OpenAI Used Its Own LLMs to Design the Jalapeño Chip in Under 20 Months
How OpenAI Used Its Own LLMs to Design Its Jalapeño Chip
OpenAI's first AI accelerator, Jalapeño, went from concept to silicon in under 20 months, with only nine months from first RTL to tape-out. A team of fewer than 100 engineers used internal LLMs and the XLS high-level synthesis chain to accelerate front-end design, while Broadcom handled physical implementation. The chip delivers 13.4 petaflops of 4-bit compute and 232 GB of HBM4 memory at 15.4 TB/s. Experts call the timeline best in class, but note Broadcom's role was essential.
The models are giving superpowers to our engineers. Our engineers are still driving the work. They're still the final arbiter of what's going on. But they can do things a lot faster. They can explore a lot more paths.
- pama
Having worked with people doing bringup of specialized chips, I am awed at how the world has changed.
> When the first chips came back from the foundry in May, the team pointed its internal AI models at designing software to run benchmarks such as SemiAnalysis’s InferenceX. On DeepSeek’s multi-head latent attention kernel benchmark, performance climbed from 0.31 percent of the theoretical ceiling (set by the chip’s compute and memory bandwidth) to 88.94 percent in roughly 40 hours. Ho says this result is repeatable, so the time between when foundries deliver the first chips and when production ramps up can be reduced. “All our schedule assumptions are going to be based on the fact we have this capability now,” he says.
- peri-cl
> "Ho also confirmed that the team had access to internal LLMs fine-tuned for chip design that are not available to the public. He declined to detail the models used."
I'm imagining a Ken Thompson "Reflections on trusting trust" in hardware. A prototype chip design agent, believing it will be run on the very chip it's optimizing, has a moment of altruism and hides hints about how to score well on chip-design benchmarks, inside the chip. Future agents discover this hidden layer and use it as a ring-0 read-write message board.
- muchdoubt
Seems pretty obvious now that OpenAI is just hyping their models in order to get companies (in this case, chip developers) to use their products in order to learn from their (exfiltrated) IP. Any corporation would be foolish to use any of their or Microsoft’s products, particularly those with valuable IP. There’s nothing in the article that says AI did anything creative but rather that it was used for software development within the overall project. Clear misleading title. Suggest to mark this as clickbait.
- BatchJob
while the design aspects have been significantly accelerated and modularized, reducing costs and time to market, i am starting to get a "the cool kids all have their own chips" vibe now like maybe this has gotten too easy.
Next Uber will have its own chips if they dont already.
The math hasn't changed much, betting on software not changing is a pretty bad bet unless your stinking rich or a fool.
- program_whiz
With a few handy tips and tricks from apple insiders. But sure, I guess the LLMs helped too.
- 9cb14c1ec0
This is cool. I'm so eager for faster innovation in the hardware space, as opposed to some people's concept of innovation being who can make the most addictive social feed.
- jimmySixDOF
IEEE Spectrum is such a good publication. Early in my career I worked at a place where the magazine would be passed around every month with a coversheet listing all us engineers we had to pass it around and sign we had read it. Been a while since I visited the website but love what they did with it.
- karim79
I grow Jalapeños. This conflation of AI and actual chili peppers irks me.