CN102023961A - Communication method based on shared memory and apparatus thereof - Google Patents
Communication method based on shared memory and apparatus thereof Download PDFInfo
- Publication number
- CN102023961A CN102023961A CN2009101721317A CN200910172131A CN102023961A CN 102023961 A CN102023961 A CN 102023961A CN 2009101721317 A CN2009101721317 A CN 2009101721317A CN 200910172131 A CN200910172131 A CN 200910172131A CN 102023961 A CN102023961 A CN 102023961A
- Authority
- CN
- China
- Prior art keywords
- message
- passage
- length
- transfer
- message body
- 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
Links
Images
Abstract
The present invention discloses a communication method based on a shared memory and an apparatus thereof, and relates to the communication technology field. The communication method disclosed by the invention can be complemented in such a way that: a sender writes the content to be transmitted into a memory channel as a message body and provides a fixed-length message head for the message body to form a transmission message, wherein the message head at least carries the length of the message body; and a receiver reads the message head from the channel, determines the initial address of the message body according to the initial address and the length of the message head, then determines the position of the message body in the memory channel according to the initial address of the message body and the length of the message body in the message head, reads the message body in the position, and then conducts treatment. The technical scheme provided by the present invention can support multiple channels and variable length messages.
Description
Technical field
The present invention relates to communication technical field, be specifically related to a kind of communication means and device based on shared drive.
Background technology
When communicating by letter by shared drive between two CPU, at present more common have a following several method.
First method is shared drive to be deposited be divided into two, respectively as transmission, the receiving cable of two CPU, as shown in Figure 1.Each passage provides a read-write zone bit, and this sign is initially can write attitude.To read and write sign after the transmit leg transmission data and be revised as readable attitude, wait for that the take over party receives by writing attitude.The take over party receives and will read and write sign after the data and be revised as by readable attitude and can write attitude, so that transmit leg can continue to send.Adopt this method, data interaction each time needs all to wait for that the other side reads or writes finishes, and efficient is very low.
Second method also is that shared drive is divided into two, and as transmission, the receiving cable of two CPU, each passage is realized the circulation read-write with a circle queue, as shown in Figure 2 respectively.Circle queue manages by the read-write pointer that leaves in the mailbox.Be sent as example with CPU1, when CPU1 had data to send, at first the reading and writing pointer by circle queue 1 calculated whether enough remaining spaces are arranged, if the space is enough, then the message bag is write write pointer indication position, and upgraded write pointer.CPU2 automatic regular polling circle queue 1 when finding new message bag is arranged, then reads the message bag, and upgrades read pointer.Because transmit leg and take over party can operate shared drive simultaneously,, still still there is following problem than improving greatly on the method efficient of front:
1, data generally send by the fixed length packing, differ greatly for the message packet length, and for example minimum length is 4 bytes, and maximum length is 40 bytes, all will send by the 40 bytes packing of maximum, cause waste.
2, when the rear of queue end spaces is deposited the new information bag inadequately, generally for easy to operate do not allow the message winding around, just need to fill particular values (for example 0xFFFF) and indicate this tail end space invalid, and the message bag is placed into the formation head.Needs and particular value compare during reception, the filling value when judgement is normal messages bag or coiling.If comprise particular value in the normal messages bag, will produce conflict.
The third method, promptly existing patent documentation " a kind of double CPU communication method " based on shared storage, number of patent application is 200610103231.0, two circle queues have been used, as shown in Figure 3, one is used to deposit message index, and another is used to deposit message entity.Wherein, message index is the pointer that size is fixed as 4 bytes and refer message entity, as shown in Figure 4, and the message entity variable size.But the method has following deficiency:
1, in program design, must note the synchronous of message index and message entity formation constantly, need safeguard two formations simultaneously, increase the complicacy of program.
2, easily cause waste.When a lot of little message bags caused the message index queue full, whole message channel was with unavailable, even the message entity formation also has very big space to use.
Summary of the invention
Technical matters to be solved by this invention is, a kind of communication means and device based on shared drive is provided, and can support hyperchannel, variable message-length.
In order to address the above problem, the invention discloses a kind of communication means based on shared drive, comprising:
Transmit leg is the content that will the send passage as the message body write memory, and for the message header of this message body configuration fixed length to constitute message transfer, wherein, carry the length of described message body in the described message header at least;
The take over party reads described message header from described passage, determine the start address of described message body according to the length of the start address of described message header and message header, again according to the length of message body in the start address of described message body and the described message header, determine the position of described message body at described main memory access, on this position, read described message body, handle.
Further, before described transmit leg was with described message body write memory passage, said method also comprised;
Described transmit leg and described take over party are divided into a plurality of passages with internal memory, are each channel arrangement passage descriptor, and described passage descriptor comprises the base address of passage, the size of passage and the read-write pointer of passage.
Wherein, transmit leg is during with the message body write memory passage that will send, also with the next available cell of this passage of write pointers point of this passage;
Described take over party judges when the reading and writing pointer of described passage is unequal, just reads described message transfer, and the read pointer of described passage is pointed to next message transfer.
Described message header also comprises next hop address, and described next hop address is represented the start address of the message header of next message transfer.
Described transmit leg is during with the passage of described message transfer write memory, if described channel bottom free space is less than the length of described message transfer, and described channel roof free space is greater than the length of described message transfer, then write a null message head in the bottom of described passage, described message transfer is write the top of described passage, wherein, the length of message body is zero in the described null message head, and next hop address is zero;
If described take over party reads described null message head from described passage, then read message transfer from the top of described passage, handle.
The invention also discloses a kind of communicator, comprise transmitting element, receiving element based on shared drive, processing unit, wherein:
Described transmitting element is used for the passage with the message transfer write memory of described processing unit transmission;
Described receiving element, be used for reading the message header of message transfer from the passage of internal memory, determine the start address of the message body of described message transfer according to the length of the start address of described message header and message header, again according to the length of message body in the start address of described message body and the described message header, determine the position of described message body at described main memory access, on this position, read described message body, and the message body of being read is sent to described processing unit;
Described processing unit, the content that is used for will transmitting is as message body, for the message header of this message body configuration fixed length constituting message transfer, and described message transfer is sent to described transmitting element, and be used to receive the message body that described receiving element sends, this message body is handled.
Further, in the above-mentioned communicator, described processing unit also is used for internal memory is divided into a plurality of passages, is each channel arrangement passage descriptor, and described passage descriptor comprises the base address of passage, the size of passage and the read-write pointer of passage.
Wherein, described transmitting element during with the passage of described message write memory, also is used for the next available cell with this passage of write pointers point of this passage;
Described receiving element is used to also judge whether the reading and writing pointer of described passage equates, when the reading and writing pointer of described passage is unequal, reads the message header of described message transfer, and the read pointer of this passage is pointed to next message transfer.
Described processing unit disposes next hop address in described message header, described next hop address is represented the start address of the message header of next message transfer.
Described processing unit, in the channel bottom free space of described internal memory length less than described message transfer, and described channel roof free space is during greater than the length of described message transfer, also be used for sending a null message head to described transmitting element, wherein, the length of message body is zero in the described null message head, and next hop address is zero;
Described transmitting element, also be used to receive the null message head that described processing unit sends, and described null message head is write the bottom of described passage, described message transfer is write the top of described passage, and when reading the null message head, read message transfer from the top of described passage again, and the message body of described message transfer is sent to described processing unit.
After adopting technical solution of the present invention, can support hyperchannel, can support variable length message, technical solution of the present invention is particularly useful for the situation of the big and message bag random length of message traffic.The present invention also can be used for based on communicating by letter between the multitask under the single CPU of shared drive in addition.
Description of drawings
Fig. 1 is the dual-cpu communication synoptic diagram of the shared drive of prior art;
Fig. 2 is the dual-cpu communication synoptic diagram of each passage of prior art with a circle queue;
Fig. 3 is the dual-cpu communication synoptic diagram of each passage of the prior art with two circle queues;
Fig. 4 is that message index of the prior art and message entity concern synoptic diagram;
Fig. 5 is the synoptic diagram that apparatus of the present invention realize communication;
Fig. 6 is the structural representation of message transfer among the present invention;
Fig. 7 sends message flow chart among the present invention;
Fig. 8 is a passage descriptor synoptic diagram among the present invention;
Fig. 9 is each access diagram among the present invention;
Figure 10 receives message flow chart among the present invention.
Embodiment
Main design of the present invention is, definition first device (for example, the implement device of CPU1 or task one) passage that send, second device (for example, CPU2 or task two) receives is a down going channel, and the passage that second device sends, first device receives is a data feedback channel.For down going channel, write pointer first device can be write, and second device is read-only, and read pointer first device is read-only, and second device can be write; For data feedback channel, write pointer second device can be write, and first device is read-only, and read pointer second device is read-only, and first device can be write, as shown in Figure 5.
Behind transmit leg (first device or the second device) message transfer, can notify take over party's (second device or first device) to go to receive by interrupt mode, in addition, the take over party also can receive with the mode of poll.
In whole communication processing procedure, be further divided into following three flow processs:
First, the initialization flow process:
According to system's needs, set down going channel and data feedback channel number respectively, wherein, a passage is a formation, and initialization read-write pointer refers to all to the formation head.
Second portion sends the message transfer flow process:
Size according to message transfer and formation, judge whether to write new message transfer, if then new message transfer is write respective channel, and upgrade the write pointer (available cell after the new message transfer of write pointers point) of this passage, otherwise send out again after postponing.
Third part receives the message transfer flow process:
By judging whether formation reading and writing pointer equates, to determine whether new message transfer, when the reading and writing pointer was unequal, expression had new message transfer; The reading and writing pointer equates that expression does not have new message transfer;
When new message transfer, obtain message header, upgrade formation read pointer (pointing to next message transfer), and, use the call back function of user's registration that the data of this new message transfer are handled according to message header.
Technical solution of the present invention will be further described below in conjunction with specific embodiment and accompanying drawing.
A kind of communication device based on shared drive comprises transmitting element, receiving element and processing unit.Introduce the function of each unit below.
Transmitting element is used to send the new message transfer that processing unit sends, and is about to new message transfer and writes passage;
Wherein, transmitting element is in sending the message transfer process, whether length (being the total length of message header and message body) that need to judge the new message transfer that will send is more than or equal to the free space of this passage, wherein, when the length of the new message transfer that will send during more than or equal to the free space of this passage, the expression passage is full, can't write new message transfer, needs this moment to continue to wait for; When the length of the new message transfer that will send during less than the free space of passage, the expression passage less than, can write new message transfer;
Further, (promptly the message-length in this null message head is 0 when processing unit sends empty message header to described transmitting element, next hop address is 0) time, transmitting element writes this null message head in this channel bottom, new message transfer is write the top of this passage;
Receiving element, be used to receive the new message transfer that the opposite end sends, it is the new message transfer in the fetch channel, read the message header of new message transfer, and, determine the start address of message body according to message header address and message header length, begin to read message body from this start address, the length that reads is the message body length in the message header, and the message body of being read is sent to processing unit;
Processing unit is used to construct new message transfer, and new message transfer is sent to transmitting element, and is used to receive the message body that receiving element sends, and uses the call back function of registration that this message is handled;
Wherein, the new message transfer that processing unit is constructed is divided into message header and message body (being the content that will transmit) two parts of fixed length, as shown in Figure 6, wherein, it is 16 bytes that fixed length has message header, in the message header, the evil spirit number accounts for 4 bytes, and type of message accounts for 4 bytes, and message body length accounts for 4 bytes, next hop address (being the message header address of next message) accounts for 4 bytes, and message body length is variable.
Further, when the bottom free space of the passage of internal memory length less than new message transfer, and the top free space of this passage is during greater than the length of new message transfer, processing unit is also constructed a null message hair and is given transmitting element, message-length is changed to 0 in this null message head, and next hop address is set to 0.
Introduce the process of carrying out communication between the said apparatus below, in the present embodiment, each device is a CPU, and promptly present embodiment is the process that realizes communication between two CPU, and existing down direction with this communication process (promptly first device is to the direction of the second device message transfer) is an example, introduce communication process, this process is divided into transmission part and receiving unit, wherein, and process of transmitting, as shown in Figure 7, may further comprise the steps:
Step 700: shared drive is divided into a plurality of data feedback channels and down going channel respectively, be each channel arrangement passage descriptor, and the read-write pointer of passage in the passage descriptor is initialized as 0, with expression queue empty, no message, the call back function of handling when message is received in registration simultaneously;
In the present embodiment, can be according to the size of user's needs or message transfer, shared drive is divided into four passages (passage is a transmit queue), wherein, two passages are data feedback channel, and two other passage is a down going channel, each passage descriptor, be used to describe the base address of each passage, the size of passage and the read-write pointer of passage, as shown in Figure 8.
Step 701: transmit leg judges whether down going channel is full, if then continue to wait for, otherwise enter step 702;
In this step, whether the length (length of new message transfer refers to the total length of message header and message body) that transmit leg can be judged the new message transfer that will send is more than or equal to the free space of this passage, to judge whether down going channel is full, wherein, when the length of the new new message transfer that will send during more than or equal to the free space of this passage, the expression passage is full, can't write new message transfer, needs this moment to continue to wait for; When the length of the new new message transfer that will send during less than the free space of passage, the expression passage less than, can write new message transfer;
Particularly, according to the reading and writing pointer of this passage, whether the length that can judge new message transfer is more than or equal to the free space of this passage.The free space of passage can calculate by the reading and writing pointer: write pointer is during greater than read pointer, the length of the free space=passage of passage-(write pointer-read pointer); Read pointer is during greater than write pointer, the free space=read pointer of formation-write pointer.
Step 702: whether the bottom free space of judging this passage is more than or equal to the length of new message transfer, if enter step 706, otherwise enter step 703;
Step 703: whether the top free space of judging this passage is smaller or equal to the length of new message transfer, if then continue to wait for, otherwise enter step 704;
Step 704: transmit leg writes the null message head in this channel bottom, and the message-length in this null message head is set to 0, and the next hop address in this null message head is set to 0;
Step 705: transmit leg writes new message transfer at the top of this passage free space, finishes transmission flow;
Step 706: new message transfer is write the free space of this passage successively, and upgrade the next hop address in the message header of this new message transfer, and the write pointer of this passage, finish transmission flow.
In the present embodiment, in down going channel, write each message after, as shown in Figure 9; Each new message transfer is divided into message header and message body two parts, as shown in Figure 6, wherein, message header is 16 bytes of fixed length, and in the message header, magic number accounts for 4 bytes, type of message accounts for 4 bytes, message body length accounts for 4 bytes, and next hop address accounts for 4 bytes, and message body length (being the particular content of message) is variable.The size of whole passage is with length (also the being 16 bytes) alignment of message header.The length of new message transfer to be written when writing formation also with the alignment of the length (also 16 bytes) of message header.
Receiving course may further comprise the steps as shown in figure 10:
Step 1001: whether the take over party judges has new message transfer, if having, enter step 1002 in the down going channel, otherwise continues to wait for;
In this step, the take over party judges when down going channel is sky, i.e. expression does not have new message transfer, judge that expression had new message transfer, particularly when down going channel was not empty, when the reading and writing pointer of judging this down going channel equates, the expression passage is empty, when the reading and writing pointer of judgement down going channel is unequal, represents this down going channel non-NULL.
Step 1002: the message header that reads this new message transfer, and the start address of determining the message body of the message transfer that this is new according to the address and the length thereof of this message header, it is the address of length=message body of the address+message header of message header, and use the call back function of registration that this message is handled, simultaneously and upgrade the read pointer (be about to read pointer and point to next message) of this down going channel.
In this step, when the message body length in the message header that the take over party obtains and next hop address are 0, show that this message is not enough owing to the formation bottom space when sending, only deposited a bear in the bottom, and real message deposit directly reads the formation top at this moment and can obtain real message header at the top of formation.
In the present embodiment, when access message head and queue descriptor, be also noted that the problem of syllable sequence, because CPU1 is different with CPU2 possibility syllable sequence.
In other embodiments, each device can be represented the implement device of a task, and the communication process between two devices is the communication process that carries out big data quantity between two tasks (for example task 1 and task 2).
From the foregoing description as can be seen, technical solution of the present invention can be supported hyperchannel, can support variable length message.And, for fear of the message winding around the time fill particular value, when the rear of queue end spaces is deposited the new information bag inadequately, directly be stored in queue heads, need not at all to be concerned about whether the message bag reels.Transmit leg can also send message continuously, and multiple messages is deposited in the buffer zone, and the take over party then can handle the multiple messages in the buffer zone continuously.So just reduce transmit leg and take over party's stand-by period, reduced the number of times that the take over party repeats into interruption or inquiry, improved the utilization factor of CPU, improved data throughout and processing speed.
The above is the preferred embodiments of the present invention only, is not limited to the present invention, and for a person skilled in the art, the present invention can have various changes and variation.Within the spirit and principles in the present invention all, any modification of being done, be equal to replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (10)
1. the communication means based on shared drive is characterized in that, this method comprises:
Transmit leg is the content that will the send passage as the message body write memory, and for the message header of this message body configuration fixed length to constitute message transfer, wherein, carry the length of described message body in the described message header at least;
The take over party reads described message header from described passage, determine the start address of described message body according to the length of the start address of described message header and message header, again according to the length of message body in the start address of described message body and the described message header, determine the position of described message body at described main memory access, on this position, read described message body, handle.
2. the method for claim 1 is characterized in that, before described transmit leg was with described message body write memory passage, this method also comprised;
Described transmit leg and described take over party are divided into a plurality of passages with internal memory, are each channel arrangement passage descriptor, and described passage descriptor comprises the base address of passage, the size of passage and the read-write pointer of passage.
3. method as claimed in claim 2 is characterized in that,
Transmit leg is during with the message body write memory passage that will send, also with the next available cell of this passage of write pointers point of this passage;
Described take over party judges when the reading and writing pointer of described passage is unequal, just reads described message transfer, and the read pointer of described passage is pointed to next message transfer.
4. as each described method of claim 1 to 3, it is characterized in that,
Described message header also comprises next hop address, and described next hop address is represented the start address of the message header of next message transfer.
5. method as claimed in claim 4 is characterized in that,
Described transmit leg is during with the passage of described message transfer write memory, if described channel bottom free space is less than the length of described message transfer, and described channel roof free space is greater than the length of described message transfer, then write a null message head in the bottom of described passage, described message transfer is write the top of described passage, wherein, the length of message body is zero in the described null message head, and next hop address is zero;
If described take over party reads described null message head from described passage, then read message transfer from the top of described passage, handle.
6. the communicator based on shared drive is characterized in that, this device comprises transmitting element, receiving element, processing unit, wherein:
Described transmitting element is used for the passage with the message transfer write memory of described processing unit transmission;
Described receiving element, be used for reading the message header of message transfer from the passage of internal memory, determine the start address of the message body of described message transfer according to the length of the start address of described message header and message header, again according to the length of message body in the start address of described message body and the described message header, determine the position of described message body at described main memory access, on this position, read described message body, and the message body of being read is sent to described processing unit;
Described processing unit, the content that is used for will transmitting is as message body, for the message header of this message body configuration fixed length constituting message transfer, and described message transfer is sent to described transmitting element, and be used to receive the message body that described receiving element sends, this message body is handled.
7. communicator as claimed in claim 6 is characterized in that,
Described processing unit also is used for internal memory is divided into a plurality of passages, is each channel arrangement passage descriptor, and described passage descriptor comprises the base address of passage, the size of passage and the read-write pointer of passage.
8. communicator as claimed in claim 7 is characterized in that,
Described transmitting element during with the passage of described message write memory, also is used for the next available cell with this passage of write pointers point of this passage;
Described receiving element is used to also judge whether the reading and writing pointer of described passage equates, when the reading and writing pointer of described passage is unequal, reads the message header of described message transfer, and the read pointer of this passage is pointed to next message transfer.
9. as each described communicator of claim 6 to 8, it is characterized in that,
Described processing unit disposes next hop address in described message header, described next hop address is represented the start address of the message header of next message transfer.
10. communicator as claimed in claim 9 is characterized in that,
Described processing unit, in the channel bottom free space of described internal memory length less than described message transfer, and described channel roof free space is during greater than the length of described message transfer, also be used for sending a null message head to described transmitting element, wherein, the length of message body is zero in the described null message head, and next hop address is zero;
Described transmitting element, also be used to receive the null message head that described processing unit sends, and described null message head is write the bottom of described passage, described message transfer is write the top of described passage, and when reading the null message head, read message transfer from the top of described passage again, and the message body of described message transfer is sent to described processing unit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2009101721317A CN102023961A (en) | 2009-09-10 | 2009-09-10 | Communication method based on shared memory and apparatus thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2009101721317A CN102023961A (en) | 2009-09-10 | 2009-09-10 | Communication method based on shared memory and apparatus thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102023961A true CN102023961A (en) | 2011-04-20 |
Family
ID=43865272
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2009101721317A Pending CN102023961A (en) | 2009-09-10 | 2009-09-10 | Communication method based on shared memory and apparatus thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102023961A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102970598A (en) * | 2012-12-11 | 2013-03-13 | 四川九洲电器集团有限责任公司 | Method and system for demultiplexing TS (transport stream) transport stream by set top box |
| CN103166873A (en) * | 2011-12-12 | 2013-06-19 | 中兴通讯股份有限公司 | Inter-core communication method and core processor |
| CN103246622A (en) * | 2013-04-10 | 2013-08-14 | 华为技术有限公司 | Method for expanding memory, memory nodes, master node, and system |
| CN104052831A (en) * | 2014-06-11 | 2014-09-17 | 华为技术有限公司 | Data transmission method and device based on queues and communication system |
| WO2014205691A1 (en) * | 2013-06-26 | 2014-12-31 | 华为技术有限公司 | Data packet processing method and data packet processing device and system |
| CN104461933A (en) * | 2014-11-07 | 2015-03-25 | 珠海全志科技股份有限公司 | Memory management method and device thereof |
| CN107463526A (en) * | 2017-08-15 | 2017-12-12 | 南京国电南自电网自动化有限公司 | A kind of high speed information sharing method between SOC |
| CN108304269A (en) * | 2017-01-13 | 2018-07-20 | 阿里巴巴集团控股有限公司 | A kind of sending, receiving method of data, device and communications framework |
| WO2018228238A1 (en) * | 2017-06-14 | 2018-12-20 | 阿里巴巴集团控股有限公司 | Method and apparatus for communication between processes |
| CN109117268A (en) * | 2018-07-20 | 2019-01-01 | 首钢集团有限公司 | A kind of implementation method and device of mill control system communication middleware |
| CN110010167A (en) * | 2019-03-26 | 2019-07-12 | 记忆科技(深圳)有限公司 | It is a kind of to improve method, apparatus, computer equipment and the storage medium for obtaining descriptor state |
| CN110069438A (en) * | 2018-01-22 | 2019-07-30 | 普天信息技术有限公司 | A kind of method of isomery device Memory communication |
| CN110532109A (en) * | 2019-08-16 | 2019-12-03 | 东南大学 | A kind of shared multichannel process communication internal storage structure and method |
| CN111736533A (en) * | 2020-06-04 | 2020-10-02 | 佛山智能装备技术研究院 | Data synchronization method and device based on control and drive integrated robot |
| CN112711491A (en) * | 2021-03-29 | 2021-04-27 | 江苏未来智慧信息科技有限公司 | Message transmission method based on shared memory |
-
2009
- 2009-09-10 CN CN2009101721317A patent/CN102023961A/en active Pending
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103166873A (en) * | 2011-12-12 | 2013-06-19 | 中兴通讯股份有限公司 | Inter-core communication method and core processor |
| CN102970598A (en) * | 2012-12-11 | 2013-03-13 | 四川九洲电器集团有限责任公司 | Method and system for demultiplexing TS (transport stream) transport stream by set top box |
| CN102970598B (en) * | 2012-12-11 | 2015-06-17 | 四川九洲电器集团有限责任公司 | Method and system for demultiplexing TS (transport stream) transport stream by set top box |
| CN103246622B (en) * | 2013-04-10 | 2015-12-02 | 华为技术有限公司 | A kind of method of exented memory, memory node, host node and system |
| CN103246622A (en) * | 2013-04-10 | 2013-08-14 | 华为技术有限公司 | Method for expanding memory, memory nodes, master node, and system |
| WO2014205691A1 (en) * | 2013-06-26 | 2014-12-31 | 华为技术有限公司 | Data packet processing method and data packet processing device and system |
| CN104396196A (en) * | 2013-06-26 | 2015-03-04 | 华为技术有限公司 | Data packet processing method and a data packet processing device and system |
| CN104052831A (en) * | 2014-06-11 | 2014-09-17 | 华为技术有限公司 | Data transmission method and device based on queues and communication system |
| CN104461933A (en) * | 2014-11-07 | 2015-03-25 | 珠海全志科技股份有限公司 | Memory management method and device thereof |
| CN104461933B (en) * | 2014-11-07 | 2017-10-03 | 珠海全志科技股份有限公司 | EMS memory management process and its device |
| CN108304269A (en) * | 2017-01-13 | 2018-07-20 | 阿里巴巴集团控股有限公司 | A kind of sending, receiving method of data, device and communications framework |
| US11216320B2 (en) | 2017-06-14 | 2022-01-04 | Alibaba Group Holding Limited | Method and apparatus for communication between processes |
| WO2018228238A1 (en) * | 2017-06-14 | 2018-12-20 | 阿里巴巴集团控股有限公司 | Method and apparatus for communication between processes |
| CN107463526A (en) * | 2017-08-15 | 2017-12-12 | 南京国电南自电网自动化有限公司 | A kind of high speed information sharing method between SOC |
| CN110069438A (en) * | 2018-01-22 | 2019-07-30 | 普天信息技术有限公司 | A kind of method of isomery device Memory communication |
| CN109117268A (en) * | 2018-07-20 | 2019-01-01 | 首钢集团有限公司 | A kind of implementation method and device of mill control system communication middleware |
| CN110010167A (en) * | 2019-03-26 | 2019-07-12 | 记忆科技(深圳)有限公司 | It is a kind of to improve method, apparatus, computer equipment and the storage medium for obtaining descriptor state |
| CN110532109A (en) * | 2019-08-16 | 2019-12-03 | 东南大学 | A kind of shared multichannel process communication internal storage structure and method |
| CN110532109B (en) * | 2019-08-16 | 2023-06-30 | 东南大学 | Shared multi-channel process communication memory structure and method |
| CN111736533A (en) * | 2020-06-04 | 2020-10-02 | 佛山智能装备技术研究院 | Data synchronization method and device based on control and drive integrated robot |
| CN112711491A (en) * | 2021-03-29 | 2021-04-27 | 江苏未来智慧信息科技有限公司 | Message transmission method based on shared memory |
| CN112711491B (en) * | 2021-03-29 | 2021-07-09 | 江苏未来智慧信息科技有限公司 | Message transmission method based on shared memory |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102023961A (en) | Communication method based on shared memory and apparatus thereof | |
| CN100517294C (en) | Double CPU communication method based on shared memory | |
| EP0551242B1 (en) | Multiprocessor buffer system | |
| US8230180B2 (en) | Shared memory burst communications | |
| US5805823A (en) | System and method for optimal multiplexed message aggregation between client applications in client-server networks | |
| AU751616B2 (en) | System and method of data communication in multiprocessor system | |
| US8874797B2 (en) | Network interface for use in parallel computing systems | |
| CN101150485A (en) | A management method for network data transmission of zero copy buffer queue | |
| CN104796337A (en) | Method and device for forwarding message | |
| US9602436B2 (en) | Switching device | |
| US20030018737A1 (en) | System and method for a distributed shared memory | |
| CN101707565B (en) | Method and device for transmitting and receiving zero-copy network message | |
| CN102129411A (en) | Access buffer | |
| CN101150486A (en) | A management method for receiving network data of zero copy buffer queue | |
| CN103946803A (en) | Processor with efficient work queuing | |
| TW201237632A (en) | Buffer management scheme for a network processor | |
| JPS61243554A (en) | Communication system | |
| TW200407717A (en) | Mail box interface between processors | |
| CN102065568A (en) | Data descriptor-based medium access control (MAC) software and hardware interaction method and hardware realization device | |
| CN110045922A (en) | The network equipment and operating method | |
| US6529945B1 (en) | Data buffer management between two different systems | |
| JP2008512942A5 (en) | ||
| CN101237346B (en) | Network processor and method for network processor to read and write serial port | |
| CN101656658A (en) | Method and device for improving dequeuing efficiency in queue management | |
| CN111201516A (en) | Message passing in data processing system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20110420 |