Nvidia Jetson
Edge AI solutions with Nvidia Jetson family
Following the global technology trends, we are aiming for bringing AI to the edge. To do this, we collaborate with the best – Nvidia has already created a golden standard for on-device AI with its Jetson product family.
Using high-performance & energy-efficient Nvidia Jetson Nano, Jetson TX2, Jetson Xavier NX, or Jetson AGX Xavier AI computing platforms in FPGA programming projects, we provide premier hardware design services.
About Nvidia Jetson
Nvidia Jetson products are great embedded solutions that are scalable and power-efficient. Each system represents a comprehensive SoM (System-on-Module), containing a CPU, GPU, DRAM, flash storage, and PMIC.
The whole product family has a common software stack, which adds to easy and widespread deployment. Nvidia provides Jetson platforms with the same Jetpack SDK, including BSP (board support package), Linux OS, and Nvidia CUDA. It is compatible with 3rd-party platforms.
Our services
We offer a range of development services using NVIDIA Jetson platforms: from custom software/hardware design to turnkey product development, whether for startups, niche companies, market leaders or enterprises.
Electronic hardware design on Jetson
Power & performance optimization
ML/DL algorithms deployment
Audio & Video
Firmware & BSP development
Mobile & Cloud apps development
Edge AI solutions application areas
Smart Surveillance
Industrial robotics
Audio analytics
Predictive maintenance
Body monitoring
Autonomous vehicles
Face recognition
Expression analysis
Nvidia Jetson module specification comparison
| Jetson Nano | Jetson TX2 Series | Jetson Xavier NX | Jetson AGX Xavier | |||
| TX2 NX | TX2 4GB | TX2 | TX2i | |||
| 472 GFLOPS | 1.33 TFLOPS | 1.26 TFLOPS | 21 TOPS | 32 TOPS | ||
| 128-core NVIDIA Maxwell™ GPU | 256-core NVIDIA Pascal™ GPU | 384-core NVIDIA Volta™ GPU with 48 Tensor Cores | 512-core NVIDIA Volta™ GPU with 64 Tensor Cores | |||
| Quad-core ARM®Cortex®-A57MPCore processor | Dual-core Denver 2 64-bit CPU and quad-core Arm® Cortex®-A57 MPCore processor | 6-core NVIDIA Carmel ARM®v8.2 64-bit CPU 6MB L2 + 4MB L3 | 8-core NVIDIA Carmel Arm®v8.2 64-bit CPU 8MB L2 + 4MB L3 | |||
| 4 GB 64-bitLPDDR4 25.6GB/s | 4 GB 128-bit LPDDR4 51.2GB/s | 8 GB 128-bitLPDDR4 59.7GB/s | 8 GB 128-bitLPDDR4 (ECC Support) 51.2GB/s | 8 GB 128-bit LPDDR4x 51.2GB/s | 32 GB 256-bitLPDDR4x 136.5GB/s | |
| 16 GB eMMC 5.1 | 16 GB eMMC 5.1 | 32 GB eMMC 5.1 | 32 GB eMMC 5.1 | 16 GB eMMC 5.1 | 32GB eMMC 5.1 | |
| 5W | 10W | 7.5W | 15W | 10W | 20W | 10W | 15W | 10W | 15W | 30W | ||
| 1 x4 (PCIe Gen2) | 1 x1 + 1 x2 (PCIe Gen2) | 1 x1 + 1 x4 OR 1 x1 + 1 x1 + 1 x2 (PCIe Gen2) | 1 x1 (PCIe Gen3) + 1 x4 (PCIe Gen4)* | 1 x8 + 1 x4 + 1 x2 + 2 x1 (PCIe Gen4, Root Port & Endpoint) | ||
| Up to 4 cameras 12 lanes MIPI CSI-2 D-PHY 1.1 (up to 18 Gbps) | Up to 5 cameras (12 via virtual channels) 12 lanes MIPI CSI-2 D-PHY 1.2 (up to 30 Gbps) | Up to 6 cameras (12 via virtual channels) 12 lanes MIPI CSI-2 D-PHY 1.2 (up to 30 Gbps) | Up to 6 cameras (24 via virtual channels) 14 lanes MIPI CSI-2 D-PHY 1.2 (up to 30 Gbps) | Up to 6 cameras (36 via virtual channels) 16 lanes MIPI CSI-2 | 8 lanes SLVS-EC D-PHY 1.2 (up to 40 Gbps) C-PHY 1.1 (up to 91 Gbps) | ||
| 1x 4K30 (H.265) 2x 1080p60 (H.265) | 1x 4K60 (H.265) 3x 4K30 (H.265) 4x 1080p60 (H.265) | 2x 4K30 (H.265) 6x 1080p60 (H.265) | 4x 4K60 (H.265) 16x 1080p60 (H.265) 32x 1080p30 (H.265) | |||
| 1x 4K60 (H.265) 4x 1080p60 (H.265) | 2x 4K60 (H.265) 7x 1080p60 (H.265) 14x 1080p30 (H.265) | 2x 4K60 (H.265) 12x 1080p60 (H.265) 16x 1080p30 (H.265) | 2x 8K30 (H.265) 6x 4K60 (H.265) 26x 1080p60 (H.265) 72x 1080p30 (H.265) | |||
| 2 multi-mode DP 1.2/eDP 1.4/HDMI 2.0 1 x2 DSI (1.5Gbps/lane) | 2 multi-mode DP 1.2/eDP 1.4/HDMI 2.0 1x 2 DSI (1.5Gbps/lane) | 2 multi-mode DP 1.2/eDP 1.4/HDMI 2.0 2 x4 DSI (1.5Gbps/lane) | 2 multi-mode DP 1.4/eDP 1.4/HDMI 2.0 No DSI support | 3 multi-mode DP 1.4/eDP 1.4/HDMI 2.0 No DSI support | ||
| - | - | 2x NVDLA Engines | 2x NVDLA Engines | |||
| - | - | 7-Way VLIW Vision Processor | 7-Way VLIW Vision Processor | |||
| 10/100/1000 BASE-T Ethernet | 10/100/1000 BASE-T Ethernet | 10/100/1000 BASE-T Ethernet, WLAN | 10/100/1000 BASE-T Ethernet | 10/100/1000 BASE-T Ethernet | 10/100/1000 BASE-T Ethernet | |
| 69.6 mm x 45 mm 260-pin SO-DIMM connector | 69.6 mm x 45 mm 260-pin SO-DIMM connector | 87 mm x 50 mm 400-pin connector | 69.6 mm x 45 mm 260-pin SO-DIMM connector | 100 mm x87 mm 699-pin connector | ||
Our tech map in FPGA
Software platforms
Xilinx Deep Neural Network (xDNN), Xilinx Alveo, Intel OpenVINO Toolkit, TensorFlow, Keras, Caffe
Tools & Languages
C++, Python, Matlab/Simulink, Verilog, VHDL, HLS, DSP, AI toolboxes
Specialized tools
Xilinx Vitis AI, Xilinx Vivado Design Suite, Intel Quartus Prime, SDAccel, SDSoC, HDL Coder
Hardware design
High-speed interfaces, DDR4, JESD204b, SI, PI, thermo modelling, video processing
Platforms
Zynq, Zynq US+, RF SoC, Xilinx Versal, FPGA
Tranceivers
AD9361, AD9371, ADRV9009, radars, Promwad AFE, antenas
Network software
DPDK, UDP 10G, TCP 10G, TAPs, L1/L2 IP cores
Communications
PCI-e, 1G, 10G, 25G/40G, 100G
Our FPGA design projects
Digital handheld transceiver We've helped a startup to design a digital handheld transceiver for kite surfers with a built-in MP3 player
Microcomputer 88F6282 We designed a solution that decreases the time, costs and risks when designing new products with WiFi and Gigabit Ethernet interfaces
TI DM3730 SoM We've designed the CPU module based on the TI DM3730, which helps cut the time, costs, and risks of designing new products
IMX6UL processor module We've designed an affordable processor module in the SODIMM form factor for a significant reduction of development time and costs.
Satellite modem We designed a hardware & software platform for a broadband software-defined radio satellite modem
Industrial switches We have designed a new product line of 1Gb/10Gbps Ethernet switches operating at an industrial temperature range (−20 to +70°C)
Framebuffer IP & PCI-e cores We developed a versatile framebuffer FPGA IP core and integrated PCI-e IP core into the customer’s FPGA project
Railway navigation unit We offered the customer a hardware solution based on three modules (units) that are connected with cables
Air monitoring system We designed a hardware and software system with measuring devices to collect and send the data to an IoT cloud server
Jade Automotive platform We developed hardware & software platform for automotive display, monitoring, and diagnostics systems based on the Fujitsu Jade MB86R01
AM1808 computer We've designed a multi-functional and small-size single board computer with open architecture for the development of industrial built-in systems
Neuronavigator Promwad engineering team designed a working prototype with the support of 3D images of ultrasound / MRI / CT.
S-Terra trusted module We have developed a custom bootable medium, which is a USB device and designed to build trusted computing modules
Controller for traction driveWe upgraded the controller of an electric traction device for subway carriages made more than ten years ago
MPEG2/4 transcoder softwareWe finalized the firmware design for multi-channel transcoding of MPEG2-TS (transport streams) into H264 format
Locus DVB-T STBWe have developed a digital TV set-top box (STB) with support for DVB-T (MPEG-2/4) and terrestrial digital broadcasting
AK1100 thin clientWe have developed a new turn-key product, the AK1100 thin client based on the processor Marvell Sheeva 88F6282
5D video hardware+softwareWe have developed a 5D cinema hardware and software complex at the order of a company which supplies animatronics
Smart house controller We have designed the HDMI-CEC controller to manage a home multimedia complex: cinema, tuner, VCR and other devices
Onboard multimedia computerWe have developed a sophisticated hardware and software system for multimedia, GPS navigation, travel time calculation, control of air conditioning
JPEG2000 4-channel recorderWe developed a video registration device for storage and distribution of audio and video streams on request from 4 analogue sources
IP-Plug ARM mini-serverWe have developed the multifunction mini-server for solving a wide range of tasks in IP networks, functions as a computer or a server
Do you need a quote for your Edge AI project?
Drop us a line about your project! We will contact you today or the next business day. All submitted information will be kept confidential.