However, stating that the data cache bandwidth is twice as high as Intel's Core is ignoring a few things. Eric Bron, probably one of the most knowledgeable developers when it comes to SSE, stated: "Intel Core can sustain one 128-bit load and one 128-bit store per cycle (I've measured actual timings very near this theoretical peak), so Core can copy 128 bits per cycle. Barcelona (K10) can only copy 64 bits per cycle from the above store bandwidth limitation." So the twice as much "load bandwidth" is only a small part of the story:

* Intel Core can do a 128-bit Load and 128-bit Store in one cycle if possible
* AMD's K10 can either do two 128-bit loads, or two 64-bit stores, or one 128-bit Load and one 64-bit Store

Depending on the situation, AMD's K10 can do twice as much, about equal or about 33% less work in one cycle. So you cannot conclude that the AMD K10 has twice as much SSE bandwidth as the Intel quad core Xeon. It will only be faster if loads happen twice as often (or more) as Stores. In most "harder to vectorize" FP code, this is the case, so here the K10 chip will probably win by a small margin (as the percentage of SSE code is low). An example of this is the SpecFP benchmark. In some "easy to vectorize" SSE code this is not the case, and in that case the K10 will probably not be beaten per clock cycle, but the clock speed disadvantage might give the Xeon the edge.

The result is that the dual Xeon x5355 (eight cores) is heavily bottlenecked by a lack of bandwidth and hardly faster than the dual Opteron 2220SE (four cores) in CPU FP2000 rates. If we take a look at the best dual core Xeon 5150 (2.66 GHz) score, it gets a score of 78.2. That means that the quad Xeon 2.66 GHz is only about 32% faster than its dual core brother at the same clock speed, another clear indication that the dual Xeon x5355 scores are seriously limited by memory bandwidth. It is no surprise that the quad socket Opteron 8220 is about 34% faster than the Xeon x5355 (and we are ignoring the probably inflated result of 184 you can get with the Sun Studio Compiler).

This puts AMD's claim that the best "K10" (most likely at 2.3 GHz) will be 42% faster than the Xeon x5355 in Spec FP rate in the right perspective. We reported in our Barcelona architecture article that the AMD K10's Northbridge is set up to handle higher bandwidth than the current AMD chips. As has been shown numerous times, the current Athlon 64 X2/Opteron architecture is not able to use the extra bandwidth that DDR2 gives.

So most of the 42% advantage is probably due to K10's better Northbridge and better use of DDR2. Ron Myers of AMD claimed that the difference is now already greater than 42%. Combine this with the fact that the K10 is running at only 2.3 GHz, and we can conclude that the memory subsystem (Load/store unit, L1, L2, Northbridge) of the K10 is simply (vastly) superior compared to the Athlon 64s and to the quad Xeon. This confirms our and Intel's assumption that the K10 will probably make the largest impact as a very potent HPC chip. The hardware virtualization features in AMD's K10 are quite impressive, but we'll discuss them later.

Technically, you are engaging in selective quoting too. Hello pot, my name is kettle.

Nice selective quote there Ninja. How 'bout this.

The result is that the dual Xeon x5355 (eight cores) is heavily bottlenecked by a lack of bandwidth and hardly faster than the dual Opteron 2220SE (four cores) in CPU FP2000 rates. If we take a look at the best dual core Xeon 5150 (2.66 GHz) score, it gets a score of 78.2. That means that the quad Xeon 2.66 GHz is only about 32% faster than its dual core brother at the same clock speed, another clear indication that the dual Xeon x5355 scores are seriously limited by memory bandwidth. It is no surprise that the quad socket Opteron 8220 is about 34% faster than the Xeon x5355 (and we are ignoring the probably inflated result of 184 you can get with the Sun Studio Compiler).

This puts AMD's claim that the best "K10" (most likely at 2.3 GHz) will be 42% faster than the Xeon x5355 in Spec FP rate in the right perspective. We reported in our Barcelona architecture article that the AMD K10's Northbridge is set up to handle higher bandwidth than the current AMD chips. As has been shown numerous times, the current Athlon 64 X2/Opteron architecture is not able to use the extra bandwidth that DDR2 gives.

So most of the 42% advantage is probably due to K10's better Northbridge and better use of DDR2. Ron Myers of AMD claimed that the difference is now already greater than 42%. Combine this with the fact that the K10 is running at only 2.3 GHz, and we can conclude that the memory subsystem (Load/store unit, L1, L2, Northbridge) of the K10 is simply (vastly) superior compared to the Athlon 64s and to the quad Xeon. This confirms our and Intel's assumption that the K10 will probably make the largest impact as a very potent HPC chip. The hardware virtualization features in AMD's K10 are quite impressive, but we'll discuss them later.

Technically, you are engaging in selective quoting too. Hello pot, my name is kettle.

Two small, tiny, possibly insignificant things you have might forgotten in your rush to always have something to say against the, "big bad Intel(or VIA or AMD, depending on who is doing the calling) fanboy" Ninja. I posted the conclusion to the statement you quoted (which is being selective I might add) meaning that the people in the know, when looking at all the data showed that the bandwidth problem isn't as big as its been played out to be.

Two, you still haven't shown any proof that shows that a monolithic multicore performs better than the same arch in a dual die - single processor solution.

With that, I await someone calling me a fool, biased, idiot, moron, jackass, meanie or a derivative of these terms.

Have a nice day,
Ninja

Thanks for the link BM, I can't wait for people to start giving this post one star simply because it came from you/is pro AMD.

I've heard about the load/store "problem" with K10 before. It worried me then, as it still worries me. I love the "can be twice as fast, as fast or 33% slower" quote. If I understand this correctly, this means that when executing SSE code, K10s performance will be better then, equal to, or vastly slower then C2D. Does anyone know/can explain when these will be true? For example, when using a SSE encoder, ripping video will be faster while running LAME will be slower? I want to know when this worst case senerio will take place.

I'm also worried about the comment about the better memory arch in K10. If much of the improvment is because of better memory management, why didn't they simply tweek the K8L arch? I remember when AMD dropped DDR and switched to DDR2. You had to run DDR2-800 inorder to have 1-3% better performance then DDR. The memory management on the DDR2 chips has been horrid. If they could make these tweeks, why not just do it? If they could get ~30-40% gains just by tweeking the memory controller, I'd do that while working on K10 more. I'd keep working on K10 if the max frequency is only 2.3GHz. (nearly 30% slower then the current max frequency.)