AMD A8-3850 2.9GHz Llano Desktop APU Review

AMD announced the Fusion A-Series Accelerated Processing Unit (APU) for desktop PCs. AMD has upped the ante, packing their newly minted desktop A6/A8 APUs with much beefier central and graphics processors manufactured using a 32 nm fabrication process (down from 45/40 nm). The CPU portion has four cores, built on the same K10 architecture as the Phenom II family. Driving graphics are modified Redwood chips (HD 5000 series cores) with the latest version of UVD and improved power gating to maximize energy efficiency. They also sport whopping 320/400 Radeon cores (AKA stream processors or shaders) compared to the 80 in the HD 6250/6310 chips found in Brazos APUs, so they’ve got some teeth and can do more than play HD video. Along with these upgrades comes a new socket, FM1, which with its 905 pins is incompatible with AM3 and AM3+.This is a significant milestone for AMD as it means that the company has now successfully launched their ‘Llano’ APU architecture for both mobile and desktop platforms.The A8-3850 has a 2.9GHz quad-core CPU, 600MHz GPU w/ 400 Radeon cores, 4MB of L2 cache and a 100W TDP.

On quad core versions of Lynx, the CPU takes up just over a half of the die, while the GPU occupies a significant portion on the other side. Due to space, cost, and energy constraints, L3 has been omitted. Each CPU core has its own dedicated 1MB of L2 cache, twice that of the Athlon II line. The die size is 228 mm² compared to 216 mm² for Sandy Bridge and and 256 mm² for Deneb (Phenom II).

AMD A-Series APU’s come in two main series the A6 and the A8. One of the major differences between the two series is the GPU that is inside of the APU. The AMD A8-3800 and A8-3850 will have AMD Radeon HD 6550D GPUs inside the APU that have 400 Radeon cores and a clock speed of 600MHz. The Radeon HD 6550D is capable of reaching 480 GFLOPS of GPU peak compute, which is rather impressive.  For those that don’t need that much graphics power the AMD A6 series features the Radeon HD 6530D GPU, which has 320 Radeon cores running at 443MHz and just 284 GFLOPS of GPU compute power.

A version of Hybrid CrossFireX is also included with the new APUs called Dual Graphics which allows one to combine the prowess of the IGP with a discrete GPU.You need to use discrete add-in video cards like the Radeon HD 6350, 6450, 6570 and 6670. When you add this GPU to an APU the naming scheme gets rather crazy as you can see from the chart above.

The image above shows an actual A8-3850 APU. It is different from previous AMD processors since it is packaged with 905-pins in a socket FM1 configuration for the new AMD A75 ‘Hudson D3’ chipset that is needed for a ‘Lynx’ platform.

The AMD A75 chipset is very impressive and should make for the foundation of a solid mainstream platform. In the block diagram above you can see that the A75 chipset connects to the APU using AMD’s Unified Media Interface (UMI) that is rated as having 2GB/s of bandwidth. Main highlights of the A75 chipset is support for six SATA 6GB/s ports, with RAID 0,1,10 support and FIS based switching, 4 USB 3.0 ports, 10 USB 2.0 ports, and 2 USB 1.1 ports. It then features an additional 4×1 PCI Express Gen 2 lanes and a magnitude of other connection possibilities for motherboard makers to use if they wanted to.

CPU-Z, GPU-Z and Windows Index Score

Here is a CPU-Z v1.58 screen shot of the AMD A8-3850 APU to show you what everything looks like with the latest version of CPU-Z.  The processor has a base clock of 100MHz with a multiplier of 29. There are four x86 cores that each have 128 KB L1 cache (64KB data and 64KB instruction) along with 1MB of L2 cache per core. The AMD A6 and A8 series are not Black Edition processors, so that means they feature  a locked multiplier that you can lower the in the BIOS.

The latest build of GPU-Z is 0.54, but it doesn’t properly detect the Radeon HD 6550D GPU. The Radeon HD 6550D has 400 shader cores and a clock speed of 600MHz.

Benchmark Results: The x264 HD benchmark is said to be ideal for a benchmark because the application reports fairly accurate compression results for each pass of the video encoding process, and it uses multi-core processors very efficiently. The Intel Core i3-2105 does fairly well in this benchmark, but turned out to be slower than the AMD A8-3850 APU.  Keep in mind that the Intel Core i3-2105 is a dual-core processor with hyper-threading and the AMD A8-3850 is a true quad-core processor.

The AMD A8-3850 APU has a TDP of 100W.At an idle the AMD A8-3850 is amazingly power friendly and used just 36.2W.The AMD A8-3850 clearly uses more power at load than the Intel Core i3-2105, but as you saw in the benchmarks the AMD A8-3850 also had slightly better performance across the board.