What happened
Boardcon announced the launch of the PICOT536 System-on-Module and EMT536 single-board computer, according to CNX Software and Boardcon product pages. Per CNX Software, both products are built around the Allwinner T536 SoC, which includes a quad-core Arm Cortex-A55 CPU running up to 1.6 GHz, two RISC-V coprocessors (XuanTie E907 at up to 600 MHz and XuanTie E902 at up to 200 MHz), and an integrated 2 TOPS NPU.
Technical details
Per CNX Software, the PICOT536 SoM ships with configurable system memory (2GB/4GB/8GB LPDDR4/LPDDR4X with inline ECC) and storage options from 8GB to 64GB eMMC. The module uses a 314-pin MXM 3.0 edge connector that exposes LVDS and MIPI DSI display output, support for 2x 4-lane or 4x 2-lane MIPI CSI camera inputs, Gigabit Ethernet, PCIe, a USB 3.0/PCIe 2.1 interface, four USB 2.0 host ports, one USB 2.0 OTG, and a collection of UART, I2C, SPI, PWM, ADC, and audio I/O. Video capabilities listed by CNX Software include decoding up to 4K at 15 fps (MJPEG) or 1080p at 60 fps (JPEG) and encoding up to 4K at 25 fps (H.264). Optional wireless connectivity is available via a VS6621S80 module providing WiFi 6 and Bluetooth 5.4. Boardcon provides a Buildroot-based software environment with Linux kernel 5.15.147 and U-Boot 2023.04, and supplies cross-compilation toolchains and debugging utilities, CNX Software reports.
Industry context
Editorial analysis: Edge-focused SoMs and SBCs with modest NPUs, like the 2 TOPS device here, continue to target cost-sensitive industrial applications where low-power, real-time inference is sufficient for tasks such as HMI, basic vision, and sensor fusion. Observers in embedded compute note that pairing small NPUs with heterogeneous CPU and RISC-V microcontrollers is a common pattern to balance deterministic control and ML inference at the edge.
What to watch
For practitioners and integrators, monitor Boardcon product pages and CNX Software follow-ups for pricing, long-term availability, mainline kernel support status, and upstream driver availability. Industry signals to watch include kernel version updates beyond 5.15.147, documentation for the camera/display stacks, and Boardcon statements about extended-temperature or long-term supply options for industrial deployments.
Key Points
- 1Industry context: 2 TOPS NPUs on SoMs enable low-power, on-device inference for HMI and basic vision, lowering latency versus cloud calls.
- 2Industry context: Heterogeneous stacks combining Arm CPU, RISC-V microcontrollers, and small NPUs are a recurring design choice for deterministic control plus ML.
- 3Industry context: Shipments with Buildroot and Linux 5.15 indicate immediate usability, but practitioners should track upstream driver support for long-term maintenance.
Scoring Rationale
This is a solid product launch for industrial edge AI hardware: relevant to embedded and robotics practitioners, but it is an incremental hardware release rather than a frontier-model or platform-shifting event.
Practice interview problems based on real data
1,625 SQL & Python problems across 15 industry datasets — the exact type of data you work with.
Try 250 free problems
