While NVIDIA dominates the market for AI-specific silicon accelerating the training of neural networks, many AI startups are developing silicon to accelerate inference processing, both for data center and edge applications. CPUs have typically been the choice for inference processing, but this is changing rapidly as the size of neural networks grows exponentially and applications are emerging that require multiple neural networks to solve complex problems. This far surpasses a CPU’s processing power. One of the critical challenges for inference processors is the selection of the right balance of performance, cost, and power consumption for a specific set of applications – one size will not fit all. Into this mix jumps California-based startup Blaize with the announcement of its first generation of production-ready platforms that, it contends, provide that balance for targeted edge applications.
You can download the paper from Moor Insights & Strategy, where it was published. by clicking on the logo below:
Table Of Contents
- Introduction
- Blaize Target Markets And Products
- The Blaize Software Suite: Picasso And AI Studio
- Early Blaize Customer Projects
- Conclusions And Recommendations
- Figure 1: Blaize’s Packaging Options For Its GSP Chip For Standalone And Host-Connected Applications
- Figure 2: Blaize Picasso Software Stack
- Figure 3: Industrial Monitoring
- Figure 4: Smart City Applications For Traffic Flow And Public Safety
- Figure 5: Retail Applications
Companies Cited
- Arm
- Blaize
- Daimler
- Denso
- NVIDIA