The NXP LPC315x combine an 180 MHz ARM926EJ-S CPU core, High-speed USB 2.0OTG, 192 KB SRAM, NAND flash controller, flexible external bus interface, an integratedaudio codec, Li-ion charger, Real-Time Clock (RTC), and a myriad of serial and parallelinterfaces in a single chip targeted at consumer, industrial, medical, and communicationmarkets. To optimize system power consumption, the LPC315x have multiple powerdomains and a very flexible Clock Generation Unit (CGU) that provides dynamic clockgating and scaling.The LPC315x is implemented as multi-chip module with two side-by-side dies, one fordigital fuctions and one for analog functions, which include a Power Supply Unit (PSU),audio codec, RTC, and Li-ion battery charger.
Today in many applications such as network switches, routers, multi-computers,and processor-memory interfaces, the ability to integrate hundreds of multi-gigabit I/Os is desired to make better use of the rapidly advancing IC technology.
中文版詳情瀏覽：http://www.elecfans.com/emb/fpga/20130715324029.html
Xilinx UltraScale:The Next-Generation Architecture for Your Next-Generation Architecture
The Xilinx® UltraScale™ architecture delivers unprecedented levels of integration and capability with ASIC-class system- level performance for the most demanding applications.
The UltraScale architecture is the industr y's f irst application of leading-edge ASIC architectural enhancements in an All Programmable architecture that scales from 20 nm planar through 16 nm FinFET technologies and beyond, in addition to scaling from monolithic through 3D ICs. Through analytical co-optimization with the X ilinx V ivado® Design Suite, the UltraScale architecture provides massive routing capacity while intelligently resolving typical bottlenecks in ways never before possible. This design synergy achieves greater than 90% utilization with no performance degradation.
Some of the UltraScale architecture breakthroughs include:
• Strategic placement (virtually anywhere on the die) of ASIC-like system clocks, reducing clock skew by up to 50%
• Latency-producing pipelining is virtually unnecessary in systems with massively parallel bus architecture, increasing system speed and capability
• Potential timing-closure problems and interconnect bottlenecks are eliminated, even in systems requiring 90% or more resource utilization
• 3D IC integration makes it possible to build larger devices one process generation ahead of the current industr y standard
• Greatly increased system performance, including multi-gigabit serial transceivers, I/O, and memor y bandwidth is available within even smaller system power budgets
• Greatly enhanced DSP and packet handling
The Xilinx UltraScale architecture opens up whole new dimensions for designers of ultra-high-capacity solutions.
Today’s digital systems combine a myriad of chips with different voltage configurations.Designers must interface 2.5V processors with 3.3V memories—both RAM and ROM—as wellas 5V buses and multiple peripheral chips. Each chip has specific power supply needs. CPLDsare ideal for handling the multi-voltage interfacing, but do require forethought to ensure correctoperation.
This application note provides a functional description of VHDL source code for a N x N DigitalCrosspoint Switch. The code is designed with eight inputs and eight outputs in order to targetthe 128-macrocell CoolRunner™-II CPLD device but can be easily expanded to target higherdensity devices. To obtain the VHDL source code described in this document, go to sectionVHDL Code, page 5 for instructions.
The Virtex-4 features, such as the programmable IDELAY and built-in FIFO support, simplifythe bridging of a high-speed, PCI-X core to large amounts of DDR-SDRAM memory. Onechallenge is meeting the PCI-X target initial latency specification. PCI-X Protocol Addendum tothe PCI Local Bus Specification Revision 2.0a ([Ref 6]) dictates that when a target signals adata transfer, "the target must do so within 16 clocks of the assertion of FRAME#." PCItermination transactions, such as Split Response/Complete, are commonly used to meet thelatency specifications. This method adds complexity to the design, as well as additional systemlatency. Another solution is to increase the ratio of the memory frequency to the PCI-X busfrequency. However, this solution increases the required power and clock resource usage.
The data plane of the reference design consists of a configurable multi-channel XBERT modulethat generates and checks high-speed serial data transmitted and received by the MGTs. Eachchannel in the XBERT module consists of two MGTs (MGTA and MGTB), which physicallyoccupy one MGT tile in the Virtex-4 FPGA. Each MGT has its own pattern checker, but bothMGTs in a channel share the same pattern generator. Each channel can load a differentpattern. The MGT serial rate depends on the reference clock frequency and the internal PMAdivider settings. The reference design can be scaled anywhere from one channel (two MGTs)to twelve channels (twenty-four MGTs).
