About UPMEM
UPMEM, based in Grenoble, France, developed processing-in-memory technology. Its chips place small general-purpose processors, which it calls DRAM Processing Units, inside the memory chips themselves, so data-heavy tasks such as analytics and AI inference can run where the data sits rather than being moved to a separate CPU. This reduces traffic over the memory bus, which is often the bottleneck. Academic benchmarks describe it as the first commercially available processing-in-memory architecture. The company was founded in 2015 and has been reported as acquired by Qualcomm in 2025, though no primary announcement was found.
UPMEM was founded in 2015 and is based in Grenoble, France. It is listed under In-Memory Computing, AI Accelerators, Memory & Storage. Reported funding is $15.9M.
Compute Technologies
- In-Memory Computing
- AI Accelerators
What UPMEM works on
In-Memory Computing
In-memory computing does calculations inside or right next to the memory that stores the data, instead of copying the data to a separate processor. It is also called processing-in-memory (PIM) or compute-in-memory.
AI Accelerators
An AI accelerator is a chip, or a part of a chip, designed to run machine learning faster or with less energy than a general-purpose processor. The category includes GPUs, TPUs, neural processing units (NPUs) and chips from many startups.
Memory & Storage
Memory and storage hold the data that processors work on. Memory such as DRAM is fast and loses its contents when power is removed. Storage such as flash (NAND) is slower, cheaper per bit and keeps data without power.
Also in France
Arago, GreenWaves Technologies, Biomemory, Antaios, Thales Group
