Photonics as a Carbon-Sustainable Solution for Next-Gen AI Hardware (Boston Univ., NY CREATES, Lightmatter, Cornell Tech)


A new technical paper titled "Photonics for sustainable AI" was published by researchers at Boston University, NY CREATES, Lightmatter and Cornell Tech. Abstract "The rising computational demands of Artificial Intelligence (AI) are driving a rapid surge in carbon emissions from the Information and Communications Technology (ICT) sector. Traditional CMOS-based computing is reaching its scali... » read more

2024 UMC Sustainability Report


Message from UMC's ESG Steering Committee Chairman: Jason Wang and Shan-Chieh Chien, Co-presidents and ESG Steering Committee Chairmen. "While the global economy gradually recovered from the pandemic, 2024 presented different challenges, including geopolitical shifts, inflation, inventory adjustments, and industry overcapacity. Despite these headwinds, our management team demonstrated strong... » read more

The Impact Of Simulation On The Carbon Footprint of Wafer Fab Equipment R&D


A new technical paper titled "Achieving Sustainability in the Semiconductor Industry: The Impact of Simulation and AI" was published by researchers at Lam Research. Abstract "Computational simulation has been used in the semiconductor industry since the 1950s to provide engineers and managers with a faster, more cost-effective method of designing semiconductors. With increased pressure in t... » read more

Heterogeneous Integration As A Path Towards Sustainable Computing, Using Chiplets


A technical paper titled "Towards Sustainable Computing: Assessing the Carbon Footprint of Heterogeneous Systems" was published by researchers at Arizona State University and University of Minnesota. Abstract: "Decades of progress in energy-efficient and low-power design have successfully reduced the operational carbon footprint in the semiconductor industry. However, this has led to an incre... » read more

Google’s TPU v4 Architecture: 3 Major Features


A new technical paper titled "TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddings" was published by researchers at Google. Abstract: "In response to innovations in machine learning (ML) models, production workloads changed radically and rapidly. TPU v4 is the fifth Google domain specific architecture (DSA) and its third supercomputer f... » read more