Fujitsu is in the development phase of its next-generation processor aimed at the HPC market. The company currently offers its A64FX design based on Arm ISA and its power Fugaku supercomputer. However, with the next-generation design, much larger data sets will need to be processed, and a lot of computational work power will be required to handle it. So, to prepare for that, Fujitsu is making some bold claims that its CPU will have an "overwhelming efficiency." Codenamed MONAKA, the next-generation CPU will be based on Arm ISA (probably version 9 and up) and will compete in a wider range of workloads than A64FX, currently powering HPC sites only. MONAKA's design is reportedly made with HPC, AI, and data analytical workloads.

According to The Register, we have some finer details about the next-generation CPU. Slated for release in 2027, the MONAKA design is set to appeal to hyperscalers, not just HPC sites. Scalability and energy efficiency are the keywords, as Fujitsu claims that MONAKA will have 1.7x lead in application performance while offering 2x the performance per watt compared to solutions provided by other vendors at the time. That includes Intel, AMD, and others. A Fujitsu spokesperson noted that "The next-generation DC CPU (MONAKA) that we're developing will have a wider range of features and will prove more energy efficient. The range of potential applications is wider than that of the A64FX, which has special characteristics (e.g., interconnects) specific to Fugaku." Cloud Service Providers (CSPs) will undoubtedly be interested in a new design and Fugaku NEXT supercomputer that will replace the current Fugaku system as the top-end system could be powered by MONAKA. Fugaku NEXT is still in the evaluation phase at Japanese RIKEN laboratories.