Tenstorrent changes leadership roles

The Toronto-based startup is growing rapidly, swapping the roles of CEO and CTO, and crafting a compelling roadmap for AI Y RISC-V.

A Toronto-based startup that raised more than $200 million in venture funding at a $1 billion valuation in May 2021, Tenstorrent now has more than 280 employees and is backed by Eclipse Ventures and Real Ventures, among others. The company hired legendary chip designer Jim Keller as CTO in early 2021, an early angel investor and advisor. At the time, he said that Tenstorrent has “the best architecture out there” for AI.

Now Jim and founder Ljubisa Bajic have swapped roles. Jim became CEO and founder Ljubisa Bajic took over as CTO. In our opinion, these roles are really what everyone has been doing all along, so the change will hardly be noticeable. But let’s take a look at the initial impact Jim has already had.

When Jim joined the company, he saw changes he wanted to make to the accelerator roadmap, which has already produced two production chips, most notably the high-performance Greyskull. But aside from learning about AI while designing Tesla’s FSD, Jim’s forte has always been designing CPU cores. He led the AMD Zen effort that led to incredible market share gains for AMD, especially in HPC with the EPYC line.

So when you put a CPU designer in charge of a design team, it should come as no surprise that he, well, designs new CPUs. In addition to high-performance AI accelerators already in development, Jim envisioned an opportunity to build on the momentum RISC-V is enjoying and potentially lead the market with enhanced cores as a second line of business. His team has created CPUs that could be built as chips, chipsets in accelerators, or maybe even made available to some customers as chiplet IPs. Companies like Meta and Google have been cajoling and lobbying AMD and Intel for specific additional features for decades. Now they could choose to work with Tenstorrent and use Tenstorrent RISC-V IP as a solid foundation from which to innovate. Below you can see that this is much more than a sliding line business for Tenstorrent as they plan CPUs that will run as clients, on edge processors, and in HPC and server applications.

Tenstorrent’s Buddha software stack is independent of CPU type, so the accelerator can be connected to an Intel, AMD, or RISC-V CPU core cluster. Below you can see a portion of the roadmap that, similar to the AMD MI300 and NVIDIA Grace Hopper, combines CPU and AI cores into a single chiplet. So if you’re wondering why Tenstorrent is heading down the RISC-V path, you can see the value the company is engineering by doing AI and CPU.

So, you might ask, what is Ljubisa working on now? Pretty much the same as before. The founder is leading the development of the Tenstorrent software stack, which enables the company’s mantra of ease of use, providing target-agnostic AI development with the open source stack developers need to build and run, and optimize. when needed, all in Python and now Python 2.0. More ambitiously, Ljubisa plans to build AI models that can scale across an arbitrarily large array of nodes, vastly simplifying the development and deployment of even the largest language models currently under development.

conclusions

We’ve barely scratched the surface of what Tenstorrent is up to in this short article, and we plan to cover more on Tenstorrent in the near future. We believe Tenstorrent has a distinct AI hardware and software history and a compelling RISC-V CPU roadmap. In the emerging era of chiplets, Tenstorrent is well positioned for success, and we think Jim and Ljubisa’s new roles are a perfect fit.