CN104931930A - Beam control information message caching method - Google Patents

Beam control information message caching method Download PDF

Info

Publication number
CN104931930A
CN104931930A CN201510359213.8A CN201510359213A CN104931930A CN 104931930 A CN104931930 A CN 104931930A CN 201510359213 A CN201510359213 A CN 201510359213A CN 104931930 A CN104931930 A CN 104931930A
Authority
CN
China
Prior art keywords
bram
ripple control
data
control
fifo
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201510359213.8A
Other languages
Chinese (zh)
Inventor
周邦华
于志伟
刘剑
吴卫
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
724th Research Institute of CSIC
Original Assignee
724th Research Institute of CSIC
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 724th Research Institute of CSIC filed Critical 724th Research Institute of CSIC
Priority to CN201510359213.8A priority Critical patent/CN104931930A/en
Publication of CN104931930A publication Critical patent/CN104931930A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S7/00Details of systems according to groups G01S13/00, G01S15/00, G01S17/00

Abstract

The invention relates to a beam control information message caching method. The beam control information message caching method is implemented in an FPGA processor, beam control information data from an RAPIDIO link is received, two levels of caches are adopted, the first level is to pass through an FIFO at first, and the second level is to store the beam control information data in a BRAM. The write-in of the FIFO is controlled by the RAPIDIO link, and the FIFO starts read-out after caching 5000 pieces of data. The write-in of the BRAM is effectively controlled by a beam-control controller or by reset enabled control, thus the beam control information message can be read out by taking a counter as an address, and the BRAM can be reset, thereby reducing difficulty of external control. In order to shorten reset time of the BRAM, all-zero data is only written into the first 32 addresses, and the whole beam control information message stored in the BRAM is invalid through invalidating the head part of the beam control information message, thereby achieving the reset purpose.

Description

A kind of ripple control infomational message caching method
Technical field
The present invention relates to a kind of ripple control infomational message caching method, belong to Transmission System of Radar Data technology, mainly for phased-array radar real time beam control technology.
Background technology
Phased-array radar generally adopts CPU application embedded system to do ripple control resource scheduling algorithm, obtains multitask ripple control infomational message under calculating cycle a period of time.General use two storeies realize ping-pong operation, carry out circulation read-write.Do like this and cause controlling the more difficult storage resources with taking twice.In order to improve FPGA internal storage resources service efficiency, reducing and controlling difficulty, proposing a kind of new caching technology to reduce ripple control Software for Design difficulty.
Summary of the invention
The object of the invention is to design a kind of caching method, is satisfied different phased-array radar real time beam control technology, reduces ripple control infomational message Read-write Catrol difficulty.
The technical solution realizing the object of the invention is: in phased-array radar, and mode module and scheduling of resource software are in different hardware processors, and mode module uses FPGA processor, scheduling of resource software application POWERPC processor.Ripple control module is to scheduling of resource software application task, and scheduling of resource software calculates one group of ripple control infomational message, issues ripple control module by RAPIDIO link.In ripple control inside modules, the ripple control infomational message sent by RAPIDIO link first carries out buffer memory through a FIFO, realize the conversion of data transfer rate and bit wide, reach after 5000 according to the data volume of buffer memory in FIFO, write counter with one to be written in BRAM as the data of address accumulator by FIFO, until FIFO is sky.Ripple control program is according to radar requirements of one's work, from BRAM, the data of one section of fixed size are read as a frame ripple control information task message every one period of work period, along with work schedule need to read each ripple control infomational message one by one time, read counter can be used as address easily to read message in BRAM like clockwork.At present, when the reset signal RST of BRAM puts 1, make output be null value, can not remove the data of storage inside, when reset signal RST sets to 0, the value of reading remains original storage data.Simple and easy to operate for making BRAM reset, because front 32 addresses of BRAM are ripple control infomational message heads, these 32 addresses can be write full zero data, the ripple control infomational message that whole BRAM is stored is invalid, completes BRAM reset with this.After having read last ripple control infomational message, control program has completed BRAM and has reset, then to scheduling of resource software application task, just can before the arrival of next group task cycle more new task message.Issue even without new task message, also can not read original message with making the mistake.Concerning BRAM, reset and two work of write ripple control infomational message, ripple control control program separates completely from the time, so can guarantee that BRAM read-write is errorless.
Accompanying drawing explanation
Fig. 1 is ripple control method for caching information schematic diagram.
Fig. 2 is that ripple control information produces and buffer memory sequential chart.
Embodiment
Ripple control infomational message caching method of the present invention, as shown in Figure 2, is divided into following 5 steps:
1. ripple control controller produces task message application pulse, carries out FIFO, BRAM reset as benchmark.FIFO is set to 64 inputs, 16 way of outputs, and the input and output of BRAM are 16.When FIFO resets, be directly 1 by the RST signal assignment of FIFO, after keeping 3 clock period, then assignment is 0.When BRAM resets, write full zero data to address, address 0 to 32, because this sector address is ripple control infomational message head, after effective message of head is written into full zero data, the ripple control infomational message in whole BRAM is all judged as invalid packet by ripple control controller.
2., after completing the 1st step, ripple control controller generates task application message and doorbell information, is dealt into scheduling of resource software end by RAPIDIO transmission program.Scheduling of resource software can calculate the ripple control parameter of future time sheet, forms ripple control infomational message.Ripple control module FIFO receives the ripple control infomational message from RAPIDIO interface, realizes the conversion being transformed into 100MHz, 16 bit data by 156.25MHz, 64 bit data.During write FIFO, by high 14 trigger pips as write process of RAPIDIO receiver address signal, when this address signal is the value of setting each time, write 64 bit data to FIFO.
3. judge that FIFO is data cached whether more than 5000, if more than 5000, then start immediately and write BRAM control program.From address 0, the ripple control infomational message head read by FIFO one by one, each subtask message of ripple control infomational message are written in BRAM, until FIFO is empty.
4. when entering next timeslice from a work slice circulation, first more senior task order is judged whether by ripple control controller, if have, enter the mode of operation of high priority, if without, carry out from BRAM, read ripple control infomational message and produce ripple control control signal and message.
5. read the data of front 32 addresses, address 0 to 31 of BRAM, judge that whether the ripple control infomational message in current BRAM is effective, if invalid, stop.If effectively, then extract the initial time of each subtask in this timeslice from ripple control infomational message head, timeslice can be divided into multiple continuous print work period.At each work period initial time, from BRAM, read ripple control subtask message, and produce every gating pulse and optical fiber control message according to ripple control subtask message.After in the end a task message reads, produce task application pulse by ripple control controller, enter the 1st step and do FIFO, BRAM clearing work.

Claims (3)

1. a ripple control infomational message caching method, is characterized in that: the buffer memory link forming RAPIDIO interface data with FIFO+BRAM; The clearing of FIFO and BRAM is staggered with reading and writing data from the time by ripple control Control timing sequence; FIFO write end carries out control by the control signal of RAPIDIO interface and writes; When the buffer data size of FIFO is more than 5000, runs through continuously with regard to disposable and be written in BRAM, using as ripple control infomational message; After ripple control infomational message reads under the control of ripple control program from BRAM, ripple control program is by front for BRAM 32 addresses write complete zero, and it is invalid to be set to by BRAM internal wave control infomational message; Such design, avoiding when not having new ripple control infomational message write, again can read the mistake of original message as current time message again.
2. ripple control infomational message caching method according to claim 1, is characterized in that: described FIFO converts RAPIDIO link data to 16 by 64, and is transformed into real work clock frequency by data transfer rate by 156.25MHz.
3. ripple control infomational message caching method according to claim 1 and 2, it is characterized in that: described BRAM is the ripple control information data in buffer memory maximum 10 cycles, after according to radar work schedule, in the end a ripple control infomational message reads, 32 addresses before BRAM are write full zero data, and it is invalid the data in whole BRAM to be set to; Clearing work is replaced with this, then to the new ripple control infomational message of ripple control scheduling of resource software application.
CN201510359213.8A 2015-06-25 2015-06-25 Beam control information message caching method Pending CN104931930A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510359213.8A CN104931930A (en) 2015-06-25 2015-06-25 Beam control information message caching method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510359213.8A CN104931930A (en) 2015-06-25 2015-06-25 Beam control information message caching method

Publications (1)

Publication Number Publication Date
CN104931930A true CN104931930A (en) 2015-09-23

Family

ID=54119183

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510359213.8A Pending CN104931930A (en) 2015-06-25 2015-06-25 Beam control information message caching method

Country Status (1)

Country Link
CN (1) CN104931930A (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7038952B1 (en) * 2004-05-04 2006-05-02 Xilinx, Inc. Block RAM with embedded FIFO buffer
CN101141296A (en) * 2007-08-16 2008-03-12 华为技术有限公司 Channelizing logic single channel statistic method and apparatus
US7492780B1 (en) * 2005-02-25 2009-02-17 Xilinx, Inc. Method and apparatus for detecting timeout for packets transmitted in a packet-switched point-to-point communication architecture
CN103593237A (en) * 2013-11-20 2014-02-19 中国船舶重工集团公司第七二四研究所 Embedded active phased array multifunction integration scheduling method based on VPX framework

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7038952B1 (en) * 2004-05-04 2006-05-02 Xilinx, Inc. Block RAM with embedded FIFO buffer
US7492780B1 (en) * 2005-02-25 2009-02-17 Xilinx, Inc. Method and apparatus for detecting timeout for packets transmitted in a packet-switched point-to-point communication architecture
CN101141296A (en) * 2007-08-16 2008-03-12 华为技术有限公司 Channelizing logic single channel statistic method and apparatus
CN103593237A (en) * 2013-11-20 2014-02-19 中国船舶重工集团公司第七二四研究所 Embedded active phased array multifunction integration scheduling method based on VPX framework

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
周晓春等: ""基于串行RapidIO的舰载相控阵雷达波束控制设计"", 《科学技术与工程》 *
唐清善等: ""基于FPGA的高速异步FIFO的设计与实现"", 《微计算机信息》 *

Similar Documents

Publication Publication Date Title
CN107992271B (en) Data pre-reading method, device, equipment and computer readable storage medium
CN104321716B (en) Use device idle duration information optimizes energy efficiency
US20130187935A1 (en) Low latency concurrent computation
CN105446893A (en) Data storage method and device
JP6340481B2 (en) Data caching method, apparatus and storage medium
CN105404598A (en) Real-time data acquisition system and method
CN109359729B (en) System and method for realizing data caching on FPGA
CN104200846A (en) Embedded-type PROM test system and achieving method
US9239804B2 (en) Back-off mechanism for a peripheral page request log
CN110147254A (en) A kind of data buffer storage processing method, device, equipment and readable storage medium storing program for executing
CN104931930A (en) Beam control information message caching method
CN116074267B (en) Data communication system and SoC chip
CN102542525B (en) Information processing equipment and information processing method
CN115905046B (en) Network card driving data packet processing method and device, electronic equipment and storage medium
CN104317747A (en) Data caching and sending device and method of network receiver
CN112840309B (en) Command scheduling method, device and storage medium
CN109062843A (en) A kind of date storage method and system based on iic bus
CN105518617B (en) Data cached processing method and processing device
CN108196849A (en) A kind of low latency instruction scheduler
CN103685961B (en) Real-time processing system for achieving video data synchronization using single-chip SRAM
CN113434304A (en) Multi-thread-based multi-view vision camera synchronous acquisition method
CN104597805A (en) System and method for achieving circular register shifting based on FIFO
CN105573937A (en) Data retransmitting system
CN116155843B (en) PYNQ-based pulse neural network chip data communication method and system
CN116660899B (en) Near-field target ISAR imaging system and device based on FPGA+DSP

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20150923

WD01 Invention patent application deemed withdrawn after publication