AMD claims next-gen Zen 6 server CPU will deliver 330% of Nvidia Vera's performance per rack

[Daniel Sims]

What we know so far: As the server battle between AMD and Nvidia enters a new phase, the two companies have begun trading jabs through performance estimates and early benchmarks. While Nvidia-approved results suggest its Vera processors outperform most AMD Epyc chips, Team Red believes its upcoming Venice lineup can leave Vera in the dust.

AMD recently published performance projections claiming its upcoming server CPU platform will dramatically outpace Nvidia's latest showing. AMD's estimates directly reference earlier results from controlled benchmarks that had favored Nvidia's processor.

Team Red's next data center CPU platform recently entered production and is on track to launch later this year. Built on AMD's Zen 6 architecture, Epyc Venice chips will offer up to 256 cores and 512 threads. The lineup also marks AMD's transition to TSMC's 2nm process, a jump directly from the 4nm Epyc Turin that skips the 3nm node entirely.

AMD is projecting a 70% overall improvement in performance and efficiency over Turin, along with a 30% increase in thread density.

Nvidia, for its part, formally launched its Vera server CPU at GTC in March. The Arm-based SoC packs 88 cores and 176 threads. In recent benchmarks, Phoronix described Vera as the most capable Arm processor it has ever tested, outclassing Intel Xeon and AMD Epyc across most workloads. However, the tests were conducted at Nvidia's headquarters and came with several restrictions to ensure Nvidia's sign-off.

AMD drew on Phoronix's figures when building the methodology for its Venice projections.

Comparing core counts per CPU, node power, nodes per rack, and a 100kW rack power budget, the company estimates Venice will deliver 3.3 times Vera's per-rack performance. AMD also projects its 192-core Epyc 9965 Turin and the 128-core Intel Xeon 6980P GNR-AP can reach 2.37x and 1.46x of Vera's output, respectively.

AMD is also challenging Nvidia on per-core performance, claiming a 64-core Venice chip can beat Vera by 27%, with the 96-core variant edging it by 11%.

As both processors target AI workloads, AMD argues that Venice's higher core counts will translate into a meaningful advantage for agentic AI deployments. Even so, the true performance gap will remain uncertain until independent benchmarks arrive.

While promoting Venice's theoretical performance, AMD is already hinting at what comes next. "Verano" will be AMD's first CPU designed specifically for AI infrastructure. That chip is expected to introduce the Zen 7 architecture. Supply chain reports suggest Zen 7 will target TSMC's A14 node, a 1.4nm-class process that would mark AMD's entry into the angstrom era and deliver further gains in performance and efficiency beyond 2nm. AMD has not confirmed those details.

Permalink to story:

AMD claims next-gen Zen 6 server CPU will deliver 330% of Nvidia Vera's performance per rack

 

[Rapob]

If ARM is not cheaper or has better perf per watt, it makes no sense over x86/x64.

 

[godrilla]

If ARM is not cheaper or has better perf per watt, it makes no sense over x86/x64.

While true Nvidia's gpus are in extreme demand and puts Nvidia in a position to incentives the coupling with its all in one server solution by prioritizing customers who are willing to pay for the arm solution vs those just seeking Nvidia gpus alone.

 

[Loadedaxe]

AMD's claim is interesting. If Zen 6 really delivers anywhere near the performance per rack improvements they're talking about versus Nvidia's platform, then Nvidia has a problem. One of ARM's biggest selling points in the data center has been efficiency and density. If AMD can match or beat those metrics while maintaining x86 compatibility, many customers will ask why they should go through the hassle of moving away from an ecosystem that already runs their applications, virtualization stacks, and management tools.

If AMD's numbers are even close to accurate, Nvidia may have its toughest sell yet. Convincing customers to adopt a new CPU architecture is difficult enough. Convincing them to do it when a competing x86 platform offers similar or better performance, competitive efficiency, and avoids migration headaches is even harder.

AMD still has to prove those numbers in real world deployments. Every vendor's launch presentation is designed to show them in the best possible light. But if the claim holds up, then ARM doesn't win simply because it's ARM.

The bottom line is that data centers buy results, not architectures. If AMD can deliver better performance per rack, competitive power efficiency, and let customers keep their existing x86 software investments, then Nvidia's ARM based CPU strategy becomes a much tougher proposition. The future isn't ARM versus x86, it's whichever platform delivers the best value for the workload.

 

[BrightlightJohn]

If ARM is not cheaper or has better perf per watt, it makes no sense over x86/x64.

The huge numbers of applications what would needed to be converted to run on ARM makes any change to ARM archetechure a difficult choice.