Energy-efficient artificial intelligence-powered supercomputing components developing company Ceremorphic announces that it plans to launch a new 5nm-based microchip.
According to Ceremorphic, the new chipset will be highly scalable and less power-consuming, which would deliver better performance, efficiency, security, and reliability. The technology firm says that the new processor will be able to handle next-generation applications such as AI model training, HPC, automotive processing, drug discovery, and metaverse processing.
Ceremorphic has an advantage over other chip firms since it has access to TSMC’s 5-nanometer process node. The company plans to use 2024 for its Hierarchical Learning Processor.
Read More: Jio Invests $15 million in Pranav Mistry’s AI firm Two Platforms
CEO and Founder of Ceremorphic , Venkat Mattela, said,” Having developed many innovations in multi-thread processing, algorithm-driven VLSI, reliable performance circuits, low-energy interface circuits, quantum-resistant security microarchitecture, and new device architectures beyond CMOS, Ceremorphic is well on its way to accomplishing our goals.”
He further added that the issues this market faces with reliable performance computing require an entirely new architecture built specifically to ensure dependability, security, energy efficiency, and scalability.
This new development will now allow Ceremorphic to compete with several global giants like NVIDIA, which is a developer of processors used for artificial intelligence and high-performance computing. The processor will come with multiple top-notch features like –
- Custom Machine Learning Processor and custom FPU clocked at 2Ghz.
- ThreadArch based RISC –V processor for proxy processing.
- Open AI framework software support with optimized compiler and application libraries.
- Custom designed X16 PCIe 6. 0 / CXL 3.0 connectivity interface
- Custom video engines for Metaverse Processing
United States-based technology firm Ceremorphic was founded by Venkat Mattela in 2020. The enterprise specializes in developing an architecture that is used for multiple purposes, including AI model training, HPC, drug discovery, metaverse processing, and many more. To date, the company has raised nearly $5 million in its recently held series A funding round.
Professor of Electrical Engineering and Computer Science at Stanford University, Subhasish Mitra, said, “Reliable performance computing is absolutely something this industry needs, and the approach that Ceremorphic is pursuing is a significant step in the right direction.”