Compression Enabled MRAM Memory Chiplet Subsystems for LLM Inference Accelerators
By Andy Green (Numen) and Nilesh Shah (Zeropoint Technologies)
This session unveils an AI-specific chiplet alternative to GPU-based inference that can deliver HBM-like bandwidth at 30-50% lower power.
Related Chiplet
- DPIQ Tx PICs
- IMDD Tx PICs
- Near-Packaged Optics (NPO) Chiplet Solution
- High Performance Droplet
- Interconnect Chiplet
Related Videos
- Chiplet Quilting for the Age of Inference
- China Target Chiplet, will it be a shortcut for China semiconductor self sufficiency？
- Chiplet Architecture for Next Gen Infrastructure
- Paving the way for the Chiplet Ecosystem
Latest Videos
- Inside the AI Bottleneck: Data Movement, Chiplets, and System Scaling
- On-Package Chiplet Innovations with UCIe
- Advanced Semiconductor Packaging Explained: Hybrid Bonding, Chiplets & Manufacturing Innovation
- The Chiplet Market Today and Where It's Headed
- Advanced Packaging & Chiplet Design with Chipletz