Taiwan Semiconductor Manufacturing Company (TSMC) has partnered with NVIDIA (NASDAQ:NVDA) and Broadcom (NASDAQ:AVGO) to develop advanced silicon photonics, aiming to significantly enhance transmission speeds for artificial intelligence (AI) computing, according to reports on Monday. The collaboration is seen as a significant move in the AI industry towards rapid development in silicon photonics.
Silicon photonics, a next-generation adaptation of traditional copper transmission cables, combines laser and silicon technology to provide high data transfer speeds. This technology has gained considerable traction in the industry, especially with the advent of the AI boom, as it plays a vital role in data centers and high-performance computing (HPC) machines.
The partnership between TSMC, Broadcom, and NVIDIA aims to innovate the silicon photonic industry. TSMC is rumored to have allocated 200 professionals for research and development, primarily focusing on integrating silicon photonic technology into high-speed computing chips. This could potentially lead to a significant breakthrough for the AI industry.
The semiconductor industry views silicon photonics as the future due to its numerous benefits. Traditional electricity data transmissions often face compromised transfer speeds, while the industry demands higher computational speeds given that general AI development has reached unprecedented levels. Silicon photons convert electricity into light, offering faster speeds with a cost-efficient method.
NVIDIA and its partners are working on expanding the technology from the 45-nanometer process up to the 7-nanometer process, which is expected to bring significant performance uplift. This process is projected for implementation by 2024, with mass production expected by 2025. This advancement could lead to next-gen AI GPUs boasting significant transmission speeds in the coming years.
The rapid growth of the AI industry has made it evident that innovation will occur, and the integration of silicon photonics is a prime example. Over time, significant developments are expected, particularly in the HPC department, which is seen as the path to leading the future of general AI.
This article was generated with the support of AI and reviewed by an editor. For more information see our T&C.