United Homes Group stock plunges after Nikki Haley, directors resign
Investing.com -- GSI Technology (NASDAQ:GSIT) stock surged 200% on Monday after Cornell University researchers published a study confirming the company’s Associative Processing Unit (APU) can match GPU-level performance while using 98% less energy.
The Cornell-led research team found that GSI’s Gemini-I APU delivered comparable throughput to NVIDIA’s A6000 GPU on retrieval-augmented generation (RAG) workloads. The study, published on ACM and presented at the Micro ’25 conference, represents one of the first comprehensive evaluations of a commercial compute-in-memory device under realistic workloads.
Researchers benchmarked the GSI Gemini-I APU against established CPUs and GPUs, focusing on RAG tasks over datasets ranging from 10GB to 200GB. The findings showed the APU can perform retrieval tasks several times faster than standard CPUs, shortening total processing time by up to 80%.
"Cornell’s independent validation confirms what we’ve long believed—compute-in-memory has the potential to disrupt the $100 billion AI inference market," said Lee-Lean Shu, Chairman and CEO of GSI Technology.
The company noted that its recently released second-generation APU silicon, Gemini-II, can deliver approximately 10x faster throughput and lower latency for memory-intensive AI workloads while further improving energy efficiency.
GSI Technology specializes in compute-in-memory technology, which it describes as a paradigm shift in artificial intelligence and high-performance computing processing.
This article was generated with the support of AI and reviewed by an editor. For more information see our T&C.