Cassia Proposes ‘Better Math’ for AI Efficiency
By Sally Ward-Foxton, EETimes | October 1, 2025
Startup Cassia wants to ‘do math better’ by approximating mathematical functions and implementing these approximations in smaller, more power efficient hardware IP for AI acceleration.
The idea began as a spare time project for Cassia founder and CEO James Tandon after he came across scientific papers from another group that discussed the accuracy loss associated with approximating certain math functions rather than quantizing (reducing numerical precision, which reduces prediction accuracy).
To read the full article, click here
Related Semiconductor IP
- AI Processor Accelerator
- Powerful AI processor
- Dataflow AI Processor IP
- Scalable Edge NPU IP for Generative AI
- AI inference processor IP
Related News
- CAST Licenses TCP/IP Hardware Stack Core for Keysight FieldFox Handheld Spectrum Analyzers
- SkyeChip Advances Custom Interface IP Engagement with Cerebras for Wafer-Scale AI Platforms
- CAST Introduces 100 Gbps TCP/IP Hardware Stack IP Core for High-Performance ASIC and FPGA Designs
- SignatureIP Unveils IP Library for Chiplet-based AI, HPC and Data Center Systems
Latest News
- Rapidus Unveils “Rapidus CORE”, New Global Ecosystem Framework Supporting the Development and Mass Production of Cutting-Edge Semiconductors
- JEDEC® Publishes First Industry-Wide Silicon Photonics Reliability Standard for AI, Datacenter and Telecom Infrastructure
- Orthogone Technologies Launches Ultra-Low-Latency FPGA IP Portfolio for Multi-Industry Deterministic Networking
- TIER IV joins Arm Total Design for Physical AI to accelerate ready-to-use Autoware solutions through Open AD Kit
- SEMIFIVE Signs Turnkey Contract with Mobilint to Develop Robotics AI Chip Under 'K-On-Device AI Semiconductor' Program