Compiler Engineer - MLIR / Pytorch Infrastructure

Mythic, a pioneer in analog compute-in-memory technology, has acquired Videantis, a leading European digital processor IP company. The transaction unites Mythic's analog compute platform with Videantis' unified digital processor architecture to create a hybrid AI computing system claiming 100x energy efficiency advantage over conventional GPU-based systems. Videantis has shipped over 25 million chips worldwide with zero field defects, powering systems across all top three European automotive manufacturers. Its unified processor architecture runs deep learning, computer vision and AI inference workloads on a single platform. The acquisition follows Mythic's $125 million funding round and its agreement with Honda to co-develop next-generation AI chips. All five Videantis founders, including CEO Hans-Joachim Stolberg, will join Mythic, which will operate Videantis as a wholly owned subsidiary.

Japan targets 26% global share in self-driving cars by 2030s. Japan will target a 26% global share in self-driving cars in the 2030s under a new growth strategy that Takaichi Sanae's government plans to draft this summer. The government set numerical goals for 34 of 61 products and technologies chosen in March for priority public and private investment. It also wants Japanese companies' share of undersea cable installations to rise to about 35% by 2030 from 20% now, citing demand tied to AI. For content, the government aims to lift overseas sales of Japanese anime to 6 trillion yen (US$38 billion), in 2033, about four times 2022 levels. Officials plan to add a roadmap covering investment needs and expected economic effects to the growth strategy. Food for thought. Implications, context, and why it matters. Demographic pressures are the driving force behind Japan's new growth strategy. * The targets respond to demographic strain, since Japan has the world's highest share of people aged 65 and older at 29.1% 1. * Labor gaps are already biting, with a projected shortfall of 36,000 bus drivers by 2030 that is forcing service cuts in cities and rural areas 1. * Freight faces a similar squeeze, as a 36% shortage of truck drivers is expected by 2031 and could reduce national transport capacity by about a third by 2030 2. * Corporate bankruptcies have climbed to a 13-year high and household consumption is falling, so the government is tying its push into self-driving vehicles and AI to keeping growth going despite worker shortages 3. Japan's new strategy is steering rival automakers toward alliances. * To reach its goals for self-driving cars, the government is supporting frameworks that nudge long-time rivals such as Toyota and Honda to work together on AI-powered self-driving technology 4. * Nissan and Honda have also teamed up, saying they have fallen behind foreign rivals and cannot catch up while trying to do everything on their own 5. * Companies are also looking overseas for know-how to speed up work on self-driving technology. * Honda is co-developing AI chips with U.S. startup Mythic, a semiconductor company, under a joint development agreement, while Toyota has a preliminary agreement with Waymo, Alphabet's self-driving technology company, to explore collaboration on autonomous driving technologies 67. Stay updated on the go with our mobile app. Get latest insights with smoother, more personalized experience through TIA mobile app. How would you feel if you could no longer use Tech in Asia? Share, tag us, and land on our Wall of!

Mythic selects memBrain technology from Silicon Storage Technology for its next generation of ultra-low-power Analog Processing Units. Mythic has chosen memBrain neuromorphic hardware intellectual property (IP) from Microchip Technology's Silicon Storage Technology (SST) subsidiary for its next-generation edge to enterprise Analog Processing Units (APUs). Mythic will utilize SST's SuperFlash embedded non-volatile memory (eNVM) bitcells to deliver high levels of analog compute-in-memory (aCIM) performance per watt. The partnership enables Mythic to achieve 120 TOPS/watt inference processing for power-efficient AI acceleration at the edge and in the data center: Mythic's APUs are targeted to be up to 100 times more energy-efficient than conventional digital Graphics Processing Units (GPUs). One hundred fifty billion units of SST SuperFlash technology that Mythic is licensing have been shipped to date. SuperFlash technology is the de facto eNVM solution for a broad spectrum of industries including industrial, automotive, consumer and computing for critical data and code storage, and is licensed by all of the top ten semiconductor foundries worldwide. "Mythic is pioneering innovative solutions in AI inference processing and AI sensor fusion for industrial, automotive and data center applications, effectively overcoming current AI power limitations," said Mark Reiten, vice president of Microchip's Edge AI business unit. "As the core memory technology for Mythic's next-generation products, memBrain delivers significant power efficiency and high performance for both edge and data center applications." The memBrain cell features: * Up to 8 data bits per bitcell (8 bpc) storage * Single digit nanoamp (nA) bitcell read current * 10-year data retention at operating temperature * 100,000 endurance cycles * Full state machine control of the 8 bpc multi-state write operation * Single cycle multiply-and-accumulate operations for aCIM "Mythic selected SST after an industry-wide search of eNVM technologies and determined the memBrain cell technology best enabled us to achieve the ultra-low-power and high performance required by our customers," said Dr. Taner Ozcelik, Mythic's chief executive officer. "Additionally, the wide foundry availability of its industry-proven SuperFlash technology, coupled with the outstanding support of the SST engineering team has been invaluable during our product development cycle." SST's memBrain technology has been developed and deployed in 40 nm and 28 nm foundry processes using production-ready SuperFlash memory. 22 nm memBrain development is planned to extend the technology roadmap. Designed to provide reliable, high-performance and low-power non-volatile storage directly on the chip, SuperFlash memory is widely used in applications that require fast access times, high endurance and data retention without the need for external memory components. Pricing and Availability Customers interested in SST's memBrain solutions and SuperFlash technology should access the SST website or contact a regional SST sales executive for details. Those interested in Mythic's products should visit the Mythic website or contact Taner Ozcelik at [email protected].