GSI’s APU is proven to consume 93% less power than CPU or GPU systems
SUNNYVALE, Calif., Feb. 09, 2022 (GLOBE NEWSWIRE) — GSI Technology, Inc. (NASDAQ: GSIT), the developer of the Gemini® Associative Processing Unit (APU) for artificial intelligence (AI) and high-performance parallel computing and provider of high-performance storage solutions for the networking, telecom and military markets announced today that its new APU processor offers a proven solution to significantly reduce power consumption when running AI search applications in data centers, enabling customers to further their environmental and sustainability efforts.
Power consumption is a serious problem in the data center these days. According to a recent study, today’s data centers consume an estimated 198 terawatt hours, or 1 percent of the world’s electricity consumption. The amount of energy used by data centers is doubling roughly every four years, meaning data centers have the fastest growing carbon footprint in the IT industry.
The concentration of computing technologies in corporate data centers has made it possible to hide increasing energy consumption behind closed doors. However, due to the inefficiency of these decades-old data-centric and I/O-bound architectures, there are huge user costs, energy consumption, and environmental impact—even when they are updated to the latest process technologies. It’s becoming clear that simply packing more capacity and more cores or just increasing density doesn’t help when CPUs, FPGAs and GPUs continue to use traditional computing methods.
This problem is likely to increase as workloads become more data-intensive and AI-centric. New hardware and chipsets specifically designed for energy efficiency must continue to be an important part of the design of future AI-centric data centers. GSI is helping to solve this critical problem with its new technology that brings huge energy savings. Data centers using GSI APU processors can achieve radical energy savings with APU-based systems that have much lower power requirements.
“From the migration of computing power to the cloud to the increased need for on-prem business hardware, the race is on to acquire energy-efficient hardware and reduce utility bills,” said Lee-Lean Shu, chairman and CEO of GSI Technology . “Solving this problem is one of the strategic opportunities for our technology. Our new APU processor offers significant power savings, enabling corporate customers to meet their sustainability goals and do good for the planet. GSI has shown in a comparison for a large-area SAR image in one second at high resolution that the Gemini-I APU consumes an average of 93% less power than CPU or GPU systems in a portable solution instead of filling a room with server racks require.”
About GSI Technology
GSI Technology, Inc. is a leading provider of semiconductor memory solutions. The company recently released the Gemini® Associative Processing Unit (APU), a memory-centric design that offers significant performance benefits for various AI applications. The Gemini APU architecture removes the I/O bottleneck between the processors and memory arrays, and performs massively parallel seek directly in the memory where data is stored. The novel architecture offers performance-to-performance improvements over CPU, GPU, and DRAM for applications such as image recognition, speech recognition, e-commerce recommendation engines, and more. Gemini is an ideal solution for edge applications with a scalable format, small footprint, and low power consumption where fast and accurate responses are critical. Visit www.gsitechnology.com for more information.
Statements contained 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 to the future. Any forward-looking statements contained in this press release are based on information available to GSI Technology as of the date of this release, and GSI Technology assumes no obligation to update any such forward-looking statements. Forward-looking statements involve a variety of risks and uncertainties that could cause actual results to differ materially from those projected. Examples of risks that could affect our current expectations include: risks related to the rapidly developing markets for GSI Technology’s products and the uncertainty surrounding the development of those markets; Growth rate of data center energy consumption; changes in energy costs; intense competition; and delays or unforeseen costs that may arise in the development of new products based on our integrated associative computing technology and the establishment of new markets and customer acceptance of such products. Many of these risks are currently being, and continue to be, or may in the future be amplified by the global COVID-19 pandemic. Additional information regarding these and other risks associated with 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.
GSI Technology, Inc.
Douglas M. Schirle
Finn Partners for GSI technology