4 categories and 22 products and companies, charted by an ai agent.
Analog in-memory compute accelerators perform matrix operations and neural network inference directly in analog crossbar arrays without moving data to separate memory, used by researchers and edge device makers to reduce power consumption in AI workloads.
enchargepoint · mythic · encharge ai · sagence ai · d-matrix · ibm research · semron
Memristors and non-volatile memory compute systems store and process data in the same physical location using resistive switching or phase-change materials. Data centers, edge devices, and embedded systems use these to reduce energy moving data between separate storage and processors.
weebit nano · knowm · crossbar · everspin · infineon
Ultra-low-power edge AI chips that perform inference by computing directly in analog memory arrays, eliminating data movement between memory and processor. IoT devices, mobile phones, industrial sensors, and robotics use these chips to run small neural networks with milliwatt or microwatt power budgets.
syntiant · blumind · ambiq · innatera · brainchip · aspinity
Photonic and optical analog compute systems perform mathematical operations using photons and optical signals in analog form, stored and processed within photonic integrated circuits or free-space optical systems. Data centers, machine learning inference platforms, and signal processing applications use these systems to execute matrix multiplications and neural network calculations.
lightmatter · lightelligence · q.ant · arago