TetraMem Inc., a Silicon Valley semiconductor company specializing in analog in-memory computing (IMC), has announced the successful tape-out, manufacturing, and initial silicon validation of its MLX200 platform, a 22nm multi-level RRAM-based analog IMC system-on-chip developed on TSMC’s commercial 22nm process. The milestone represents a major step toward commercializing analog computing architectures designed to address the growing power, thermal, and data movement challenges associated with modern AI workloads. The MLX200 platform combines multi-level RRAM arrays with mixed-signal compute engines to perform vector-matrix operations directly within memory, reducing data transfer bottlenecks and improving energy efficiency.
Also Read: Excelitas and Acconeer Partner to Advance Sensor Fusion for Smart Applications
Building on earlier research conducted on its MX100 platform, TetraMem has demonstrated scalable multi-level RRAM technology with strong endurance, retention, and compute density characteristics suitable for edge AI applications such as wearable devices, IoT systems, voice processing, and always-on sensing. “This milestone reflects years of close collaboration with our foundry partner TSMC and demonstrates the feasibility of bringing multi-level RRAM and analog in-memory computing from computing architecture breakthrough into advanced-node commercial silicon,” said Dr. Glenn Ge, Co-founder and CEO of TetraMem. Evaluation kits for the MLX200 platform are expected to begin shipping in the second half of 2026.
