Alphawave Semi collaborates with Arm on high-performance compute chiplet
Alphawave Semi has collaborated with Arm on the development of an advanced compute chiplet built on Arm Neoverse Compute Subsystems (CSS) for artificial intelligence/machine learning (AI/ML), high-performance compute (HPC), data centre and 5G/6G networking infrastructure applications. The development follows last year’s announcement that Alphawave Semi joined Arm Total Design, an ecosystem building custom silicon solutions based on Arm Neoverse CSS.
Alphawave Semi’s chiplet-based custom silicon design platform adds a differentiator in our portfolio that includes IO extension chiplets, memory chiplets, and compute chiplets, as well as Alphawave Semi’s ultra-high-speed connectivity IP and advanced packaging capabilities. This compute chiplet lineup features an Arm Neoverse N3 CPU core cluster and the Arm Coherent Mesh Network (CMN) ensuring efficient, scalable performance. Available on industry-leading process nodes, the technology allows customers to accelerate development and reduce the time-to-market (TTM) of a new generation of custom system-on-chip (SoC) technologies. These advanced SoCs support the rapid deployment of high-performance digital infrastructure, enabling the creation of custom silicon solutions tailored to specific needs.
In collaboration with Arm, Alphawave Semi enhances this setup with their advanced packaging techniques and a leading-edge portfolio of connectivity technologies, including PCIe Gen 6.0 and 7.0, Universal Chiplet Express (UCIe), 112/224G Ethernet and HBM subsystems. This strategic integration ensures that the Arm-based compute chiplet delivers robust performance and flexibility, catering to next-generation HPC, data centre, AI/ML, and 5G/6G infrastructure needs while accelerating time-to-market for customers.
