Intel Falcon Shores AI GPUs Reportedly Utilize TSMC’s 3nm & CoWoS Packaging
Intel Falcon Shores AI GPUs Reportedly Utilize TSMC’s 3nm & CoWoS Packaging
Intel's next-gen AI GPU, Falcon Shores, is expected to utilize TSMC's 3nm process, and may not use its own process technologies.
The markets expected Intel's move, not only because the IFS is underperforming but also because the firm hasn't made strides in the AI industry through its Gaudi AI offerings.
Intel's Falcon Shores GPUs will be the first true GPU IP for the AI segment based on the next-gen Xe graphics architecture, and the firm has hyped up the architecture immensely, claiming that it is far superior to Gaudi offerings, probably being the product that will potentially bring the "redemption" of Intel in the markets. Well, that's something that remains to be seen as Intel's Ponte Vecchio chip, despite being an engineering marvel, failed to amass a sizable customer base, and the one product where it was going to be a leadership design was delayed immensely (Aurora Supercomputer).
Taiwanese media outlet Cnyes reports that Intel has yet again opted for the "outsourcing" route with its upcoming Falcon Shores AI GPU generation, citing that Team Blue is eager to create a capable product, ready to compete with the likes of NVIDIA's Blackwell products. Intel plans on adopting an aggressive product portfolio with Falcon Shores, and rather than just "specializing" on a set of products, Intel plans on creating high, mid-range, and low-end variants, catering to every type of consumer in the AI segment. Having several variants will mean that Intel will be able to attract a diverse range of customers and also let them enter markets that are regulated heavily by the US, such as China.
Additionally, Intel plans to utilize TSMC's CoWoS-R packaging, which is known as one of the best solutions for making HPC/Datacenter chips on the market and is currently being used by the likes of NVIDIA's Blackwell chips.
This means that for Falcon Shores, Intel is completely dependent on TSMC for production, which does have a huge benefit considering that the Taiwan giant is known for its quality and capable products. This can potentially mark Intel releasing a lineup that competes with NVIDIA's offerings directly, challenging Team Green's monopoly over the markets. However, one thing remains to be seen whether TSMC will be able to fulfill the supply of Intel's orders as the company might face a tight supply moving forward with AI demand rising and all three vendors, AMD, NVIDIA & Intel, leveraging TSMC for its next-gen AI products.
Recently, we reported on Intel's Falcon Shores products utilizing TDPs as high as 1500W. This does hint that Intel is expected to provide a massive generational bump in performance. Apart from that, Falcon Shores is expected to utilize liquid cooling entirely, yet again showing the power encapsulated by Intel's upcoming AI-focused architecture. Thought we might see some non-liquid cooled offerings too for entry-level designs that don't boast such high TDPs.
Given that Falcon Shores GPUs are expected to launch by next year (2025), we still have a long way to go, but it does seem like Team Blue has decided to take things seriously, given that with the Gaudi generation, the company was only able to bag in $500 million this year, phenomenally low to what its competitors were able to earn. However the software team is working to get things going and bring Intel's AI chips on par with the competition.
News Source: Cnyes
What's Your Reaction?
