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
Calin - Monday, April 10, 2006 - link
DDR2-800 at 4-4-4 should be equivalent to DDR-400 at 2-2-2. Also, DDR2-800 at 6-6-6 would be the same (latency-wise) as DDR-400 at 3-3-3.Furen - Monday, April 10, 2006 - link
Not quite, DDR2-800 at 4-4-4 is the equivalent of DDR-400 at 4-4-4 because the memory cells run at 200MHz on both modules. Like I said above, though, module latency is not the only factor affecting the total latency, so perhaps DDR2 memory controllers help mitigate this huge latency hit. One of the main reasons why DRAM manufacturers love DDR2 is because their yields are much higher than they are on higher-clocked, aggresively-timed DDR1 due to the higher prefetch (lower operating clock) and the looser timings.defter - Monday, April 10, 2006 - link
That's not true. "Cas latency" values are relative to the 400MHz clock instead of 200MHz base clock that DDR2-800 has.
Furen - Monday, April 10, 2006 - link
The 400MHz clock is the clock the IO operates at, while the memory arrays operate at half the IO clock, so 200MHz in this case (so yes, DDR2 ram operates at a sort of quad data rate). Since a Column Access Strobe is a memory array operation it is, naturally, measured in memory array clocks. The "base clock" for DDR2 is actually 400MHz because it is the external clock.menting - Monday, April 10, 2006 - link
defter is correct,time delay on memory is calculated by the clk speed that the memory takes in * latency
think of it as a black box operation.
MrKaz - Monday, April 10, 2006 - link
OK. Didnt know that.I always tought that DDR1 2-2-2 was always better than higher DDR2 numbers...
Furen - Monday, April 10, 2006 - link
It is, the main factor affecting latency is the memory cell clock, which runs at the same clock on both modules. So you can do a straight comparison between the two latencies to see which will yield you a better MODULE latency. Of course, module latency is just one part of the whole latency equation, the memory controller being the other big part. Perhaps AMD made the controller more latency-friendly by sacrificing maximum bandwidth, which would explain the abnormally-low usable bandwidth.ozzimark - Monday, April 10, 2006 - link
just something to keep in mind. same 1.8ghz cpu clock:200mhz at 2-2-2 = 51.5ns
300mhz at 3-3-3 = 43.8ns
mhz wins over timings when it comes to comparing absolute latency
Furen - Monday, April 10, 2006 - link
That only applies when comparing the same type of memory.DDR2 memory cells run at 1/4 the "Effective clock," so DDR2 800 runs at 200MHz, which is the same as DDR 400.
ozzimark - Monday, April 10, 2006 - link
true, but you notice the latency that is in the review. seems that what i say holds true to an extentbtw, the timings are in signal clocks last i checked, not cell clocks, which runs at 1/2 the speed of the double data rate signal. kinda confusing, but oh well. point of the matter is that ddr400 at 2-3-2 is higher latency than ddr2-800 at 4-5-4