NVIDIA Vera CPU leads early server benchmarks

NVIDIA's pre-release Vera server CPU posted strong early results against Intel Xeon and AMD EPYC in a limited set of data center tests. The Arm-based design pairs custom cores, high memory bandwidth, and native FP8 support aimed at demanding compute and Artificial Intelligence workloads.

NVIDIA’s Vera CPU emerged as a strong early contender in server benchmarking, with results indicating it can outperform recent Intel Xeon and AMD EPYC processors in selected data center workloads. The Arm-based platform reflects NVIDIA’s push deeper into custom CPU design and, in the reported tests, ranked ahead of both x86 rivals and NVIDIA’s earlier Grace design.

Vera is equipped with 88 custom Armv9.2 Olympus cores and 176 threads through physical resource partitioning. These custom cores support native FP8 processing, allowing certain Artificial Intelligence workloads to be executed directly on the CPU with a 6×128-bit SVE2 implementation. The chip offers 1.2 TB/s of memory bandwidth and supports up to 1.5 TB of LPDDR5X memory in the SOCAMM2 format. A second-generation Scalable Coherency Fabric provides 3.4 TB/s of bisection bandwidth, connecting the cores across a unified monolithic die and eliminating the latency issues common in chiplet architectures.

The comparison set included single and dual Intel Xeon Granite Rapids 6980P CPUs, along with AMD EPYC Turin and Turin Dense parts such as the AMD EPYC 9755, 9575F, and 9475F. NVIDIA also allowed comparison with its first-generation Grace processor based on Arm Neoverse V2 cores. Testing on the pre-release chip was limited to a specific subset of workloads, including code compilation, stream memory performance, video encoding, Python/Java, and database performance.

In the geometric mean of all test results, NVIDIA’s Vera topped the chart, performing nearly 11% better than AMD’s most advanced designs and about 55.3% better than the best single-socket Intel Xeon. It also outperformed dual-socket configurations, suggesting that some workloads have scaling issues across multiple sockets. These limited results place Vera above any Arm-based design, with a 450 W TDP for the CPU and 50 W for the 768 GB memory pool.

63

Impact Score

NVIDIA Vera CPU targets agentic Artificial Intelligence workloads

NVIDIA positions Vera as a CPU built for agentic Artificial Intelligence factories, with custom Olympus cores, high memory bandwidth and strong performance under sustained load. Early benchmark results from Phoronix and additional testing highlighted gains in throughput, memory efficiency and competitiveness against Intel and AMD processors.

Entry-level work faces an Artificial Intelligence squeeze

Employment has remained broadly stable, but early-career hiring in Artificial Intelligence-exposed occupations is showing signs of strain. The pressure is raising concerns about how young workers will gain skills, experience, and a path into long-term careers.

Labor data challenges the Artificial Intelligence jobs panic

Fears of an immediate white-collar jobs collapse from Artificial Intelligence are not yet reflected in broad US labor data. Early evidence points instead to a more uneven transition, with younger workers in some exposed fields facing the greatest pressure.

Artificial Intelligence jobs fears face a reality check

Fears that Artificial Intelligence is already causing broad white-collar job losses are not yet supported by labor market data. The sharper warning is emerging around entry-level work, where generative Artificial Intelligence may be eroding early career opportunities.

SpaceX filing reveals losses, Starlink growth, and xAI exposure

SpaceX’s public filing opens a detailed view into the rocket company ahead of its planned IPO, including the financial impact of its xAI acquisition. The disclosure shows strong Starlink revenue, heavy Artificial Intelligence spending, and major risks tied to Musk’s expanding empire.

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.