The architecture relies on an interaction net execution model where computational steps remain strictly local and values are consumed only once. In rigorous testing across 25 workloads, the design delivered a 4.59x performance-per-watt advantage over a modern silicon-proven dual-issue superscalar core. An end-to-end automated workflow co-designed the entire hardware and software stack, discovering novel primitives from the instruction set down to the physical layout. This expansion of earlier automated accelerator research demonstrates the viability of machine-driven exploration for general-purpose processors.
Key points
Replacing shared mutable states with interaction nets removes the heavy area and power ov…: Replacing shared mutable states with interaction nets removes the heavy area and power overhead typically caused by traditional cache coherence protocols.
Automated co-design of both hardware and software stacks enables the discovery of highly…: Automated co-design of both hardware and software stacks enables the discovery of highly efficient architectural primitives beyond conventional human engineering methods.
The developers expect this end-to-end machine-driven methodology to expand into datacente…: The developers expect this end-to-end machine-driven methodology to expand into datacenter processors, AI accelerators, and networking silicon.
Sources checked by our analysis pipeline: 1
Abstract
In our previous post, Redwood, we showed that given an architecture, our AI systems could implement, verify, and deploy an inference accelerator in record time. However, similar to other scientific domains, we believe that AI systems, given the correct freedom and guardrails, can co-design software and hardware together, making optimizations across the stack and opening a design space so large it was previously inaccessible. We set out to answer the question: “Could our AI systems & tools lead to a novel hardware discovery that radically outperforms human-made designs?”
Today, we're introducing Frostbite, a general-purpose CPU with a new instruction set built from the ground up. Frostbite exploits the properties of interaction nets, namely that every step is local, every dependency is explicit, and every value has exactly one owner, to reach a step-function gain in CPU performance that has long stagnated. On a set of 25 initially chosen workloads, including 15 held out until the final evaluation, we achieved a 4.59x performance-per-watt multiple when compared to a modern, silicon-proven superscalar (dual-issue, in-order) CPU core.
Following a landmark public debut that valued the artificial intelligence lab at $1.7 trillion on a fully diluted basis, the company's immediate stock slide reflects intensifying scrutiny over steep tech multiples. Investors are questioning whether a valuation of roughly 40 times sales is sustainable amid broader Wall Street pullbacks. The retreat threatens to dampen market-wide enthusiasm for substantial corporate spending across the sector.
Market observers are raising inquiries after observing a downward trajectory in the company's valuation. Clear explanations clarifying the exact factors driving this market retreat remain unavailable. Stakeholders are left evaluating the situation without explicit details addressing the cause of the decline.
Frontier software systems are uncovering programming flaws far faster than human engineers can patch them, triggering widespread outages across corporate, government, and healthcare networks. Hostile actors and low-skill hackers are exploiting these automated discoveries to compromise vital infrastructure and steal billions of dollars. With traditional software defense strategies collapsing under the volume of new vulnerabilities, the stability of basic internet systems faces unprecedented risk.