Industrial-Grade GPU Computing System Released

By Mike Ball / 24 Feb 2021
Follow UST

Cincoze GP-3000 GPU Computer

Cincoze has released its new flagship GPU edge computing system, the GP-3000. Based around an 8th or 9th generation Intel Xeon or Core i3/i5/i7 (Coffee Lake and Coffee Lake-R) CPU, the system supports two sets of DDR4-2666 ECC/non-ECC SO-DIMM up to 64 GB, as well as up to two 250 W high-end full-length GPU graphics cards. It is ideal for a variety of unmanned systems and robotics applications such as machine vision and image processing.

The GP-3000 provides high-efficiency edge computing capabilities with its GPU Expansion Box, which fixes graphics cards in place for extra protection in high-vibration environments. It also features multiple built-in PCIe slots for various high-speed I/O cards or image capture cards.

In addition to the standard five LAN ports and six USB 3.2 ports, the GP-3000 uses Cincoze’s exclusive CMI and CFM modular design, which offers expansion modules with eight Gigabit PoE, two USB 3.2, or dual 10 Gb/s LAN ports. Storage options include high-speed M.2 NVMe storage slots and four hot-swappable 2.5” HDD/SSD trays accessible through the front maintenance panel. The IGN module (power ignition sensing) can monitor the on-board battery voltage and set a delayed shutdown time to avoid damage to the system due to unstable current.

The GP-3000 is MIL-STD-810G certified and pending addition to the US Department of Defense’s qualified military equipment list. It features 9–48 VDC power input, is built for -40 to 70℃ temperature operation, and supports multiple installation methods, including wall, desktop, face-up, and 19″ rack mount. The GP-3000 has E-mark and EN 50155 (EN 50121-3-2 only) certifications, making it capable of withstanding harsh vehicular environments.

Brandon Chien, General Manager of Cincoze, commented: “We already know AI will drive innovation and expansion for industrial applications. The GP-3000 is Cincoze’s answer for intensive image processing and complex calculations, such as deep machine learning, autonomous driving, automated visual inspection, and mobile monitoring. As our latest flagship model, the GP-3000 multiplies edge computing efficiency, amplifies productivity and reliability, and accelerates AIoT automation.”

Posted by Mike Ball Mike Ball is our resident technical editor here at Unmanned Systems Technology. Combining his passion for teaching, advanced engineering and all things unmanned, Mike keeps a watchful eye over everything related to the unmanned technical sector. With over 10 years’ experience in the unmanned field and a degree in engineering, Mike’s been heading up our technical team here for the last 8 years. Connect & Contact