Using Geode?

Wait until you see what you can do with AMD T16R and other AMD G-Series family of processors

Why should I migrate to G-T16R?

  • Lower average power consumption 2.3W vs. 2.45W
  • Support 64-bit OS with additional instruction sets, SSE, SSE2, SSE3 etc., to facilitate latest software development
  • Unparalleled video processing unit, featuring Radeon HD6000 series with hardware video acceleration engine
  • Most up to date video display interface, DisplayPort, LVDS and HDMI etc.
  • AMD-V™ support for virtualized application development
  • Lower cost, faster, higher capacity DDR3 memory replaces DDR1 used by Geode LX series
  • Legacy I/O (ISA with DMA) still supported via companion Hub controller

Processor Comparison: Geode LX800 vs. G-T16R

  AMD Geode LX800+CS5536 AMD G-T16R APU+A55E
Architecture x86 32-bit Scalar x86 64-bit Superscalar w/ full OOO Execution
x86 CPU Cores 1 1
Clock Speed 500MHz 615MHz
Memory DDR1 64-bit @ 400MT/s DDR3 64-bit @ 1066MT/s
L1 Cache 64KB/64KB 32KB/32KB
L2 Cache 128KB Unified 512KB L2
FPU MMX™, 3DNow! SSE1,2,3, SSSE3 ISA, SSE4A, MMX™
Virtualiation DirectX® 9 (2D) DirectX® 11 3D
I/O VIP / VOP 1 x4 PCIe® gen 2 (configurable)
Video Acceleration External Internal: UVD 2.0
Video Processing Supports video scaling, mixing and VOP, Hardware video up/down scalar, Graphics/video alpha blending and color key multiplexing HD HQV and SD HQV support: noise removal, detail enhancement, color enhancement, cadence detection, sharpness, and advanced de-interlacing, super up-conversion for SD to HD resolutions
Video Output Single: CRT, TFT Dual Independent: DisplayPort, eDP, HDMI, DVI, LVDS, VGA
Max Display Resolution 1920x1440x32-bpp @ 85Hz 1920x1200 @ 60Hz
Southbridge / Companion Device Connection PCI 33/66MHz "UMI": 1 x4 PCIe
Security 128-bit AES (CBC/ECB), True Random Number Generator None None
Debug JTAG - FS2 (Inactive) JTAG - Sage (Acive)
Power Consumption TDP = 3.9W (Max) Average = 2.45W TDP = 4.5W (Max) Average = 2.3W
Technology 13nm 40nm
Package 481-terminal BGA cavity up 413-terminal BGA ("FT1")
Solution footprint 40 x 40mm + 23 x 23mm = 2129mm2 19 x 19mm + 23 x 23mm = 890mm2
Ethernet External PCI device Internal (A55E) or through PCIe (A50M)
BootROM LPC SPI

Hub (companion I/O controller chip) Comparison

  CS5536 (Geode LX) A50M (G-T16R) A55E (G-T16R)
Processor Connection PCI 66MHz PCIe - x4 gen 1 PCIe - x4 gen 2
Clock Generation  
Ethernet MAC, EEE     , Gigabit MAC
Hard Drive ATA 66 SATA - 6 x 6Gb/s SATA - 6 x 6Gb/s
Flash NAND Flash and/or NOR Flash    
RAID, FIS-Based Switching     , 0/1/5/10
Audio AC '97 DMA Audio HD Audio - up to 4 channels HD Audio - up to 4 channels
PCIe   x 1 gen 1 4 x 1 gen 2
PCI PCI 66   32-bit, 33MHz up to 4 slots
I/O LPC, SMBus, UART, up to 16 GPIO SPI, LPC, SMBus, up o 102 GPIO Spi, LPC, SMBus, up to 102 GPIO
USB 2.0 + 1.1 ports 3 Host Ports, 1 Host/Client 14 + 2 14 + 2
APU Fan Control  
Consumer IR
RTC
MCTP  
Boot LPC SPI SPI
Power Consumption TDP = 0.65W
Average = 0.425W
TDP = 5.9W (Max)
Average = 0.965W
TDP = 5.9W (Max)
Average = 0.965W
Package 208-pin PBGA
23mm x 23mm
605-pin FCBGA
23mm x 23mm
605-pin FCBGA
23mm x 23mm

AMD G-Series Accelerated Processing Units

Model OPN Package CPU Cores L2 Cache / Core Memory Interface CPU Core Frequency Discrete Class Graphics  
T56N GET56NGBB22GVE FT1 413-pin µBGA 19mm2 2 512KB DDR3-1333, Unbuffered 1.65GHz AMD Radeon™ HD 6320 See the full chart →
T44R GET44RFPB12GVE 1 512KB DDR3-1066, Unbuffered 1.2GHz AMD Radeon™ HD 6250
T16R GET16RFWB12GVE 1 512KB LVDDR3-1066 615MHz AMD Radeon™ HD 6250
T48L GET48LGBB22GVE 2 512KB DDR3-1066, Unbuffered 1.4GHz N/A
T30L GET30LGBB12GVE 1 512KB DDR3-1066, Unbuffered 1.4GHz N/A
T24L GET24LFQB12GVE 1 512KB DDR3-1066, Unbuffered 1.0GHz N/A
See the full chart ↓

Need a little more muscle?

Introducing AMD Embedded G-Series System-on-Chip (SOC)

The AMD Embedded G-Series SOC platform is a high-performance, low-power System-on-Chip (SOC) design, featured with enterprise-class error-correction codec (ECC) memory support, dual and quad-core variants, integrated discrete-class GPU and I/O controller on the same die.

The AMD G-Series SOC achieves superior performance per watt in the low-power x86 microprocessor class of products when running multiple industry standard benchmarks. This helps enable the delivery of an exceptional HD multimedia experience and provides a heterogeneous computing platform for parallel processing. The small-footprint, ECC capable SOC sets the new foundation for a power efficient platform for content-rich multimedia processing and workload processing that is well-suited for a broad variety of embedded applications.

Architectural Overview of the AMD G-Series SOC

1st Generation APU SOC Design


Click on image to enlarge
  • Integrates Controller Hub functional block as well as CPU+GPU+NB
  • 28nm process technology, FT3 BGA package, 24.5mm x 24.5mm
  • Dual- or Quad-"Jaguar" CPU cores with 2MB shared L2 cache

Next Generation Graphics Core

  • Compute performance (GFLOP) improvement
  • DirectX® 11.1 graphics support

Memory Support: Single-Channel DDR3

  • Up to 2 UDIMMs or 2 SO-DIMM DDR3-1600 @ 1.35V & 1.25V
  • Support for ECC DIMMs

Integrated Display Outputs

  • Supports two simultaneous displays
  • Supports 4-len DisplayPort 1.2, DVI, HDMI™ 1.4a, Integrated VGA and Integrated eDP or 18bpp single channel LVDS

Updated I/O

  • Four x1 links of PCIe® Gen 2 for GPPs
  • One x4 link of PCIe Gen 2 for discrete GPU (not on lower TDPs)
  • 8 USB 2.0 + 2 USB 3.0
  • 2 SAATA 2.x/3.x (up to 6Gb/s)
  • SD Card Reader v3.0 or SDI controller