欢迎访问ic37.com |
会员登录 免费注册
发布采购

PM7380-PI 参数 Datasheet PDF下载

PM7380-PI图片预览
型号: PM7380-PI
PDF下载: 下载PDF文件 查看货源
内容描述: 帧引擎和数据链路管理32P672 [FRAME ENGINE AND DATA LINK MANAGER 32P672]
分类和应用:
文件页数/大小: 332 页 / 2479 K
品牌: PMC [ PMC-SIERRA, INC ]
 浏览型号PM7380-PI的Datasheet PDF文件第67页浏览型号PM7380-PI的Datasheet PDF文件第68页浏览型号PM7380-PI的Datasheet PDF文件第69页浏览型号PM7380-PI的Datasheet PDF文件第70页浏览型号PM7380-PI的Datasheet PDF文件第72页浏览型号PM7380-PI的Datasheet PDF文件第73页浏览型号PM7380-PI的Datasheet PDF文件第74页浏览型号PM7380-PI的Datasheet PDF文件第75页  
RELEASED  
PM7380 FREEDM-32P672  
DATA SHEET  
PMC-1990262  
ISSUE 5  
FRAME ENGINE AND DATA LINK MANAGER 32P672  
complete. This action will result in any write data being lost and any read data  
being erroneous.  
9.6.2 Master Local Bus Interface  
The master local bus is a 32 bit data bus which connects the local master device  
to the GPIC. The GPIC contains two local master interface blocks, with one  
supporting the RMAC672 and the other the TMAC672. Each local master  
interface has been optimised to support the traffic pattern generated by the  
RMAC672 or the TMAC672 and are not interchangeable.  
The data path between the GPIC and local master device provides a mechanism  
to segregate the system timing domain of the core from the PCI bus. Transfers  
on each of the RMAC672 and TMAC672 interfaces are timed to its own system  
clock. The DMA controllers isolated from all aspects of the PCI bus protocol, and  
instead “sees” a simple synchronous protocol. Read or write cycles on the local  
master bus will initiate a request for service to the GPIC which will then transfer  
the data via the PCI bus.  
The GPIC maximises data throughput between the PCI bus and the local device  
by paralleling local bus data transfers with PCI access latency. The GPIC allows  
either DMA controller to write data independent of each other and independent of  
PCI bus control. The GPIC temporarily buffers the data from each DMA  
controller while it is arbitrating for control of the PCI bus. After completion of a  
write transfer, the DMA controller is then released to perform other tasks. The  
GPIC can buffer only a single transaction from each DMA controller.  
Read accesses on the local bus are optimised by allowing the DMA controllers  
access to the data from the PCI bus as soon as the first data becomes available.  
After the initial synchronisation and PCI bus latency data is transferred at the  
slower of PCI bus rate or the core logic SYSCLK rate. Once a read transaction  
is started, the DMA controller is held waiting for the ready signal while the GPIC  
is arbitrating for the PCI bus.  
All data is passed between the GPIC and the DMA controllers in little Endian  
format and, in the default mode of operation, the GPIC expects all data on the  
PCI bus to also be in little Endian format. The GPIC provides a selection bit in  
the internal Control register which allows the Endian format of the PCI bus data  
to be changed. If enabled, the GPIC will swizzle all packet data on the PCI bus  
(but not descriptor references and the contents of descriptors). The swizzling is  
performed according to the “byte address invariance” rule, i.e. the only change to  
the data is the mirror-imaging of byte lanes.  
The interface for the RMAC672 provides for byte addressability of write  
transactions whereas the interface for the TMAC672 provides for byte  
PROPRIETARY AND CONFIDENTIAL TO PMC-SIERRA,INC., AND FOR ITS CUSTOMERS’ INTERNAL USE  
60