Sagire AI’s SagireEdge AI 600 is a SMARC-compliant system-on-module (SoM) and a development kit based on Qualcomm QCS6490 octa-core Cortex-A78/A55 IoT processor and designed for Edge AI applications.
The module comes with 8GB LPDDR5 and 128GB UFS storage, a WiFi 6E and Bluetooth 5.5 wireless module, a CAN Bus controller, and on-module camera and audio input connectors. Its MXM 3.0 edge connector exposes additional camera interfaces, a MIPI DSI display interface, PCIe Gen3 x2, gigabit Ethernet, a few USB interfaces, and a range of low-speed I/Os.
SagireEdge AI 600 SoM specifications:
- SoC – Qualcomm QCS6490
- CPU – Octa-core Kryo 670 with 1x Gold Plus core (Cortex-A78) @ 2.7 GHz, 3x Gold cores (Cortex-A78) @ 2.4 GHz, 4x Silver cores (Cortex-A55) @ up to 1.9 GHz
- GPU – Adreno 643L GPU @ 812 MHz with support for Open GL ES 3.2, Open CL 2.0, Vulkan 1.x, DX FL 12
- DSP – Hexagon DSP with dual HVX and 4K HMX
- VPU – Adreno 633 VPU up to 4K60 decode for H.264/H.265/VP9, Up to 4K30 encode for H.264/H.265; Support for HDR10 and HDR10+ playback
- Spectra ISP – 64 MP / 36 + 22 MP / 3×22 MP at 30fps ZSL; 192 MP non-ZSL
- AI – 6th gen Qualcomm AI Engine that combines Compute Hexagon DSP with dual Hexagon Vector, eXtensions (HVX), Hexagon Co-processor (Hexagon CP) 2.0 and Hexagon Tensor accelerator for up to 12 TOPS of AI performance
- System Memory – 8GB LPDDR5
- Storage – 128GB UFS flash (µMCP: i.e. the RAM and UFS are in the same chip)
- Wireless – WiFi 6E (802.11ax) and Bluetooth 5.2 module
- Camera I/F – 2x 4-lane MIPI CSI connectors on-module
- Audio – On-module DMIC connector
- CAN Bus – On-module CAN Bus controller
- 314-pin MXM 3.0 edge connector as per SMARC specifications;
- Storage – 4-bit SD interface
- Display – 1x MIPI-DSI or 1x eDP
- Camera
- 1x 4-lane MIPI-CSI
- 1x 2-lane MIPI-CSI
- Networking – Gigabit Ethernet
- USB
- 2x USB 2.0, including 1x OTG
- 2x USB 3.1
- Expansion
- 1x PCIe Gen3 x2
- 12 x Digital IO, 3 x I2C, 1x SPI, 2x UART, 1 x PWM, 1x CAN Bus
- Debugging – JTAG connector
- Dimensions – 82 x 50 mm
- Temperature Range – -20 to +60°C
Sagire AI provides support for Android, Ubuntu Linux, and Windows IoT for the system-on-module. Ubuntu is ready now, but Android and Windows IoT appear to be “coming soon” if the information we’ve received is up-to-date.
The company also launched the Sagire AI Studio suite of software tools and resources to develop, deploy, execute, analyze, and manage AI applications at the Edge. That’s about all we know about it since Sagire AI did not share any other public information about it.
![SagireEdge AI 600 devkit SagireEdge AI 600 devkit](https://www.cnx-software.com/wp-content/uploads/2024/07/SagireEdge-AI-600-devkit-720x424.webp)
The company provides the SEA-600-DK development kit based on the SagireEdge AI 600 system-on-module with a baseboard offering the following interfaces:
- Display Interface – HDMI
- Networking – 2x Gigabit Ethernet ports
- USB
- 2x USB 3.1 port
- 1x USB 2.0 OTG port
- Expansion – Terminal block with CAN Bus, UART, 8x GPIO
- Dimensions – 110 x 110 mm
- Temperature Range – -20 to +60°C
![Qualcomm QCS6490 evaluation kit block diagram Qualcomm QCS6490 evaluation kit block diagram](https://www.cnx-software.com/wp-content/uploads/2024/07/Qualcomm-QCS6490-evaluation-kit-block-diagram-720x532.webp)
It’s not the first Qualcomm QCS6490 hardware development platform we’ve come across, as Thundercomm launched the RB3 Gen 2 Platform for robotics, IoT, and embedded applications in collaboration with Qualcomm last April, and Avnet followed suit with the Avnet AI Vision Development Kit in May. The Avnet design is similar to the Sagire AI one with a Qualcomm QCS6490 SMARC module and a carrier board.
Sagire AI did not provide availability and pricing information for the SagireEdge AI 600 SoM, but the devkit can be pre-ordered for $745 with shipping scheduled by the end of August. A few more details may be found on the product page. Note the company is US-based, but only provides a phone number on its website and no office address. All job offers appear to be remote but in “North America”.
![Jean Luc Aufranc](https://www.cnx-software.com/wp-content/uploads/2023/05/Jean-Luc-Aufranc.webp)
Jean-Luc started CNX Software in 2010 as a part-time endeavor, before quitting his job as a software engineering manager, and starting to write daily news, and reviews full time later in 2011.
Support CNX Software! Donate via cryptocurrencies, become a Patron on Patreon, or purchase goods on Amazon or Aliexpress