GSI Technology’s NRT SAR Image Processing Acceleration System Approved for use by IAI/ELTA

GSI Technology,developer of the Gemini Associative Processing Unit (APU) for AI and high-performance parallel computing (HPPC) and a leading provider of high-performance memory solutions for the networking, telecommunications and military markets,announced that its Synthetic Aperture Radar (SAR) image processing acceleration system using GSI’s APU technology has been approved for use by IAI/Elta System Ltd, a subsidiary of Israeli Aerospace Industries (IAI).

“We are pleased to be selected by IAI/Elta, Israel’s leading provider of innovative defense and space technology, for use of GSI Technology’s SAR image acceleration system,” said Dr. Avidan Akerib, Vice President, Associative Computing Business Unit at GSI Technology. “This prestigious recognition of our solution’s capabilities showcases the technological superiority of our APU and opens new opportunities to the field of accelerating SAR image formation.”

Recommended AI News: Cyient to Acquire Portugal-Based Celfinet to Strengthen its Wireless Communications Offerings

GSI has developed a SAR image processing acceleration system using GSI’s APU technology and has delivered the first system to IAI/Elta. The GSI system passed all IAI/Elta’s requirements including quality, accuracy and performance tests, and has been approved to use.

The scalable APU architecture allows expanding to multiple boards on servers for added performance and redundancy without specialized links. The APU platform has the capability to stack servers together and bring near real-time capability to time-consuming, compute-intensive processes. GSI has shown in comparisons for a large area SAR image processed in one second at high resolution scenarios that the APU uses, on average, 88% less power than CPU or GPU systems by using one tenth the number of servers. Further, the GSI solution used in this comparison is small enough to be installed on fixed-wing flight platforms.

GSI’s APU technology is ideal for SAR observation missions needing near real-time solutions and higher processing power that use the Fast Back Projection (FBP) algorithm. FBP is considered by SAR experts as the ideal algorithm for forming SAR image data, permitting optimal results (quality and accuracy), high ground resolution at various ranges (hundreds of meters to hundreds of kilometers), various frequencies and supporting any kind of SAR sensor carrying platform.

Recommended AI News: New Cisco Technology Can Predict Network Issues Before They Happen

Prohibitive costs and power usage due to the high computational requirements of running the FBP algorithm on a CPU or GPU has previously limited its usage. With its significantly higher processing speed, high accuracy, and lower power usage, GSI’s APU chip architecture enables the usability of the FBP algorithms for a variety of platform use cases from onboard UAV and Satellite to Data Center applications.

GSI’s APU SAR processing system reduced the processing time from a few minutes to a few seconds, significantly shortening the customer’s delivery time (images and data). The APU also offers onboard processing capabilities and substantially lower computing costs.

Recommended AI News: Getty Images Revolutionizes Visual Communications with VisualGPS Insights Launch

[To share your insights with us, please write to sghosh@martechseries.com]