Intel has announced the addition of three new models to its Xeon 6 CPU series. These processors are specifically designed to manage the most advanced graphics-processing-unit-enabled AI systems. Featuring a Performance-Core (P-Core) architecture, the new processors also feature Priority Core Turbo technology and Intel Speed Select Technology – Turbo Frequency. These technologies offer customizable CPU core frequencies to boost GPU performance across demanding AI workloads.
Three new models added to the Intel Xeon 6 series!
The new Xeon 6 processors are available today. One of the three models currently serves as the main CPU for NVIDIA’s latest-generation AI-accelerated system, the DGX B300. The NVIDIA DGX B300 uses the Intel Xeon 6776P processor, which plays a critical role in managing, orchestrating, and supporting the AI-accelerated system. With its powerful memory capacity and bandwidth, the Xeon 6776P supports the growing demands of AI models and datasets.
“ These new Xeon SKUs showcase the unmatched performance of Intel Xeon 6, making it the ideal CPU for next-generation GPU-accelerated AI systems,” said Karin Eibschitz Segal, corporate vice president and interim general manager, Intel Data Center Group. “We are excited to deepen our collaboration with NVIDIA to deliver one of the industry’s highest-performing AI systems and help accelerate AI adoption across industries .”
Revolutionizing AI performance with Priority Core Turbo!
Priority Core Turbo technology paired with Intel SST-TF also delivers a significant leap forward in AI system performance. PCT enables dynamic prioritization of high priority cores, allowing them to operate at higher turbo frequencies.
At the same time, lower-priority cores run at base frequency, ensuring optimal allocation of CPU resources. This capability is critical for AI workloads that require sequential or serial processing, as it powers GPUs faster and improves overall system efficiency.
Intel Xeon 6 P-core processors deliver industry-leading features for any AI system. They provide high core counts of up to 128 P-cores per CPU and exceptional single-thread performance, ensuring balanced workload distribution for intensive AI tasks.
Delivering 30 percent faster memory speeds than the competition, Intel Xeon 6 delivers superior memory performance in high-capacity configurations and supports leading memory bandwidth with MRDIMMs and CXL.
For improved I/O performance, the new processors feature up to 20 percent more PCIe lanes than previous Xeon processors, enabling faster data transfers for I/O-intensive workloads. Designed for maximum uptime with robust reliability, availability and serviceability features that minimize business disruptions, these processors deliver unmatched reliability and serviceability.
Intel Advanced Matrix Extensions support arithmetic operations with FP16 precision, enabling efficient data preprocessing and critical CPU tasks in AI workloads.
