Sigmastar Sdk -

Here is a typical workflow for a developer unboxing a SigmaStar development board (like the Eagle or Infinity board).

Step 1: Environment Setup You cannot build the Sigmastar SDK on macOS; you need Ubuntu 18.04 or 20.04 (22.04 often has glibc compatibility issues).

tar -xjf Sigmastar_SSCV5_SDK.tar.bz2
cd Sigmastar_SSCV5_SDK
source build/envsetup.sh

You will be prompted to select your chipset. Type the number corresponding to your target (e.g., 33 for SSC333). sigmastar sdk

Step 2: Configuration Unlike generic Linux, you configure the kernel and drivers using a menuconfig system:

make menuconfig

Here you select your sensor driver (Sony IMX307, Omnivision OV4689, etc.), enable WiFi drivers (Realtek/MTK), and configure memory partitions. Here is a typical workflow for a developer

Step 3: The Build Building the full SDK for the first time can take 30–60 minutes depending on your CPU.

make image

This produces:

The newest version of the Sigmastar SDK (v5.x and v6.x) focuses heavily on NPU pipelining. To achieve 30 FPS inference on a 2MP stream, you must avoid copying memory from the ISP to the NPU.

Best practice: Use the MI_SYS_Bind function to create an in-memory pipeline: Sensor -> ISP -> VPE -> NPU (NN) -> VENC This prevents "User Space copying," which is one of the biggest performance bottlenecks in embedded vision. You will be prompted to select your chipset

To master the Sigmastar SDK, you must understand its modular architecture. When you download the SDK (typically a compressed .tar.bz2 file), you will find several distinct directories: