Rambus Introduces PCIe 7.0 Switch IP with Time Division Multiplexing for Scalable AI and Data Center Infrastructure

Summary:

Supports bandwidth scaling, low latency, and efficient data movement for AI, cloud, and HPC systems
Increases link utilization through intelligent traffic multiplexing, enabling simpler architectures and scalable disaggregated and pooled compute designs
Extends the industry-leading Rambus PCIe IP portfolio which spans switches, controllers, retimers, and debug solutions to support next‑generation AI infrastructure

Rambus Inc., a player chip and silicon IP provider making data faster and safer, announced the Rambus PCIe 7.0 Switch IP with Time Division Multiplexing (TDM), a new addition to its advanced interconnect IP portfolio designed to address the rapidly escalating bandwidth, latency, and scalability requirements of AI, cloud, and high-performance computing (HPC) systems.

As AI infrastructure grows in scale and architectural complexity, system designers are increasingly challenged to move massive volumes of data efficiently across CPUs, GPUs, accelerators, and NVMe storage. The Rambus PCIe 7.0 Switch IP with TDM is architected to help meet these demands by enabling more flexible and efficient utilization of PCIe links, supporting emerging disaggregated and pooled compute architectures while maintaining low latency and deterministic performance.

Rambus PCIe 7.0 Switch IP with TDM Optimized for Next-Generation AI and Data Center SoCs
Built on the PCIe 7.0 specification, the Rambus newest switch IP is optimized for next‑generation AI and data center SoCs that require extreme bandwidth density, advanced traffic management, and seamless scalability. By incorporating TDM capabilities, the switch enables designers to intelligently schedule and multiplex traffic across shared links, helping maximize fabric utilization while supporting diverse workload profiles, from large‑scale AI training to latency‑sensitive inference and data movement.

“The acceleration of AI is fundamentally reshaping system architectures, and it’s no longer sufficient to simply add more lanes or more endpoints,” said Simon Blake‑Wilson, SVP and GM, Silicon IP, Rambus. “With our PCIe 7.0 Switch IP with TDM, Rambus is giving system architects a new degree of freedom to scale bandwidth efficiently and deterministically, while reducing complexity and improving overall system utilization. This is a critical enabler for scale up and scale out of the next wave of advanced AI clusters and HPC networks.”

“AI infrastructure is increasingly defined by how efficiently data can move between heterogeneous compute and memory resources,” said Jeff Janukowicz, VP, semiconductors and enabling technologies. “Advanced PCIe switching technologies that improve link utilization and enable flexible traffic orchestration will be key to building scalable, cost‑effective AI platforms as next‑generation interconnect technology evolves.”

Rambus PCIe 7.0 Switch IP with TDM Expands Industry-Leading PCIe IP Portfolio
The Rambus PCIe 7.0 Switch IP with TDM is designed to integrate seamlessly into leading-edge ASIC platforms and complements Rambus’ broader PCIe 7.0 IP portfolio, which includes controllers, retimers, and debug solutions. Together, these IP offerings help customers accelerate time‑to‑market while addressing the demanding performance, power, and reliability requirements of modern AI infrastructure.

The Rambus PCIe 7.0 Switch IP with TDM reinforces the company’s long‑standing leadership in high‑speed interface IP and its commitment to delivering differentiated interconnect technologies that help customers solve the most challenging problems in AI, cloud, and HPC Infrastructure.