Toronto-based chip design company Tenstorrent is leveraging Samsung Foundry US to build the next generation of artificial intelligence (AI) chips. Samsung’s Foundry Design Service team will develop the chip using its new SF4X process.
In addition to AI chips, Samsung will also manufacture central processing units (CPUs) for Tenstorrent. Both product categories are designed around Tenstorrent’s new RISC-V chip design.
Samsung’s U.S. business accelerates with new chips
Samsung plans to manufacture Tenstorrent chips at a factory in Austin, Texas, but the company is currently building another factory to expand production in the United States. Jim Keller, CEO of Tenstorrent saying Samsung’s experience in electronics manufacturing will help bring Tenstorrent chips to consumers.
“Samsung Foundry’s commitment to advances in semiconductor technology aligns with our vision of advancing RISC-V and AI, making them an ideal partner to bring our AI chips to market.”
Tenstorrent’s selection of Samsung is a predictable move for a member of the struggling U.S. chip industry. Samsung’s U.S. operations can make chips using a 4-nanometer (4nm) process, which some consider close to cutting-edge technology.
The company’s new facility in Austin aims to make 3-nanometer (3nm) chips that are 30 percent more powerful but use half the energy. However, Samsung is not expected to start mass producing 3-nanometer chips until 2024, giving Asian rival Taiwan Semiconductor Manufacturing Co. (TSMC) a chance to take the lead. .
TSMC already makes 3nm chips for the A17 chip in Apple’s latest iPhones, and has dominated semiconductor manufacturing since the U.S. fell behind several years ago. President Joe Biden supports the construction of several new semiconductor manufacturing facilities in the United States.
How AI is changing the approach to chip design
The global war for semiconductor supremacy is coming into sharper focus with the advent of AI. Advances in large-scale language models, such as those used by OpenAI and Google, are directly related to the capabilities of semiconductors.
As a result, several companies, including Tenstorrent, Nvidia, and Graphcore, have invested heavily to maximize the ability of semiconductors to process AI models. Tenstorrent uses his RISC-V, an open source instruction set that chip designers can rearrange to optimize his AI’s computations.
Read more: 9 AI stocks to buy in 2023
Graphcore, a UK-based company backed by Microsoft and SoftBank, has developed a chip that can process multiple data streams simultaneously. Nvidia software tools allow you to customize graphics processing units for large-scale AI workloads in large data centers.
Read more: How will artificial intelligence (AI) transform cryptocurrencies?
I have something to say about the agreement between Tenstorrent. Samsung to manufacture AI chips in the US Or something else?Write to us or join our discussion Telegram channel. You can also view it here tick tock, Facebookwhich one X (Twitter).
In accordance with Trust Project guidelines, BeInCrypto is committed to fair and transparent reporting. This news article is intended to provide accurate and timely information. However, before making any decisions based on this content, readers are encouraged to independently verify their facts and consult a professional.