The Brazos Performance Preview: AMD E-350 Benchmarked
by Anand Lal Shimpi on November 16, 2010 12:01 AM ESTMemory and Cache Latencies
The Brazos platform was configured with 4GB of DDR3-1066 memory. The IDF system had memory running at DDR3-1333, however AMD had to decrease clocks presumably to meet validation requirements for final silicon. I measured an 86.9ns trip to main memory, a 3 cycle L1 and a ~22 cycle L2 cache. That's a lower latency memory interface than Atom or Core 2 based processors, but a higher latency L2.
CPU Performance: Better than Atom, 90% of K8 but Slower than Pentium DC
AMD's performance target for Bobcat was 90% of the performance of K8 at the same clock speed and our Photoshop CS4 benchmark shows that AMD can definitely say that it has met that goal. At 1.6GHz the E-350 manages to outperform a pair of K8s running at 1.5GHz in the Athlon X2 3250e. Unfortunately for AMD, Intel's Pentium dual-core running at 2.2GHz is much quicker. Most notebooks in the $400+ range have at least a 2.2GHz Pentium. Even the Atom D510 isn't far behind.
AMD tells me that in general purpose integer tasks, the E-350 should do well and it may even exceed AMD's 90% design target. However in higher IPC workloads, for example many floating point workloads, the E-350 is constrained by its dual issue front end. In these situations, the out of order engine is starved for instructions and much of Bobcat's advantage goes away.
Our x264 HD test has the E-350 performing within 86 - 92% of the Athlon X2 3250e, once again meeting AMD's design targets. Unfortunately, this isn't much faster than an Atom - mostly thanks to Atom's Hyper Threading support. Although not an out of order architecture, Atom gets a healthy efficiency boost by being able to execute instructions from two threads per core. Once again, compared to a 2.2GHz Pentium, the E-350 isn't close. Even VIA's dual core Nano is faster. When it comes to power consumption however, the E-350 can't be touched. I measured max system power consumption at 25.2W while running the x264 encode test. With the exception of the Atom D510, the rest of the desktop platforms here consume much more than that at idle (much less under load).
Despite being a offline 3D rendering benchmark, our 3dsmax 9 test does fall in line with expectations. The E-350 delivers 92% of the performance of the Athlon X2 3250e and outperforms the Atom D510 by 26%. Unfortunately for AMD, the Pentium dual-core holds onto a significant performance advantage here. Clock for clock, Bobcat won't be able to do much against anything Core 2 based. The real advantage here will be GPU performance.
Single Threaded Performance
In most of our benchmarks the performance advantage over Atom isn't huge, yet using Brazos is much better than using an Atom based machine. It all boils down to one thing: single threaded performance. Atom can make up for its deficiencies by executing a lot of threads in parallel, but when you're bound by the performance of a single thread the E-350 shines. The E-350 is 65% faster than the Atom D510 in the single threaded Cinebench R10 test. It's this performance advantage that makes the E-350 feel so much quicker than Atom.
The Core i3-330UM manages a 46% performance advantage over the E-350. Even in the ultraportable Arrandale ULV space at lower clocks, AMD still leaves a lot of CPU performance on the table. The advantage here will be cost. A single E-350 is less than 40% of the die area of a Core i3-330UM. You may not get the same CPU performance, but performance per mm^2 is much higher.
In the multithreaded Cinebench test Atom is able to catch up quite a bit, but the E-350 still holds an 11% advantage.
File Compression/Archive Recovery Performance
Our final two CPU tests are both multithreaded and they show the E-350 equaling and falling behind the performance of the 1.5GHz Athlon X2. As we explained earlier, the gap between the E-350 and Atom shrinks as you add more threads to the workload.
Facebook
Twitter
RSS
207 Comments
View All Comments
mino - Tuesday, November 16, 2010 - link
Yeah, as well as some fail to see the forest for the treas.Anand Lal Shimpi - Tuesday, November 16, 2010 - link
The focus here is obviously Zacate, which is why the text that accompanies graphs is centered around comparisons with reference to Zacate.As far as the gaming benchmarks go. I tried to put together a varied list of titles to show performance across a spectrum of game types. Starcraft 2 was the largest non-FPS game release this year, it of course had to be included. DAO simply provided another datapoint for an RPG showing how CPU limits can appear even in 3D games.
I don't think anyone is arguing that Intel's HD Graphics are faster (note the title on the desktop IGP comparison page). But I do believe it's important to show both sides of the coin.
Once final hardware is out we'll definitely spend more time with the platform and run through an even wider range of games and benchmarks. This merely serves as a preview until then.
Take care,
Anand
mino - Tuesday, November 16, 2010 - link
"Once final hardware is out we'll definitely spend more time with the platform and run through an even wider range of games and benchmarks. This merely serves as a preview until then."That is expected and waited for! :D
Just think about splitting at least the conclusion as I have mentioned above. ;)
Dark_Archonis - Tuesday, November 16, 2010 - link
I find it more strange that you're criticizing the gaming benchmark selections. Consumers don't talk about "this game is very CPU intensive" when they typically buy games.The average Joe does not care how CPU intensive Starcraft 2 or Civilization 5 is. They just want to play it.
These are both popular games, so their inclusion in the benchmarks is perfectly acceptable.
Crysis is quite CPU intensive. Are you going to criticize Crysis as well for being CPU intensive?
I guess any games that show Zacate as a poor performer should not be used according to you right?
Jamahl - Tuesday, November 16, 2010 - link
I have no issue with Starcraft 2 being used.I do have an issue with Starcraft 2, Civ 5 and Dragons Age being used however. These are supposed to be gaming benchmarks, yet the majority of them are far more cpu dependent.
This is not the norm in gaming, however it is the norm in Anands benchmarking.
You would be very hard pressed to find two games more cpu dependent than Starcraft 2 and Dragons Age.
Dark_Archonis - Tuesday, November 16, 2010 - link
I will bet you anything that Diablo 3 will be very CPU intensive.As I mentioned, Crysis is CPU intensive. What do you have to say regarding that?
While these are only a few games, these are very popular games.
What exactly do you mean that it is not "the norm"? Do you mean to say that most sites don't include Starcraft 2 or Dragon Age in benchmarks? I don't see why people would have issues with this. It illustrates a variety of games that stress different parts of a computer.
RPG and strategy games are typically quite CPU intensive. Also, they are rarely included in gaming benchmarks.
I for one applaud Anand for including them, as far too many sites lack these kinds of benchmarks.
Jamahl - Wednesday, November 17, 2010 - link
Crysis is cpu AND gpu intensive. The point is most benchmarking suites would not have a MAJORITY of cpu intensive games. There's a reason why people actually spend a lot of money on gpu's.Did you even read Anands preview? Let me help you understand as you're making a great job of failing to.
Page 2 - "Setting Performance Expectations"
You get a slower CPU than most existing mainstream platforms, but a much better GPU.
The expectations here are better CPU performance than Atom, but lower than Arrandale ULV. GPU performance should easily trump both.
Then what does he do? Well lets look at the gaming benchmarks shall we?
First of all, lets look at the comparison benchmarks.
http://www.anandtech.com/show/3871/the-sandy-bridg...
http://www.anandtech.com/show/2952/2
So the 5450 was benched using a i5 661 and an i7 920 - And you wonder why Bobcat can't keep up? To see if it is actually close to discrete graphics performance, it should have been benched on a 1.5ghz athlon for a fair comparison.
1 in 3 of the desktop tests was Dragon age - a massively cpu bound game which hugely favours intel cpu's over AMD's...and he benched it in comparison to a 5450 with two fast intel cpu's. Not right however you look at it. MW2 is not particularly heavy on graphics either so basically the only true graphical test is Bioshock 2.
Next page
In the mobile gaming comparison, he's gone and added Starcraft 2 - TWICE.
Lets see what we got then -
MW 2 - 50/50 split cpu/gpu
Bioshock 2 - gpu
Dragon Age - cpu
Warcraft - 50/50 split
SC2 TWICE - (yes even the gpu test is more like cpu obviously looking at the results)
I'm not even gonna talk about using Civ 5. Civ 5 got a huge question mark over it's reliability in the fallout over the 6800 benchmarks, then he goes and uses it here?
So...yeah. ONE pure recognised gpu benchmark used in all of those tests compared to 3 or 4 cpu gaming benchmarks.
It's really very simple. benchmark 20 games at random and Bobcat will beat any intel integrated graphics by around 50% in 15 of them. Anand has managed to make it lose more often that not in the very, very few games that massively favour cpu's.
The fact is, he knows this or should. He said at the start what to expect, then went and benchmarked what he knew would happen.
techworm - Tuesday, November 16, 2010 - link
all of us know anandtech is intel PR site so no complaintnitrousoxide - Tuesday, November 16, 2010 - link
Watch your words, unless you can give evidence that Anand is indeed an Intel PR.silverblue - Tuesday, November 16, 2010 - link
Do me a favour and step back before making judgements.If Anand was biased towards Intel, why would AMD even entertain him with an offer to benchmark their newest CPU, let alone let him publish the results? He already said he was time constrained so you can't very well do everything. Moreover, he did mention that this was a "preview" - this isn't final silicon, it's an engineering sample, and that the final product should use less power.
You should be grateful that there's a preview at all.
It is a shame that the chip seems bandwidth starved, but I don't think AMD ever intended for it to be a triple-channel, SMT-enabled, out-of-order ULV solution - just think of the cost. As long as it does what you want of it, isn't that its point? Atom was "just enough" for browsing, basic media and light workloads, yet Brazos is at the very least an improvement in IPC, and substantially better if you take into account gaming, movies and so on. If Anand truly wanted to give it a bad name, he wouldn't have benched so many games AND highlighted where the chip's true strengths are. He also mentioned that most games should be GPU bound and thus will extol the virtues of the Brazos architecture - how very anti-AMD of him (!).