Infineon Technologies AG, global industry experts in power semiconductors, AI power delivery, and energy-efficient semiconductor technologies, has announced a collaboration with AI inference computing company d-Matrix focused on optimizing performance, power efficiency, and system integration for interactive AI inferencing platforms used in data center environments.
The collaboration combines Infineon’s semiconductor-based power delivery technologies with d-Matrix’s Corsair AI inference accelerator architecture. According to the companies, Infineon’s OptiMOS TDM2254xx dual-phase power modules support true vertical power delivery while enabling power densities of approximately 1.0 A/mm² within high-density accelerator board designs.
Infineon and d-Matrix are collaborating on AI inference accelerator technologies optimized for low latency, energy efficiency, and high-density data center deployments.
AI inference applies trained machine learning models to new data in order to generate predictions, classifications, and decision outputs without additional training. As demand grows for real-time AI interactions and large language model (LLM) deployments, data center operators are increasingly seeking hardware architectures capable of balancing compute performance, latency, thermal efficiency, and power consumption.
“Infineon has been collaborating with customers specializing in inference processors, such as d-Matrix, from the early days when the industry was mostly focused on training hardware,” said Raj Khattoi, Vice President and General Manager of Consumer, Computing and Communication at Infineon. “These early, strategic engagements have positioned Infineon as a leader in the inference hardware industry, further extending our leadership in powering AI with semiconductor solutions for both inference and training processors.”
d-Matrix stated that its Corsair platform was designed specifically for interactive AI workloads requiring low-latency inferencing performance within large-scale data center environments.
“AI is rapidly moving from back-office experimentation to a real-time interactive experience – and that shift demands a fundamentally different compute architecture. Corsair was purpose-built for this moment: delivering the sub-2ms token latency that interactive applications require, at multiples better energy efficiency than traditional approaches,” said Sid Sheth, founder and CEO of d-Matrix. “Infineon has been a design partner since the inception of our platform, and their power semiconductors are a meaningful contributor to our ability to deliver what the market demands.”
According to the companies, the AI inference platform is intended for workloads including large language model response generation, agentic AI systems, and predictive analytics applications within industries such as finance and healthcare. Infineon noted that growing AI infrastructure requirements continue driving demand for advanced semiconductor-based power management technologies across both AI training and inference markets. The company’s power semiconductor portfolio includes silicon (Si), silicon carbide (SiC), and gallium nitride (GaN) technologies designed to support higher power density, improved energy efficiency, and scalable system integration across modern AI data center architectures.
About Infineon Technologies AG
Infineon develops semiconductor technologies focused on power systems, automotive electronics, industrial automation, security technologies, and Internet of Things (IoT) applications. Headquartered in Germany, the company supplies semiconductor solutions designed to support energy efficiency, electrification, decarbonization, connected infrastructure, and advanced computing systems across industrial and commercial markets.
The company’s product portfolio includes power semiconductors, microcontrollers, sensors, connectivity solutions, memory products, and security technologies based on silicon (Si), silicon carbide (SiC), and gallium nitride (GaN) semiconductor materials. The company’s technologies are used across automotive systems, renewable energy infrastructure, AI data centers, industrial automation platforms, consumer electronics, and communications applications.
Most recently, Infineon has expanded its focus on AI infrastructure and high-performance computing applications through development of advanced power delivery technologies designed to support AI training and inference architectures requiring high power density, thermal efficiency, and scalable system integration. Infineon operates globally with approximately 57,000 employees and reported revenue of approximately €14.7 billion during its 2025 fiscal year. For more information, please click here.
About d-Matrix:
d-Matrix develops AI inference computing platforms designed for interactive, low-latency artificial intelligence workloads within data center environments. Founded in Silicon Valley, the company focuses on hardware and software architectures optimized specifically for AI inference applications involving large language models, generative AI, and real-time AI interaction systems.
The company’s Corsair platform is designed to support high-throughput AI inferencing while emphasizing energy efficiency, reduced latency, and scalable deployment within modern data center infrastructure. d-Matrix has stated that its architecture is intended to address challenges associated with power consumption and performance scaling as AI workloads transition from experimental systems toward interactive production environments.
d-Matrix’s technology portfolio includes AI accelerator hardware, inference-focused compute architectures, and related software technologies intended to support enterprise AI deployments, conversational AI systems, agentic AI applications, and large-scale inference processing workloads. Markets served by the company include cloud computing, enterprise AI infrastructure, hyperscale data centers, financial analytics, healthcare AI, and advanced computing environments requiring high-performance inference acceleration. To learn more, please click here.
Source/Photo Credit: Infineon Technologies AG
(Editor’s Note: All trademarks mentioned in this article, including company names, product names, and logos, are the property of their respective owners. Use of these trademarks is for informational purposes only and does not imply any endorsement.)
Molly is the Founder, Publisher, and Editor-in-Chief of Components Source Network, the industry’s first and only known 100% woman- and disability-owned and led B2B publishing platform serving the global high-tech manufacturing and engineering sectors. Her portfolio includes Semiconductor Industry Monthly and ten additional specialized e-news sites. With more than 25 years of experience spanning strategic technical marketing, public relations, and business development in highly specialized technical markets, she also leads Embassy Global, LLC, a virtual consultancy that has supported the growth of more than 200 high-tech industry brands worldwide since 2008. In addition to her publishing and advisory work, Molly has been appointed to serve as Second Vice Chair of the Government Team for the Women’s Business Enterprise National Council (WBENC) Forum, beginning in 2026, supporting policy development and advocacy initiatives advancing women-owned businesses. A long-standing voice for small business, supplier diversity, and women in STEM, she was also a 2025 finalist for the WBEC Metro New York Outstanding Advocate Award. Connect with her on LinkedIn.
- Siemens, Samsung Foundry Advance EDA Collaboration - May 29, 2026
- Featured Expert: d-Matrix - May 21, 2026
- Applied Materials, Broadcom Collaborate on AI Chip Packaging - May 21, 2026