The Linley Group today announced an exemplary lineup of more than 30 technical presentations by industry leaders at the Linley Fall Processor Conference to be held on October 20–22 and 27–29, 2020. The conference will showcase the latest innovations in processors and IP cores for AI (artificial intelligence) applications, automotive, embedded, data center, IoT, and server designs.
This year’s event offers its biggest program ever, underscoring the massive growth in the AI chip industry. The program includes 33 technical talks, a dozen new announcements and disclosures, and several panel discussions. Attendees will be able to view live-streamed presentations and interact with the speakers during Q&A, breakout sessions, and scheduled one-on-one meetings daily from 8:30 am–12:30 pm Pacific Daylight Time (11:30 am–3:30 pm Eastern).
Here are some of the many new product announcements and technology disclosures:
- SiFive will announce its first CPU core that implements the RISC-V Vector extension for high-performance vector processing.
- Untether AI will emerge from stealth and disclose a new non-von Neumann architecture designed to accelerate AI inference.
- Flex Logix will disclose new details on its InferX chip, an embedded inference coprocessor.
- Marvell will disclose new details about OCTEON CN98xx DPU architecture, including hardware accelerators for inline cryptography, regular expression matching, and virtualization.
- Imagination will announce a new multicore AI accelerator that is highly scalable so as to enable the most demanding applications.
- Think Silicon will introduce the NEOX AI IP Series, which enables the rapid deployment of AI applications on resource-constrained devices.
- Cornami will disclose details of its unique TruStream Computational Fabric for next-generation machine-learning algorithms.
- Deep AI will disclose its accelerated deep-learning solution for the edge, which implements training at a fraction of the cost of GPUs.
- SiFive will introduce the Freedom U740, a next-generation SoC that combines a heterogeneous CPU complex with modern PC I/O.
- Groq will disclose new benchmark results and details of its chip-to-chip interconnect capability.
- Google Technical Lead for TensorFlow Micro, Pete Warden, will present “What TinyML Needs from Hardware.”
- The Linley Group Principal Analyst, Linley Gwennap, will present “Application-Specific Accelerators Extend Moore’s Law.”
Sponsoring companies include Arm, Flex Logix, Intel, SiFive, Arteris IP, Andes Technology, Achronix, Lattice Semiconductor, Ceva, Synopsys, Marvell, Ambient Scientific, Cadence, Think Silicon, Centaur Technology, Imagination, Cornami, Tenstorrent, SiMa.ai, GlobalFoundries, Hailo, GSI Technology, Fungible, Untether AI, Groq, Deep AI Technologies, BrainChip, Nvidia, The Khronos Group, and SemiWiki.
The Linley Group offers free admission to qualified registrants who sign up by October 16. For the full conference program, and to register, please visit http://www.linleygroup.com/FPC20.
About The Linley Group
The Linley Group is the industry’s leading source for independent technology analysis of semiconductors for a broad range of applications including networking, communications, data-center applications, mobile, and embedded. The company provides strategic consulting services, in-depth analytical reports, and conferences focused on advanced technologies for chip and system design. The Linley Group is the publisher of the noted Microprocessor Report, a weekly publication. For insights on recent industry news, subscribe to the company’s free email newsletter: Linley Newsletter.