Artificial intelligence (AI) is transforming industries, driving innovation and efficiency. However, sustainability is crucial for long-term benefits.
A key challenge in sustainable AI growth is energy consumption. AI large language models (LLMs) require significant computational power, leading to high energy consumption.
Industry executives anticipate a factor of 100 times more computes required for the next generation of LLM training, with energy needs multiplying by 10 every two years.
Partitioning processing over accelerators is driving key parameters. LLM processing is typically partitioned over different accelerators to optimize performance.
Author's summary: ST silicon photonics and BiCMOS technologies enable sustainable AI growth.