| Customization: | Available |
|---|---|
| Type: | Development Board |
| Trademark: | chipboard |
| Shipping Cost: | Contact the supplier about freight and estimated delivery time. |
|---|
| Payment Methods: |
|
|---|---|
| Support payments in USD |
| Secure payments: | Every payment you make on Made-in-China.com is protected by the platform. |
|---|
| Refund policy: | Claim a refund if your order doesn't ship, is missing, or arrives with product issues. |
|---|
Suppliers with verified business licenses
Audited Supplier Audited by an independent third-party inspection agency
| Descripition |
The K230 chip is the latest generation SoC product in Canaan Technology's (NASDAQ: CAN) Kendryte® series of AIOT chips. The chip adopts a brand-new multi-heterogeneous unit acceleration computing architecture, integrates two RISC-V C908 computing cores, and has a built-in new generation KPU (Knowledge Process Unit) intelligent computing unit. Multi-precision AI computing power with INT8 and INT16. Supports general AI computing framework. The chip also has a variety of peripheral interfaces, as well as multiple scalar, vector, graphics, and other dedicated hardware acceleration units such as image 2D engine, AI 2D engine, 2.5D GPU, and 3D depth engine. K230 provides full-process computing acceleration for various computing tasks such as images, videos, audio, AI, etc. The chip has many features such as low latency, high performance, low power consumption, fast startup, and high security. K230 can be used in various smart hardware products, such as smart door locks, home smart security cameras, dictionary pens, payment recognition, 3D structured light vision modules, drones, interactive robots, smart home appliances, smart toys, and smart manufacturing, intelligent vehicle cockpit and many other fields.
CPU: core1 - 64bit, RISC-V processor, 1.6GHz, supports RISC-V Vector Extension 1.0 specification with FPU, VPU; core0 - 64bit, RISC-V processor, 800MHz, supports RISC-V 64GCB instruction set;
KPU: Support INT8 and INT16, TVM / TensorFlow / Pytorch / ONNX; Typical network performance: Resnet 50 ≥ 85fps @INT8; Mobilenet_v2 ≥ 670fps @INT8; YoloV5S ≥ 38fps @INT8;
DPU: Using 3D structured light depth calculation; Typical performance is 1280*800@30fps
VPU: Video encoding/decoding: H.264/H.265/JPEG/MJPEG, 4K@40fps/20fps
Memory: 512MB DDR, TF Card Storage up to 1T, QSPI Flash
Camera: 500M Camera *1, Max 3ch MIPI CSI input;
Display: HDMI 1; MIPI DSI 1, Max 1920 * 1080@60fps
USB: USB2.0 OTG * 1
Ethernet: 100Mbps * 1
Others: Audio Interface 1, Debug UART 2, I2C 4, PWM 5, GPIO * 29
Board Size: 56 x 85mm
){kind=link}