- Kioxia develops 5TB Flash Memory Prototype with 64 GB/S Bandwidth to Edge Competence
- Prototype memory module demonstrates Daisy Chain Design Maintenance of Bandwidth at Higher Capacities
- New Module uses PAM4 -Signaling and Controller to improve flash performance
Kioxia has developed a new type of prototype flash memory module that offers both large capacity and high bandwidth.
The module was created under Japan’s infrastructure improvement of R&D project after 5G information and communication systems.
The module offers 5TB storage and a transfer rate of 64 GB/s that places it as a potential alternative or supplement to conventional drama in data processing. Kioxia said the design addresses the long-standing balance between bandwidth and capacity found in drama modules by arranging flash memory chips in a daisy chain rather than a bus connection.
Flash beads
Each flash unit, described as a gem, is connected in order with its own controller. Daisy-Chain design allows capacity to expand without degrading bandwidth, something that has been a limitation in previous architectures.
The company also developed high -speed transformers capable of 128 Gbps flow. These use PAM4 modulation that encodes two bites of information per Signal that doubles the effective bandwidth compared to traditional binary signaling.
Alongside this, new controllers, such as advance development of, help reduce reading slab time, while signaling low amplitude and distortion increases the speed of the memory interface to 4.0 Gbps.
Kioxia reported that the prototype consumes less than 40W when working at full bandwidth over a PCIE Gen 6 eight-course connection.
The combination of effect efficiency and flow is presented as a step towards making flash more convenient in memory -intensive roles that are usually full of drama.
The work is targeted at servers in mobile edge calculation environments, where 5G and 6G networks create the need to process information closer to end units.
IoT and AI workload in real time drives interest rates in memory systems that balancing costs, capacity and performance.
Kioxia said it is planning to continue to develop this technology against commercialization, with potential use in IoT, Big Data Analytics and advanced AI models including generative AI.
