Overview:
Data centre technology is evolving rapidly to meet the explosion in demand for AI training and inference. No company has benefited more from this AI boom than Nvidia. However, in 2017, the introduction of Google’s Tensor Processing Unit (TPU) – a chip designed specifically for Deep Learning – demonstrated that it was possible for new players to build domain-specific chips with better performance, lower power consumption and cost than Nvidia’s general-purpose GPUs. Now, the emergence of generative AI with its unique and heavy computational requirements presents new opportunities for domain-specific ASICs vendors.
This insights report provides an overview of the AI chip start-up market and highlights the opportunities and challenges facing new players entering this burgeoning market.
Table of Contents:
- Snapshot
- Introduction
- Nvidia – A One Stop Shop For AI
- The Compute Challenge
- Established AI-Chip Start-ups
- Cerebras
- SambaNova
- Groq
- Tenstorrent
- Emerging AI-Chip Start-ups
- Key Challenges for Start-ups
- Technical Complexity
- Funding Difficulties
- The Nvidia Effect
- Developing Open Standards
- Big Tech
- Analyst Viewpoint
Number of Pages: 8
Published Date: June 2024