Ncore Cache Coherent Interconnect IP
Overview
Solve multi-core design challenges with safety support
Built on more than a decade of volume silicon, Ncore™ is silicon-proven coherent NoC IP that is highly configurable, power-efficient, and works with any processor, including Arm® and RISC-V.
- Extends full cache-coherency across chiplets for rapid, modular innovation.
- ISO 26262 ASIL D ready.
- Pairs with Magillem® automation for IP integration software, so teams can scale modular architectures, simplify multi-die design and compress development schedules.
Combining Ncore and FlexNoC gives designers foundational technology for unparalleled performance optimization, scalability, and system integration in an expanded multi-die solution. This enables robust cache-coherence, efficient communication, and flexibility, which can result in market differentiation and accelerated time-to-market.
Advantages
Create high-performance coherent SoCs
Scalable
Ncore provides a high-bandwidth, low-latency interconnect fabric for efficient communication between different components of an SoC and between multiple dies. This provides scalable performance and power efficiency from small embedded systems to large multi-billion transistor and multi-die designs.
Configurable
Multi-protocol coherency gives choice and reuse for legacy and future IP support. CHI-E, CHI-B, and ACE coherent, as well as ACE-Lite I/O coherent agent interfaces, allow multiple initiator IP to be connected to the same Ncore. Ncore also enables AXI non-coherent agents to act as I/O coherent agents.
Safe
ISO-certified by an external assessor to ensure Ncore readiness for use in ISO 26262 -compliant chips from ASIL B to ASIL D, enabled by the Ncore Safety and Reliability product option. Fault Modes Effects and Diagnostic Analysis (FMEDA) data is generated automatically for the Ncore configuration.
Features
Ncore key features
- Highly scalable system
- True heterogeneous coherency with mixed AMBA CHI and AMBA ACE support
- Full coherency for cached processors and I/O coherency for accelerators
- Multi-die cache coherency over UCIe™ 1.1 via an AMBA CXS.B interface — up to four chiplets, and up to 4 × 128 GB/s links per die*
- Configurable network and topologies
- Mesh topology with physical tiling of repetitive blocks*
- Functional safety with FMEDA generation and ASIL D certification*
- Configurable snoop filters
- I/O proxy cache and system memory cache
- Low power consumption
- Quality of service (QoS)
- Debug and trace/monitoring
Explore additional Ncore features, download the datasheet.
* Denotes product option
Feature Spotlight
NoC tiling with Ncore
NoC tiling with mesh topology for cache coherent CPUs. Up to 256 CPUs with 8-core cluster size.
- Scale performance
- Condense design time
- Speed testing
- Reduce design risk
- Supports Arm and RISC-V architectures
Create modular, scalable designs, with faster integration, verification, and optimization.
Benefits
Ncore product benefits
Higher frequencies, lower latencies
Use of multiple configurable snoop filters to accommodate different cache organization.
Lower power consumption
Fewer off-chip main memory accesses result in lower power consumption.
Smaller die area
Fewer wires use the optimal NoC transport layer.
Easy configuration
Ncore adapts to each coherent agent’s behavior and characteristics.
Faster time to market
Tiling accelerates physical design, implementation, and timing closure.
Flexible topologies
Choose from crossbar, mesh, and ad-hoc topologies.
Safety
Automated FMEDA safety documentation and ISO26262 ASIL B to D certified.
Automated verification
Save hundreds of hours of work compared to manual verification generation.
Shorter schedules
Fewer iteration loops speed development time.
Multi-die solution accelerates AI-driven silicon innovation
- Flexible design scalability
- Differentiated AI performance
- Aligned with evolving industry standards
Resources
- SemiWiki: How NoC Tiling Capability is Changing the Game for AI Development with Andy Nightingale
- EE Journal: Managing the Massive Data Throughput: AI-Based Designs and The Value of NoC Tiling
- Electronic Design: All About NoCs
- SemiWiki: The Impact of Arteris on Automotive and Beyond with Frank Schirrmeister
- SemiWiki: A Broad View of Design Architectures and the Role of the NoC with Arteris’ Michal Siwinski
- EE Journal: The Freedom to Innovate: Arteris and the Rise of RISC-V
- Automating the Generation of Scalable and Reusable FMEDA in Complex Systems-on-Chip (SoCs)
- Efficient Scaling of AI Accelerators Using NoC Tiling
- FMEDA Automation for Scalability and Reuse in Complex Systems on Chips (SoCs)
- Is the Missing Safety Ingredient in Automotive AI Traceability?
- Lessons Learned Integrating AI/ML Accelerators into Complex ISO 26262 Compliant Systems-on-Chip
- Safety Considerations for Network-on-Chip (NoC) Development
- The Role of Networks-on-Chips Enabling AI/ML Silicon and Systems
- Tiled Approach to System Scaling
- Chiplets: Opportunities and Challenges
- NoC-Centric System Performance for the Chiplet-Era with Platform Architect
- Optimizing Data Transport Architectures in RISC–V SoCs for AI/ML Applications
- Cache Coherency in Heterogeneous Systems
- Integration Challenges for RISC-V Designs
- Promises and Pitfalls of SoC Restructuring
- Scaling Performance in AI Systems
Support and Training
Need help?
Support and services
Arteris provides world-class design support and services to our customers and partners.
Training
Unlock the full potential of Arteris products. Explore customized learning solutions designed to boost your expertise.
Arteris Academy
Learn at your own pace, on your schedule. Access our library of on-demand training modules and develop new skills today.
Latest news