MemSilicon

Compute-in-memory (CIM) AI memory chips and inference racks that let data centers support more users and longer context at the same power.

Analog in-memory computing AI inference chips based on RRAM memristors (NPU chips and IP) for low-power edge and endpoint AI devices.

Develops dedicated AI accelerators for large model inference, with an architecture built around memory capacity and bandwidth rather than raw compute

Series C · $1.2B · 2026-09 · Valuation $5.0B

Neuromorphic sensing-memory-compute chips, using brain-inspired computing and mixed-signal design to integrate sensing, storage and computation

Series C · $139M · 2026-10

3D compute-in-memory AI inference chips: 64 TOPS CIM units with in-house RISC-V vector architecture, 6GB-48GB 3D DRAM

Angel · $15M · 2026-10

3D compute-in-memory (3D-CIM) AI inference chips

Series C · $154M · 2026-09

Compute-in-memory AI inference chips and complete systems for data centers

Series B · $236M · 2026-05

Photonic AI inference chip (DX-1/optical tensor processing unit) that uses SRAM plus photonic interconnects to bypass the HBM bottleneck, with accompanying optical networking and rack-scale systems

Series B · $532M · 2026-08 · Valuation $3.3B

General-purpose reconfigurable RISC-V processor for physical AI (sensing, AI inference and real-time control on a single chip)

Seed · $18M · 2026-10

Programmable ASICs and rack-scale systems for foundation model inference, using processor-memory co-design to cut energy use

Series A · 2026-09

Develops the RNGD data center inference accelerator card and the WARBOY vision NPU for enterprises running large model inference

Series C · $125M · 2025-08

Develops quantum computing systems based on a multi-core trapped-ion architecture

Series A · $164M · 2026-05