PCI-SIG reveals PCI Express 8.0 specification with 256 Gbps per lane, targets 2028 release

PCI-SIG has announced PCIe 8.0, doubling data rates to 256 Gbps per lane to address booming Artificial Intelligence and high-performance needs.

PCI-SIG has formally announced the forthcoming PCI Express 8.0 specification, marking yet another milestone in the relentless progression of the PCIe interconnect standard. Set for release to PCI-SIG members by 2028, PCIe 8.0 will double the data transfer rate of the recently finalized PCIe 7.0, delivering a staggering 256 giga-transfers per second (GT/s) per lane per direction. This advancement continues the organization´s established cadence of doubling bandwidth approximately every three years.

The announcement comes on the heels of the PCIe 7.0 standard, as the technology sector demands ever-increasing throughput to power new generations of compute-intensive workloads. Al Yanes, PCI-SIG President and Chairperson, emphasized that this leap supports the surging data requirements of Artificial Intelligence and other emergent applications. The organization sees the new specification as critical for maintaining PCIe´s role as a high-performance, low-latency, and cost-effective I/O interconnect for a variety of industry uses.

While technical details of PCIe 8.0 beyond headline speeds remain pending, this doubling of bandwidth per lane will have sweeping implications across data center, enterprise, and consumer platforms. Developers and manufacturers will have to wait until the standard´s expected release in 2028 to integrate the evolution, but the commitment to rapid progress signals the industry’s dedication to supporting next-wave computing demands—whether driven by Artificial Intelligence advancements, big data analytics, or bandwidth-hungry hardware. PCIe’s predictable advance is set to equip future systems with the interconnect muscle they require, ensuring scalability for years to come.

72

Impact Score

Saudi Artificial Intelligence startup launches Arabic LLM

Misraj Artificial Intelligence unveiled Kawn, an Arabic large language model, at AWS re:Invent and launched Workforces, a platform for creating and managing Artificial Intelligence agents for enterprises and public institutions.

Introducing Mistral 3: open artificial intelligence models

Mistral 3 is a family of open, multimodal and multilingual Artificial Intelligence models that includes three Ministral edge models and a sparse Mistral Large 3 trained with 41B active and 675B total parameters, released under the Apache 2.0 license.

NVIDIA and Mistral Artificial Intelligence partner to accelerate new family of open models

NVIDIA and Mistral Artificial Intelligence announced a partnership to optimize the Mistral 3 family of open-source multilingual, multimodal models across NVIDIA supercomputing and edge platforms. The collaboration highlights Mistral Large 3, a mixture-of-experts model designed to improve efficiency and accuracy for enterprise artificial intelligence deployments starting Tuesday, Dec. 2.

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.