Maxaa dhacay
Semifive, a global provider of custom AI ASIC solutions, signed a contract worth roughly KRW 70.3 billion (US $52 million) with an unnamed U.S.âbased AI fabless company to develop a nextâgeneration AI inference accelerator. The deal represents more than 40 % of Semifiveâs total orders for 2025 and about 60 % of new orders booked in the first half of 2026, making it the companyâs largest single contract to date. Under Semifiveâs âSpec Handâoffâ model, the customer supplies performance specifications while Semifive handles fullâstack development, including design, software, packaging, testing, and mass production. The accelerator will use LPDDR6 memory and PCIe Gen5 interfaces, target high memory bandwidth, low power consumption, and reduced total cost of ownership. Tapeâout is planned for the first half of 2027, with mass production slated for 2028 aimed at hyperscalers and cloud service providers.
Semifiveâs press release states the contract is valued at KRW 70.3 billion (approximately US $52 million) and is the companyâs first "Spec Handâoff" engagement in the North American market. The agreement accounts for over 40 % of the firmâs total order book for 2025 and roughly 60 % of the new orders recorded in the first half of 2026.
The Spec Handâoff model differs from traditional turnkey engagements by allowing the customer to provide only highâlevel performance specifications, while Semifive assumes responsibility for detailed chip design, software development, packaging, testing, and eventual mass production. This approach aims to reduce timeâtoâmarket and development risk for the fabless partner.
Technical highlights include the integration of LPDDR6 memory to lower power consumption associated with memory accesses, and PCIe Gen5 interfaces to alleviate dataâtransfer bottlenecks. Semifive also plans to leverage its experience with largeâdie (up to 800 mm²) projects to deliver high compute throughput and operational stability.
The development timeline targets a tapeâout in the first half of 2027, followed by global mass production in 2028. The accelerator is intended for deployment by hyperscale cloud service providers and other largeâscale AI inference workloads.
Faahfaahinta isha: prnewswire.com â
Maxay muhiim u tahay
The contract underscores the growing demand for custom AI silicon optimized for largeâscale model inference, a market segment traditionally dominated by inâhouse designs at firms like Google and Amazon. By securing a sizable North American deal, Semifive expands its footprint beyond Asia and positions itself as a viable partner for U.S. hyperscale cloud operators seeking to lower inference costs and power usage. The use of LPDDR6 and PCIe Gen5 reflects industry trends toward higher bandwidth and energyâefficient memory solutions, which could influence future ASIC design standards. If the accelerator meets its performance targets, it may provide a costâeffective alternative to existing offerings from established ASIC vendors, potentially reshaping the competitive dynamics of the AI hardware supply chain.
Custom AI ASICs are increasingly critical for reducing the cost and energy footprint of large language model inference. By securing a major contract with a U.S. fabless firm, Semifive demonstrates its ability to compete for highâvalue design work outside its traditional Asian market.
The contractâs size relative to Semifiveâs overall order book highlights the strategic importance of the North American AI hardware market and suggests that customers are seeking alternatives to the dominant players that have historically controlled AI silicon supply chains.
Adoption of LPDDR6 and PCIe Gen5 aligns with industry moves toward higher bandwidth, lowerâpower memory subsystems, potentially setting a new for future AI inference chips.
If successful, the accelerator could provide cloud providers with a more costâeffective solution for serving AI workloads, influencing pricing and performance expectations across the AI inference ecosystem.
Farsamaynta Is-dhexgalka: Sida Dhabta Ay U Shaqeyso
U baadh tignoolajiyada hoose ee ka dambeeya horumarkan si isdhexgal leh.
What did neural scaling law research (e.g. Kaplan et al., 2020) observe?
Maxaa la daawan doona xiga
Key milestones to monitor include the scheduled tapeâout in early 2027 and the commencement of mass production in 2028. Observers should watch for announcements of the unnamed U.S. fabless partner, which could reveal which cloud providers or AI workloads the accelerator will serve. Additionally, any performance benchmarks or powerâefficiency data released by Semifive will indicate whether the chip can compete with incumbent solutions from companies like Nvidia, Broadcom, or Marvell. Finally, the broader market responseâsuch as interest from other hyperscalers or potential followâon contractsâwill signal the commercial viability of Semifiveâs Spec Handâoff model in North America.
The scheduled tapeâout in early 2027 will be a key technical milestone; any delays or design changes could affect the projected 2028 massâproduction timeline.
Identification of the U.S. fabless partner will clarify which hyperscalers or AI service providers are likely to adopt the accelerator, offering insight into market demand.
Performance and powerâefficiency benchmarks released after tapeâout will be essential for assessing competitiveness against existing solutions from Nvidia, Broadcom, Marvell, and other ASIC vendors.
Potential followâon contracts or additional orders from other North American customers will indicate whether Semifiveâs Spec Handâoff model gains broader acceptance in the region.