NPU terminology

SAPEON launches X330 AI semiconductor for data centers

Retrieved on: 
Thursday, November 16, 2023
AIX, CCTV, Peta, Natural language processing, IP, ONNX, NPU terminology, SKT, TCO, BERT, ChatGPT, Environment, AI, Car, X220, NPU, SK Telecom, LLM, Mobile phone, Video game, Medical device

Santa Clara, California, Nov. 16, 2023 (GLOBE NEWSWIRE) -- SAPEON (CEO Soojung Ryu, www.sapeon.com ), a global AI semiconductor company, announced the launch of the X330, an AI semiconductor for data centers with four times higher performance than its predecessor, the X220.

Key Points: 
  • Santa Clara, California, Nov. 16, 2023 (GLOBE NEWSWIRE) -- SAPEON (CEO Soojung Ryu, www.sapeon.com ), a global AI semiconductor company, announced the launch of the X330, an AI semiconductor for data centers with four times higher performance than its predecessor, the X220.
  • The X330 forms the core of SAPEON’s plan to proactively focus on AI service model development companies and data center markets.
  • Along with the recently released X330, SAPEON plans to introduce AI NPUs for high-performance edge devices such as IP (semiconductor design assets) for self-driving cars and CCTV.
  • Additionally, SAPEON and SKT will utilize AI semiconductors to establish voice phishing and spam/smishing prevention systems based on AI and big data analysis to protect customers from external security threats.

Renesas Launches Cloud-Based Environment to Accelerate Automotive AI Software Development and Evaluation

Retrieved on: 
Thursday, December 14, 2023
Technology, Semiconductor, Vehicle Technology, Automotive, Automotive Manufacturing, Software, Manufacturing, Hardware, IOT (Internet of Things), Artificial Intelligence, Shift, Cloud, Socs, Corporation, SDK, Infrastructure as a service, Hyco Lake, SILS, Web browser, ONNX, Multimedia, MCU 8051 IDE, Hardware-in-the-loop simulation, NPU terminology, Advanced driver-assistance system, SOC, DSPS, Visual Studio Code, Loop, HPC, Azure, ADAS, Cloud computing, AI, Microsoft, Environment, Architecture, Video game, Medical device, Renesas Electronics

Renesas Electronics Corporation (TSE:6723), a premier supplier of advanced semiconductor solutions, today launched a new cloud-based development environment aimed at streamlining the software design process for automotive AI engineers.

Key Points: 
  • Renesas Electronics Corporation (TSE:6723), a premier supplier of advanced semiconductor solutions, today launched a new cloud-based development environment aimed at streamlining the software design process for automotive AI engineers.
  • The new platform, AI Workbench, is an integrated virtual development environment that empowers automotive AI engineers to design, simulate and fine-tune their automotive software - all within the cloud.
  • “We are thrilled to introduce a cloud-based virtual development and AI model performance testing environment for automotive AI engineers in collaboration with Microsoft, a leading cloud technology provider," said Mandali Khalesi, Global VP, HPC AI and Cloud Technology at Renesas.
  • “With Renesas’ AI Workbench, developers can now efficiently build and test software for a myriad of applications using Renesas SoCs in a cloud-based environment powered by Azure."

STRADVISION to Unveil Next-Gen '3D Perception Network' and Showcase SVNet Portfolio at CES® 2024

Retrieved on: 
Wednesday, December 13, 2023
Advanced driver-assistance system, Perception, ARM, NPU terminology, CES, Heart, Build automation, CPU, SOC, 2D, IPO, Deep learning, Original equipment manufacturer, ADAS, AI, SDV, Role, AI accelerator, NPU, Hotel, Renewable energy, Video game, Lidar

Located at the Westgate Hotel Hospitality Suite #28115, the showcase will be open to industry professionals from January 9th to 12th.

Key Points: 
  • Located at the Westgate Hotel Hospitality Suite #28115, the showcase will be open to industry professionals from January 9th to 12th.
  • At the heart of STRADVISION's presentation is unveiling the next-generation approach, the '3D Perception Network,' a transformative leap in autonomous systems.
  • The 3D Perception Network, developed by STRADVISION, represents a significant advancement in the field of ADAS/AD.
  • The 3D Perception Network and the SVNet portfolio showcase represent the next significant milestones for STRADVISION.

Cadence Expands Tensilica IP Portfolio with New HiFi and Vision DSPs for Pervasive Intelligence and Edge AI Inference

Retrieved on: 
Tuesday, October 24, 2023
Technology, Semiconductor, 5G, Engineering, Aerospace, Software, Manufacturing, Hardware, Electronic Design Automation, Artificial Intelligence, CDNS, Vision, DSPS, Cadence Design Systems, High fidelity, Original equipment manufacturer, Research, Socs, DSP, NPU, SDK, CPU, GPU, SOC, Algorithm, TTM, NPU terminology, Investment, AI, IP, Radar, Medical device, Video game, Hailo, Tensilica, Cadence

The new HiFi and Vision DSPs address increasing system-level performance and AI requirements for an expanded range of applications—delivering enhanced performance across multiple algorithms with even greater energy efficiency.

Key Points: 
  • The new HiFi and Vision DSPs address increasing system-level performance and AI requirements for an expanded range of applications—delivering enhanced performance across multiple algorithms with even greater energy efficiency.
  • The expanded portfolio includes the Cadence® Tensilica HiFi 1s DSP and HiFi 5s DSP for audio/voice, lightweight imaging and AI applications and the Tensilica Vision 110 DSP and Vision 130 DSP for image sensor, camera, radar and lidar applications.
  • On-device and edge AI systems feature numerous diverse sensors, so any AI inference solution must be adaptable to the end application requirements,” said David Glasco, vice president of research and development for Tensilica IP at Cadence.
  • “We continue to use Cadence Tensilica Vision DSPs, which provide the computational throughput and flexibility needed to keep up with today’s complex AI workload requirements.

GIGABYTE Announces AI Strategy for Consumer Products to Map the Future of AI

Retrieved on: 
Wednesday, October 18, 2023
AMD, ChatGPT, Microsoft, Multimedia, GIGABYTE, Intel, First officer (aviation), Ecosystem, Partnership, Machine learning, Cloud computing, NPU terminology, AI, BIOS, Medical device, Customer service, NVIDIA

In the cloud, GIGABYTE's AI servers deliver robust computing power for demanding AI workloads, encompassing generative AI services and machine learning applications like ChatGPT.

Key Points: 
  • In the cloud, GIGABYTE's AI servers deliver robust computing power for demanding AI workloads, encompassing generative AI services and machine learning applications like ChatGPT.
  • In scenarios involving AI collaboration systems like Microsoft Copilot, GIGABYTE offers a power-saving, secure, and user-friendly AI operating platform explicitly engineered for the next-generation AI processors like NPUs.
  • Amidst the booming AI software market, GIGABYTE also partners with various generative AI software developers, ensuring compatibility of their products with GIGABYTE hardware while emphasizing user-friendly interfaces and experiences (UI/UX), enabling users to leverage generative AI with ease.
  • GIGABYTE's AI Strategic Framework represents a significant milestone in the company's commitment to AI, signaling the imminent launch of a range of new AI-centric PC consumer products.

GIGABYTE Announces AI Strategy for Consumer Products to Map the Future of AI

Retrieved on: 
Wednesday, October 18, 2023
AMD, ChatGPT, Microsoft, GIGABYTE, Intel, First officer (aviation), Ecosystem, Partnership, Machine learning, Cloud computing, NPU terminology, AI, BIOS, Medical device, Customer service, NVIDIA

In the cloud, GIGABYTE's AI servers deliver robust computing power for demanding AI workloads, encompassing generative AI services and machine learning applications like ChatGPT.

Key Points: 
  • In the cloud, GIGABYTE's AI servers deliver robust computing power for demanding AI workloads, encompassing generative AI services and machine learning applications like ChatGPT.
  • In scenarios involving AI collaboration systems like Microsoft Copilot, GIGABYTE offers a power-saving, secure, and user-friendly AI operating platform explicitly engineered for the next-generation AI processors like NPUs.
  • Amidst the booming AI software market, GIGABYTE also partners with various generative AI software developers, ensuring compatibility of their products with GIGABYTE hardware while emphasizing user-friendly interfaces and experiences (UI/UX), enabling users to leverage generative AI with ease.
  • GIGABYTE's AI Strategic Framework represents a significant milestone in the company's commitment to AI, signaling the imminent launch of a range of new AI-centric PC consumer products.

Cadence Accelerates On-Device and Edge AI Performance and Efficiency with New Neo NPU IP and NeuroWeave SDK for Silicon Design

Retrieved on: 
Wednesday, September 13, 2023
Electronic Design Automation, Semiconductor, Technology, Other Technology, Software, Artificial Intelligence, Hardware, Natural language processing, TensorFlow, Cadence Design Systems, Magic, CDNS, Internet of things, Macs, ML, Neo, Multimedia, Research, SOC, FP16, NLP, CNN, DSPS, Personal computer, Radar, Apache MXNet, Investment, NPU terminology, Socs, RNN, JAX, Architecture, PyTorch, ADAS, Integer, PPA, ONNX, SDK, AR, KPI-driven code analysis, Automation, Medical device, Video game, Cadence, Tensilica, AI

The new highly scalable Cadence® Neo™ Neural Processing Units (NPUs) deliver a wide range of AI performance in a low-energy footprint, bringing new levels of performance and efficiency to AI SoCs.

Key Points: 
  • The new highly scalable Cadence® Neo™ Neural Processing Units (NPUs) deliver a wide range of AI performance in a low-energy footprint, bringing new levels of performance and efficiency to AI SoCs.
  • Complementing the AI hardware, the new NeuroWeave™ Software Development Kit (SDK) provides developers with a “one-tool” AI software solution across Cadence AI and Tensilica® IP products for no-code AI development.
  • View the full release here: https://www.businesswire.com/news/home/20230913932401/en/
    The new highly scalable Cadence® Neo™ Neural Processing Units (NPUs) deliver a wide range of AI performance in a low-energy footprint, bringing new levels of performance and efficiency to AI SoCs.
  • Complementing the AI hardware, the new NeuroWeave™ Software Development Kit (SDK) provides a "one-tool" AI software solution across Cadence AI and Tensilica IP products for no-code AI development.

CEVA Doubles Down on Generative AI with Enhanced NeuPro-M NPU IP Family

Retrieved on: 
Monday, August 7, 2023
Acceleration, LLM, TVM, VPU, CEVA, Synthetic media, CNN Airport, SOC, PC, VR, Tablet, NPU, Running, NPU terminology, Machine learning, Algorithm, Generative, Workload, Architecture, Growth, Research, ONNX, Memory, AR, Video game, Medical device

ROCKVILLE, Md., Aug. 7, 2023 /PRNewswire/ -- CEVA, Inc. (NASDAQ: CEVA), the leading licensor of wireless connectivity, smart sensing technologies and custom SoC solutions, today announced its enhanced NeuPro-M NPU family, directly addressing the processing needs of the next era of Generative AI with industry-leading performance and power efficiency for any AI inferencing workload, from cloud to the edge. The NeuPro-M NPU architecture and tools have been extensively redesigned to support transformer networks in addition to CNNs and other neural networks, as well as support for future machine learning inferencing models. This enables highly-optimized applications leveraging the capabilities of Generative and classic AI to be seamlessly developed and run on the NeuPro-M NPU inside communication gateways, optically connected networks, cars, notebooks and tablets, AR/VR headsets, smartphones, and any other cloud or edge use case.

Key Points: 
  • Our NeuPro-M NPU IP is designed specifically to handle both classic AI and Generative AI workloads efficiently and cost-effectively today and in the future.
  • Reece Hayden, Senior Analyst, ABI Research, stated: "The hardware market for Generative AI today is heavily concentrated with dominance by a few vendors.
  • CEVA's NeuPro-M NPU IP offers a compelling proposition for deploying generative AI on-device with an impressive power budget, while its scalability also allows NeuPro-M to address more performance-intense use cases in network equipment and beyond."
  • The NPM11 NPU IP is generally available for customer deployment today, with the NPM12, NPM14, and NPM18 available for lead customers.

AiM Future Successfully Closes Series A Round of Investment

Retrieved on: 
Friday, July 7, 2023
Technology, Finance, Semiconductor, Professional Services, Software, Networks, Hardware, Robotics, Artificial Intelligence, Senior, CFA, Ai Maeda (voice actress), LG Electronics, Investment, Electronics, Partner, Deep learning, AI, Multimedia, Virtus Investment Partners, NPU, Computer, NPU terminology, Algorithm, Series, Growth, LG, Silicon, CAIA, Cryptocurrency, Renewable energy

AiM Future announced today the successful closure of a Series A funding round.

Key Points: 
  • AiM Future announced today the successful closure of a Series A funding round.
  • The round consists of a multi-million-dollar investment led by L&S Venture Capital, Hi Investment Partners, Daedeok Venture Partners, and existing investors KB Investments and We Ventures.
  • AiM Future is the company that meets all these requirements with cutting-edge technology.”
    “I am happy to close this series-A funding during an extended period of turbulent economic conditions.
  • The proceeds will be deployed to hiring world-class talent and producing test silicon of our next-generation architecture,” said ChangSoo Kim, Chief Executive Officer of AiM Future.

Quadric Announces Vision Transformer Support for Chimera GPNPUs

Retrieved on: 
Tuesday, June 20, 2023
Electronic Design Automation, Semiconductor, Technology, Software, Artificial Intelligence, Hardware, ALU, Softmax, DSP, ML, IP, SOC, History, NPU, MAC, CPU, NPU terminology, Machine learning, Map, Algorithm, Vision transformer, Architecture, Silicon, ResNet, Quadric, Video game, Computer data storage, Chimera

Quadric® today announced that its Chimera™ general purpose neural processing unit (GPNPU) processor intellectual property (IP) supports vision transformer (ViT) machine learning (ML) inference models.

Key Points: 
  • Quadric® today announced that its Chimera™ general purpose neural processing unit (GPNPU) processor intellectual property (IP) supports vision transformer (ViT) machine learning (ML) inference models.
  • ViT models are the latest state-of-the-art ML models for image and vision processing in embedded systems.
  • The general-purpose architecture of the Chimera core family intermixes integer multiply-accumulate (MAC) hardware with a general purpose 32-bit ALU functionality, which enabled Quadric to rapidly port and optimize the ViT_B transformer model.
  • Quadric’s Chimera family of GPNPUs blends the ML performance characteristics of a neural processing accelerator with the full C++ programmability of a modern digital signal processor (DSP).