Tagged Content
Everything on the platform tagged with asic.
AttoTude is a Menlo Park, California deep-tech startup building the world's first THz (terahertz) radio over wire - an interconnect platform that moves data between AI servers and GPUs at hundreds of gigabits per second over standard wire, without photonics or exotic packaging. Founded in 2024 by optical-networking veteran Dave Welch and RF/semiconductor pioneer Joy Laskar, the company adapts fiber-grade signaling to terahertz frequencies on low-cost ASICs to break the bandwidth, power, and reliability bottlenecks choking AI data centers. It came out of stealth at OFC 2025 and has raised roughly $91M total, including a $50M Series B led by Mayfield.
Dave Welch is the founder and CEO of AttoTude, a Menlo Park deep-tech startup building the world's first terahertz interconnect that runs over wire instead of fiber or photonics, aimed at unclogging the data-movement bottleneck inside AI and hyperscale data centers. A co-founder of Infinera, where he pioneered large-scale photonic integrated circuits, and former CTO at SDL, Welch holds more than 200 patents, has authored roughly 300 publications, and is a member of the National Academy of Engineering. In April 2025 AttoTude raised a $50M Series B, pushing total funding past $90M.
Artis, LLC (Advanced Real-Time Information Systems) is a Herndon, Virginia defense and technology developer that builds systems for problems measured in microseconds. Founded in 1999 by Keith Brendley, the company is best known for active protection systems for military vehicles - Iron Curtain and its third-generation successor, Sentinel - that detect and defeat incoming rockets, missiles and drone-borne threats in fractions of a second. Beyond defense, Artis applies its high-speed sensing and parallel-processing work to highway worker safety, 3D imaging and pedestrian monitoring.
Eximietas Design is a San Jose-headquartered engineering services firm that takes products from idea to silicon to intelligent ecosystem. Founded in 2023 by serial entrepreneur Jay Avula, its team covers the full stack of modern hardware and software - SoC and RTL-to-GDSII chip design, embedded firmware and board bring-up, and cloud, cybersecurity and AI/ML solutions. With roughly 600 engineers across the US and India and a leadership team that has collectively taped out more than 100 chips for the likes of Google, Cisco, Broadcom, Microsoft and Oracle, the company positions itself as a one-stop, full-cycle product development partner.
Chain Reaction is an Israeli-American semiconductor company designing custom ASICs for encrypted computation and Bitcoin mining. Its EL3CTRUM line powers next-generation hashing hardware, while its 3PU (Privacy Processor) accelerates Fully Homomorphic Encryption so cloud workloads in finance, healthcare and defense can run on encrypted data.
Alon Webman is the co-founder and CEO of Chain Reaction, an Israeli semiconductor company building purpose-built chips for encrypted computation, Bitcoin mining, and privacy-preserving AI. Before Chain Reaction, he co-founded Mellanox Technologies in 1999 and spent nearly two decades there, rising to VP-level roles before NVIDIA acquired Mellanox for $7 billion in 2020. A Technion graduate, Webman is now betting his second act on making fully homomorphic encryption practical at scale - a technology that would let clouds compute on data they can never see.

Hao Zhong is the CEO and Co-Founder of ScaleFlux, a San Jose-based fabless semiconductor company that builds computational storage drives and CXL memory solutions for cloud, AI, and data center workloads. With 20+ years in flash storage and LDPC technology — including stints at LSI, SandForce, and Fusion-io — Zhong co-founded ScaleFlux in 2014 to rethink what a storage device can do: compress data in hardware, cut write amplification, and deliver 4x effective capacity at roughly half the price of standard NVMe SSDs. ScaleFlux has raised $288M in funding and posted record-breaking growth in 2024.
ScaleFlux designs computational storage drives and CXL memory devices that push compute into the storage layer itself. Founded in 2014 by chip and flash veterans Hao Zhong, Tong Zhang and Yang Liu, the Milpitas company sells NVMe SSDs whose on-drive ASICs handle compression, encryption and data services that used to burn host CPU cycles - giving enterprises more usable capacity, longer flash endurance, and faster database and AI workloads.
Positron AI designs purpose-built inference hardware for transformer models, aiming to make Nvidia GPUs optional for running large language models at production scale. Its first product, Atlas, ships from US fabs and claims roughly 3x lower latency and 4x better performance-per-watt versus an H100 system.
Frank Ferrante is the CEO of ForwardEdge ASIC, a Lockheed Martin subsidiary dedicated to advancing U.S. domestic semiconductor chip design. A 30-year veteran of the semiconductor industry, Ferrante has held leadership roles at Intel (Senior Director of Military, Aerospace and Government), Wolfspeed (VP of Worldwide Automotive Sales and Marketing), and Altera. He is a vocal advocate for U.S. advanced manufacturing policy, having advised policymakers on the CHIPS Act, SHIP, and RAMP-C initiatives. Under his leadership, ForwardEdge ASIC achieved U.S. Government Trusted IC Vendor Status in February 2026 and selected the MIPS S8200 for mission-critical autonomous platform ASICs.
Gavin Uberti is the co-founder and CEO of Etched, a Cupertino-based AI chip startup building the world's first transformer-specific ASIC called Sohu. A Harvard dropout and 2024 Thiel Fellow, Uberti co-founded Etched in 2022 alongside Chris Zhu and Robert Wachen after betting that transformer architecture would dominate AI for years to come. That bet has paid off spectacularly: Etched has raised over $625 million (including a $500M round in January 2026 at a $5 billion valuation), and Sohu claims to run transformer inference 20x faster than Nvidia's H100 at a fraction of the cost - positioning Etched as one of the most serious challengers to Nvidia's dominance in AI compute.