欢迎访问ic37.com |
会员登录 免费注册
发布采购

MUAC4K64-90TDI 参数 Datasheet PDF下载

MUAC4K64-90TDI图片预览
型号: MUAC4K64-90TDI
PDF下载: 下载PDF文件 查看货源
内容描述: [Microprocessor Circuit, CMOS, PQFP100, TQFP-100]
分类和应用: 外围集成电路
文件页数/大小: 32 页 / 276 K
品牌: MUSIC [ MUSIC SEMICONDUCTORS ]
 浏览型号MUAC4K64-90TDI的Datasheet PDF文件第1页浏览型号MUAC4K64-90TDI的Datasheet PDF文件第3页浏览型号MUAC4K64-90TDI的Datasheet PDF文件第4页浏览型号MUAC4K64-90TDI的Datasheet PDF文件第5页浏览型号MUAC4K64-90TDI的Datasheet PDF文件第6页浏览型号MUAC4K64-90TDI的Datasheet PDF文件第7页浏览型号MUAC4K64-90TDI的Datasheet PDF文件第8页浏览型号MUAC4K64-90TDI的Datasheet PDF文件第9页  
MUAC Routing CoProcessor (RCP) Family  
General Description  
GENERAL DESCRIPTION  
The MUAC RCP family consists of 4K and 8K x 64-bit  
Routing CoProcessors (RCPs) with a 32-bit wide data  
interface and a 32-bit ternary compare instruction. The  
device is designed for use in layer 3 switches, routers, and  
layer 2 switches to provide very high throughput address  
translation using tables held in external RAM. The MUAC  
RCP has a fully deterministic search time, independent of  
the size of the list and the position of the data in the list.  
This unique feature guarantees that the wire speed address  
recognition does not impact the latency or induce some  
jitter on the latency of the global system. Address fields  
from the packet header are compared against a list of  
entries stored in the array. As a result of the comparison,  
the MUAC RCP generates an index that is used to access  
an external RAM where port mapping data and other  
associated information is stored.  
A set of control states provides a powerful and flexible  
control interface to the MUAC RCP. This control structure  
allows memory read and write, register read and write,  
data move, comparison, validity control, addressing  
control, and initialization operations.  
The MUAC RCP architecture uses direct hardware control  
of the device and an independent bus for returning match  
results. Software control is also supported for systems  
where maximum performance is not needed.  
OPERATIONAL OVERVIEW  
The MUAC RCP is designed to act as an address  
translator for lookup tables in layer 3 switches, routers,  
and layer 2 switches. Refer to Figure 2 for a simplified  
block diagram of a switch. During normal operation, the  
controller extracts the address information from an  
arriving packet to form the comparand, which is then  
compared against the contents of the MUAC RCP. The  
MUAC RCP generates an index that is used to access the  
data in an external RAM, which holds the destination port  
for accessing the network. The controller reads the data  
from the RAM and forwards the packet.  
DQ bus data are used as both the comparand and compare  
mask bits 63–32. As a result, this instruction matches a  
DQ bit of 0 with bit pairs storing both 0 and X, and a DQ  
bit of 1 matches bit pairs storing both 1 and X.  
IPv4 CIDR addresses are prioritized by placing their  
ternary-encoded values into the MUAC RCP memory  
such that entries with longer netmasks (longer matches)  
have higher priority (lower indices). Thus, when the  
MUAC RCP performs a ternary comparison, it will return  
the index of the longest matching entry. Typically, the  
system is initialized by a processor that writes routing  
table information into the MUAC RCP. The index at  
which a write takes place is driven onto the PA:AA bus, so  
that output port data can be written simultaneously into the  
external RAM at the correct index.  
A unique feature of the MUAC RCP is its ternary  
comparison that processes IPv4 CIDR addresses in a  
single cycle. The bits of each MUAC RCP word are  
paired, such that each pair can contain two binary values  
(0,1) or one ternary (0,1,X= “Don’t Care”) value. A  
ternary value uses two bits, pairing bit n from the first 32  
bits (31-0) with bit n+32. When storing a ternary 0 or 1,  
the value to be stored is written into bit n (0<=n<=31), and  
the complement of the value is written to bit n+32. Thus, a  
ternary 0 written to ternary pair 7 would consist of a 0  
stored in bit 7 and a 1 stored in bit 39. When storing a  
ternary X, 0 is written to both bits in the pair.  
The validity of a location in the Address Database is  
determined by an extra bit called the Validity bit. This bit is  
set and reset either with an index or an associative match.  
Therefore, when a new entry is written to the database, its  
Validity bit is set valid.  
When a database location is deleted, the Validity bit for that  
entry is reset, and the index of the location is driven onto  
the Active Address bus. This simple mechanism allows  
easy maintenance of the tables in both the database and the  
external RAM.  
Using bit pairs that are 32 bits apart simplifies the  
computation of the pair by a processor. Assume that the  
ternary value we wish to store is contained in two 32-bit  
processor words. Word A contains the value to be stored  
and word M contains a mask value, with a 0 in each  
position at which an X is to be stored. The value to be  
written to bits 31-0 of the MUAC RCP is (A&M) and the  
value to be written to bits 63-32 of the MUAC RCP is  
(~A&M).  
The MUAC RCP supports simple daisy chained vertical  
cascading that serves to prioritize multiple devices and  
provides system-level match and full indication. If the  
slight timing overhead associated with the daisy chain is  
unacceptable, the MUAC RCP is designed to facilitate  
external prioritization across multiple devices.  
For layer 2 applications, the MAC addresses are processed  
in a binary mode, and the MUAC RCP looks for an exact  
match. An MUAC RCP can be used to process both MAC  
addresses and IPv4 CIDR in the same device.  
A special instruction, CMPT DQ, performs the ternary  
comparison processing for IPv4 CIDR addresses. The data  
on the DQ bus are used directly as both the comparand and  
compare mask bits 31–0, and the one’s complement of the  
2
Rev. 4a  
 复制成功!