Jensen Huang, co-founder and CEO of Nvidia, will be exhibiting his new Blackwell GPU chips at the NVIDIA GPU Technology Conference held in San Jose, California on March 18, 2024.
David Paul Morris/Bloomberg via Getty Images
nvidia CEO Jensen Huang will reveal details about Rubin, the chipmaker’s next AI graphics processor, at the company’s annual GTC meeting on Tuesday.
Other tech companies usually use inexplicable combinations of letters and numbers to name their products, but most of Nvidia’s latest GPU architectures are named after famous female scientists.
Nvidia has named the next important AI chip platform after American astronomer Vera Rubin:
The company never explains the naming treaties and does not highlight the diversity aspects of its choice, but Nvidia’s chip name, which highlights women and minority scientists, is one of the most visible efforts to celebrate diversity in the tech industry during a period when diversity, equality, inclusion, or DEI is being cut by the Trump administration.
Rubin discovered much of what is known about “dark matter.” This is a form of problems that can make up a quarter of the problems of the universe and emit no light or radiation, and she defended women in science throughout her career.
Nvidia has named the architecture after scientists since 1998, when the first chip was based on the company’s “Fahrenheit” microarchitecture. It’s part of the company’s culture. Nvidia sold cartoons of several well-known scientists and employee-only T-shirts.
This is one of the more attention-grabbing Nvidia quirks as it has resurrected to become one of the most important suppliers of Google, Microsoft, Amazon, Openai, Tesla and Meta.
Investors want to hear on Tuesday how fast Rubin chips will be, what configurations will come in, and when they will begin shipping.
Before uncovering the new architecture, Nvidia CEO Jensen Huang usually provides a one-sentence biography of the scientist it was named.
“I would like to present a very large GPU named after Mathematics theorist David Blackwell,” Huang said at last year’s GTC conference. “We thought it was the perfect name.”
Rubin is a fitting name for Nvidia’s next chip. This comes when companies are trying to solidify the profits they have gained as a leader in AI hardware in recent years. “Vera” refers to Nvidia’s next-generation central processor, and “Rubin” refers to Nvidia’s new GPU.
File Photo: World-famous astronomer Belarubin, 82, at the Carnegie Institute office in Washington, DC, on January 14, 2010.
Linda Davidson | Washington Post | Getty Images
Born in Philadelphia in 1928, Rubin studied deep space and worked with other scientists to develop better telescopes and instruments that allow them to collect more detailed data on the universe. In 1968, according to a Nova documentary, she began to observe Andromeda Galaxy and collect data that overturned her understanding of the universe of science.
Her claim to fame came after she observed how fast the galaxy spins.
“We hypothesized that stars near the center of the galaxy orbit very rapidly, and that stars on the outside would go very slowly,” Rubin said in 1987.
However, Rubin noticed that, contrary to his expectations, he was observing that the outer stars were moving quickly. They hadn’t jumped out of orbit, so it had to be that more popular scientists hadn’t observed – affirming the concept of dark matter.
She was praised throughout her life, published over 100 papers and earned three advanced degrees, but she still faced discrimination due to her sex. According to the documentary, early in her career, Rubin was not permitted to collect her data, and some observatory did not allow women.
Rubin passed away in 2016. In 2019, Chile’s cutting-edge telescope, the Vera C. Rubin Observatory, was named after her. According to ProPublica, the biography of the federally funded observatory website was compiled and earlier this year deleted details about women’s advocacy in science.
“I love doing astronomy, so I hope you like your work,” Rubin said in his 1996 opening speech. “I hope that all outfits will fight injustice and discrimination.”
Rubin is not the first woman to be honored with the nvidia chip, named after her.
Before Blackwell, the first Black American to be appointed to the National Academy of Sciences, Nvidia’s most advanced AI chip family was Hopper. In 2022, Nvidia released the “Ada Lovelace” architecture, named after the British mathematician who pioneered computer algorithms in the 19th century.
Scientist names were previously secondary naming treaties, with the back seat of the actual product name, appearing primarily in marketing copies. Nvidia users have more frequently referred to the “H100” chip or marketing names on consumer graphics cards such as the GeForce RTX 3090.
However, last year, Huang emphasized that Blackwell is not a single chip, not a technology platform, and Nvidia began using the term “Blackwell” to refer to all the latest generation of AI products, such as the GB200 chip and DGX server rack.
Maintain momentum
Investors and analysts are now tracking how many “Hoppers” numbers are being used, and large companies boast that they have early access to “Blackwell.”
For Nvidia, it is important that Rubin achieves the same last name familiarity as Hopper and Blackwell.
The company’s sales more than doubled in fiscal year 2025, closing in January, bringing it to $124.62 billion thanks to durable sales of its hopper chips and early demand for the company’s blackwell chips.
To maintain growth, Nvidia needs to justify costs and provide next-generation chips that improve the speed, power efficiency and cost of ownership of previous generations.
According to an investor presentation last fall, the company is targeting 2026 with the aim of rolling out Vera chips. In addition to Vera Rubin, Nvidia is expected to discuss Blackwell Ultra. Blackwell Ultra is an updated version of the Blackwell chips that analysts are hoping to start selling later this year.
Huang teased last month’s revenue call to show “next click” after Vera Rubin. Its architecture may also have been named after a scientist.
“These products need to encourage partners at meetings ranging from Microsoft to Dell to Sovereigns, which usually pleases investors.”
Tuesday’s keynote also tests Nvidia’s relatively new release cadence, striving to reveal new chips each year. Investors will also want to see if NVIDIA will continue to impress technology critics and developers and be able to release new chip families on a faster schedule than before. Blackwell was announced last March, and its sales began to rise in Nvidia’s October quarter.
Watch: Last Trading: Nvidia, Taiwan Semi, Amazon, IEFA
