AMD’s Brazos vs. Atom Thermals, Revisited
by Jarred Walton on January 14, 2011 5:35 PM ESTAMD’s Brazos vs. Atom Thermals, Revisited
Last week, we met with AMD at their CES location to see some of their upcoming systems and laptops. While they’ve also recently released several new desktop GPUs, there wasn’t anything new to discuss in that area. The same applies to their desktop CPUs—we’re all waiting to see Llano and Bulldozer. So the focus at CES was understandably on Brazos, aka the “first APU” Vision C- and E-series processors.
We’ve been critical of some of the staged platform comparisons we’ve seen in the past—as Anand put it, the onus is on AMD in this case to provide a truly representative comparison between their new product and Intel’s competing offerings. After the demonstration of their Brazos netbooks on Thursday, AMD called us back and said they wanted to let us rerun the tests to make sure we accurately represented the two platforms. See, there was a slight snafu in the initial thermal imaging comparison. Specifically, AMD thought they put out a netbook with a C-50, but the test system was actually a C-30. So, we returned….
The reason for the mix-up was simple: they had both a C-30 and C-50 system from the same OEM, and they’re basically identical (one was dark blue and the other was light blue). Given that the two C-series parts are both 9W TDP, we didn’t expect much to change, and the new testing confirmed this. We did get some better images of both the top and bottom of the three test netbooks—Atom N550 vs. C-30 and C-50. Unfortunately, stupidity on my part resulted in the loss of said images (it’s a long story…), so all we have are the thermal shots from the keyboard area and screenshots showing CPU utilization during playback along with screen captures taken with FRAPS.
_thumb.jpg)
_thumb.jpg)
_thumb.jpg)
The above gallery shows essentially the same thing as our initial testing: Brazos using its GPU uses less power and runs cooler than Atom N550 doing the decoding in software. The difference between the C-30 and C-50 is pretty much non-existent, as expected. The testing environment was not conducive to doing any form of noise comparison, so while the N550 setup was clearly warmer we couldn’t say if it was quieter or not. Battery life is looking to roughly equal Atom, so that’s good to see. Now we’re waiting for final hardware to see if we can shed any more light on the situation, as well as running our full suite of tests.
We also took the opportunity to capture a video showing the 1080p playback comparison, as that’s part of the story. The video in question is Big Buck Bunny, an open movie demo created as part of the Peach movie project. (You can read more about it on their site, though it’s old enough now that if you haven’t heard of it already there’s not much to add. Suffice it to say, the lack of any licensing issues meant BBB was all over the CES floor, and I’m tired of the short now!) This particular version is a stereoscopic rendering, so instead of the normal 24FPS the frame rate is 48FPS according to FRAPS.
I believe during playback Arcsoft TotalMedia Theater 5 is skipping half the frames, as none of the netbooks come equipped with a 3D 120Hz panel. Does that actually matter? Not that we could tell—now that we’re home from CES, I ran the regular 24FPS version of Big Buck Bunny on a different dual-core N550 netbook, and frame rates still frequently dropped into the teens. Actually, it was worse than the netbook at AMD’s demonstration, but that’s probably more to do with lack of optimizations and some bloatware that came preinstalled; but I digress….
You can see during playback that the Atom N550 periodically stutters and drops below 48FPS—and more importantly, it’s far below 24FPS as well at times. In comparison, both the Vision C-30 and C-50 Brazos/Ontario chips manage a consistent 48FPS. The C-30 does flicker between 47 and 48FPS, but again, that may simply be an artifact of using a stereoscopic 3D video on a non-3D panel. Temperatures are in line with what we reported in our earlier coverage, and the two AMD netbooks are virtually identical. CPU utilization on the dual-core C-50 is lower by about half, as expected.
Once More, With Feeling
This is essentially the killer app of Brazos compared to Atom, and it’s important to keep things in perspective. These chips have a much better IGP than Atom, but at least on the nettop side of things the faster AMD E-350 isn’t miles ahead of Atom D510 in the CPU department. When we drop clock speeds down to 1.0GHz (dual-core C-50) from 1.6GHz (E-350) and compare that to the Atom N550 (1.5GHz)… well, 62.5% of the performance of E-350 compared to 90.4% of the performance of D510 means that in some tests the N550 will probably beat the C-50 for raw CPU potential. Yeah, that’s a concern for me. The GPU is the real difference, so naturally a video decoding test is the best-case scenario. I suspect C-50 will be underpowered for most 3D games, even if the DX11 GPU inside Brazos is fast enough—it will just be the AMD equivalent of Atom + NVIDIA ION, only without as many discrete chips.
We also have to consider performance of the next tier of CPUs and IGPs. Atom is the lowest of the low hanging fruit; we have much faster chips and IGPs from both AMD and Intel, and we don’t need to move up to current generation parts like 2nd Gen Core processors. Even the old Core 2 Duo CULV chips are a darn sight faster than Atom (2x-3x faster), and bad as GMA 4500MHD is, it could do an okay job at H.264 offload. It appears that the E-350 will end up delivering performance roughly equal to the old CULV chips (probably a bit slower, to be honest). That means it will also be around the same level as the Athlon II Neo K325, only with a better IGP and apparently improved power characteristics.
The biggest point in favor of Brazos isn't performance, though. It's going to be cost. If AMD can get partners to put out $400 netbooks (hopefully without Win7 Starter and with more than 1GB RAM), that will hopefully put the nail in the current iteration of Atom. We've seen the Brazos chips, and they're extremely small—smaller even than Atom—so pricing should be very compelling. AMD also doesn't appear concerned about protecting their more expensive mobile offerings (mostly because there aren't many), so they don't have to castrate Brazos in the same way Atom has been stagnant since the first N270 rolled out. Well equipped Brazos netbooks (and nettops) in the $500 range should also be a more elegant choice than Atom + ION/NG-ION, so again AMD looks set to win several matchups.
We’re working to get Brazos hardware in for testing as soon as possible, but it looks like the biggest beneficiaries will be users that want good H.264 decoding in a 10.1” form factor, or an alternative to ION. If you’re looking for the ultimate HTPC chip, we’ll have to investigate that area in further detail, as bitstreaming support and other features are still a question mark. Right now, Brazos is shaping up to be what we all wanted from Atom last year; whether that will be enough in 2011 remains to be seen.
Facebook
Twitter
RSS
151 Comments
View All Comments
d00ki_br0wn - Friday, January 14, 2011 - link
Sorry pal, but you guys are thoroughly considered to be the biggest Intel fanboys on the net, it's considered a given at this point. For one, synthetic benchmarks should be dropped altogether. They consistently produce results that favor Intel (many of them are compiled with ICC, bit of an odd choice, don't you think?), moreso than any real-world benchmarks favor Intel. So that instantly skews your aggregate results, and because you rely on them for your power use results, those are skewed too.Here's a general history of your bias:
Core2: It WAS faster than AMD's competing chips, but when I bought one, it wasn't nearly as fast as I expected it to be based on hardware reviews, compared to the Athlon 64 it replaced. It also still had the Pentium 4 denormal bug, but this was ignored by you guys. I encountered it many times, I had to avoid certain DSP applications because of it. I also owned a Phenom 9500 later with the OMGBAD TLB errata, never encountered the TLB errata that made it so awful...
Nehalem: Not appreciable faster than Core2 in many real world applications, but much faster at video encoding: Anandtech's response: Make synthetics and video encoding like 90% of the review article.
Phenom II: reasonably close to Nehalem, a normal person couldn't tell the difference in normal use. Anandtech's response: Well, it is comparable in gaming, but you should still get a Nehalem for it's superior synthetic benchmarks and video encoding(whether you ecode or not). Then you say that Core2 has issues with stuttering in games, whereas P2 and i7 don't have stuttering in games because of the IMC. RLY? You never mentioned that when you were touting Core2 as the gaming CPU to buy.
Core i5: Anandtech went way the heck out of their way to promote this as a "must have upgrade" to "last year's" Nehalem: Thinking people scratched their head at this one.
Sandy Bridge: Not necessarily too much faster than Nehalem in the real-world(and therefore not necessarily too much faster than Core2), but even better at video encoding. So, let's keep on pushing the video encoding, run the benches ignoring that most of the performance comes from a bump in clockspeed, and imply that every single one can OC anywhere from 4.5 to 5ghz, even though we know that they won't last an entire month at those speeds.
Yours Truly,
Long Time Reader
AnandThenMan - Friday, January 14, 2011 - link
"Sorry pal, but you guys are thoroughly considered to be the biggest Intel fanboys on the net, it's considered a given at this point."True, but I think it's more actually. Anandtech's true colours really shone through when they violated their own policy and included overclocked Nvidia cards. And justified it by saying that Nvidia "insisted".
And you'll notice that this can't give a compliment to AMD without some sort of slight or caveat somewhere. Well Brazos is good, but Atom sucks so it's really nothing special etc. etc. Or they will talk about what Intel has in the pipeline instead of just giving AMD credit and leave it at that.
Paulsbo.Otellini - Friday, January 14, 2011 - link
None of this is intended to survive real scrutiny in the comments section. The intent of the subtle Intel praise and subtle negativity towards AMD in every article is that people who don't read or understand tech but who want to research their next purchase will stumble on this via google, skim over the article, and say "well gosh, Intel is just flat out better, I'd be cheating myself if I bought AMD".JarredWalton - Saturday, January 15, 2011 - link
No, the intent is to tell the facts as they are and not make excuses for AMD *or* Intel. All of you looking to root for the underdog (AMD) aren't doing them any favors by overlooking their faults. I understand it's very difficult to compete with a company that makes tons more money than you do, but pretending a product with flaws is perfect isn't going to help. The fact is that AMD has a product with good power characteristics, moderate performance, and a reasonable GPU. It's better than Atom. CULV and ULV are also substantially better options than Atom (unless the only criterion you're interested in is minimum cost). Brazos should beat the current Atom chips in every meaningful way.On the other hand, have you noticed how most of the Brazos netbooks appear to be going after a higher price segment? I suppose that's necessary when you do a full Win7 install with at least 2GB RAM, but that means the $300 market will remain in the hands of crap like Atom (or equally bad crap like Brazos netbooks with 160GB HDDs, Win7 Starter, and 1GB RAM).
We had CULV with Celeron SU2300, and I think Intel may have simply done their best to kill that off when people saw what you could get for $400 in an ultraportable (i.e. the Acer Aspire 1410). Or maybe Acer killed it off because they make more money on the Timeline 1810 and wanted people to go there for dual-core computing? Either way, things are done as business decisions.
Look, I'm glad we have AMD. I've used a lot of their products. I've built AMD systems for a lot of friends. In nearly every case in the past three years, I've used AMD because they offer good performance at a great price, and the person really just needs office, email, and Internet. If that's what you're after (and you don't care about power draw), even the four year old socket 939 dual-core parts are still fine. I should know -- I have one of them and my eight-year-old daughter uses it to play some of the current web games and activities targeting her age group.
Without AMD, Intel prices go up, their performance stagnates, and consumers don't win. So if you don't need Sandy Bridge, Arrandale, Core 2, or even K10 levels of performance, by all means get a Brazos system. It should sip power, handle a lot of multimedia tasks quite well, and it should be pretty darn cheap.
Just don't pretend that it's the only way to build a good chips, because Llana and Bulldozer shows that AMD certainly knows Bobcat only works in the "low cost above all else" category of computers. The GPU is an order of magnitude better than GMA 3150, but it's apparently at the same level as NVIDIA's ION. The CPU is up to twice as fast as Atom, but then so is Intel's Core 2 CULV. That's all I'm saying, and all of that is true. We already had "Brazos" 12 months ago with CULV + ION (or G 310M if you prefer). Now, we're getting about the same thing for a lower price. That's great for cost but does nothing for performance.
ghost_of_goebbles - Saturday, January 15, 2011 - link
Well, when somebody's job involves propaganda and influencing public perception, generally, they respond to being called-out with "we're not biased, we're like Fox News: Fair and Balanced". Upon being pressed further, the paid shill will accuse the accuser of being anything from paranoid to delusional or even flat out crazy... Because, of course, we live in a world where nobody ever conspires to do anything dishonest for profit, especially not our beloved Intel. *raucous laughter*Nowhere along the line does anyone expect you to say "Oh noez, u r haz caught me!!!". Go read any other tech forum on the web, people all over the world say "yeah, there's this benchmark on Anandtech, but I'd take it with a grain of salt, we all know whose side their on... *wink, wink, nudge, nudge*"
Dustin Sklavos - Sunday, January 16, 2011 - link
We do?See, this is why I feel out of the loop being a relatively new guy. Nobody told me I could get paid to shill Intel here. :(
redisnidma - Monday, January 17, 2011 - link
Keep pretending. :)seapeople - Saturday, January 15, 2011 - link
You Anand-Loves-Intel people are seriously retards. In every article the last three years AnandTech has basically said that Intel rocks the performance market, but sucks below $200 where AMD is king. They have also unilaterally praised Intel's notebook CPUs during that timeframe.Now why would this be? Is it a giant conspiracy theory? No! It's because starting with the Core2 series Intel's high performance offerings have completely obliterated AMD's, and AMD gives worse laptop performance with worse battery life at the same time. This is not unique to AnandTech. This is what pretty much everyone else has been saying.
ninjaquick - Tuesday, January 18, 2011 - link
Wait a minute, didn't Conroe come out three years ago? You see, I was under the impression that Conroe destroyed K8, and then AMD scrapped the original K9 and K10 designs and went for an upgraded K8 to compete against the Core 2 Quads but fell horribly short.Yeah, I'm pretty sure that is exactly what happened. Check ANYWHERE and see that AMD has been limping along for the past three years.
silverblue - Wednesday, January 19, 2011 - link
Clock for clock, K10.5 and Penryn are pretty much neck and neck, depending on application. The comparison is quite difficult though; Penryn comes in a variety of flavours with differing inclusive L2 cache sizes, plus has SSE4.1 and 4.2 whereas K10.5 has SSE4a and generally sports an exclusive L3 cache. You are correct in that AMD hasn't really gotten to a level where they can compete on performance, however they've done pretty well with K10.5 derivatives so I'm not sure that could be considered "limping along".