AMD A8-3850 Llano APU and Lynx Platform Preview


Introduction and Specifications

A couple of weeks back, we took a look at AMD's Llano mobile platform, with a mainstream notebook from Compal, and we came away impressed. If you're unfamiliar with Llano, be sure to check out our launch coverage (available here). But to quickly recap, Llano is the codename for AMD's latest Fusion-based product, that combines a CPU and GPU on a single piece of silicon. In the mobile space, Llano offers a capable quad-core CPU, with excellent DX11-class integrated graphics, in a very low power-envelope. Those things translate into good performance and solid battery life in a notebook, two highly desirable traits of mobile system.

AMD is now ready with Llano-based products for the desktop. On the desktop, Llano offers similar things. In fact, the underlying technology is identical. But the desktop landscape is very different from the mobile space. Desktops aren't constrained by the limited form-factors and thermal requirements of mobile systems, and as such, Llano has to compete with a much broader range of options and architectures.


AMD Llano Die Shot...

AMD thinks they have struck the right balance between CPU and GPU performance though, and at some very budget-friendly price points. Ultimately, consumers will decide if AMD is on target. In the meantime, we've got the first AMD Llano-based desktop APU, the A8-3850, in the lab, complete with a quartet of A75-chipset based motherboards. Pairing an A-Series APU and A-Series chipset results in what AMD is calling their "Lynx" platform. Cool codenames aside, there's lots of tech to discuss here, so take a gander at the features and specifications below and join as as we find out if Llano is as desirable on the desktop as it is in a notebook...

AMD A8-3850 "Llano" APU
Specifications & Features
Tech / Package 32nm / FM1 905-pin lidded μPGA, 40x40 mm, 1.27 mm pitch
TDP Configurations 65W and 100W configurations
Processor Core “Stars” 32nm HKMG process core (up to 4 cores), 128 KB L1 Cache(64 KB Instruction, 64 KB Data) 1 MB L2/Core, 128-bit FPUs
Memory Up to DDR3 1866
Graphics Core Up to 400 Radeon Cores, DirectX 11 capable, UVD3
Displays Digital Display I/F DP0: Display Port, HDMI, DVI
Digital Display I/F DP1: Display Port, HDMI, DVI
Graphics Features AMD Dual Graphics
Blu-ray 3D
AMD Steady Video
AMD Perfect Picture
DisplayPort 1.1a, HDMI 1.4a
 
Power Management Multiple low-power states
32-nm process for decreased power consumption
PCIe core power gating
PCIe speed power policy
GPU power gating of Radeon Cores and video decode (UVD3)
AMD Turbo Core technology on select models
AMD A75/AMD A55 FCH  
Tech/Package 65nm / FC BGA, 605-Ball, 23x23mm, .8mm pitch
TDP Configurations A75: 7.8W, A55: 7.6W
UMI x4 Gen 2
SATA A75: 6 ports at 6 Gb/s, A55: 6 ports at 3 Gb/s
RAID 0,1,10
USB A75: 4 USB 3.0 Ports, 10 USB 2.0 Ports, 2 USB 1.1 Internal Ports A55: 14 USB 2.0 Ports, 2 USB 1.1 Internal Ports
PCIe GPPs 4x1 Gen2
FIS Support A75 only
CIR CIR Receiver
Clock Gen Integrated
Power Rails SVID for VDDCR_CPU & VDDR_NB, fixed voltage for other rails
 
Software/Firmware
 
Software Drivers: Windows 7, Windows Vista, Windows XP, Linux


Click to Enlarge

The specifications above give a glimpse into what makes Llano tick, but the slide pictured here tells more of the story. With Llano, AMD has taken the position that GPU performance is more important than CPU performance, when said CPU is "fast enough" for the vast majority of workloads. To illustrate, the slide above compares a Llano die with a Sandy Bridge die. Although they're of roughly similar size (228mm2 vs. 216mm2), AMD has devoted much more real estate to Llano's integrated GPU core, whereas Intel's x86 cores cover a larger area. There are far more technical details at play here, and we're simplifying the explanation, but the moral of the story is that Intel's architecture will offer better general compute / x86 performance, while AMD's will offer better graphics and multimedia performance. Which aspect of system performance is more important is up to the application workload, of course, but the diverging philosophies are interesting to say the least.


Related content