Compute-In-Memory APU achieves GPU-class AI performance at

SUNNYVALE, Calif., October 20, 2025 (GLOBE NEWSWIRE) — GSI Technology, Inc. (Nasdaq:GSIT)The inventor of the associative processing unit (APU), a paradigm shift in artificial intelligence (AI) and high-performance computing (HPC) processing providing true in-memory computing technology, announced the publication of a paper led by researchers at Cornell University. The results confirmed that GSI Technology’s Compute-In-Memory (CIM) APU architectures can match GPU-level performance for large-scale AI applications with a dramatic reduction in power consumption thanks to the high-density, high-bandwidth memory associated with the CIM architecture.

Key findings include:

• GPU Class Performance – The Gemini-I APU delivered comparable throughput to NVIDIA’s A6000 GPU on RAG workloads.
• A considerable energy advantage – The APU delivers over 98% lower power consumption than a GPU on various large enterprise datasets, highlighting its efficiency and durability.
• Faster and more efficient than processors – The APU’s unique design allows it to perform recovery tasks several times faster than standard processors, reducing total processing time by up to 80%.

“Cornell’s independent validation confirms what we have long believed: in-memory computing has the potential to disrupt the $100 billion AI inference market,” said Lee-Lean Shu, president and CEO of GSI Technology. “The APU delivers GPU-class performance at a fraction of the power cost, thanks to its highly efficient memory-centric architecture. »

Published on ACM and presented at the Micro ’25 conference, the Cornell research team’s paper titled “Characterization and Optimization of Realistic Workloads on a Commercial SRAM Compute Device” represents one of the first comprehensive evaluations of a commercial in-memory compute device under realistic workloads. The Cornell-led team benchmarked the GSI Gemini-I APU against established CPUs and GPUs, focusing on recovery augmented generation (RAG) tasks on datasets ranging from 10 GB to 200 GB.

The researchers’ findings indicate significant opportunities for GSI technology as customers increasingly demand performance gains per watt in various industries, including Edge AI for robotics, drones and power-constrained IoT devices, as well as defense and aerospace applications where the APU can deliver high performance in environments with stringent power and cooling constraints.

Mr. Shu continued: “This exciting work from Cornell highlights the benefits of CIM using Gemini-I silicon. Our recently launched second-generation APU silicon, Gemini-II, can deliver approximately 10x faster throughput and even lower latency for memory-intensive AI workloads, while further improving power efficiency. Looking ahead, Plato represents the next step in before, offering even greater computing capacity at lower consumption for cutting-edge embedded applications. APU’s unique combination of speed, efficiency and programmability positions us to unlock high-growth opportunities in advanced AI, data centers, defense and other markets where energy efficiency is a critical strategic advantage.

The Cornell study also introduced a new analytical framework for general-purpose in-memory computing devices, providing optimization principles that strengthen the APU’s position as a scalable platform for developers and systems integrators. A copy of the publication can be found on the GSI website at https://gsitechnology.com/characterizing-and-optimizing-realistic-workloads-on-a-commercial-compute-in-sram-device/.

ABOUT GSI TECHNOLOGY
Founded in 1995, GSI Technology, Inc. is a leading provider of semiconductor memory solutions. GSI’s resources are focused on bringing new products to market that leverage existing core strengths, including radiation-resistant memory products for extreme environments and Gemini-I, the associative processing unit designed to provide performance benefits for various artificial intelligence applications. GSI Technology is headquartered in Sunnyvale, California, and has sales offices throughout the Americas, Europe and Asia. For more information, please visit www.gsitechnology.com.

About the ACM

ACM publishes more than 50 peer-reviewed scientific journals in dozens of computing and technology disciplines. Available in print and online, ACM’s high-impact, peer-reviewed journals constitute a broad and comprehensive archive of computing innovation, covering emerging and established computing research for practical and theoretical applications. ACM journal editors are thought leaders in their fields, and the ACM’s emphasis on rapid publication ensures minimal delay in communicating exciting new ideas and findings.

Forward-looking statements

Statements in this press release that are not purely historical are forward-looking statements within the meaning of Section 21E of the Securities Exchange Act of 1934, as amended, including statements regarding GSI Technology’s expectations, beliefs, intentions or strategies regarding the future. All forward-looking statements included in this press release are based on information available to GSI Technology as of the date hereof, and GSI Technology undertakes no obligation to update these forward-looking statements. Forward-looking statements involve various risks and uncertainties, which could cause actual results to differ materially from those projected. These risks include those associated with the normal quarterly closing and year-end process. Examples of risks that could affect our current expectations regarding future revenues and gross margins include those associated with fluctuations in GSI Technology’s operating results; GSI Technology’s historical reliance on sales to a limited number of customers and fluctuations in customer and product mix over any given period; global public health crises that reduce economic activity; rapid developments in markets for GSI Technology’s products and uncertainty regarding the development of these markets; the need to develop and introduce new products to offset the historical decline in the average unit selling price of GSI Technology’s products; the challenges of rapid growth followed by periods of contraction; intense competition; the continued availability of government funding opportunities; delays or unanticipated costs that may be encountered in developing new products based on our existing associative computing technology and in establishing new markets and customer and partner relationships for the sale of such products; and unexpected delays or challenges related to establishing customer relationships and ordering GSI Technology’s radiation-resistant and radiation-tolerant SRAM products. Many of these risks are currently amplified and will continue to be amplified by, or may be amplified in the future, economic and geopolitical conditions, such as changes in interest rates, global inflationary pressures, policy unpredictability, the imposition of tariffs and other trade barriers, military conflicts and declines in the global economic environment. Further information regarding these and other risks relating to GSI Technology’s business is contained in the Company’s filings with the Securities and Exchange Commission, including the factors discussed under the heading “Risk Factors” in those filings.

Source: GSI Technology, Inc.

Contacts:
Investor Relations
Hayden IR
Kim Rogers
541-904-5075
Kim@HaydenIR.com

Media Relations
Finn partners for GSI technology
Rich Silverio
(415) 348-2724
gsi@finnpartners.com

Business
GSI Technology, Inc.
Douglas M. Schirle
Financial Director
408-331-9802