Nvidia's Secret x86 CPU Ambitions: How Legal Hurdles Transformed Project Denver

· 1 min read

article picture

In a surprising revelation at the recent SC24 conference, former Transmeta CEO Dave Ditzel uncovered that Nvidia's Project Denver was originally conceived as an x86 processor aimed to compete with Intel and AMD, before being transformed into an Arm-based design.

During a technical session, Ditzel shared that Nvidia's initial server CPU ambitions were derailed by legal complications, forcing the company to pivot to Arm architecture. The transition was aided by Nvidia's licensing of Transmeta's Tokamak technology, which enabled x86 code translation to RISC instruction sets.

"Nvidia brought out a product called Denver. It was actually that same design. It originally started as an x86 [CPU], but through certain legal issues, had to turn itself into an Arm CPU," Ditzel explained during his presentation.

The revelation sheds new light on Nvidia's processor development history. Project Denver was officially announced in 2011 as an Arm-based CPU and later became part of Nvidia's Tegra product line. However, the project's x86 origins remained unknown until now.

The story highlights the complex legal landscape surrounding x86 architecture. These challenges eventually influenced Ditzel's own venture, Esperanto Technologies, to adopt RISC-V architecture instead. "At least we have a playground where we can test some new things out, and some lawyer is not going to be ringing your bell," he noted.

While Project Denver as an Arm CPU saw limited success due to software ecosystem challenges, it laid the groundwork for Nvidia's current processor initiatives, including the Grace CPU. The company has since established itself as a major player in the ARM ecosystem, despite its failed attempt to acquire Arm Holdings.

This historical insight reveals how legal constraints shaped not only Nvidia's processor strategy but also the broader competitive landscape in the CPU market.