Intel Reveals New Technology to Boost Chip Performance

FILE PHOTO: U.S. chipmaker Intel Corp's logo is seen on their "smart building" in Petah Tikva, near Tel Aviv, Israel December 15, 2019. Picture taken December 15, 2019. REUTERS/Amir Cohen
FILE PHOTO: U.S. chipmaker Intel Corp's logo is seen on their "smart building" in Petah Tikva, near Tel Aviv, Israel December 15, 2019. Picture taken December 15, 2019. REUTERS/Amir Cohen
TT
20

Intel Reveals New Technology to Boost Chip Performance

FILE PHOTO: U.S. chipmaker Intel Corp's logo is seen on their "smart building" in Petah Tikva, near Tel Aviv, Israel December 15, 2019. Picture taken December 15, 2019. REUTERS/Amir Cohen
FILE PHOTO: U.S. chipmaker Intel Corp's logo is seen on their "smart building" in Petah Tikva, near Tel Aviv, Israel December 15, 2019. Picture taken December 15, 2019. REUTERS/Amir Cohen

Intel Corp on Thursday disclosed a new method for making transistors on semiconductors that its chief architect said could boost the performance Intel’s next round of processors by as much as 20%.

The Santa Clara, California-based company is one of the few remaining in the world that both designs and manufactures its own chips.

However, its manufacturing operations have become a concern among investors after Intel last month said that its next-generation chip-making process, called its 7-nanonmeter process node, would be delayed.

Analysts believe the delays could cement the lead that rivals such as Taiwan Semiconductor Manufacturing Co (2330.TW) have gained in making smaller, more power efficient chips. Intel’s shares have fallen nearly 20% since the delays were disclosed, Reuters reported.

On Thursday, Intel sought to buck the notion that the single-number names given to each generation of chip process node tell the entire story by disclosing improvements on its existing 10-nanonmeter process node.

It announced a new way of making what it now calls “SuperFin” transistors, which, along with a new material being used to improve the capacitors on chips, is expected to boost the performance of Intel’s forthcoming processors, despite their still being made on 10-nanonmeter manufacturing lines.

“It is 20%, the largest intra-node jump ever in our history,” Raja Koduri, Intel’s chief architect, said of the performance gain in an interview with Reuters.

“It’s actually same as what you would get with one full Moore’s Law node of performance.”

It will not be possible to test those claims in the real world until Intel’s new chips come out, but its “Tiger Lake” laptop chips slated for release this fall will use the chips.

Even with the new transistor technology, Koduri said Intel has re-worked its chip design process to be able to more easily use either its own chip factories or outside chip factories, whichever is needed to create the best chips.

“Whatever gets us to deliver those products on time, with leadership performance, we have the flexibility and are going to utilize that,” he said.



Tesla Reportedly Shuts Down Dojo Supercomputer Team, Reassigns Workers

Tesla vehicles line a parking area at the company's Fremont, Calif., factory on Tuesday, Aug. 5, 2025. (AP Photo/Noah Berger)
Tesla vehicles line a parking area at the company's Fremont, Calif., factory on Tuesday, Aug. 5, 2025. (AP Photo/Noah Berger)
TT
20

Tesla Reportedly Shuts Down Dojo Supercomputer Team, Reassigns Workers

Tesla vehicles line a parking area at the company's Fremont, Calif., factory on Tuesday, Aug. 5, 2025. (AP Photo/Noah Berger)
Tesla vehicles line a parking area at the company's Fremont, Calif., factory on Tuesday, Aug. 5, 2025. (AP Photo/Noah Berger)

Tesla CEO Elon Musk has ordered to shut down its Dojo supercomputer team, with team leader Peter Bannon departing the company, Bloomberg News reported on Thursday, citing people familiar with the matter.

The Dojo supercomputer was designed around custom training chips to process vast amounts of data and video from Tesla EVs to train the automaker's autonomous-driving software.

Tesla did not reply to a Reuters request for comment. CEO Elon Musk said on X that it didn't make sense for Tesla to divide its resources and scale two different AI chips.

Over the past year, Tesla, amid a company-wide restructuring, has seen multiple executive departures and thousands of job cuts. The company has redirected its focus to

AI-driven self-driving technology and robotics, with CEO Elon Musk pursuing an integration strategy across his business empire.

In March, xAI acquired the social media platform X for $33 billion to bolster its chatbot training capabilities, while Tesla integrated the Grok chatbot into its vehicles.

The automaker also plans to increase its reliance on external technology partners such as Nvidia and Advanced Micro Devices for compute, and Samsung Electronics for chip manufacturing, as per the Bloomberg report.

Last month, Samsung secured a $16.5 billion deal to supply AI chips to Tesla, expected to power self-driving cars, humanoid robots and data centers.

Tesla CEO Elon Musk earlier said that Samsung's new chip factory in Taylor, Texas would make Tesla's next-generation AI6 chip.

While no timeline was provided for AI6 chip production, Musk has previously said that next-generation AI5 chips will be produced at the end of 2026, suggesting AI6 would follow.

"The Tesla AI5, AI6 and subsequent chips will be excellent for inference and at least pretty good for training. All effort is focused on that", Musk said in an X post late Thursday.

Musk also said that in a supercomputer cluster, it would make sense to put many AI5/AI6 chips. "One could call that Dojo 3, I suppose", he said.

The Dojo team recently lost about 20 workers to newly formed DensityAI, and the remaining workers are being reassigned to other data center and compute projects within Tesla, the Bloomberg report said.

Nvidia declined to comment on the Bloomberg report, while AMD and Samsung did not immediately respond to Reuters requests for comment.