IP Catalog > Automotive AI Accelerator

Automotive AI Accelerator IP

Filter
Filter

Login required.

Sign in

Search (8)
Compare 8 IP from 7 vendors (1 - 8)
  • NPU IP for Data Center and Automotive
    • 128-bit vector processing unit (shader + ext)
    • OpenCL 1.2 shader instruction set
    • Enhanced vision instruction set (EVIS)
    • INT 8/16/32b, Float 16/32b in PPU
    • Convolution layers
    Block Diagram -- NPU IP for Data Center and Automotive
  • ARC NPX Neural Processing Unit (NPU) IP supports the latest, most complex neural network models and addresses demands for real-time compute with ultra-low power consumption for AI applications
    • ARC processor cores are optimized to deliver the best performance/power/area (PPA) efficiency in the industry for embedded SoCs. Designed from the start for power-sensitive embedded applications, ARC processors implement a Harvard architecture for higher performance through simultaneous instruction and data memory access, and a high-speed scalar pipeline for maximum power efficiency. The 32-bit RISC engine offers a mixed 16-bit/32-bit instruction set for greater code density in embedded systems.
    • ARC's high degree of configurability and instruction set architecture (ISA) extensibility contribute to its best-in-class PPA efficiency. Designers have the ability to add or omit hardware features to optimize the core's PPA for their target application - no wasted gates. ARC users also have the ability to add their own custom instructions and hardware accelerators to the core, as well as tightly couple memory and peripherals, enabling dramatic improvements in performance and power-efficiency at both the processor and system levels.
    • Complete and proven commercial and open source tool chains, optimized for ARC processors, give SoC designers the development environment they need to efficiently develop ARC-based systems that meet all of their PPA targets.
  • NPU IP for AI Vision and AI Voice
    • 128-bit vector processing unit (shader + ext)
    • OpenCL 3.0 shader instruction set
    • Enhanced vision instruction set (EVIS)
    • INT 8/16/32b, Float 16/32b
    Block Diagram -- NPU IP for AI Vision and AI Voice
  • Vision AI DSP
    • Ceva-SensPro is a family of DSP cores architected to combine vision, Radar, and AI processing in a single architecture.
    • The silicon-proven cores provide scalable performance to cover a wide range of applications that combine vision processing, Radar/LiDAR processing, and AI inferencing to interpret their surroundings. These include automotive, robotics, surveillance, AR/VR, mobile devices, and smart homes.
    Block Diagram -- Vision AI DSP
  • Standard Cell Library
    • Basic Cells: A full suite of fundamental logic gates and flip-flops.
    • Optimal Cells: High-performance variants of basic cells, optimized for power, area, and speed, including high-speed flip-flops, advanced multiplexers, clock gated cells, clock buffers, arithmetic cells and custom-designed cells for critical paths.
  • CXL - Enables robust testing of CXL-based systems for performance and reliability
    • CXL Verification IP is a cutting-edge solution for validating designs based on the Compute Express Link (CXL) protocol. With features like protocol compliance checks, cache coherency validation, and advanced debugging tools, it ensures robust and efficient testing of high-performance computing systems.
    • From HPC and AI to automotive and edge computing, CXL Verification IP supports diverse applications. It enables seamless communication between processors, memory, and accelerators, ensuring reliable performance in data centers, ML systems, cloud infrastructures, and telecom networks.
    Block Diagram -- CXL - Enables robust testing of CXL-based systems for performance and reliability
  • Data Movement Engine - Turnkey network compute subsystem for data movement applications.
    • Industrial Networking: Rapid packet processing of data through multiple, switched ethernet ports with support for factory automation protocols
    • 5G/6G Communications: Scalable L2/L3 Ethernet switch with flexible port counts/speeds, including TSN and security
    • Automotive Gateway: High-speed data packet networking with multiple communication interfaces and support for switching and bridging
    • Datacenter Infrastructure: Standalone data processing units to handle highly multiplexed data streams corresponding to millions of network connections with high efficiency and low power
  • Radar processing IP suite for Advanced Driver Assistance Systems
    • The eSi-ADAS™ is a suite of radar accelerator IP including a complete Radar co-processor engine, they enhance the overall performance and capabilities of radar  systems for automotive, drone and UAV applications that require fast and responsive situational awareness.
    • The IP has been licensed to some of the leading automotive Tier 1 and Tier 2 suppliers and is in production vehicles.
    Block Diagram -- Radar processing IP suite for Advanced Driver Assistance Systems
×
Semiconductor IP