PCI-SIG announces PCIe 7.0 specification with 128.0 GT/s transfer rates

PCI-SIG unveils PCIe 7.0, targeting Artificial Intelligence, 800G ethernet, and quantum computing with blazing fast 128.0 GT/s throughput.

PCI-SIG has officially released the PCI Express (PCIe) 7.0 specification, pushing performance boundaries to a raw bit rate of 128.0 GT/s and supporting bidirectional throughput up to 512 GB/s in an x16 configuration. The new standard leverages advanced technologies like pulse amplitude modulation with four levels (PAM4) signaling and Flit-based encoding to drive faster data transfers and improved protocol efficiency. Despite this leap in performance, PCIe 7.0 retains backwards compatibility with prior PCI Express generations, easing the industry’s transition to next-generation platforms.

Key features introduced in PCIe 7.0 address the escalating bandwidth needs of cutting-edge applications across Artificial Intelligence, machine learning, 800G ethernet, large-scale cloud infrastructure, and quantum computing. The integration of PAM4 signaling technology represents a significant shift from previous standards, boosting channel capacity and making PCIe 7.0 suitable for demanding, data-driven workloads. Improved power efficiency further positions this standard as an attractive option for hyperscale data centers and high-performance computing environments striving to optimize both throughput and energy consumption.

Looking beyond the latest announcement, PCI-SIG has already commenced pathfinding efforts for PCIe 8.0, seeking to ensure sustained engineering momentum and continual enhancement of the PCI Express ecosystem. This continued roadmap reflects the organization´s commitment to supporting both current and future product requirements from cloud service providers, semiconductor manufacturers, and enterprise IT stakeholders. With every new specification, PCI-SIG reinforces its leadership in defining interconnect standards that power modern digital infrastructure.

73

Impact Score

A trillion dollars is a terrible thing to waste

Gary Marcus argues that the machine learning mainstream’s prolonged focus on scaling large language models may have cost roughly a trillion dollars and produced diminishing returns. He urges a pivot toward new ideas such as neurosymbolic techniques and built-in inductive constraints to address persistent problems.

experts divided over claim that Chinese hackers launched world-first Artificial Intelligence-powered cyber attack

Anthropic said in a Nov. 13 statement that engineers disrupted a ‘largely autonomous’ operation that used its Claude model to automate roughly 80-90% of reconnaissance and exploitation against 30 organizations worldwide. Experts dispute the degree of autonomy but warn even partial Artificial Intelligence-driven orchestration lowers barriers to espionage and increases scalability.

Seagate HAMR prototype achieves 6.9 TB per platter for 55 TB HDDs

Seagate disclosed a prototype heat-assisted magnetic recording platter that stores roughly 6.9 TB and enables drives with roughly 55 TB of capacity. The company says the technology would benefit data center cold tiers and workloads such as Artificial Intelligence.

Rapidus plans second Hokkaido plant, targets 1.4 nm production in early 2029

Rapidus reportedly plans to begin construction of a second factory in Hokkaido in 2027 and aims to start production of 1.4 nm chips in early 2029 as part of a trillion-yen initiative. A Rapidus spokesperson said the recent reports are speculation and that any roadmap updates will come directly from the company.

Contact Us

Got questions? Use the form to contact us.

Contact Form

Clicking next sends a verification code to your email. After verifying, you can enter your message.