Product details
The Best Single Board Computer AI Accelerator Card FZ5 is an outstanding Artificial Intelligence (AI) accelerator card based on the Xilinx Zynq UltraScale+ ZU5EV MPSoC. It features a 1.5 GHz quad-core ARM Cortex-A53 64-bit application processor, a 600 MHz dual-core real-time ARM Cortex-R5 processor, a Mali 400 embedded GPU, and a H.264/H.265 Video Codec Unit (VCU), along with rich FPGA fabric. The card delivers up to 2.4 TOPS of computing power and can handle 55 FPS with ResNet-50 backbone networks, making it highly versatile for AI applications.
In addition to its powerful processing capabilities, the Best Single Board Computer AI Accelerator Card FZ5 is equipped with 8GB DDR4 RAM, 32GB eMMC storage, 64MB QSPI Flash, and 32KB EEPROM. It also features a wide range of peripheral interfaces, including RS232, RS485, 4 x USB 3.0, Gigabit Ethernet, CAN, TF, DisplayPort (DP), HDMI-IN, USB-UART, JTAG, and IO expansion interfaces. This makes it highly suitable for secondary development and ideal for use in AI boxes or various other embedded designs.
FZ5 Top View (delivered with active heat sink by default)
FZ5 Bottom View
The Best Single Board Computer AI Accelerator Card FZ5 is capable of running PetaLinux 2019.1 and comes with a complete Linux BSP. It also supports the PaddlePaddle AI framework, which is fully compatible with Baidu Brain’s AI development tools such as EasyDL, AI Studio, and EasyEdge. This enables developers and engineers to quickly leverage Baidu’s proven technology or deploy their own custom models, facilitating faster deployment.
MYIR also provides the FZ5 EdgeBoard AI Box for the FZ5, featuring a rugged and fanless enclosure designed for efficient development in various embedded vision applications, including multimedia, automotive ADAS, surveillance, industrial quality inspection, and medical diagnosis. The device supports an extended operating temperature range from -40 to 70 degrees Celsius, ensuring reliability in harsh environments. Its compact size and robust stability make it ideal for deployment in the field. The FZ5 EdgeBoard AI Box offers powerful AI capabilities, capable of running massive and iterative models for image recognition tasks such as face, human body, animal, object, text, logo detection, and various customized scenarios.
FZ5 EdgeBoard AI Box Front View
FZ5 EdgeBoard AI Box Rear View
| Features | Description |
| Dimensions | 107mm x 96mm (14-layer PCB design) |
| Power supply | DC 12V/3A |
| Working Temp. | -40~85 Celsius |
| SoC | Xilinx Zynq UltraScale+ XCZU5EV-2SFVC784I (ZU5EV, 784 Pin Package) MPSoC – 1.5 GHz 64 bit Quad-core ARM® Cortex™-A53 Application Processing Unit – 600MHz Dual-core ARM® Cortex™-R5 Real-time Processing Unit – ARM Mali™-400 MP2 Graphics Processing Unit (GPU) – H.264 and H.265 Video Codec Unit (VCU) – 16nm FinFET+ FPGA fabric |
| Memory | 8GB DDR4 (64bit, 2400MHz) |
| Storage | 32GB eMMC
64MB QSPI Flash 32KB EEPROM 1 x TF card interface |
| Communications | 1 x RS232
1 x RS485 1 x CAN interface 1 x 10/100/1000 Mbps Ethernet 4 x USB 3.0 Host 1 x USB-UART debug interface |
| Display | 1 x HDMI In port
1 x Mini DisplayPort (DP), 4K/30fps |
| RTC | 1 x 3V Rechargeable RTC Battery Interface (battery is not soldered by default, Model MS621T is recommended)
1 x 1.5V Non-Rechargeable RTC Battery Holder (battery is not provided by default, Model AG3 or LR41 is recommended) |
| User I/O | 1 x FPC_40PIN (Reserved for MIPI-CSI) 1 x 1.27mm pitch 2 x 50-pin IO Expansion Interface (5 x PS_MIO, 69 x PL_IO) |
| Others | 1 x 2.54mm pitch 6-pin JTAG interface 2 x Buttons (1x FPGA Reset, 1 x System Reset) 5 x LEDs (Power LED: 1 x RED; Status LED: 2 x RED, 2 x Green) |
| Software | Supports Running PetaLinux
Supports Baidu’s PaddlePaddle AI Framework |
| Target Applications | Evaluation and Prototyping for XCZU5EV Zynq UltraScale+ MPSoC
Intelligent Security Industrial Testing Medical Diagnosis UAV Inspection Scientific Research Consumer Electronics Driverless Technology |
Features of FZ5
Best Single Board Computer AI Accelerator Card Hardware Features
Zynq® UltraScale+™ MPSoC devices offer 64-bit processor scalability, integrating real-time control with soft and hard engines for graphics, video, waveform, and packet processing. Built on a unified platform that combines a real-time processor and programmable logic, the devices are available in three distinct variants:
- Dual application processor (CG) devices
- Quad application processor and GPU (EG) devices
- Video codec (EV) devices
These variants provide flexibility to meet a wide range of application requirements.
Zynq UltraScale+ MPSoCs
The Zynq UltraScale+ family ensures footprint compatibility, allowing users to easily migrate designs between different devices. Any two packages with the same footprint identifier code (the last letter and number sequence) are footprint compatible. By default, MYIR uses the XCZU5EV-2SFVC784I MPSoC for the FZ5. The C784 package offers the widest footprint compatibility, enabling users to choose devices from the CG, EG, and EV variants without changing the board design.
Zynq UltraScale+ MPSoC Device Migration Table
The main features for the MPSoC devices are summarized as below.
| Device | XCZU2CG | XCZU3CG | XCZU3EG | XCZU4EV | XCZU5EV |
| Logic cells (k) | 103 | 154 | 154 | 192 | 256 |
| CLB Flip-Flops (K) | 94 | 141 | 141 | 176 | 234 |
| CLB LUTs (K) | 47 | 71 | 71 | 88 | 117 |
| Block RAM (Mb) | 5.3 | 7.6 | 7.6 | 4.5 | 5.1 |
| UltraRAM (Mb) | – | – | – | 13.5 | 18.0 |
| DSP Slices | 240 | 360 | 360 | 728 | 1,248 |
| GTX transceivers | PS-GTR4x (6Gb/s) | PS-GTR4x (6Gb/s) | PS-GTR4x (6Gb/s) | PS-GTR4x (6Gb/s), GTH4x (16.3Gb/s) | PS-GTR4x (6Gb/s), GTH4x (16.3Gb/s) |
| Processor Units | |||||
| Application Processor Unit |
Dual-core ARM® Cortex™-A53 MPCore™ up to 1.3GHz |
Quad-core ARM® Cortex™-A53 MPCore™ up to 1.5GHz |
|||
| Memory w/ECC |
L1 Cache 32KB I / D per core, L2 Cache 1MB, on-chip Memory 256KB |
||||
| Real-Time Processor Unit |
Dual-core ARM Cortex-R5 MPCore™ up to 600MHz |
||||
| Memory w/ECC |
L1 Cache 32KB I / D per core, Tightly Coupled Memory 128KB per core |
||||
| Graphics Processing Unit | – | – |
Mali™-400 MP2 up to 667MHz |
||
| Video Codec | – | – |
– |
H.264 / H.265 |
|
| Memory L2 Cache |
64KB |
||||
|
External Memory, Connectivity, Integrated Block Functionality |
|||||
| Dynamic Memory Interface |
x32/x64: DDR4, LPDDR4, DDR3, DDR3L, LPDDR3 with ECC |
||||
| Static Memory Interfaces |
NAND, 2x Quad-SPI |
||||
| High-Speed Connectivity |
PCIe® Gen2 x4, 2x USB3.0, SATA 3.1, DisplayPort, 4x Tri-mode Gigabit Ethernet |
||||
| General Connectivity |
2 x USB 2.0, 2 x SD/SDIO, 2 x UART, 2 x CAN 2.0B, 2 x I2C, 2 x SPI, 4 x 32b GPIO |
||||
| Power Management |
Full / Low / PL / Battery Power Domains |
||||
| Security |
RSA, AES, and SHA |
||||
| AMS – System Monitor |
10-bit, 1MSPS – Temperature and Voltage Monitor |
||||
Zynq UltraScale+ MPSoC Device Selection Guide
Dimensions of FZ5
Best Single Board Computer AI Accelerator Card Software Features
The Best Single Board Computer AI Accelerator Card FZ5 is capable of running PetaLinux 2019.1 and supports the PaddlePaddle AI framework, which is fully compatible with Baidu Brain’s AI development tools such as EasyDL, AI Studio, and EasyEdge. This enables developers and engineers to quickly leverage Baidu’s proven technology or deploy their own custom models, facilitating faster and more efficient deployment.
|
Item |
Features |
Description |
Source code provided |
|
Tool chains |
gcc8.2.0 |
gcc version 8.2.0 |
|
|
gcc 5.2.1 |
gcc version 5.2.1 (Linaro GCC 5.2) |
|
|
|
Bootloader |
boot.bin |
First boot program including FSBL and u-boot2019.01 |
Yes |
|
Linux Kernel |
Linux 4.19.0 |
Customized kernel for FZ5 |
Yes |
|
|
USB2.0/3.0 Host |
USB2.0/3.0 Host driver |
Yes |
|
Ethernet |
Gigabit Ethernet driver |
Yes |
|
|
MMC/SD/TF |
MMC/SD/TF card driver |
Yes |
|
|
Qspi flash |
Qspi flash driver |
Yes |
|
|
CAN |
CAN driver |
Yes |
|
|
DP |
DP driver |
Yes |
|
|
I2C |
I2C driver |
Yes |
|
|
UART |
UART driver |
Yes |
|
|
Watchdog |
Watchdog driver |
Yes |
|
|
GPIO |
GPIO driver |
Yes |
|
|
LED |
LED driver |
Yes |
|
|
Button |
Button driver |
Yes |
|
|
RTC |
RTC driver |
Yes |
|
|
HDMI |
HDMI IN driver |
Yes |
|
|
Application |
HDMI |
HDMI IN example |
Yes |
|
CAN |
CAN example |
Yes |
|
|
Net |
Socket example |
Yes |
|
|
File system |
Ramdisk |
Ramdisk System Image |
|
|
Rootfs |
Buildroot making including Qt |
Yes |
|
|
Petalinux |
Petalinux2019.1 |
Supports Xilinx Petalinux2019.1 development tools. MYIR provides complete BSP for the FZ5 |
|
Features of Linux BSP
Baidu Brain’s AI development tools
Software Architecture of FZ5
FZ5 Top View (delivered with active heat sink by default)
Best Single Board Computer AI Accelerator Card FZ5 Top View
Best Single Board Computer AI Accelerator Card FZ5 Bottom View
There are no reviews yet.