Brenda Marie Rivers
Mercury Systems has launched a graphics processing unit engine based on NVIDIA’s Turing microarchitecture intended for supercomputers supporting defense and aerospace applications.
The GSC6204 OpenVPX 6UÂ GPU coprocessing platform has GPU-to-GPU interconnect elements and is designed to support key features of high-performance embedded edge compute environments, Mercury said Thursday.
The GPU module is also meant to operate with the Mercury HDS6605 Intel Xeon Scalable processor to support a range of applications such as sensor fusion, artificial intelligence, radar, electronic warfare and electro-optical/infrared imaging.
Joe Plunkett, vice president and general manager of Mercury’s sensor processing group, said the offering will support customers’ need for a real-time processing technology with the performance level of a data center.
Anthony Robbins, VP of federal at NVIDIA and 2020 Wash100 Award recipient, noted that the integrated offering has “a significant impact†on efforts to leverage AI to address needs across industries.
Mercury expects to deliver the first GSC6204 engines in the third quarter of this year.
