The Brazos Review: AMD's E-350 Supplants ION for mini-ITX
by Anand Lal Shimpi on January 27, 2011 6:08 PM ESTAMD has been curiously absent from the value netbook and nettop segments since Atom’s arrival nearly three years ago. These markets are highly profitable only for component vendors, as the OEMs that sell netbooks and nettops must survive on very slim margins in order to hit aggressive price points. It wasn’t too long ago that we were shocked by $699 desktop PCs, but to now be able to get a fully functioning portable PC with display at below $300 is impressive. In order for the profit equation to work out however, you can’t simply scale down a larger chip - you need an architecture targeted specifically at the type of very light workloads you expect to encounter in these segments. Underclocking and undervolting an architecture targeted at high end desktops or servers won’t cut it.
Generally a single microprocessor architecture can cover an order of magnitude of power envelopes. You can take an architecture from 10W - 100W using clock speed, voltage scaling and disabling features (e.g. cutting cache sizes). You can’t efficiently take a 100W architecture and scale it down to 1W. Intel realized this with Atom, and what resulted was a new architecture designed to span the 0.5W - 5W range. Given the constraints of the process (Atom was built at 45nm) and a desire to keep die size down to a minimum (and thus maximize profits), Intel went with a dual-issue in-order architecture reminiscent of the old Pentium - but with a modern twist.
AMD came to the same realization. For it to compete in these value markets, AMD couldn’t rely on its existing Phenom II derived architectures. The Phenom II and its relatives currently span a range of TDPs from 9W to 140W, and at the lower end of that spectrum we’re talking about some very low clock speeds and performance targets. Getting down to 1W was out of the question without a separate design.
What AMD came up with was a core called Bobcat, initially targeted for netbooks, notebooks, nettops and entry level desktops. Architecturally Bobcat is a significant step ahead of Atom: while still dual-issue, it features an out-of-order execution engine making it the Pentium Pro to Atom’s Pentium.
It isn’t just CPU architecture that AMD surpassed Atom with, the first incarnation of Bobcat is an integrated SoC with on-die DirectX 11 GPU. AMD calls this combination a Fusion APU (Accelerated Processing Unit) as it places both a CPU and GPU on a single die. The possible CPU/GPU combinations for Bobcat based APUs are listed in the table below:
| AMD Brazos Lineup | ||||||||
| APU Model | Number of Bobcat Cores | CPU Clock Speed | GPU | Number of GPU Cores | GPU Clock Speed | TDP | ||
| AMD E-350 | 2 | 1.6GHz | Radeon HD 6310 | 80 | 500MHz | 18W | ||
| AMD E-240 | 1 | 1.5GHz | Radeon HD 6310 | 80 | 500MHz | 18W | ||
| AMD C-50 | 2 | 1.0GHz | Radeon HD 6250 | 80 | 280MHz | 9W | ||
| AMD C-30 | 1 | 1.2GHz | Radeon HD 6250 | 80 | 280MHz | 9W | ||
AMD avoided branding its first APUs, they’re simply the AMD E-series and C-series Fusion APUs. The emphasis isn’t on the CPU or the GPU in this case, just the company name and a model number.
AMD's E-350
| CPU Specification Comparison | ||||||||
| CPU | Manufacturing Process | Cores | Transistor Count | Die Size | ||||
| AMD Zacate | 40nm | 2 | ? | 75 mm2 | ||||
| AMD Thuban 6C | 45nm | 6 | 904M | 346mm2 | ||||
| AMD Deneb 4C | 45nm | 4 | 758M | 258mm2 | ||||
| Intel Gulftown 6C | 32nm | 6 | 1.17B | 240mm2 | ||||
| Intel Nehalem/Bloomfield 4C | 45nm | 4 | 731M | 263mm2 | ||||
| Intel Sandy Bridge 4C | 32nm | 4 | 995M | 216mm2 | ||||
| Intel Lynnfield 4C | 45nm | 4 | 774M | 296mm2 | ||||
| Intel Clarkdale 2C | 32nm | 2 | 384M | 81mm2 | ||||
| Intel Sandy Bridge 2C (GT1) | 32nm | 2 | 504M | 131mm2 | ||||
| Intel Sandy Bridge 2C (GT2) | 32nm | 2 | 624M | 149mm2 | ||||
These APUs do need the aid of an additional chip - the Hudson Fusion Controller Hub (FCH). The FCH adds support for things like SATA, USB, Ethernet and Audio.The Hudson FCH is very tiny measuring approximately 4mm x 7mm for a total die size of around 28mm2.
The Hudson FCH
The combination of these Bobcat based APUs and the FCH is called the Brazos platform.
Late last year AMD invited me to spend several hours with a Brazos system at its brand new campus in Austin, TX. While the preview gave us some insight into what we could expect from Brazos, I didn’t have enough time to really dive in as much as I would’ve liked to.
Earlier this month, AMD officially launched Brazos with hardware expected sometime this quarter. For the past couple of weeks I’ve been testing a Brazos mini-ITX motherboard from MSI and today, it’s time to break the silence and share the results. They are quite good.
Facebook
Twitter
RSS
176 Comments
View All Comments
Belard - Tuesday, February 1, 2011 - link
It would fail at bluRay 3D.the 1080i is a bit unimportant since flatscreen TVs don't do interlace.
doctorpink - Tuesday, February 1, 2011 - link
if i remember correctly, nano runs 1.8ghz and is much faster but more power hungry...are there netbooks with nano anyway?
grego3d - Tuesday, February 1, 2011 - link
I'm sold on this Sandy Bridge / Atom killer. Well, maybe not Sandy Bridge killer yet, but i'm sure the second generation fusion processors will be. Now I need help finding a great little mini-itx case. I'd love to build a mini pc the size of my Wii. I have found a few small cases, but where on earth are the slot feed DVD/BD players. I always start my daily reading right here @ Anandtech.com so please save me some time and help us all out by rounding up a case review for this new Fusion platform. Go AMD Fusion - Boo Intel (and your 1$Billion oops!)Belard - Tuesday, February 1, 2011 - link
Sure is such excitement over such a tiny chip.It also reminds me why one of the P4s Dells I use at work is sooooooooooo Slooooooooooooooow.
I'll admit I'm using my very old computer (AMD X2 3800) as an HTPC somewhat, since it wasn't worth selling when I upgraded. But its a 90watt CPU... so saving power is the big thing, eh?
lovansoft - Tuesday, February 1, 2011 - link
I've got an Acer Aspire 5517 with an AMD Athlon tk-42 processor and integrated HD3200 video. It's also 1.6 Ghz so I wanted to showcase a relative clock for clock comparison. It is a 20W chip with 1meg cache built on a 65nm process and no VT. It's not an Athlon II, just an Athlon 64 x2, I believe.On Cinebench R10:
Single Thread: E-350=1174, TK-42=1340 :-: 1174/1340 = 87.6%
2 Threads: E-350=2251, TK-42=2373 :-: 2251/2373 = 94.4%
(1174+2251=3425)/(1340+2373=3713) = 92.2%
Scaling seems better on the new chips than on the older ones.
At idle with the screen off the laptop pulls about 18 watts. In Cinebench on a single thread it pulls about 30 watts, with 2 threads it pulls about 33 wats. Opening the screen to run the LCD at full brightness adds about 9 watts at any time.
I ran these tests with a Kill-A-Watt meter. It's not quite an exact comparison, but is pretty close. But to see that they kept performance close, added graphics, and still managed to shave 10% off TDP it's pretty dang impressive.
lovansoft - Tuesday, February 1, 2011 - link
Actually, I just let my laptop sit idle for a while. Now, idle power usage dips down to 11 watts with the lid closed and generally stays switching between 11-13 watts. Hmmm, the power usage on these new chips aren't quite as I would expect unless it's a platform thing. This article shows that the new chips pull 9W at full load under Cinebench. My testing shows I ramp from about 12W up to 33W which is a 21W increase by taxing the TK-42, right inline with the 20W spec giving my rounding of numbers. All other parts being equal and I only ramp up 9W instead of 21W then my peak should be about 12W less, or about 21W total instead of 33W total. That would be a significant gain. Interesting that this article has the new platform at 32.2W with the same workload. That's about 50% higher than my rough estimations. Is it because it's a desktop board and not a laptop design?sebanab - Wednesday, February 2, 2011 - link
Thanks for the performance comparison. I really helps putting the Zacate into perspective.On the power consumption comparison:
Ofcourse the desktop board system will consume more than a laptop with same specs.
Your laptop consumes less because of different PSU , less USBs , less components in general (PCIex) and so on.
So in order to make a correct comparison , wait for a HP DM1z review for example.
lovansoft - Wednesday, February 2, 2011 - link
I figured as much, but 50% seems high. But then again, it really is only a few watts... Lower efficiency PSU, a couple more chips to provide some extra ports. A couple of watts here and there do add up I suppose. And to think it provides more than 90% of my current performance into only 2/3 the power. I'd think if they can up it to 2Ghz it'd be about the same as mine without tapping the power too much. From the speculation I've read, it makes it seem that the revision coming in a year should grow the performance by quite a bit without really increasing power, about what you'd expect from a die shrink.You know, with this architecture, it'd be nice if a board could be made that would have multiples of these chips for server use. From my experience in SMB, I rarely find servers being CPU bound. Usually if they are, then there is some runaway process that needs to be tamed. Maybe this current generation isn't quite fast enough, but with a process shrink and some speed adjustments, getting a few of these on a board would make a very low energy server. But it'd only be feasible if there were something they could use that built in graphics portion for. Otherwise it'd be a waste.
Oh, and Cinnebench R10 on an AthlonXP 3000+ (2Ghz) = 1438.
Single Thread: E-350=1174, XP3000=1438 :-: 1174/1438 = 81.6%
1.6/2=80% Seems to be about the same IPC as the AthlonXP line.
I don't have power numbers for it, though.
torkemada - Wednesday, February 2, 2011 - link
Is E350IA-E45 board HDMI 1.4? Info on the net is confusing.Hrel - Thursday, February 3, 2011 - link
that VIA chip is pretty impressive.