Supergate is a Korean fabless semiconductor design company that focuses on custom SoCs for high-performance computing, AI and autonomous driving, acting as an Arm Approved design partner for Neoverse and other Arm IP. In this interview they explain how their in-house design team builds supercomputer accelerators, multi-core CPUs and domain-specific SoCs that can be tailored to a customer’s workload, from scientific computing to automotive perception and control. Their design flow spans custom Arm Neoverse CPU complexes, bespoke AI engines and system integration into rack-scale servers, positioning Supergate as an outsourced silicon team for HPC and mobility platforms, with more detail on their SoC design offerings at https://supergate.cc/technology/soc-design/
—
HDMI® Technology is the foundation for the worldwide ecosystem of HDMI-connected devices; integrated with displays, set-top boxes, laptops, audio video receivers and other product types. Because of this global usage, manufacturers, resellers, integrators and consumers must be assured that their HDMI® products work seamlessly together and deliver the best possible performance by sourcing products from licensed HDMI Adopters or authorized resellers. For HDMI Cables, consumers can look for the official HDMI® Cable Certification Labels on packaging. Innovation continues with the latest HDMI 2.2 Specification that supports higher 96Gbps bandwidth and next-gen HDMI Fixed Rate Link technology to provide optimal audio and video for a wide range of device applications. Higher resolutions and refresh rates are supported, including up to 12K@120 and 16K@60. Additionally, more high-quality options are supported, including uncompressed full chroma formats such as 8K@60/4:4:4 and 4K@240/4:4:4 at 10-bit and 12-bit color.
—
A central part of the discussion is a large supercomputer accelerator developed as one of the first Korean-designed chips for national-scale scientific supercomputing. The accelerator combines Arm Neoverse CPU clusters with custom vector and AI engines, targeted at K-class systems where domestic IP is a strategic priority for Korea’s compute roadmap. Alongside that, Supergate shows an autonomous-driving SoC integrating a 160 TOPS MPU, designed to fuse many heterogeneous sensors and run perception and planning workloads under tight power and thermal envelopes in automotive environments, where the same IP blocks can later be re-used in edge AI infrastructure.
They also present the “Test T1” CPU chip, a 128-core Arm Neoverse N2 device fabricated on TSMC’s 5 nm process and aimed at high-performance servers and supercomputer nodes. This device targets hyper-dense Arm server blades, where many cores with coherent memory and high-speed I/O feed external accelerator cards over standard fabrics in a modular rack. The prototype boards and servers shown in the video illustrate a typical deployment pattern: Arm Neoverse host CPUs orchestrating multiple accelerator cards in each node, with Supergate providing both the silicon and the reference platforms for OEMs building HPC clusters and data-center hardware.
Beyond the individual chips, Supergate emphasizes that they deliver full-turnkey custom SoC projects, from specification and microarchitecture through logic design, verification, physical design, manufacturing and bring-up, all the way to software and board-level validation.([supergate.cc][2]) Depending on process node complexity, they quote project timescales from under a year on mature nodes to multiple years for cutting-edge geometries such as 5 nm, and they frame this as a way for system companies to turn their own ideas for accelerators into production silicon without building a large internal chip team. Filmed at the SC25 Supercomputing conference in St Louis, the conversation underlines a broader trend in HPC and automotive: custom Arm-based SoCs with tightly integrated accelerators, developed by specialist design houses like Supergate, are becoming the preferred path to differentiate both supercomputers and future autonomous vehicles while optimizing power, latency and total system cost.
I’m publishing about 90+ videos from Embedded World North America 2025, I upload about 4 videos per day at 5AM/11AM/5PM/11PM CET/EST. Join https://www.youtube.com/charbax/join for Early Access to all 90 videos (once they’re all queued in next few days) Check out all my Embedded World North America videos in my Embedded World playlist here: https://www.youtube.com/playlist?list=PL7xXqJFxvYvjgUpdNMBkGzEWU6YVxR8Ga
This video was filmed using the DJI Pocket 3 ($669 at https://amzn.to/4aMpKIC using the dual wireless DJI Mic 2 microphones with the DJI lapel microphone https://amzn.to/3XIj3l8 ), watch all my DJI Pocket 3 videos here https://www.youtube.com/playlist?list=PL7xXqJFxvYvhDlWIAxm_pR9dp7ArSkhKK
