Getting Started

The Arm CoreLink CMN-600 Coherent Mesh Network is designed for intelligent connected systems across a wide range of applications including networking infrastructure, storage, server, HPC, automotive, and industrial solutions.  The highly scalable mesh is optimized for Armv8-A processors and can be customized across a wide range of performance points. 

Notable highlights include:

  • Build more powerful infrastructure SoCs from edge to cloud.

  • 5x throughput uplift compared to today’s solution.

  • Coherent mesh interconnect with integrated agile system cache.


Specifications

Feature  Details  
AMBA specifications AMBA 5 CHI
Scalable mesh network Custom sizing and device placement  
Fully coherent CHI slave interfaces

1-32 fully coherent requesters, for example up to 128 Armv8-A processors

Agile System Cache 0MB-128MB shared between compute, accelerators, and IO
IO Coherent slave interface 1-96 IO interfaces
Memory and system master interfaces 1-8 memory interfaces
1-8 system interfaces
Coherency and snoop filter Integrated snoop filter reduces processor core snoops, and reduces system power
Coherent multichip links Extend coherency to multichip supporting the CCIX standard


  • A program that is running on a desktop.
  • QoS for High-Performance and Power-Efficient HD Media... - Arm

    Ensuring the demands of video streaming are consistently met while minimizing cost and maximizing battery life are the challenges for today's SoC designer. This paper explores how QoS mechanisms can enable lower latency while maintaining sufficient overall system bandwidth.

    Download
  • A program that is running on a desktop.
  • Quality of Service (QoS) in Arm Systems: An Overview

    Nearly all performance-oriented SoCs are dependent on high bandwidth and low latency external memory systems to deliver within cost and performance constraints. This paper goes through the QoS functions that help deliver predictable performance in Arm® systems.

    Download
  • A program that is running on a desktop.
  • System Validation at Arm

    Enabling Partners to Build Better Systems

    Download

CMN-600 key features

High performance, scalable coherent mesh 

The scalable mesh network can be customized to meet system performance and area requirements. The native AMBA 5 CHI network provides high-frequency, non-blocking data transfers between compute, accelerator, and IO to shared memory resources.  

  • Custom, automated design with CoreLink Creator
  • Minimum size less than 1mm2 in 16nm
  • Frequencies greater than 2.5GHz
  • Coherent multichip link extends coherency off-chip

Agile system cache

Keeping data on-chip greatly improves performance and efficiency. The integrated agile system cache was designed to boost IO throughput workloads such as networking and storage.

  • Shared cache for compute, accelerators, and IO.
  • Intelligent cache stashing allows accelerators and IO peripherals to allocate critical data to any cache level.
  • Far atomic operations supported within the Agile System Cache to enable high frequency updates of shared data such as counters.  
  • Programmable on-chip scratch pad RAM partitioning options allow applications to lock down critical data structures such as counters, statistics, and tables.      

Optimized for system performance

The CoreLink CMN-600 has been designed with the CoreLink DMC-620 to provide the highest performance coherent backplane for Armv8-A systems from small, efficient access points to data center solutions maximizing compute density. Notable highlights include:

  • 7.5x more compute.
  • 5x higher throughput.
  • 50% lower latency.
  • Sustainable bandwidth exceeding 1TB/s.

CoreLink Creator reduces SoC integration time

CoreLink Creator guides designers through the configuration and creation of an optimized and viable CoreLink CMN-600 interconnect fabric.

It addresses the most complex challenges associated with Interconnect configurability and assembly and enables a faster and easier design that produces a higher quality interconnect.

Get support

Arm support

Arm training courses and on-site system-design advisory services enable licensees to realize maximum system performance with lowest risk and fastest time-to-market.

Arm training courses  Open a support case

Community Blogs

Community Forums

Answered ACE protocol : Eviction and snoop request at same time
  • AMBA
  • l1
  • ACE
  • cache
0 votes 329 views 1 replies Latest 6 days ago by Christopher Tory Answer this
Suggested answer AXI3 write data interleaving with same AWID
  • AMBA
  • AXI
0 votes 392 views 4 replies Latest 6 days ago by mveereshm622 Answer this
Suggested answer AHB revisions from AHB3 to AHB5
  • AMBA
  • AHB
0 votes 143 views 1 replies Latest 7 days ago by Colin Campbell Answer this
Suggested answer Burst termination with BUSY transfer on AHB
  • AMBA
  • AHB
0 votes 125 views 1 replies Latest 7 days ago by Colin Campbell Answer this
Suggested answer Regarding retry response
  • AMBA
  • AHB
0 votes 116 views 1 replies Latest 7 days ago by Colin Campbell Answer this
Suggested answer APB3 Slave responding when PSEL = 0
  • APB
  • AMBA
0 votes 320 views 2 replies Latest 11 days ago by vshankar11 Answer this
Answered ACE protocol : Eviction and snoop request at same time Latest 6 days ago by Christopher Tory 1 replies 329 views
Suggested answer AXI3 write data interleaving with same AWID Latest 6 days ago by mveereshm622 4 replies 392 views
Suggested answer AHB revisions from AHB3 to AHB5 Latest 7 days ago by Colin Campbell 1 replies 143 views
Suggested answer Burst termination with BUSY transfer on AHB Latest 7 days ago by Colin Campbell 1 replies 125 views
Suggested answer Regarding retry response Latest 7 days ago by Colin Campbell 1 replies 116 views
Suggested answer APB3 Slave responding when PSEL = 0 Latest 11 days ago by vshankar11 2 replies 320 views