Samsung, Toshiba Detail AI Chips
ISSCC papers target smartphones, cars
By Rick Merritt, EETimes
February 20, 2019
SAN FRANCISCO — Samsung described a new neural network accelerator for smartphones that matches blocks from rivals such as Huawei. Toshiba detailed one for self-driving cars that pulls ahead of competitors such as Intel’s Mobileye at the International Solid-State Circuits Conference here.
A 5.5mm2 block in the latest 8nm Exynos chip delivers 1.9 Tera-operations/second using 8-bot precision running at up to 933 MHz, said Jinook Song, a Samsung AI engineer. That’s about the rating for the latest Kirin processor in Huawei phones and the latest commercial IP blocks.
To read the full article, click here
Related Semiconductor IP
- LLM AI IP Core
- RISC-V-Based, Open Source AI Accelerator for the Edge
- RISC-V AI Acceleration Platform - Scalable, standards-aligned soft chiplet IP
- CNN AI IP Core
- High-Performance Memory Expansion IP for AI Accelerators
Related News
- Samsung Foundry Adopts Leading Voltage-Timing Signoff Solution from Synopsys and Ansys for Advanced-Node, Energy-Efficient Chips
- Chiplet Interconnect Pioneer Eliyan Closes $60 Million Series B Funding Round, Co-led by Samsung Catalyst Fund and Tiger Global Management to Address Most Pressing Challenge in Development of Generative AI Chips
- Samsung Slows Opening of Texas Fab Despite CHIPS Stimulus
- M31 Debuts at ICCAD 2025, Empowering the Next Generation of AI Chips with High-Performance, Low-Power IP
Latest News
- Fraunhofer IPMS develops new 10G TSN endpoint IP Core for deterministic high-speed Ethernet networks
- A new CEO, a cleared deck: Is Imagination finally ready for a deal?
- SkyeChip’s UCIe 3.0 Advanced Package PHY IP for SF4X Listed on Samsung Foundry CONNECT
- Victor Peng Joins Rambus Board of Directors
- Arteris Announces Financial Results for the Fourth Quarter and Full Year 2025 and Estimated First Quarter and Full Year 2026 Guidance