In-Memory ComputingMemory & StorageInterconnect & Networking
Panmnesia
Daejeon, South Korea, South Korea
About Panmnesia
Panmnesia designs technology for CXL, an open standard that lets processors, accelerators and memory devices share memory over a fast link. Its products include CXL switches and controllers that let many chips draw on a shared pool of memory, which helps AI systems whose memory needs outgrow what one GPU can hold. The company was founded in 2022 as a spin-off from KAIST, the Korean research university in Daejeon, where it is based. It is led by KAIST professor Myoungsoo Jung.
Panmnesia was founded in 2022 and is based in Daejeon, South Korea. It is listed under In-Memory Computing, Memory & Storage, Interconnect & Networking. Reported funding is $30M project funding (May 2025); $102M total.
Compute Technologies
- In-Memory Computing
What Panmnesia 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.
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.
Interconnect & Networking
Interconnect is the set of links that move data between chips, between boards and between racks. It includes wires on a package, cables inside a server, and the network switches and optical fibre across a data center. A processor is only as useful as the speed at which it can get data in and out.
Also in South Korea
MetisX (XCENA), Netsol, Samsung Electronics (Memory), FADU, SK Hynix
