TetraMem has completed tapeout of the MLX300, a 12nm system-on-chip (SoC) using analog in-memory computing (A-IMC) and multi-level resistive random-access memory (RRAM) technology. The Silicon Valley-based company said the chip was developed using Synopsys electronic design automation (EDA) tools delivered through Synopsys Cloud FlexEDA. The tapeout follows its MLX200 and MLX200M A-IMC SoCs, implemented on a commercial 22nm process. The three designs represent two full-mask tapeouts completed by TetraMem in 2026. A-IMC combines memory and computation to reduce data movement, a major source of energy consumption in conventional computing architectures. TetraMem is targeting the MLX300 at AI inference workloads involving audio, vision and small language models. The chip supports up to 64 million INT4 parameters on-chip, eliminating the need for external DRAM to store model weights, according to the company. TetraMem is targeting energy efficiency of more than 50–80 TOPS/W. “TetraMem’s architecture represents a fundamentally new approach to AI computing by converging memory and compute together,” said Glenn Ge, CEO and co-founder of TetraMem. “Leveraging Synopsys EDA solutions through Synopsys Cloud have been instrumental in enabling efficient global collaboration and accelerating our path from research innovation to manufacturable silicon.” TetraMem used Synopsys Cloud FlexEDA for both the 22nm and 12nm designs, supporting development across engineering teams in the United States and Singapore. The company reported reducing design-environment setup time from weeks to minutes and achieving three times faster register-transfer-level (RTL) verification simulation compared with its on-premises methods. “TetraMem’s work in analog in-memory computing reflects the kind of bold innovation needed to unlock the next wave of AI performance and efficiency,” said Sanjay Bali, senior vice president of EDA Product Management and Strategy at Synopsys Inc. “At Synopsys, we are pleased to support TetraMem with our cloud-enabled design solutions, advanced EDA technologies, and proven IP to help accelerate the development of next-generation AI hardware.” The post TetraMem Tapes Out 12nm Analog In-Memory Computing AI SoC appeared first on EE Times Asia .