ChipsAugust 31, 2026via SiliconAngle
Amazon targets data-intensive workloads with Graviton5-powered R9g and R9gd instances
Why it matters
AWS is diversifying its AI compute portfolio with custom silicon optimized for memory-bound AI workloads (large-context inference, RAG, vector databases). This signals Amazon's strategy to reduce Nvidia dependency and offer practitioners a price/performance alternative for specific AI workloads.
Key signals
- New R9g and R9gd instances powered by AWS Graviton5 processors
- Memory-optimized for data-intensive workloads
- Available today in multiple AWS regions
- Announced via AWS blog by Principal Developer Advocate Daniel Abib
- Represents Amazon's silicon diversification play in AI compute
- AWS Graviton5 processors now powering R9g and R9gd memory-optimized instances
- Available today in multiple cloud regions
- Designed for data-intensive workloads
- Announced via AWS Principal Developer Advocate Daniel Abib
- Part of AWS's broader custom silicon and compute diversification strategy
The hook
Amazon expands Graviton5 reach into memory-intensive AI workloads—a direct challenge to Nvidia's hold on data-center compute.
Amazon.com Inc. is bringing its new AWS Graviton5 processors to more workloads with the launch of its new, memory-optimized R9g and R9gd instances, which are available today in multiple cloud regions. They were revealed in a blog post by AWS Principal Developer Advocate Daniel Abib, who explained th…