FZ3 Card
Deep Learning Accelerator Card based on XCZU3EG Zynq UltraScale+ MPSoC
AMD/Xilinx Zynq UltraScale+ ZU3EG MPSoC
1.2 GHz Quad Arm Cortex-A53 and 600MHz Dual Cortex-R5 Cores
4GB DDR4 (64-bit, 2400MHz), 8GB eMMC, 32MB QSPI Flash, 32KB EEPROM
USB2.0, USB3.0, Gigabit Ethernet, TF, DP, PCIe, MIPI-CSI, BT1120, USB-UART, JTAG…
Computing Power up to 1.2TOPS, MobileNet up to 100FPS
Ready-to-Run PetaLinux 2020.1
Supports Xilinx Vitis Software Development Platform
AMD Approved Adaptive Computing Partner
Powerful AI Computing Performance & Low Power Consumption
The FZ3 Deep Learning Accelerator Card, leveraging the Xilinx Zynq UltraScale+ MPSoC XCZU3EG, incorporates a 4-core Cortex-A53 processor. Its measured performance can reach up to 1.2 TOPS, achieving 100FPS for MOBILENET under quantized pruning, exceeding CPU performance by 20 times, while consuming only 5-10W of power. When the model is not pruned or quantized, the performance of the accelerator card is still excellent.
Singel Board Computer - FZ3 Card
The FZ3 Card is a powerful deep learning accelerator card based on Xilinx Zynq UltraScale+ ZU3EG MPSoC which features a 1.2 GHz quad-core ARM Cortex-A53 64-bit application processor, a 600MHz dual-core real-time ARM Cortex-R5 processor, a Mali400 embedded GPU and rich FPGA fabric. Besides, it integrates 4GB DDR4, 8GB eMMC, 32MB QSPI Flash and 32KB EEPROM as well as many peripherals including USB 2.0, USB 3.0, Gigabit Ethernet, TF, DisplayPort (DP), PCIe interface, MIPI-CSI, BT1120 camera, USB-UART, JTAG, IO expansion interfaces, etc. The rich resources enable users to integrate intelligent hardware easily.
The FZ3 Card is able to run PetaLinux 2020.1 and and provided complete BSP. It can support Xilinx Vitis Software development platform. It can also supports PaddlePaddle deep learning AI framework which is fully compatible to use Baidu Brain’s AI development tools like EasyDL, AI Studio and EasyEdge to enable developers and engineers to quickly leverage Baidu-proven technology or deploy self-defined models, enabling faster deployment. Typical applications are AI camera, AI computing device, robotics, intelligent car, intelligent electronic scale, patrol UAV and other embedded intelligent applications.
MYIR provides FZ3 Kit which contains the FZ3 Card with installed radiator and some necessary accessories including one power adaptor, one 16GB TF card, one mini USB cable and one mini DP to HDMI cable. It helps users start their development rapidly when getting the kit out-of-box right away.
Rich Development Resources and Tool Platforms
The FZ3 deep learning accelerator card, powered by the Xilinx Zynq UltraScale+ MPSoC XCZU3EG, offers seamless compatibility with the Baidu Brain tool platform, providing a one-stop solution to lower the threshold for AI development.
FZ3 Deep Learning Accelerator Card for Embedded Intelligent Applications
The FZ3 Deep Learning Accelerator Card is suited for a diverse array of applications spanning intelligent security, industrial inspection, medical diagnosis, drone surveillance, scientific research, consumer electronics, and autonomous driving. It finds applicability in various devices and systems, including AI cameras, computing boxes, robots, smart cars, intelligent electronic scales, and numerous other cutting-edge technologies.
Security Monitoring
Industrial Quality Inspection
Scientific Research and Education
Medical Diagnosis
Autonomous Driving
Intelligent Retail
Hardware & Software
Item | Description |
---|---|
Processor | Xilinx Zynq UltraScale+ XCZU3EG-1SFVC784E (ZU3EG, 784 Pin Package) MPSoC - 1.2GHz 64 bit Quad-core ARM® Cortex™-A53 - 600MHz Dual-core ARM® Cortex™-R5 processor - ARM Mali™-400MP2 Graphics Processor - 16nm FinFET+ FPGA fabric |
Memory | 4GB DDR4 (64-bit) |
Storage | 8GB eMMC 32MB QSPI 32KB EEPROM 1x Micro SD card slot |
PCB | 12-layer PCB design |
Power Supply | DC 12V/2A |
Dimensions | 100mm x 70mm |
Working Temperature | -40~+85℃ |
Debug UART | 1x Mini USB-to-UART Port |
Ethernet | 1x 10/100/1000 Mbps Ethernet |
USB | 1x USB 2.0 Host 1x USB 3.0 Host |
PCIe | 1x PCIe 2.1 Interface (1-lane) |
DP | 1x Mini DisplayPort (4K/30fps, 2-lane) |
MIPI-CSI | 1x MIPI-CSI Interface (25-pin 0.3mm pitch FPC connector) |
BT1120 | 1x BT1120 Camera Interface (32-pin 0.5mm pitch FPC connector) |
Buttons | 1x FPGA Reset Button 1x System Reset Button |
LEDs | 5x LEDs - 1x Power LED - 4x Status LEDs (2 x Red, 2 x Green) |
JTAG | 1x 6-pin 2.54mm pitch pin header |
RTC | 1x RTC Battery Socket (AG2 or LR41 battery is recommended) |
Expansion Interface | Two 2.54mm pitch 2 x 20-pin IO Expansion Interfaces Some signals are reused. Please refer to the board schematic and processor datasheet. |
Item | Features | Description | Source Code |
---|---|---|---|
Boot program | BOOT.BIN | First boot program including FSBL and u-boot2020.01 | YES |
Linux Kernel | Version | Linux 5.4.0 | YES |
Drivers | 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 | |
Button | Button driver | YES | |
UART | UART driver | YES | |
LED | LED driver | YES | |
GPIO | GPIO driver | YES | |
Watchdog | Watchdog driver | YES | |
MIPI | MIPI camera driver | YES | |
File System | Ramdisk | Ramdisk system image | |
Rootfs | Buildroot making including Qt | YES | |
Tool Chains | gcc 8.3.0 | gcc version 8.3.0 | |
gcc 9.2.0 | aarch64-none-elf-gcc version 9.2.0 | ||
Application | LED | LED example | YES |
CAN | CAN example | YES | |
NET | Socket example | YES | |
QT-Camera | MIPI Camera example | YES | |
PetaLinux | Petalinux2020.1 | Supports Xilinx Petalinux2020.1 development tools. MYIR provides complete BSP for the FZ3 card. |
Ordering