### Harnessing the Power of Fifth-Generation RISC Platforms for Edge AI
In a podcast with Fabrizio del Maffeo, CEO and Co-founder of Axelera AI, the focus is on the potential of the fifth generation of RISC platforms in edge AI applications. Del Maffeo discusses the early availability of the in-memory Metis AI platform, with a particular emphasis on the importance of edge AI in artificial intelligence and edge computing.
### Bringing Edge Computing Closer to the User
The use of edge computing moves the responsibility for processing critical workloads closer to the demand for information. This means more efficient use of energy and network bandwidth, as well as reducing latency for a better user experience. However, del Maffeo emphasizes that the promise of edge computing is still largely unrealized, with data taking far too many round trips back to central data centers.
### The Challenge of Edge AI and its Solutions
The challenge of edge AI lies in handling high volumes of table multiplications with limited power and network bandwidth. To address this, Axelera took advantage of the memory potential in the RISC-V architecture to merge memory and processing functions and parallelize processing at the edge in new ways. This innovative approach opens up the possibility of large language model processing at the edge.
### Exploring a Wide Range of Edge Use Cases
Del Maffeo also delves into a wide range of edge use cases in the podcast, from smart cities to automotive to retail. The discussion sheds light on the potential applications of edge AI in various fields, offering a glimpse into the future of artificial intelligence.
So, what do you think of this innovative approach to edge AI? Let us know in the comments below and join the conversation!
IntelliPrompt curated this article: Read the full story at the original source by clicking here