Memory 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

Adobe Photoshop CS4 - Retouch Artists Benchmark

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.

x264-HD Benchmark - 1st Pass

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).

x264-HD Benchmark - 2nd Pass

3dsmax 9 - SPECapc CPU Benchmark

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

Cinebench R10 - Single Threaded

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. 

Cinebench R10 - Multithreaded

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.

Par2 - Multi-Threaded par2cmdline 0.4

WinRAR 3.8 Compression - 300MB Archive

Setting Performance Expectations Desktop IGP Comparison: Faster than Clarkdale
Comments Locked


View All Comments

  • mino - Tuesday, November 16, 2010 - link

    Why else would anyone spend 90% of the space boasting about multithreaded benchmarks that are COMPLETELY meaningless for the target markets?

    Anand, it is a sad fact that you are not humble enough to do a proper review of the low end stuff anymore.

    Leave the space to people who are not so pampered by having the top-end stuff to play with for over a decade.
    Stick to the luxury stuff where your mind is. Your time as a "mortal" reviewer is over.

    You are far too out-of-touch to not get manipulated by PR lads without realizing it. As far as low-end and mainstream parts go, that is.
  • Anand Lal Shimpi - Tuesday, November 16, 2010 - link

    These days it's actually very difficult to find workloads that don't at least stress 2 cores, even installing Modern Warfare 2 on the Brazos system ate up 61% of the 2 cores. That's why the Cinebench test is so handy because it does give us an idea of single threaded performance as well.

    Single threaded performance does matter quite a bit to how fast the system feels. Application launch time and how quickly windows pop up is greatly based on this, which is why I pointed it out in our single threaded performance results.

    I tried to show single threaded performance, multithreaded performance in both high and low IPC workloads as well as a lot of gaming performance data to present as complete of a picture of Brazos' performance as possible.

    If I've failed in doing so by your standards I do apologize. I wanted to run a lot more but with time constraints on how long I had access to the platform I had to limit what I could run.

    Take care,
  • mino - Tuesday, November 16, 2010 - link

    I am pretty sure you have a very good understanding of Zacate's performance.

    Where I see the problem that your articles have, over the years, come to be written from an upper class POW.
    As if subconsciously disregarding the pricing part.

    Then when a part comes out that is _designed_ to be cheap first and anything else second you make an article sound as the part was a piece of crap by definition.
    While i certainly hope it was not the idea, it is how it came out ...

    People are subjective by definition and our lives DO affect our expressions however much we would like it to stay otherwise.
  • mino - Tuesday, November 16, 2010 - link

    One just needs to contrast the tone of this article with the Atom one. While Atom was being heavily praised for delivering acceptable performance for a low price an power.

    Nevermind that Silverthorne, while itself good, represented very much a crappy and imbalanced platform. (Outside the non-existent MID market.)
    Compared to that Brazos, while almost shouting out "Atom done right" gets a stamp of "undewhelming" ...
  • Anand Lal Shimpi - Tuesday, November 16, 2010 - link

    I appreciate the feedback. It's not my intention to discredit value as a piece of the equation, in fact pricing is always a major component of anything we discuss here.

    I believe we need to look at Atom in context. Two years ago Atom's level of performance might've been a decent balance of perf/power, especially given the price of good systems at the time. Today that is no longer true. Outside of smartphones, the overwhelming response tends to be that Atom based netbooks running Windows 7 aren't exactly fast enough.

    The E-350 is clearly faster than Atom. My worry is that the E-350 won't be the chip aimed at Atom. In a $299 netbook the E-350 would easily trump anything else out there. But if we're talking about $500, then you start getting into Pentium DC and Core i3 territory.

    While video encoding, 3D rendering and file compression/archive recovery aren't the only things you'd do with such a system, these are good tests of CPU performance which is the unknown we were looking to answer in this article. The tests told us three things:

    1) The E-350 is faster than a dual-core Atom by varying amounts depending on the type of workload (the tests also highlighted the limits of Bobcat's front end in high IPC workloads).

    2) The E-350 does achieve AMD's design target of 90% of the performance of a K8, and

    3) The E-350 does suffer the same fate as Atom does when it comes to CPU performance. You can get a faster CPU in a similarly priced system, although you will likely give up form factor and/or battery life.

    The E-350 is easily better than Atom, but when it comes to the Pentium/i3 comparison you have to make the tradeoff between CPU performance or GPU performance. I simply tried to present enough data to allow users to understand that tradeoff.

    Take care,
  • mino - Tuesday, November 16, 2010 - link

    Just try more care when publicly judging stuff by your personal expectations.
    Very few people will get the subtle praise in the background which a mere recognition of Zacate competing with mainstream platforms represents.

    Thanks for the reply and keep up the good work,
  • mino - Tuesday, November 16, 2010 - link

    It now came to me that what was really called for is a three-progned look at Brazos:

    1) as a netbook/ultra-thin solution
    2) as a HTPC solution
    3) as an ultra cheap alternative to mainstream parts

    IMO it shines in all those roles but for a VERY different reasons:
    1) solves GPU bottleneck that plagues this market since inception
    2) provides Atom-class power with CULV-class connectivity and performance
    3) is the cheapest kid on the block while providing _acceptable_ performance across the board (outside workstation tasks)

    Maybe a topic for a follow-up analytic article ? :)
  • JarredWalton - Tuesday, November 16, 2010 - link

    I would LOVE to have a netbook/ultraportable laptop to test right now using Brazos, but that's not what AMD is ready to show just yet. They're showing early hardware that needs the big OEMs to put it all into a compelling package. Unfortunately, I think they're going to fall short as well. Do you want an alternative to ION netbooks? This will definitely work, and even come out ahead. But ION, frankly, isn't good. Yes, it can play multimedia content a lot better than just Atom (or Atom with CrystalHD), but then so can ULV stuff.

    And the big problem is that you can get ION netbooks for $500, and ULV starting at $600. ( So if AMD were to say that Brazos is going to target the $300 to $350 netbook world, I'd be ecstatic. When they say it's going after the $500 laptop world, I'm a lot less impressed. Intel already has CULV laptops that cost under $500; add in a G 310M (which is still too slow for most recent games) and you'd have something faster than Brazos in pretty much every way. It's just nothing special.

    Is it a bad design? No. Is it an awesome design? Equally, no. It's an okay design that will fill a niche--a niche that already has plenty of options, unfortunately.
  • mino - Wednesday, November 17, 2010 - link

    Well, Jared, I was hoping there is a chance for AT to recover.
    After this reply of yours, I am pretty sure you have lost the ability to see the forest behind the trees.

    I will still not call you paid, but you are REALLY pushing for that.
    Never mind, just no more hope left.
  • silverblue - Thursday, November 18, 2010 - link

    Jarred didn't write the preview. He's entitled to his own opinion.

Log in

Don't have an account? Sign up now