Artificial Intelligence Radio Transceiver (AIR-T) AIR-T Embedded Series Product Line Overview Deepwaves AIR-T is the first software defined radio with embedded high performance computing. It contains three unique digital processors for any application: FPGA for strict real-time operations GPU for highly parallelized processing CPU for control, I/O, and software applications The AIR-T allows users to easily incorporate artificial intelligence into their radio frequency and wireless technologies. This versatile system can function as a highly parallel SDR, data recorder, or inference engine for deep learning algorithms. The embedded GPU allows for SDR applications to process bandwidths greater than 200 MHz in real-time. Key Specifications Software Support Dual Channel MIMO Transceiver - 300 MHz to 6 GHz - 100 MHz bandwidth Rx (per channel) - 100 MHz bandwidth Tx (per channel) Digital Signal / Deep Learning Processors GPU Signal Deep - Xilinx Artix 7 FPGA Acceleration Processing Learning - NVIDIA Jetson TX2 HPC with CUDA Support for Train and deploy toolkit using industry leading AI systems using ARM Cortex-A57 CPU (4 core) C/C++ or Python SDR development standard NVIDIA Denver2 CPU (2 core) interfaces environment frameworks NVIDIA Pascal GPU (256 core) 8 GB of memory Operating System Connectivity Ubuntu 18.04 - GPS Sync via 1 PPS and 10 MHz - USB 3.0, USB 2.0/3.0, SATA - High-speed digital I/O (GPIO/UART) Mechanical - 1 Gbps Ethernet Size - 17.0 x 17.0 x 3.5 cm Dual Power Mode: Weight - 0.35 kg - 22 / 14 Watts Deepwave Digital, Inc. 1429 Walnut St, Suite 1000, Philadelphia, PA 19102 www.deepwavedigital.com salesteam deepwavedigital.comArtificial Intelligence Radio Transceiver (AIR-T) AIR-T Embedded Series Product Line Performance The AIR-T uses 256 GPU cores to create a highly parallel compute environment making wideband processing for software defined radio (SDR) applications obtainable. Using the embedded NVIDIA Jetson TX2 the AIR-T provides 250% bandwidth improvement over a power-comparable CPU and 1,350% bandwidth improvement over an embedded CPU for real-time SDR applications. The AIR-T uses zero copy memory access to overcome the data transfer overhead typically associated with GPU processing. Embedded Series Models Applications AIR7101-A AIR7101-B AIR7201-A AIR7201-B Pre-trained User Developed GPU Cores 256 256 256 256 AI Cores Applications CPU Cores 6 6 6 6 Shared Memory 8 GB 8 GB 8 GB 8 GB AI DSP FGPA Model XC7A75T XC7A75T XC7A200T XC7A200T Frameworks Frameworks Logic Cells 75,520 75,520 215,360 215,360 DSP Slices 180 180 740 740 AIR-T Hardware Abstraction Memory 3,780 3,780 12,140 12,140 Enclosure No Yes No Yes AIR-T Hardware Deepwave Digital, Inc. 1429 Walnut St, Suite 1000, Philadelphia, PA 19102 www.deepwavedigital.com salesteam deepwavedigital.com