Login

CoreLink CCI-400 Cache Coherent Interconnect

CoreLink CCI-400 Cache Coherent Interconnect  Image (View Larger CoreLink CCI-400 Cache Coherent Interconnect Image)
Massive growth in system integration places on-chip communication at the center of system performance. The ARM® CoreLink™ CCI-400 Cache Coherent Interconnect provides full cache coherency between two clusters of multi-core CPUs, such as the ARM Cortex®-A7, Cortex-A15, Cortex-A17, Cortex-A57 and Cortex-A53 processors enabling big.LITTLE™; and I/O coherency for devices such as the Mali™-T600 series GPU, and I/O masters like modem and USB. To date ARM has licensed the CCI-400 product to over 20 licensees including Samsung, LSI, Freescale, HiSilicon, STEricsson, Fujitsu, Mediatek and LG.

The CCI-400 implements the AMBA® 4 ACE™ and ACE-Lite™  protocols (PDF Download - Registration / Login Required)

 


CoreLink CCI-400 Cache Coherent Interconnect

The CoreLink CCI-400 is a high performance, power efficient interconnect designed to interface between processors and the dynamic memory controller, such as the CoreLink DMC-400. It is the first product to implement AMBA® 4 ACE™, which brings system wide hardware coherency and virtual memory management.

What is hardware coherency?

Hardware coherency enables scaling and simplifies software. The latest SoC designs combine multiple processor and accelerator engines which all need to share data. These additional processors increase system performance and improve power efficiency, however this shared data needs to be managed to ensure everyone sees the same view of memory.

To manage shared data there are three techniques:

  • Disable caching: all shared memory is written externally to DDR. This is the simplest solution but expensive in high power external accesses and latency.
  • Software managed coherency: any data stored in processor caches must be cleaned and flushed to external memory before passing to accelerators and other hardware. This requires the CPU software to actively manage cached data, and requires CPU resources.
  • Hardware managed coherency: the system interconnect ensures all shared data is coherent in the system, reduces external memory accesses and removes the need for software to manage caches. This can offer improved performance and power efficiency as the CPU can do useful work or enter a lower power state.

CoreLink CCI-400 implements hardware cache coherency with the AMBA 4 ACE protocol.

Processor support and big.LITTLE

The CoreLink CCI-400 enables hardware managed coherency between two AMBA 4 ACE processor clusters such as the ARM Cortex-A7Cortex-A15, Cortex-A17Cortex-A57 and Cortex-A53, enabling big.LITTLE. Hardware coherency with CoreLink CCI-400 is an important part of ARM big.LITTLE processing and allows a single operating system to run across two processor clusters simultaneously. With big.LITTLE Global Task Scheduling (GTS) processes and applications can move dyanmically between the high performance 'big' and the high efficiency 'LITTLE' cores as demand requires. This technolgy allows can allow up to 8 cores to run at the same time.

Hardware I/O Coherency and System MMU

I/O coherency, or one-way coherency, is provided for up to three accelerator engines implementing the AMBA 4 ACE-Lite™ protocol. This could include graphics processors such as ARM Mali™-T600 series, or interface controllers such as USB, Ethernet, and WiFi. The benefits of hardware coherency include simplification of software drivers, and lower latency access of shared data.

The CoreLink CCI-400 benefits are not limited to coherency, this product also supports the virtualization extensions including a direct connection to the system MMU, such as CoreLink MMU-400 or MMU-500, to allow virtualization of hardware devices. This can take advantage of multiple OS’s running on the same hardware, or simply a more efficient way to share limited physical memory.

 


High bandwidth, low latency CCI-400

The CoreLink CCI-400 cache coherent interconnect is targeted to run at up to half the frequency of the Cortex-A15 processor to allow high performance, low latency connection to main memory.

All interfaces support 128-bit wide data allowing for systems scaling to 10’s Gbyte/s data bandwidths to support high definition multimedia requirements and the latest high performance networking interfaces.

The CCI-400 design minimizes latency to ensure the maximum performance of latency-sensitive processors.

For smaller designs, the interconnect can be configured for lower bandwidth if required, and reduced latency can be offered for lower frequency targets. This configuration space allows SoC designers to tune for performance and area.

For further details, please contact ARM.


CoreLink CCI-400 Features

ACE™ interfaces

2x AMBA 4 ACE interfaces for processor clusters, such as quad Cortex®-A7 Cortex-A15, Cortex-A17 and Cortex-A53 and Cortex-A57 MPCore™ Processors.
ACE-Lite™ interfaces 3x AMBA 4 ACE-Lite slave interfaces for connecting hardware accelerators, media processors, such as Mali™-T600 series GPU, and extending to further masters via the CoreLink NIC-400.
System and DMC interfaces 3x ACE-Lite master interfaces for connecting up to 2x dynamic memory controllers such as CoreLink DMC-400 and 1x system connection port via the CoreLink NIC-400
128-bit data width All read and write data channels are of fixed, 128-bit width
AXI support Backwards compatibility for AXI4 devices
Memory map  Configurable across 40-bit physical address space, includes support for interleaving between 2 memory controllers.
Coherency Full cache coherency for ACE masters, I/O coherency for ACE-Lite masters
Barriers Handled within interconnect or propagated to downstream ACE-Lite devices
QoS Integrated QoS mechanisms for traffic management, designed to work optimally with compatible IP including NIC-400 and DMC-400 for end-to-end Quality of Service with QoS Virtual Networks.
Distributed Virtual Memory (DVM) Supports broadcast of 44-bit DVM signalling to attached processors and system MMU, such as CoreLink MMU-400. Fully supports ARMv8-A processors.
Configurable Parameter defined interconnect, such as the number of transactions and pipeline stages are configurable to allow the design to scale across a range of performance, frequency and area targets.
Low Power Integrated clock gating allows full clock tree to be turned off in idle and near idle conditions saving significant dynamic power.

Further information is available in the CoreLink CCI-400 Technical Reference Manual  and from your ARM Sales contact.


The following products are designed and tested with CoreLink CCI-400 Cache Coherent Interconnect.

Product Type Products Details
Processors

Cortex-A7

Cortex-A15

Cortex-A17

Cortex-A53

Cortex-A57

 Full cache coherency between clusters via AMBA® 4 ACE™ interfaces, supports big.LITTLE processing.
GPU Mali-T600 series Graphics Processing Unit (GPU) with AMBA 4 ACE-Lite interface support for IO coherency with ACE processors and GPU Compute.
System IP

 CoreLink DMC-400

CoreLink NIC-400

CoreLink MMU-400

CoreLink MMU-500

 A range of CoreLink System IP designed and tested with CoreLink CCI-400 to give optimal system performance.
Development tools  ARM DS-5 ARM Development Studio 5 with Streamline Performance Analyzer supports visualisation of CoreLink CCI-400 Performance Metrics Unit .


» 
Documentation
 
» 
Powered 15506
Go Left
Go Right

Maximise


Cookies

We use cookies to give you the best experience on our website. By continuing to use our site you consent to our cookies.

Change Settings

Find out more about the cookies we set