THINCI Inc. Will Present Its Next-Generation Graph Streaming Processor Architecture At the Hot Chips Symposium
THINCI GSP Provides 50-100-Times Power, Performance Advantage over Existing Solutions
El Dorado Hills, California -- Aug. 21, 2017 -- THINCI Inc.—an innovative deep-learning, vision processing startup, developing groundbreaking machine learning technology will describe its unique Graph Streaming Processor (GSP) architecture at “Hot Chips: A Symposium on High Performance Chips,” in the Cupertino, California Flint Center for the Performing Arts. The THINCI solution provides a 50-100-times power, performance advantage over existing solutions, such as nVidia’s Tesla P4. Val Cook, Chief Software Architect at THINCI, will present during the 4:15PM Processors Track on Monday, August 21. The presentation will be the first public disclosure of THINCI’s GSP architecture and the SDK used to program chips based on the unique technology.
“THINCI products are already being adopted in key applications for automotive and consumer applications,” said Dinakar Munagala, CEO of THINCI. “Today, deep-learning and vision processing has employed large arrays of graphics processors to evaluate huge amounts of data to determine patterns—facial recognition, interpreting objects—stop signs, pedestrians, animals, cars, etc.—that can be then programmed into a chip that executes this algorithm to make decisions in real time. THINCI provides the engine that executes these algorithms, making it possible, for example, to provide surveillance cameras intelligent enough to determine a robbery in progress, a fire or other natural disaster is occurring and report it immediately to proper authorities. What makes THINCI’s technology unique is that it’s cost effective enough to install in surveillance cameras, intelligent personal assistants, smart phones, in any number of automotive sensing devices, and countless others.”
About the THINCI GSP
THINCI’s GSP SOCs, based on the innovative THINCI GSP (Graph Streaming Processing) computing architecture, are purpose-built for graph computing workloads, including smart vision, machine learning, data analysis, pattern detection/extraction and more. The GSP will provide deep-learning vision processing in edge devices: surveillance cameras, virtual reality and augmented reality displays, smart phones, among many others. The GSP achieves its optimal power/performance ratio using a highly parallel computing architecture in which data is streamed across multiple processors concurrently. The results from upstream processors providing input to downstream processors. This greatly minimizes data transfers in and out of memory and yields much lower power and cost while shortening memory latency and significantly increasing throughput. THINCI is developing hardware (boards, appliances and modules) for ultra-power-efficient supercomputing at the edge.
About THINCI Inc.
THINCI Inc. is a venture-backed, deep-learning vision processing start-up based in El Dorado Hills, California with teams in California and Hyderabad, India. The company was founded by a highly skilled management team with years of experience in massively parallel processing architectures and the software structures to execute on these computing engines. The company is currently in the final phase of producing its deep learning and vision processing solution comprising silicon and software that can be integrated into a wide range of applications, including advanced driver assistance systems in automotive; intelligent agents for personal electronics that enhances photos and video, explains the real world elements surrounding the user, protects the user from potential danger, and more; smart home automation systems that detect and prevent hazards, intelligently manages home energy consumption, and provides the optimum indoor climate. THINCI’s technology is also applicable in commercial applications, for example, providing personalized suggestions to shoppers entering a store; in industrial applications for authenticating access, determining potential problems in operating equipment and more; in smart cities, by intelligently managing traffic lights based on real time traffic conditions, collecting and analyzing real-time video surveillance on city streets and the list goes on.
|
Related News
- VIA Unveils Next-Generation Isaiah x86 Processor Architecture
- MIPS64 Architecture Licensed by NEC Electronics for Next-Generation VR Series Processor Core
- Alphawave Semi and Arm to Present on Chiplets for Architecting Next-Generation Terabit AI Networks at the TSMC OIP Ecosystem Forum North America
- Codasip announces next-generation RISC-V processor family for Custom Compute
- ADTechnology and Zaram Technology to develop the next-generation of telecommunications semiconductor chips
Breaking News
- Ubitium Debuts First Universal RISC-V Processor to Enable AI at No Additional Cost, as It Raises $3.7M
- TSMC drives A16, 3D process technology
- Frontgrade Gaisler Unveils GR716B, a New Standard in Space-Grade Microcontrollers
- Blueshift Memory launches BlueFive processor, accelerating computation by up to 50 times and saving up to 65% energy
- Eliyan Ports Industry's Highest Performing PHY to Samsung Foundry SF4X Process Node, Achieving up to 40 Gbps Bandwidth at Unprecedented Power Levels with UCIe-Compliant Chiplet Interconnect Technology
Most Popular
- Cadence Unveils Arm-Based System Chiplet
- CXL Fabless Startup Panmnesia Secures Over $60M in Series A Funding, Aiming to Lead the CXL Switch Silicon Chip and CXL IP
- Esperanto Technologies and NEC Cooperate on Initiative to Advance Next Generation RISC-V Chips and Software Solutions for HPC
- Eliyan Ports Industry's Highest Performing PHY to Samsung Foundry SF4X Process Node, Achieving up to 40 Gbps Bandwidth at Unprecedented Power Levels with UCIe-Compliant Chiplet Interconnect Technology
- Arteris Selected by GigaDevice for Development in Next-Generation Automotive SoC With Enhanced FuSa Standards
E-mail This Article | Printer-Friendly Page |