Perplexity Bets on NVIDIA’s Vera CPU, Calling The Max Single-Threaded Chip a “Dead-On” Fit After It Ran 1.5x Faster in Agentic Coding

NVIDIA's Vera CPUs are seeing increased demand as their single-threaded & inference-optimized design makes them ideal for firms such as Perplexity.

Perplexity Bets on NVIDIA's Vera As The Chip Promises A Fully Inference-Optimized Architecture, Designed Purely For AI

The Vera CPU is an ambitious chip for NVIDIA as it claims to generate $20 billion worth of revenue while becoming the leading CPU supplier this year. The chip is already in mass production & has landed at various firms such as OpenAI, xAI, Oracle and Anthropic.

This increased demand for CPUs is driven by Agentic AI workloads, which are more reliant on CPUs than GPUs. Even the competition is focusing more on enhancing the inference capabilities of their upcoming chips, which is the trend going forward. AI firms are also developing their own custom CPUs to address in-house needs.

"Vera really stood out to us as just ​like ⁠a dead-on fit for a lot of the core workloads that we have," Kupp said in an interview.

​Nate Kupp - VP at Perplexity (via Reuters)

According to Reuters, Perplexity is the latest AI firm that has placed its bets on NVIDIA's Vera CPU. VP Nate Kupp says that NVIDIA's Vera CPUs were 1.5 times faster than traditional CPUs in Agentic AI coding tasks, making it a "dead-on fit" for the majority of their core workloads. Although the AI firm hasn't disclosed the number of CPUs or their value, it should be noted that Vera is landing at every major AI firm, which shows its successes already.

NVIDIA Pitches Vera As The Only "Max Single-Threaded" CPU At Scale

In its latest blog post, NVIDIA has also described Vera as the world's only Max Single-Threaded CPU at scale. The term "Max-Single-Threaded" CPUs delivers on three key fundamentals:

• Strong performance per core under load
• Enough memory bandwidth per core to keep active cores supplied with data 
• Predictable latency  

Agentic AI workloads run in a loop: as the CPU executes work, the results come back, and the model decides what to do next, and the same process repeats over and over. NVIDIA says that this pattern is something that conventional CPUs aren't optimized for. You can add more cores, but those extra cores cannot shorten the time for each step inside a single agent loop. CPUs with more cores can also hamper performance as each core contends for resources.

This is why NVIDIA has bet on a smaller number of cores than the competition. Vera offers per-core optimizations for each core, as the throughput of additional cores, while useful, can be insufficient.

In the end, the best agentic CPU needs the best single-threaded performance per core, and every core needs to deliver that performance without compromise. The world counts in seconds. Agents count in nanoseconds. NVIDIA Vera is built for this new category — and speed — of work.

NVIDIA

Vera brings 50% higher IPC with its custom Olympus cores than Grace. It is paired with 1.2 TB/s of LPDDR5X memory bandwidth at less than 40W memory power while its monolithic compute die keeps the active cores fed with 3.4 TB/s of core-to-core bandwidth, over 3x faster than any other CPU on the market.

Vera pairs those faster cores with up to 1.2TB/s of LPDDR5X memory bandwidth at less than 40 watts of memory power, plus a monolithic compute die that helps active cores stay fed and keeps data movement predictable with 3.4TB/s of core-to-core bandwidth, 3x greater than any other data center CPU. This enables all 88 cores with the full memory performance of the CPU without creating bottlenecks that slows down every core.

NVIDIA

We have already mentioned how Perplexity was able to achieve a 50% uplift in its Agentic AI workflows versus traditional x86 CPUs. In concurrent sandboxes, this performance is up by 90%. Furthermore, NVIDIA partners are measuring 3x faster performance in large-scale SQL analytics with Starburst and up to 6x lower latency on real-time streaming with Redpanda, against x86 CPU offerings.

With NVIDIA Vera aiming for success, the company is already highlighting its next-gen Data Center CPU, codenamed Rosa, featuring the updated Rigel core architecture. Rosa looks very impressive as a follow-up to Vera, and NVIDIA is on the path to tackle x86 competitors with a big adoption rate.

Follow Wccftech on Google to get more of our news coverage in your feeds.