CoreLink Coherent Mesh Network
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.
Request more informationWant more information on ARM CoreLink CMN-600?
|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|
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.
Coherent Multichip Links
CoreLink CMN-600 coherent multichip links (CML) provide the capability of extending the high frequency, non-blocking AMBA 5 CHI protocol messages across multiple SoCs, enabling system designers to attach more compute or acceleration with a shared virtual memory.
The multichip links also supports CCIX, the open coherency standard that allows processors based on different instruction set architectures to extend the benefits of cache coherent, peer processing to acceleration devices including FPGAs, GPUs, network/storage adapters, intelligent networks and custom ASICs, http://www.ccixconsortium.com/.
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.
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.QoS for High-Performance and Power-Efficient whitepaper
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.Quality of Service (QoS) in ARM Systems whitepaper
System Validation at ARM
Enabling Partners to Build Better SystemsSystem validation at ARM