
Numem Inc., a leading provider of NuRAM MRAM and SmartMem SOC IP cores and chiplets that significantly cut power consumption in AI systems, has secured a robust Series A funding round, with investments from Cambium Capital and Doorga Capital.
This influx of capital will accelerate the evolution and rollout of its pioneering MRAM memory products and its patented SmartMem SOC subsystem, addressing the burgeoning AI, Generative AI and IoT landscapes, and initiate the introduction of an innovative line of SmartMem SOC chiplets and chips.
With the AI and smart systems realm expanding exponentially, the availability of memory that merges power, performance, and size has never been more critical. Numem is positioned at this juncture, set to redefine industry standards with its groundbreaking AI-centric offerings.
Low power NuRAM delivers 20 to 290x lower leakage power and 10 to 30x lower standby power, a game-changer for AI processing from intelligent edge IoT to data centers. It also occupies a small area, which is 2 to 3x smaller than traditional SRAM enabling the reduction of memory size or packing more memory density in the same area, thereby reducing power hungry external DRAM memory access (DRAM comes in at around 60x higher power).
NuRAM operates 2 to 5x faster with significantly lower dynamic power than most MRAM/RRAM on the Reads and up to 500x faster on the Writes. It also boasts a staggering 100x better endurance. Further, NuRAM integrates a complete Memory Management and Control which makes use of the memory as simple as an SRAM by taking care of all the necessary steps to operate the memory. It also enables simple device bringup and testing.
The SmartMem SOC subsystem extends some of the above advantages to other persistent memories including other MRAM, RRAM/ReRAM, PCRAM and even embedded/external Flash. It also enables ease-of-use and optimization for memory operation and testing. SmartMem SOC functions can be integrated in NuRAM as SOC Compute in Memory along with some DSP/AI processing accelerator compute functions.
“The rise of AI, Generative AI, Autonomous Driving and Smart IoT/embedded applications demand a significant increase in compute and memory capabilities,” stated Bill Leszinske, Operating Partner at Cambium Capital and Numem Board Member. “Numem’s IP building blocks and chiplets are enabling advanced memories like MRAM/RRAM to enable new levels of performance and ultra-low power for these new workloads.”
