OPENEDGES To Exhibit its 4-/8-bit mixed-quantization NPU IP at Embedded Vision Summit 2022
Seoul, South Korea, May 12th, 2022 --- OPENEDGES Technology, Inc. (hereinafter referred to as OPENEDGES), the world’s leading memory system and AI platform IP provider, announced today it will exhibit at 2022 Embedded Vision Summit, the premier event for the innovators incorporating computer vision and edge AI in products from May 17th to 19th in Santa Clara, California. OPENEDGES will showcase its latest mixed-precision (4-/8-bit) computation NPU IP, ENLIGHT.
Related |
4-/8-bit mixed-precision NPU IP |
OPENEDGES’ NPU IP, ENLIGHT, Toolkit Overview
The ENLIGHT, a high-performance neural network processor IP, is the industry’s first adoption of 4-/8-bit mixed-quantization IP and features a highly optimized network model compiler that reduces DRAM traffic from intermediate activation data by grouped layer partitioning and scheduling. OPENEDGES is demonstrating an on-site live demo of the comparison of the 4-/8-bit mixed-quantization output to the 8-bit quantization applied to the FPGA board. Demonstrations will take place in booth #610 at the Santa Clara Convention Center, California from May 16th through May 19th. In addition to ENLIGHT, OPENEDGES provides memory system IP, ORBIT, which consists of NoC (Network On-Chip), DDR controller (for DDR3/4, LPDDR3/4/4x/5/5x), and PHY (LPDDR4/4x/5/5x, GDDR6).
The event will feature industry innovators, top technologists, and engineers who are designing products using computer vision and edge AI for a wide range of industries including automotive, entertainment, healthcare, manufacturing, retail, robotics, security, and more. Since 2012, the Embedded Vision Summit has been the premier conference and expo devoted to practical, deployable computer vision and edge AI. The Summit is organized by the Edge AI and Vision Alliance, an industry partnership operated by BDTI.
For more information about the event, visit www.embeddedvisionsummit.com
About OPENEDGES
OPENEDGES Technology is the world's only total memory subsystem and AI platform IP solution company that delivers NPU, memory controller, DDR PHY, and on-chip interconnect IPs.
OPENEDGES is recognized for its world-class IPs with the highest level of efficiencies in power consumption, area, and DRAM optimization. The IPs and the proprietary technology shorten the customer's design and verification process by delivering the only market and silicon-proven integrated IP solutions. The Six Semiconductor (TSS) focuses on developing high-speed memory PHY IP solutions for OPENEDGES with a mission to develop high-speed PHY IP with the lowest power area. And it provides solutions that range from AI/ML, and high-performance computing (HPC) to mobile and automotive applications in multiple standards, technologies, and foundries.
The two key technologies of OPENEDGES are memory systems and AI Computing, which together, provide a sorely needed boost in performance, efficiency, and reliability for IoT.
- ORBITTM:
- DDR memory controller IP supports DDR3/4, LPDDR3/4/4x/5/5x, GDDR6
- DDR PHY supports LPDDR4/4x/5/5x, GDDR6
- NoC Bus Interconnect IP Non-coherent NoC available
- ENLIGHT:
- 4-/8-bit mixed-precision neural network processing unit (NPU) IP
Learn more about OPENEDGES at www.openedges.com or contact directly at sales@openedges.com
|
Related News
- intoPIX to showcase its lightweight compression IP at Embedded Vision Summit 2022 on Lattice Booth
- Chips&Media to Exhibit at the 2020 Embedded Vision Summit
- Quadric Presents and Demos AI+ML Chimera GPNPU at Embedded Vision Summit 2024
- ADTechnology and ANAFLASH to Team Up for Embedded Vision Summit (EVS) showcase
- BrainChip and Teksun Demonstrate Rapid Adoption of AI Solutions at Embedded Vision Summit
Breaking News
- Jury is out in the Arm vs Qualcomm trial
- Ceva Seeks To Exploit Synergies in Portfolio with Nano NPU
- Synopsys Responds to U.K. Competition and Markets Authority's Phase 1 Announcement Regarding Ansys Acquisition
- Alphawave Semi Scales UCIe™ to 64 Gbps Enabling >20 Tbps/mm Bandwidth Density for Die-to-Die Chiplet Connectivity
- RaiderChip Hardware NPU adds Falcon-3 LLM to its supported AI models
Most Popular
E-mail This Article | Printer-Friendly Page |