive table below with all of our usual CPU benchmarks and their results for the same CPU in both Socket-939 and AM2 varieties, and the performance benefit offered by AM2:
| Benchmark | Socket-939 (DDR-400) | Socket-AM2 (DDR2-800) | % Advantage (Socket-AM2) |
| PC WorldBench 5 | 115 | 115 | 0% |
| Business Winstone 2004 | 23.3 | 23.2 | -0.4% |
| Multimedia Winstone 2004 | 38.4 | 38.9 | 1.3% |
| SYSMark 2004 | 220 | 224 | 1.8% |
| ICC SYSMark 2004 | 282 | 286 | 1.4% |
| OP SYSMark 2004 | 171 | 175 | 2.3% |
| 3dsmax 7 | 2.38 | 2.38 | 0% |
| Adobe Premier Pro 1.5 (Export w/ Adobe Media Encoder) | 130 s | 128 s | 1.5% |
| Adobe Photoshop CS2 | 210.6 s | 210.3 s | 0.1% |
| DivX 6.1 | 11.6 fps | 12.0 fps | 3.4% |
| WME9 | 35.2 fps | 35.6 fps | 1.1% |
| Quicktime 7.0.4 (H.264) | 3.63 min | 3.63 min | 0% |
| iTunes 6.0.1.4 (MP3) | 43 s | 43 s | 0% |
| Quake 4 - 10x7 (SMP) | 111.3 fps | 117.4 fps | 5.5% |
| Call of Duty 2 - 10x7 | 59.3 fps | 60.1 fps | 1.3% |
| F.E.A.R. - 10x7 | 92 fps | 94 fps | 2.1% |
| Multitasking Test (LAME + WME + Anti Virus + Zip) | 216.3 s | 213.4 s | 1.4% |
| ScienceMark 2.0 (Bandwidth) | 5007 MB/s | 6805 MB/s | 36% |
| ScienceMark 2.0 (Latency 512-byte stride) | 53.83 ns | 49.77 ns | 7.5% |
We'll start at the bottom of the table and go up from there. Rev F processors feature a 128-bit DDR2-800 memory controller, which works out to offer a peak theoretical bandwidth to/from memory of 12.8GB/s. As you can expect, that's twice the bandwidth of Rev E CPUs' 128-bit DDR-400 controller at 6.4GB/s. Thus to see a 36% increase in memory bandwidth according to ScienceMark is to be expected, albeit a bit on the low side. The old DDR-400 memory controller is able to deliver 5GB/s out of a maximum of 6.4GB/s, but now we're only seeing 6.8GB/s out of a maximum of 12.8GB/s with AM2. This however is a huge step for AMD, as it is the first spin of the Rev F silicon that we've been able to see such a significant advantage in theoretical memory bandwidth over previous DDR-400 cores.
What's even more important than the increase in memory bandwidth is that access latency has been reduced by 7.5% over the DDR-400 memory controller in the Rev E cores. Lower latency and more bandwidth means that, at bare minimum, performance won't go down. At least, not perceptibly: .4% slower in one test that has a 1-2% variability is nothing to worry about.
It also doesn't guaranee that performance will go up, as you can see from the results above. If we only count the overall SYSMark score and leave out the synthetic tests, the real world performance advantage averages out to a little under 1.3%. There are some special cases such as Quake 4 and DivX were performance goes up fairly reasonably, which can be expected since both of those tasks are fairly bandwidth intensive and make good use of both cores. However similar benchmarks, such as F.E.A.R. and Windows Media Encoder 9 show lower improvements, so it is very dependent on the specific application and workload.
It's important to note that until recently, AM2 samples were not able to produce scores even on par with Socket-939, so the fact that we're seeing a performance increase at all is a major step from where we were just a couple of months ago. The real question is, is this all we get?
Facebook
Twitter
RSS
107 Comments
View All Comments
DrZoidberg - Monday, April 10, 2006 - link
Yeah it is disapointing that DDR2 800 doesnt increase performance by much for AMD. I think we will only see nice 20%+ improvements when AMD moves to 65nm CPUS, smaller transistors less power higher clock speed. Too bad 65 nm seems like Quarter 4 at earliest, next year most likely.I do hope when Conroe is released AMD does big price cuts, cause their CPUS will no longer have performance crown so they no longer have excuse to have their X2 processors more expensive than Intel, so we should hopefully get X2 4400+ for $300, or X2 3800 for low $200s.
Shintai - Monday, April 10, 2006 - link
Even a 300$ 4400+ would be a bad buy. For 300$ You will get a 2.4Ghz Conroe that will be somewhat like an FX-62. So maybe a 200-250$ 4800+ and a 150-200$ 4400+AMD really needs some extremely aggresive pricecuts to be competitive.
abhaxus - Tuesday, April 11, 2006 - link
they don't need to make price cuts yet... when conroe comes out i'm sure they will drop the prices by quite a bit. as it stands, the X2s are by far the best chip on the market and have been for quite some time, and have been reasonably static on price for half a year now. This is the first time in a long time that i remember chips staying THAT static at high prices.That said... this review makes me worry for AMD. I hope they have something up their sleeve otherwise this generation will go very badly for them.
Sunrise089 - Monday, April 10, 2006 - link
20% Seriousely?I'm no CPU expert, but I cannot imagine that kind of gain. Pentium 4's moving to 65nm and 7900GPUs didnt see anywhere near those kinds of gains.
Furen - Monday, April 10, 2006 - link
I think a 20% clock speed increase is conceivable if a) AMD's 65nm shrink goes off well (let's assume a 10% increase due to this), and b) AMD's embedded germanium technique is 10% better than current DSL silicon. Of course, clocks woul not be 20% better until yields hit a decent point.I think that the main way we'll see AMD get closer to a performance parity with Intel will be through the various architectural tweaks in Rev G, though there WILL be some clock speed increase out of manufacturing,.
bob661 - Monday, April 10, 2006 - link
I think I will wait for the die shrink and just get a dual core and some ram for now. I've been trying to decide whether to wait or not to upgrade. I was thinking about waiting for the die shrink anyways.poohbear - Monday, April 10, 2006 - link
"better late than never" is the expression we all know, not "better early than never". wow, anandtech are really trying to sell this cpu in their "final words" section, even though it seems like a waste your money according to your performance tests. i think i'll stick w/ my s939 and just upgrade to a x2 cpu instead of a whole new socket.:/Brunnis - Monday, April 10, 2006 - link
You're just reiterating what Anand wrote. He said that there's no point for S939 owners to upgrade, but that AM2 is the natural socket of choice for those who don't already own an up to date system.Are you suggesting that those people should buy S939 parts instead, despite them having a very limited future and worse performance? That makes absolutely zero sense.
poohbear - Tuesday, April 11, 2006 - link
nope it makes perfect sense. i wouldnt hold my breath for the am2 is what im saying. im sorry but a 5% increase doesnt justify ditching my s939 and opty 144. and what are u talking about limited life? w/ dualcores available on the s939 they're gonna be around well into 2008. It's 2006 and there are still tons of people using athlon xps and agp, so plz drop your enthusiast perspective on the market, it's not realistic of what the avg person has.sp1nfer - Tuesday, April 11, 2006 - link
no, it's EOL (end of life) is Q4'06, with socket 754 holding out one year more. By the time you decide to go X2, with AM2 out and all, prices are going to be higher than AM2 counterparts. AMD said it themselves that prices for s939 will be increased near and on AM2 launch. I think Brunnis covered most of it.
It makes perfect sense.