AMD Elite A-Series APU Design
AMD APUs are formed by taking AMD's core technologies from both sides of the business, CPUs and GPUs, and combining them into a single slice of silicon, as both devices were generally contained on separate PCBs in the past. This advancement in technology lowers communication latency between the two devices, allowing efficient use of both CPU and GPU compute designs as one single, seamless compute device. AMD has reiterated this design several times now and features a modular design that allows them to tailor designs specifically to their customer's needs, which has won them placement in upcoming next-generation consoles.
Here are a couple pictures of the chips themselves. They look exactly the same as all other AMD FM2 APUs but have a different model number. I noticed one other thing, though. On the surface of the PCB's corner sits a small golden "S". I've seen "T" and "N" markings on AMD PCBs before, but never an "S". What does it stand for, and how is this chip different?
The AMD Elite A-Series APU line-up includes AMD's latest x86 architecture featuring “Piledriver” cores. The five models share the same basic features.
- Turbo Charged x86 architecture featuring “Piledriver” cores
- Supports up to 4 cores and has support for the latest ISA instructions, including FMA4/3, AVX, AES, and XOP
- Up to 2MB L2 cache per dual-core module (up to 4MB total)
- Maximum Turbo Frequencies of up to 4.4 GHz
- Configurable via AMD OverDrive
The GPU portion of AMD's AMD Elite A-Series APU has seen a slight update as well. The details are listed below:
- AMD Radeon™ HD 8000 Series GPU Cores
- Featuring VLIW 4 architecture
- Up to 384 shaders
- Up to 844MHz
- Up to 8xAA and 16AF support
- Controllable via AMD OverDrive
- DirectX®11 Support