Recent #RISC-V news in the semiconductor industry
➀ Sales of RISC-V chips are unprofitable for companies, and RISC-V suppliers are discussing chip architectures at SC conferences.
➁ RISC-V's performance is far from comparable to x86 and ARM processors.
➂ RISC-V is highly flexible and suitable for small chips, and can be paired with any type of interconnect, storage, or I/O.
➀ Axelera AI, founded in 2021, aims to provide scalable edge AI hardware and software solutions.
➁ The company has raised USD 120 million and has a world-class team of over 190 employees.
➂ Axelera AI's Metis platform offers high performance with low power consumption, targeting applications like computer vision, automotive, and healthcare.
➀ A new chiplet-based RISC-V vector processor architecture aims to balance performance, efficiency, and flexibility for AI workloads.
➁ The architecture utilizes modular chiplets, including a vector processing chiplet and a matrix multiplication accelerator, to optimize various AI computation aspects.
➂ The RISC-V solution addresses memory bottlenecks and enhances energy efficiency with time-based execution and dynamic power gating.
➀ Semidynamics, founded in 2016, transitioned from RISC-V design services to licensing customizable 64-bit RISC-V processor IP in 2019.
➁ UPMEM's selection of Semidynamics' IP for large language models in 2024 led to increased interest from other fabless semiconductor companies.
➂ The company is focusing on providing customized solutions and encouraging early collaboration to address challenges and meet future demands in the AI sector.
➀ A new architecture for RISC-V CPUs introduces advanced matrix extensions and custom quantization instructions that significantly improve CNN acceleration.
➁ The design features scalable, VLEN-agnostic matrix multiplication instructions, ensuring consistent performance across different hardware configurations.
➂ A 2D load/store unit optimizes memory access for matrices, reducing overhead and increasing computational efficiency.