来自Jack's Lab
跳转到: 导航, 搜索


1 Overview


  • 64-bit RISC-V CPU Dual-Core, up to 400MHz
  • IMAFDC (RV64GC) ISA extension
  • Hardware FPU (Float Point Unit), Double Precision
  • 32 KB I-Cache per core
  • 32 KB D-Cache per core

  • 8MB On-Chip SRAM
  • 128Kbit One-Time Programmable Memory (OTP)
  • Read Only Memory (ROM)
  • DMA

  • Neural Network Accelerator (KPU)
  • Audio Accelerator (APU)
  • FFT Accelerator
  • SHA256 Accelerator
  • AES Accelerator

  • DVP x1
  • UART x4
  • GPIO x40
  • I2C x3
  • SPI x4
  • I2S x3
  • PWM x1
  • Timer x3
  • RTC x1
  • Watchdog Timer (WDT) x1

  • JTAG, OpenOCD support
  • BGA144 with 12 balls on each side
  • The chip size is 8 x 8 x 0.953mm

2 Datasheet

https://kendryte.com/downloads/ http://dl.sipeed.com/MAIX/HDK


KPU is a general-purpose neural network processor with built-in convolution, batch normalization, activation, and pooling operations.

It can detect faces or objects in real time.

  • Supports the fixed-point model that the mainstream training framework trains according to specific restriction rules
  • There is no direct limit on the number of network layers, and each layer of convolutional neural network parameters can be configured separately, including the number of input and output channels, and the input and output line width and column height
  • Support for 1x1 and 3x3 convolution kernels
  • Support for any form of activation function
  • The maximum supported neural network parameter size for real-time work is 5MiB to 5.9MiB
  • The maximum supported network parameter size when working in non-real time is (flash size - software size)


The APU pre-processing module is responsible for the pre-processing of voice direction and voice data output.

  • Up to 8 channels of audio input data, ie 4 stereo channels
  • Simultaneous scanning pre-processing and beamforming for sound sources in up to 16 directions
  • Supports one active voice stream output
  • 16-bit wide internal audio signal processing
  • Support for 12-bit, 16-bit, 24-bit, and 32-bit input data widths
  • Multi-channel direct raw signal output
  • Up to 192kHz sample rate
  • Built-in FFT unit supports 512-point FFT of audio data
  • Using system DMA to store output data in system memory


The SRAM is split into two parts, 6MB for general-purpose, 2MB for AI

The AI SRAM is for the KPU. They are distributed in a contiguous address space, available both through the normal cached interface of the CPU, but also directly through the non-cached interface.

Region                    Access                Start Address             End Address                Size
General-purpose SRAM     CPU cached              0x80000000                0x805FFFFF                0x600000
AI SRAM                  CPU cached              0x80600000                0x807FFFFF                0x200000
General-purpose SRAM     CPU non-cached          0x40000000                0x405FFFFF                0x600000
AI SRAM                  CPU non-cached          0x40600000                0x407FFFFF                0x200000

6 Quick Start


7 Reference