Yunzhisheng Officially Announced the New Multimodal AI Chip Strategy and Plan

On January 2, 2019, yunzhisheng held a conference in Beijing with the theme of "extraordinary sound and vision" "The press conference officially announced its new multimodal AI chip strategy and plan. This time, yunzhisheng broke through the positioning of the original voice AI manufacturer and further expanded to the field of visual AI. At the same time, yunzhisheng also exposed three AI chips under development, including the second-generation Internet of things voice AI chip swift Lite and the supporting image and voice for smart city The calculated multi-modal AI chip dolphin and the vehicle specification level multi-modal AI chip leopard for smart travel.

From IVM to swift, yunzhisheng's core making road

As we all know, yunzhisheng has always been a voice technology manufacturer. With the rise of artificial intelligence and edge computing, yunzhisheng began to enter the AI hardware chip scheme (IVM) of the Internet of things in 2014 And began to form mass production and shipment in 2015. Among them, customers in the home field cover almost all domestic first-line home appliance manufacturers such as Gree, Midea, Haier, Changhong, Hisense and vantage.

In addition, it is worth mentioning that according to the data released by Huang Wei, founder and CEO of yunzhisheng at today's press conference, yunzhisheng's voice AI has entered more than 500 hospitals since 2015, of which 80% are class III hospitals (such as Beijing Union Medical College Hospital, Shanghai Huashan Hospital, etc.).

In the process of providing services in-depth scenarios, yunzhisheng officially launched the self-developed AI chip program in 2015 in order to make up for the energy efficiency ratio of the general chip scheme under the given cost and power consumption conditions, as well as the weakness in edge computing power and multimodal AI data processing.

After three years of research and development, on May 16 last year, yunzhisheng took the lead in launching the industry's first voice AI chip for the Internet of things - Unione swift and its system solution. The chip adopts yunzhisheng's independent AI instruction set and has deepnet1.0 and udsp (digital signal processor) with complete independent intellectual property rights It also supports DNN / LSTM / CNN and other deep neural network models, and its performance is more than 50 times higher than that of the general scheme.

In order to further accelerate the implementation of "swift" and system solutions, on September 12 last year, yunzhisheng released the solution of smart speaker and smart home based on "swift", and announced that it would open source the solution In combination, the turnkey solution of software and hardware integration for specific scenarios provided to customers and partners can enable customers to stand at a higher design starting point and create more stable and reliable products in a shorter time cycle at a lower cost. At the same time, the open source solution can also ensure that customers can design other long tail product forms and build more stable products based on the provided AI capabilities It is rich in aiot ecology.

It is reported that at present, the full stack solution based on swift chip has been imported into more than 10 solution providers and partners, including Midea, oaks, Hisense, JD, 360, China Ping An, hard egg technology, etc. related products will be mass produced and listed as early as Q1.

The success of swift chip in the market has also successfully promoted the growth of yunzhisheng's revenue. Although the overall environment in 2018 was not very good, according to the data released by yunzhisheng, yunzhisheng's revenue in 2018 soared three times compared with 2017. The reason for such a huge growth is inseparable from the "blossom and fruit" of "swift".

Huang Wei, founder and CEO of yunzhisheng, also said that the revenue of yunzhisheng in 2018 mainly came from chips and software services.

5g promotes the landing of aiot, and multimodal AI chip is inevitable

Then, as a voice AI technology manufacturer, why did yunzhisheng break through the positioning of the original voice AI manufacturer, further expand to the field of visual AI, and announce the promotion of multimodal AI chips?

Huang Wei, founder and CEO of yunzhisheng

Huang Wei, founder and CEO of yunzhisheng, believes that at present, we are on the verge of 5g explosion. The combination of 5g and artificial intelligence will really promote the landing and implementation of aiot. It can be predicted that there will be a huge amount of multidimensional data (such as voice, image, video, etc.) in the future The demand for centralized processing and edge distributed computing is bound to further challenge the computing power of the underlying AI supporting hardware chip.

At the same time, AI applications in the aiot scenario have a strong demand for end-to-end cloud interaction. A strong cloud will make the end more capable, and a strong end can improve the real-time and effectiveness of data processing, so as to enhance the ability of the cloud. The two need to be closely combined, which requires unified consideration of chip design and cloud architecture. The traditional general solution architecture is based on high real-time The computing power in the highly intelligent scene is limited, and many practical needs such as cost, power consumption and security cannot be balanced. Therefore, a multimodal AI chip with multi-dimensional AI data centralized processing capability will become the only way.

Multimodal evolution of Internet of things AI chip

At the press conference of the first generation Unione chip swift, Li Xiaohan, co-founder of yunzhisheng, once pointed out that Unione is not a chip, but a series of chips, representing yunzhisheng's overall vision for the development strategy of IOT AI chips. At today's yunzhisheng 2019 multimode AI chip strategy press conference, Li Xiaohan once again demonstrated the multimodality of IOT from three aspects The necessity of AI chip.

Li Xiaohan, co-founder of yunzhisheng

Li Xiaohan believes that the AI chips of the current Internet of things product line increasingly reflect three trends:

The first is scenario. Chip design is gradually evolving from the original one-sided pursuit of PPA, that is, power, performance and area, to solving specific problems in a vertical field based on the integration of software and hardware, and even cloud services. The chip itself has become an important part of the whole solution, not the only one;

Secondly, end cloud interaction. In different application scenarios of the Internet of things, massive terminal devices must cooperate with the end cloud in order to realize functional intelligence, that is, to form a dynamic balance between edge computing power and cloud computing power. The proposition of end cloud interaction needs the strong support of AI chip, which further deeply affects the chip design and final delivery;

Third, data multimodality. In the 5g driven smart alliance scenario, the data dimensions contacted by the chip will change from the original simplification to diversification, and the data to be processed by the chip will also change from single mode to multi-mode, which poses new challenges to the design of the chip, especially the artificial intelligence chip of the Internet of things.

Technical layout of yunzhisheng multimodal AI chip

In order to realize the strategic landing of multimodal AI chips, yunzhisheng has accelerated the technical layout and made rapid progress in machine vision.

Among them, the lightweight image signal processor for machine vision can preprocess the sensor pictures in real time at the rate of 30 FPS without relying on external memory, so as to further improve the processing speed and effect of subsequent machine vision processing modules.

yunzhisheng lightweight image signal processor for machine vision

With the help of multimodal technology based on face information analysis, functions such as face / object recognition, expression analysis, labeling and lip movement state tracking can be realized, which can provide more playability and flexibility for product interaction and user experience.

yunzhisheng's face recognition, expression analysis and labeling technology

It is particularly worth mentioning that the release of deepnet2.0, the core IP of yunzhisheng multi-modal artificial intelligence, marks the comprehensive entry of yunzhisheng artificial intelligence processing core from the 1.0 voice era to the 2.0 multi-modal era integrating voice, image and other processing capabilities.

Deepnet2.0 is compatible with many reasoning networks such as LSTM / CNN / RNN / TDNN, and supports reconfigurable computing and Winograd processing.

According to the data released by yunzhisheng, the accuracy of deepnet2.0 based on yunzhisheng has reached 99.80% and 99.47% respectively in face recognition evaluation such as lfw2018 and megaface2018, which is close to the existing best performance.

At present, yunzhisheng deepnet2.0 has been verified on FPGA and will be launched on the new multimodal AI chip dolphin in 2019.

In addition, in terms of industry university research cooperation in image and chip technology, yunzhisheng has also reached in-depth cooperation with ASIC, the only Artificial Intelligence Computing Center of NSFC led by Duke University, and is committed to AI chip algorithm compression and quantization technology, as well as the research on non Feng's new AI chip computing architecture, which will further promote yunzhisheng's multimodal AI chip strategy Tamp the foundation.

Three chips under development are exposed and mass production will be started in 2019

Under the background that the first mass production chip Swift has been introduced by a large number of customers and occupies the first mover advantage in the market, yunzhisheng is more radical in AI chip planning in 2019. It plans to launch three AI chips and start mass production in 2019.

One is swift Lite, a lightweight Internet of things AI chip. It supports microphone matrix, lightweight voice wake-up and lightweight voice recognition.

One is a multi-modal AI chip "dolphin" for smart city. It supports camera, ISP, OD, face ID, microphone matrix, voice wake-up, offline speech recognition and synthesis, etc.

There is also a multimodal AI chip "Snow Leopard" for smart travel, in which the latter two integrate the capabilities of voice AI and visual AI at the same time.

According to the data released by yunzhisheng at the meeting, the multimodal AI chip "dolphin" will adopt the 28nm process, and the benchmark is Mobileye eq4. According to the plan, the maximum configurable computing power of yunzhisheng's "dolphin" is 4TOPS, which is 1.6 times that of eq4, and the power consumption is 4.3W, slightly higher than eq4.

In addition, according to Li Xiaohan, the multimodal car gauge AI chip leopard for smart travel scenarios is jointly built with Yikatong technology, an ecological chain enterprise of Geely Group, which also means that once the chip is successfully mass produced, it may have the opportunity to realize rapid landing commercialization with the support of Geely Group.

Summary:

At the end of 2017, baidu took the lead in announcing the free opening of its voice AI capabilities, and then iFLYTEK's iFLYTEK open platform also opened its basic capabilities for free. This also made the voice AI market extremely competitive. Against this background, many voice AI start-ups have placed their hopes on creating ecology by launching voice AI chips, so as to realize the improvement of value.

For yunzhisheng, from voice technology service providers to further expand voice AI chips to the field of visual AI, it is obviously hoped to get rid of the fierce competition in the voice AI market and share the cake of the larger visual AI market.

However, compared with the voice AI market, although the visual AI market is broader, it is also highly competitive. There are not only many unicorns such as Shangtang technology, Kuangshi technology, Yitu technology and Yuncong technology, but also old security manufacturers such as Haikang and Dahua, as well as a large number of small and medium-sized visual AI start-ups, and many visual AI manufacturers have launched or are in the process of launching In active preparation for the launch of visual AI chips / modules.

In addition, for the largest and most valuable market of visual Ai - security market, its barriers are relatively high, and it needs a long period of continuous cultivation, and this market is also the focus of everyone's competition. However, due to the different policies, preferences and requirements of local governments, this market also shows a fragmented trend. Therefore, new players rely on it

Yunzhisheng Officially Announced the New Multimodal AI Chip Strategy and Plan 1

GET IN TOUCH WITH Us
recommended articles
FAQ
Detailed Explanation of Wireless Projection Screen and Wireless Flying Screen
Detailed Explanation of Wireless Projection Screen and Wireless Flying Screen
"Wireless projection technology" is very mature today, and we will not be unfamiliar with it. Generally, the network set-top box of the family has such a function, which can mirror the image of the smartphone to the TV or projector (including the privacy displayed on your mobile phone of course). It is generally used to share mobile phone photos and videos. At present, it is also very popular in the field of conferences."Wireless flying screen technology" is often used for wireless transmission and playback of video. The TV and computer are in the same WiFi environment. The video in the computer is transmitted to the TV through WiFi through flying screen software. It is generally used for video transmission and playback in wireless network (such as video in the computer host played by TV or VR glasses)"Wireless screen shaking technology" is a multi screen interactive technology gradually popular in the field of interactive technology in recent one or two years. "Screen shaking", as the name suggests, is to interact with the screen with a "shaking" action, which can combine pictures, videos, office documents Pdf documents are thrown from one multi-point touch screen to the large screen of another or more receiving hosts through gestures by wired or wireless means, and can zoom in, zoom out, rotate and mark the content of the receiving end through the screen throwing control end. If the receiving end is a multi-point touch screen, it can also interact with the received content (zoom in, zoom out and rotate). When it is necessary to realize the interaction of multiple screens in a more cool and flexible way, then "wireless screen throwing technology" is a good choice.Suzhou mutual cloud information technology is at the domestic leading level in the field of wireless screen throwing technology, and has its unique advantages in multimedia format support, fluency, interactivity and modular combination."Multi screen live broadcasting technology" can also be called "streaming media live broadcasting technology". As the name suggests, it is to share the screen of one host to multiple clients (including host desktop, audio and video, microphone, camera and other data), and realize the synchronous live broadcasting of multiple screens through the Internet or LAN. "Multi screen live broadcasting technology" generally adopts streaming media technology to realize low bandwidth and large concurrent audio and video data transmission.At present, all major data platform operators will provide live streaming media services, but the cost is high and professional technology companies are required to use them.Suzhou mutual cloud information technology makes this service more simplified and flexible through self-developed streaming media technology. Users can build their own streaming media live broadcasting service by installing a set of streaming media live broadcasting software in less than 5 minutes.In December 2017, Suzhou mutual cloud information technology also developed China's first "OPS streaming media live host" - a multi screen live broadcasting system integrating software and hardware. The system integrates multimedia management, recording and live broadcasting functions to easily create a powerful LAN live broadcasting service, which can be applied to many application fields such as teaching, conference, exhibition, new retail, security and so on.
Detailed Explanation of Intelligent Terminal Touch Screen
Detailed Explanation of Intelligent Terminal Touch Screen
Touch screen display is not new. Long before the arrival of this wave of smart phones, you have seen touch screens on all kinds of handheld computers, mobile phones and even black-and-white screen mobile phones. But in most people's impression, the touch screen of that era always appeared together with the touch pen - you must press hard objects such as the touch pen or fingernails to input instructions. Its essence is "resistive touch screen". Until the appearance of iPhone in 2007, another kind of touch screen, "capacitive touch screen" began to appear in people's sight. However, after 4-5 years of development, the touch intelligent terminal market has become the "King banner of changes in the city", turning from resistive touch screen to capacitive touch screen. capacitive touch screenCapacitive touch screens are divided into "surface capacitive technology" and "projected capacitive technology"."Surface capacitance touch screen" only adopts single-layer it o, and the four sides of the touch screen are plated with narrow electrodes to form a low-voltage AC electric field in the conductor. Compared with the resistance type, the biggest feature of the capacitance type is that it does not need to press, and only needs to touch to input commands.As for the "projection capacitance touch screen", it can penetrate a thicker covering layer without correction. The projection capacitor can achieve the iPhone's iconic "multi touch" operation.Advantages: only touch is needed, and no pressure is needed to generate signals; It only needs to be corrected once or not at all after production; The service life is longer because the components in the capacitive touch screen do not need any movement.Disadvantages: the cost is relatively high, but with the current mainstream smart phones all choose capacitive screens, the scale increases explosively and the cost also decreases. resistive touch screenThe traditional resistive touch screen consists of five layers. The surface touched by the finger is a hard coating to protect the pet layer below (a protective material with good transparency and gas resistance). The PE t layer is a very thin and elastic PE t film. When the surface is touched, it will bend down, and make the lower two it o coatings (a nano indium tin metal oxide with good conductivity and transparency) contact each other, and connect the circuit at this point.Advantages: the technology is mature, the cost is relatively low, and the surface is not easily affected by dust, water and dirt.Disadvantages: the it o coating in the touch screen is relatively thin and easy to break. If it is too thick, it will reduce light transmission, form internal reflection and reduce clarity. The service life of this touch screen is not long, and the position correction of touch points needs to be done frequently.
A Detailed Explanation of Industrial Touch Screen Control Xpt7603
A Detailed Explanation of Industrial Touch Screen Control Xpt7603
This paper mainly introduces the industrial touch screen control xpt7603. Firstly, it introduces the principle of the industrial touch screen, secondly expounds the principle and characteristics of the resistive touch screen, and finally introduces the working principle of the xpt7603 touch screen controller. Let's follow the Xiaobian to understand it.Industrial touch screen is an intelligent interface that connects people and machines through touch industrial display. It is an intelligent operation display terminal that replaces the traditional control buttons and indicators. It can be used to set parameters, display data, monitor equipment status, and describe the automatic control process in the form of curve / animation. It is more convenient, faster and more expressive, and can be simplified into PLC control program. The powerful touch screen creates a friendly man-machine interface. As a special computer peripheral, touch screen is the most simple, convenient and natural human-computer interaction mode at present. It gives multimedia a new look and is an attractive new multimedia interactive device.2 Principle of industrial touch screenTouch screen system generally includes touch screen controller (card) and touch detection device. Among them, the main function of the touch screen controller (card) is to receive the touch information from the touch point detection device, convert it into contact coordinates and send it to the CPU. At the same time, it can receive and execute the command sent by the CPU: the touch detection device is generally installed at the front end of the display, and its main function is to detect the user's touch position and send it to the touch screen control card. The industrial touch screen has strong flexibility. It can add or add functional modules according to the design requirements, and has strong expansibility. It can meet the complex process control process, and even communicate directly with PLC through the network system, which greatly facilitates the processing and transmission of control data and reduces the amount of maintenance.3 Principle and characteristics of resistive touch screenThe screen body of the resistive touch screen is a multi-layer composite film matched with the surface of the display. A layer of glass or plexiglass is used as the base layer, and the surface is coated with a transparent conductive layer,. It is covered with an outer surface hardened, smooth and scratch resistant plastic layer. There are many small (less than one thousandth of an inch) transparent isolation points between the two conductive layers to separate them for insulation.When the finger touches the screen, the two conductive layers normally insulated from each other have a contact at the touch point. Because one of the conductive layers is connected to the 5V uniform voltage field in the y-axis direction, the voltage of the detection layer changes from zero to non-zero. After this on state is detected by the controller, conduct a / D conversion, and compare the obtained voltage value with 5V to obtain the y-axis coordinates of the touch point, Similarly, the coordinates of the X axis are obtained, which is the most basic principle common to all resistive touch screens.The key of resistive touch screen lies in material technology. According to the number of outgoing lines, the resistance screen is divided into four wire, five wire, six wire and other multi wire resistance touch screens. The resistive touch screen is coated with two layers of OTI transparent oxide metal conductive layers on the reinforced glass surface, the outermost layer of OTI coating is used as the conductor, and the second layer of OTI is attached through a precise network, with a voltage field of 5V to 0V in both horizontal and vertical directions. The two layers of OTI are separated by small transparent isolation points. When the finger contacts the screen, a contact point will appear on the two layers of OTI conductive layer. The computer detects the voltage and current at the same time and calculates the touch position. The reaction speed is 10-20 Ms.The outer conductive layer of the five wire resistance touch screen uses nickel gold coating material with good ductility. Due to frequent touch, the outer conductive layer uses nickel gold material with good ductility in order to prolong the service life, but the process cost is relatively high. Although the nickel gold conductive layer has good ductility, it can only be used as a transparent conductor and is not suitable for the working surface of the resistance touch screen, because it has high conductivity and the metal is not easy to achieve very uniform thickness, so it is not suitable to be used as a voltage distribution layer and can only be used as a probe layer.Resistive touch screen is a kind of working environment completely isolated from the outside world. It is not afraid of dust and water vapor. It can be touched by any object and can be used for writing and painting. It is more suitable for industrial control field and office. The common disadvantage of resistive touch screen is that the outer layer of composite film is made of plastic material. People who don't know too hard or touch with sharp tools may scratch the whole touch screen and lead to scrapping. However, within the limit, the scratch will only damage the outer conductive layer. The scratch of the outer conductive layer has nothing to do with the five wire resistance touch screen, but is fatal to the four wire resistance touch screen.4 Working principle of xpt7603 touch screen controllerXpt7603 is a resistive touch screen controller with a 12 bit resolution AD converter. Xpt7603 can detect the pressed screen position by performing two A / D conversion. In addition, it can also measure the pressure applied to the touch screen. Internal 2.5V reference voltage. Under the typical working state of 2.7V, turn off the reference voltage and the power consumption can be less than 0.75mw. The controller is equipped with I2C interface and can work in slave mode with the fastest conversion rateResistive touch screen has good anti-interference characteristics and application stability. It has broad application prospects in industrial production lines and even in different application environments of daily life. Touch screen will certainly play a more important role in the field of industrial control. Using xpt7603 as the controller can meet the requirements of strict reliability and service life of industrial control, and help the rapid popularization of industrial control man-machine interface (HMI) touch control.
What Is the "Happy Planet" of Contemporary Gamers? Toshiba TV Provides a "positive Solution" for Large Screen Games
What Is the "Happy Planet" of Contemporary Gamers? Toshiba TV Provides a "positive Solution" for Large Screen Games
Sit down, turn on the TV, insert the card and load. The standard configuration of bully game console TV once carried the memory of a generation of people about games. With the advancement of years and the progress of technology, the equipment for playing games is also constantly improving: from bully in the living room to game console, PC and mobile phone with different performance, each generation of game players are looking for their own "Happy Planet".Under the dual catalysis of the development of Internet technology and the popularity of cloud games, the generation Z group, which is famous for its personality, has more expectations for large screen games with TV as the carrier. On the one hand, the post-90s and post-00s, as aborigines in the Internet era, began to gain control of the living room, and the large screen is no longer a third of an acre for the elderly to watch Anti Japanese dramas and their families, Give more space to smart TV; On the other hand, compared with the narrow mobile phone screen and the isolated computer screen, the large screen in the living room is undoubtedly a more suitable game carrier. Because of this, the "hard core" strength of TV attracts more attention.Take the Toshiba rocket TV z670kf as an example. In the whole Toshiba TV product line, it is an entertainment TV tailored by Toshiba TV to meet the personalized needs of generation Z. it can be seen from its product positioning of "moving times, playing times, cool life". It uses its own REGZA painting engine, rocket sound, full ecological 120Hz, and "one touch transmission" and other black technologies in the world The performance of "big screen game" is commendable. It redefines the game TV, so that players can enjoy the professional level smooth game experience while enjoying the superior image quality experience of big screen TV.For high-performance games, it is naturally the first choice to put classic IP and 3a game masterpieces on the large screen. As we all know, contemporary 3A game masterpieces have "no highest requirements but higher requirements" for hardware. The high-profile IP "original God", "cyberpunk 2077" and "mission call" are "discouraged" because of their high requirements for hardware Many players, this is a big test for the TV display technology. Toshiba rocket TV z670kf solves this problem very well.The original God In general, the art special effects of MIHA tour are absolutely benchmark level in the industry. As a new product innovating the TV industry, z670kf's unique REGZA painting engine, mega backlight technology and super-resolution technology restore the blurred contour to be extremely fine, the picture is smooth and natural, and the crystal transparent color technology effectively improves the image contrast. In the rendering of HDR, players seem to enter the A new world of "step by step".With the blessing of Toshiba z670kf's image quality buff, players were also shocked by the Tivat continent displayed by Toshiba z670kf. Cori stood in the flowers. The flowers next to her seemed to have life and looked very beautiful. Players said frankly that "they don't want to play strange after entering the game, but just want to walk and see the scenery".In addition, Toshiba z670kf is also equipped with the current popular cloud game platform. There is no need to download a huge client. Just through its own cloud game platform, it can play classic host masterpieces such as boxing emperor 14 and soul waiting dawn without burden.2 As low as 50Hz rocket sound, advanced immersive experienceIn the moment of focusing on immersive experience, in addition to seeing six ways, the enjoyment of hearing is naturally one of the indispensable and important factors. However, for a long time, the TV "hard index" of sound quality has been ignored to a certain extent, and Toshiba z670kf has realized a new definition of game experience with rocket sound.Take the game masterpiece "Final Fantasy 15" in Migu express as an example, the soundtrack of this series of games has always been a classic in the hearts of game players, from the first generation of Castle Cornelia to the 15th generation of prologue , all give users a different auditory experience. With the super bass of Toshiba rocket TV as low as 50Hz and the power of original sound restoration black technology, the player's ears can be "pregnant".3 Full ecological 120Hz, ultra-low delay, don't miss every frameWhen playing games on a large screen, the first appeal is to "play games well!" the picture is smooth, no jam and no afterimage, which has become one of the hard indicators.The refresh rate of most TVs in the industry still stays at the 60Hz standard, while the Toshiba rocket TV z670kf adopts a high refresh rate of 120 frames per second, the picture is smooth, refresh your understanding of fluency, VRR variable dynamic refresh rate, and the picture is stable, just like when dialing comic books, 120 pieces per second must be more smooth than 60 pieces, and the most intuitive is undoubtedly playing games Play and watch super clear blockbusters bring a smoother and smoother feeling.It is worth mentioning that the Toshiba rocket z670kf supports the full ecological 120Hz of content input and decoding output.In addition to cloud games, Toshiba z670kf has broken the hearts of players on the screen. The screen projection function of smart TV is not new, but after a series of screen projection steps such as querying strategy, downloading app and checking the network, there has long been no interest in playing games. In contrast, Toshiba z670kf is equipped with "one touch transmission" Black technology is a little white. There is no need to download any app in the whole operation process. Only the mobile phone gently touches the random NFC tag, and the mobile phone content can be easily put on the large screen. The whole process takes only two seconds. Even mobile phones that do not support NFC can realize fast screen projection through wireless screen projection.In fact, compared with the single performance of traditional hosts and PCs, consumers are choosing a "comprehensive audio-visual solution" in a sense. Image quality, sound, refresh rate, game IP adaptation and AI intelligence are all "hard qualities" to be investigated , only if you pass the quality test can you meet the entertainment needs for many years in the future. Toshiba z670kf has excellent screen quality, which can create an immersive effect, so that you can observe the game scene in an all-round way and battle easily.
Mixed Emotions in Wisconsin Town Foxconn Picked for Plant
Mixed Emotions in Wisconsin Town Foxconn Picked for Plant
RACINE, Wis. - Residents of the southeastern Wisconsin town where Foxconn Technology Group plans a massive display screen plant greeted the announcement with excitement about the possible economic boost and wistfulness about how the community's changing landscape.Foxconn announced the location of its planned factory after months of negotiations with the company and the village of Mount Pleasant in Racine County. The company has said it intends to build a campus with about 20 million square feet of office space over 1.56 square miles, eventually employing as many as 13,000 people to manufacture liquid crystal display screens used on phones, televisions, computers and other devices.Tammy Graceffa, 54, the owner of the Hiawatha Bar and Grill just south of the plant's expected location, said the influx of workers and her land's possible purchase could bring her financial gains. But still, she found the moment bittersweet."Where we grew up and were raised will no longer be farm fields. It will be concrete and industry," she said. "You can't go back and say, 'This is the road where we used to play ball.'"The Wisconsin legislature approved a $3 billion incentive package for Foxconn - contingent on the company fulfilling its jobs promise, and the state's economic development agency is working on the final contract. The intended industrial complex would be the largest in the state."I think it's going to be really good. The economy ought to pick its way up around here. It's been dragging a little here in Racine (County)," said Michael Rosenbaum, a village trustee in the town of Sturtevant, just a few miles from Mount Pleasant.Rosenbaum said he understands there are landowners who are unhappy about being displaced, but hopes Foxconn will "make sure that they get a decent deal.""You can have another dream home. That's my feeling," he said.But some landowners said they felt like they didn't have much choice."It's the Foxconn train. Get on or get run over," said Katie Spencer, 27.Gonzalo Perez, meanwhile, is already brainstorming ways to get more people to his restaurant, the House of Castlewood. The 50-year-old Mexican immigrant who bought the diner in December said he's toying with the idea of having a buffet so when the future workers come they can come in and out quicker.His restaurant is in Sturtevant but it's just across the highway from the planned factory."This is like something of a miracle happening here because nobody expected that kind of business would come to a small town like Sturtevant," he said.The Associated Press
Guangxiang Technology Rushes to the Gem and Plans to Raise 630 Million Yuan to Expand the Production Capacity of LED Display Screen
Guangxiang Technology Rushes to the Gem and Plans to Raise 630 Million Yuan to Expand the Production Capacity of LED Display Screen
Following xinruida, recently, two related enterprises in the LED industry plan to be listed on the gem. According to the CSRC, the gem IPO of Shenzhen Guangxiang Technology Co., Ltd. (hereinafter referred to as "Guangxiang technology") has entered the sprint stage, and the listing guidance of Shenzhen Ming Microelectronics Co., Ltd. (hereinafter referred to as "Ming microelectronics") has been completed.Founded in 2006, Guangxiang technology is headquartered in Shenzhen and has offices in Beijing, Shanghai and other cities. It is mainly engaged in indoor and outdoor full-color LED display screens and rental screens. At present, Guangxiang technology has a wholly-owned subsidiary, HK gloss limited , Guangxiang Hong Kong wholly controls glossine USA Inc and glossine B.V. the prospectus shows that Guangxiang technology plans to issue no more than 16.0875 million shares to the public, and no less than 25% of the total share capital of the company after this offering. This offering will raise 631 million yuan to invest in LED display expansion and other projects. In 2017, 2018 and 2019, Guangxiang technology achieved revenue of 589 million yuan and 7.7 million yuan respectively The net profit was 39.45 million yuan, 42.47 million yuan and 108 million yuan respectively. The revenue and net profit increased year by year. Among them, the sales revenue of LED display screen accounted for more than 98% in each year. In addition, the proportion of overseas sales in the company's main business revenue in each year was 37.20%, 43.36% and 44.49% respectively.According to the different pixel spacing of LED display screen, Guangxiang technology divides the display screen products into four categories: below P3, P3-P4, p4-p5 and above P5. At present, the company has built 6 LED display screen assembly lines.The raised funds will be used for 80000 square meters of mobile LED display expansion project, R & D and experimental center construction project, mobile LED display marketing network construction project and supplementary working capital project. Among them, 80000 square meters of mobile LED display production capacity will be added after the 80000 square meters of mobile LED display expansion project is completed. In addition, through the mobile LED display marketing network For the project, Guangxiang technology will establish media operation centers integrating office, exhibition, storage and after-sales in overseas countries or regions such as the East Bank of the United States, the West Bank of the United States, Italy, the Netherlands, the Middle East, South Korea, India and South Africa, as well as domestic cities such as Beijing, Shanghai, Wuhan and Chongqing.According to Guangxiang technology, all the investment projects of the raised funds belong to or serve the company's main business. The main purpose of the implementation of the raised investment project is to consolidate and expand the company's current main business, further expand the company's market share in the field of LED display screen and consolidate the advantageous position in the industry. Guangxiang technology said that in the future, the company will further break through small spacing, mini / micro led and different technologies For technical difficulties such as screen, expand production capacity, improve the automation and intelligence level of the production base, further optimize the production process and consolidate the advantageous position of the industry. At the same time, the company will expand the business model by virtue of the accumulated industry reputation and customer resource channel advantages. On the one hand, the company will horizontally broaden the product lines such as lighting and sound, and provide one-stop performance equipment and technical services; on the other hand We will vertically extend the industrial chain, carry out leasing services, establish regional media operation centers at home and abroad, promote and shape brand image, and reserve mobile LED display resources. On this basis, we will further meet the needs of customers in the field of culture and media, and establish a service network covering areas with intensive cultural and sports activities all over the world.Ming microelectronics has made a three-time sprint to the capital market, and the listing guidance has been completedMing microelectronics was founded in 2003, focusing on the research and development of power management, LED lighting and LED display driver chips. According to the counseling filing report, CSC securities and Ming microelectronics signed an agreement on January 15, 2020 Guidance agreement between Shenzhen Ming Microelectronics Co., Ltd. and CSC Securities Co., Ltd. on the initial public offering and listing of Shenzhen Ming Microelectronics Co., Ltd , submitted the counseling filing materials to Shenzhen regulatory bureau on January 17, 2020. On January 21, 2020, Shenzhen Regulatory Bureau officially accepted the counseling filing application. Up to now, the scheduled work plan has been completed. According to ledinside's previous reports, Ming microelectronics has sprint into the capital market twice, this is the third time. On January 12, 2011, Ming microelectronics officially accepted Guoxin Guidance on the listing of securities; on February 16, 2012, the CSRC announced that Ming microelectronics had terminated the review. The reason given by Ming microelectronics was that the performance in 2011 did not meet expectations and the market was not optimistic, so the company voluntarily withdrew its listing application. In June 2017, Ming microelectronics launched an IPO for the second time and planned to raise 457 million yuan to invest in the R & D and industrialization of a new generation of LED display driver chips , intelligent lighting processor R & D, industrialization and integrated circuit packaging projects. However, in February 2018, Ming microelectronics was approved for the second IPO.Ledinside viewLedinside believes that the new display is one of the main development directions of LED in the future. At present, it is only in its infancy. Guangxiang technology and Ming microelectronics are related enterprises. Guangxiang technology directly produces LED display products, while Ming microelectronics has also worked in the field of display driven IC for a long time and has a certain market position, which is one of the key development directions in the future. From the perspective of the industry, the two are The development directions of the companies are more in line with the development trend of the industry, and the market prospect is expected.
Detailed Explanation of Definition, Characteristics and Development Prospect of Cob Display Screen
Detailed Explanation of Definition, Characteristics and Development Prospect of Cob Display Screen
Following Lehman's announcement of the third generation cob display on July 7 this month, recently, a message that dehuorunda led the market to develop a full flip RGB cob display module has become the focus of the industry. This is the third generation cob display technology released by Lehman on July 7. Cob display has once again successfully caught people's attention.In less than a month, led listed companies successively revealed the latest information of cob display, which is really rare. This is like letting the cob display screen, which has always had a low sense of existence, suddenly stand under the magnesium lamp and become the object of attention.Development history of cob displayCob packaging technology began to enter the field of LED display as early as around 2010. Previously, it was only widely used in the field of lighting. Compared with the display screen of traditional surface pasting technology, cob display screen has many advantages, such as high reliability, low cost, easy realization of small spacing, large viewing angle luminescence, wear and impact resistance, easy cleaning, strong heat dissipation capacity, etc. However, after several years of development, cob display screen has not been effectively solved in technical and process problems such as ink consistency, yield, after-sales maintenance, etc, As a result, cob display can not break through the bottleneck of mass production.The restriction of technology and technology, coupled with the low participation of enterprises, is the root cause of the early birth of cob display screen, but it has been unable to develop rapidly. With the demand of LED display for high-definition display, the technology, process and cost of small spacing LED display realized by surface paste technology are facing great pressure in the process of moving towards higher definition. As an alternative to the micro LED technology route of LED display, cob display naturally began to attract the attention of display enterprises and become another possibility for the development of small spacing LED display. Therefore, in recent years, more and more LED display enterprises have invested in the research and development of cob display technology. In addition to listed companies such as Lehman and dehuorunda, emerging companies such as jingtaixing optoelectronics are working on cob display technology in the industry.At present, cob display enterprises represented by HIDA electronics have brought cob display into the P1.0 era, and cob display will move towards smaller spacing in the future. In order to overcome the existing technical problems and mass production bottlenecks of cob display, enterprises engaged in cob display R & D in the industry have spared no effort.Dehao Runda's new cob display technologyIt is reported that through the resource integration of its business division and the joint research and development of the two business divisions of devices and display, Dehao Runda has successfully produced a full flip RGB encapsulated cob display module. The p0.95mm with a very small spacing and the large angle light shock experience of 180 have successfully crossed the technical problem of the current formal cob display. At present, Dehao Runda has mass produced a single display module of 171 * 76mm, which can complete a 27.5-inch full flip RGB cob display through seamless splicing. While the pixel spacing reaches p0.95, it also provides a perfect specification of 1200nits with high brightness. By making the single pixel size as small as 0.025mm2, the proportion of black optics in the display screen is greatly increased to 98%.De haorunda's flip RGB cob display adopts different technical routes. Moreover, de haorunda's full flip RGB cob experiment progress in the R & D stage has successfully completed the p0.5 ultra dense display module template. Once cob display overcomes the current bottleneck restricting mass production, the LED display industry may usher in a new situation in the future.Cob display market prospectAt present, in the field of small spacing, the competition among LED display enterprises is very fierce. Although there is a threshold for small spacing, as long as human and material resources are invested in technology, driven by funds, they can always enter this market. We can also see this from the fact that more and more display enterprises are pouring into the small spacing market. When the major display enterprises scramble to compete for the small space market, it is bound to have an impact on the industry and bring profit impact to the display enterprises. In today's small spacing market, compared with previous years, the price has fallen sharply, and the price war is beginning to take shape.However, in the cob display market, because there are few manufacturers with cob display technology in the industry, the previous enterprises that touch and roll in the field of cob display have won the first opportunity and have the first mover advantage in intellectual property rights. For example, Lehman's innovation in cob small spacing LED display technology also protects the research results of these cob small spacing display technologies through patent application. So far, Lehman has applied for more than ten patents related to cob display technology, among which patents such as an LED display screen, LED packaging method, manufacturing method of circuit board and display screen have been authorized by the State Intellectual Property Office.When latecomers enter this field, they are bound to be unable to bypass the factor of intellectual property rights. The later you enter, the more sharp your teeth will be. However, latecomers also have the advantage of late development. When the road ahead is blocked, enterprises will find another way like Dehao Runda, so as to speed up the solution of cob problems.As more and more display enterprises join the R & D and production of cob display, we believe that it is only a matter of time before cob display develops rapidly. It is expected that cob may develop rapidly like small spacing in the next three to five years. Whether cob display can become another leader in the development of LED display industry remains to be seen!
Explanation of Common Terms of LED Display Screen
Explanation of Common Terms of LED Display Screen
1. LED brightnessThe brightness of LED is generally expressed by luminous intensity, and the unit is candela CD; 1000ucd (micro candela) = 1 MCD (millicandela), 1000mcd = 1 CD. The light intensity of a single LED for indoor use is generally 500ucd-50 MCD, while the light intensity of a single LED for outdoor use is generally 100 mcd-1000 MCD, or even more than 1000 MCD.2. LED pixel moduleThe LEDs are arranged into a matrix or pen segment and prefabricated into standard size modules. 8 * 8 pixel module and 8-character 7-segment digital module are commonly used for indoor display screen. The outdoor display pixel module has 4 * 4, 8 * 8, 8 * 16 pixels and other specifications. The pixel module for outdoor display screen is also called collecting tube bundle module because each pixel is composed of more than two LED tube bundles.3. Pixel and pixel diameterEach LED light emitting unit (point) in the LED display screen that can be individually controlled is called a pixel (or pixel). Pixel diameter refers to the diameter of each pixel, in millimeters. For indoor display screen, generally one is a single LED with a circular shape. There are 3.0, 3.75, 5.0, 8.0 and so on, among which 3.75 and 5.0 are the most common. In the outdoor environment, in order to improve the brightness and increase the sight distance, one pixel contains more than two cluster LEDs; Since more than two cluster LEDs are generally not circular, the pixel diameter of solid outdoor display screen is generally expressed by the average distance between two pixels: 10, 11.5, 16, 22, 25.4. Point spacing, pixel density and information capacityCenter distance or dot pitch of two pixels of LED display screen; The number of pixels per unit area is called pixel density; The amount of display content per unit area is called information capacity. The essence of the three is to describe the same concept: the point spacing reflects the pixel density from the distance between two pixels, and the point spacing and pixel density are the physical properties of the display screen; Information capacity is the unit of information carrying capacity of pixel density. The smaller the point spacing, the higher the pixel density, the more information capacity, and the closer the distance suitable for viewing. The larger the point spacing, the lower the pixel density, the less the information capacity, and the farther the distance suitable for viewing.5. ResolutionThe number of rows and rows of LED display pixels is called the resolution of LED display. Resolution is the total number of pixels of a display screen, which determines the information capacity of a display screen.6. LED panelThe LED pixel modules are assembled and arranged into a matrix according to the actual size, and equipped with special display driving circuit, DC regulated power supply, software, frame and external decoration to form an LED display screen.7. GrayscaleGrayscale refers to the degree of light and shade change of pixels. The grayscale of a primary color generally has 8 levels to 1024 levels. For example, if the gray level of each primary color is 256, the display color of the dual primary color screen is 256 256 = 64K color, also known as 256 color display screen.8. BicolorNowadays, most color LED displays are dual primary color screens, that is, each pixel has two LED tube cores: one is red tube core and the other is green tube core. When the red light tube core is on, the pixel is red, when the green light tube core is on, the pixel is green, and when the red and green tube cores are on at the same time, the pixel is yellow. Red and green are called primary colors.9. Full colorRed green double primary color plus blue primary color, three primary colors constitute full color. Because the blue tube and pure green tube core constituting full-color are more expensive, there are relatively few full-color screens at present.
Detailed Explanation of Common Wireless Control Inventory of LED Display Screen You Don't Know
Detailed Explanation of Common Wireless Control Inventory of LED Display Screen You Don't Know
LED display screen is the perfect combination of science and technology and media. It can fully display the ideas of dream, science and technology, trend and fashion. It can fully become a new force of dance beauty. New indoor large-scale screens and outdoor advertising forms continue to appear, from traditional LED billboards to monochrome character screens to today's full-color LED display screens. With the development of LED industry, outdoor media advertising has become more and more fashionable. At present, most KTV bars and hotels are equipped with indoor HD display screens, and outdoor LED display screens have occupied 80% of the field of outdoor media advertising, becoming a new carrier of large-scale outdoor media advertising. Let's take stock of several common wireless control LED display modes.Common wireless control inventory of LED display screen you don't knowWorking principle: one end of the RF module is connected to the control computer and the other end is connected to the serial port of the control card. After installing the driver, the computer generates a virtual serial port and sends data through this serial port.Features: easy installation and debugging, data transmission distance up to 300-1000m, no cost for later use.Required equipment and price: RF transmitting and receiving module, about 350 yuan a pair. Support one to many sending, that is, one sending module to multiple receiving modules.Disadvantages: there are not many radio frequency bands allowed for civil use by the state. The batch of 433MHz is extremely vulnerable to signal interference, and the transmission rate in this way is not very low. The baud rate can only be 4800 or 9600, which is not recommended.Working principle: by adding a wireless router or other wireless equipment, bridge with the user's original wireless network, build a wireless LAN, and easily integrate the network control card into the wireless network for wireless network control.Features: no wiring, convenient installation and debugging, fast data transmission speed.Required equipment and price: bridge, within 800 yuan; Wireless router (it is better to select the equipment with changeable antenna for application on the display screen, so as to effectively receive the wireless signal), the price is about 100 yuanDisadvantages: the communication distance mainly depends on the gain capacity of the bridge. The communication distance of wireless route is relatively short, and the partition signal is relatively weak or no signal. It is suitable for places with wireless signals in short distance. If there is wireless signal coverage in the area where your display screen is located, it is even simpler. Just bridge the wireless router connected to the control card in the display screen to your wireless network, and you can control the display screen on any computer in the intranet.Working principle: after the GPRS module is powered on, it completes the process of dial-up Internet access and connects to the data center server. The customer accesses the server through the client software, and the server forwards information.Features: convenient installation and debugging, no distance limit, as long as there is a mobile phone signal, you can receive information, and the price is relatively cheap, generally in the range of 200 400 yuan.Disadvantages: GPRS module needs to install a mobile phone card to dial up internet access, which will generate a certain traffic fee every month (for example, China Mobile's minimum traffic package of 5 yuan can meet the demand). Due to the limitation of GPRS bandwidth, the transmission rate is slightly slow, so it is more suitable for LED display screen with single and dual color and mainly playing text.Working principle: the 3G module is also connected to the data center server through the wireless network. The customer directly logs in to the global simulcast cloud platform to publish programs, and the server directly sends them to the control card.Features: the WCDMA signal is stable, and there is basically no data loss in the process of program transmission. Compared with GPRS, the speed is faster. It can transmit pictures or videos, which is more suitable for full-color screen.Disadvantages: the signal coverage of China Unicom is not as high as that of China Mobile, and there may be no networking in some remote areas.Working principle: basically the same as 3G / GPRS.Features: 4G all Netcom (supported by China Mobile, China Unicom and China Telecom), with fast transmission rate, complete real-time control, and instant response to relevant control when sending instructions.Disadvantages: when the amount of data sent is relatively large, the traffic cost is relatively large. It is recommended to open the traffic package.
Detailed Explanation of Docker's Five Storage Driving Principles
Detailed Explanation of Docker's Five Storage Driving Principles
Docker first adopted aufs as the file system. Thanks to the concept of aufs layering, multiple containers can share the same image. However, aufs is not incorporated into the Linux kernel and only supports Ubuntu. In consideration of compatibility, storage drivers are introduced into docker version 0.7. At present, docker supports five storage drivers: aufs, Btrfs, device mapper, overlayfs and ZFS. As stated on docker's official website, there is no single driver suitable for all application scenarios. Only by selecting the appropriate storage driver according to different scenarios can docker's performance be effectively improved. How to select a suitable storage driver needs to understand the storage driver principle before making a better judgment. This paper introduces the detailed explanation of the five storage driver principles of docker and the comparison of application scenarios and IO performance tests. Before talking about the principle, let's talk about the two technologies of write time replication and write time allocation.Copy on write (cow)The technology used by all drivers - copy on write (cow). Cow is copy on write, which means to copy only when writing is needed. This is a modification scenario for existing files. For example, if multiple containers are started based on an image, if each container is allocated a file system with the same image, it will occupy a lot of disk space. Cow technology allows all containers to share the file system of the image, and all data is read from the image. Only when the file is to be written, the file to be written is copied from the image to its own file system for modification. Therefore, no matter how many containers share the same image, the write operation is performed on the replica copied from the image to their own file system, and the source file of the image will not be modified. If multiple containers operate on the same file, a replica will be generated in the file system of each container. What each container modifies is its own replica and isolated from each other, They don't affect each other. Using cow can effectively improve disk utilization.Allocate on demandWrite time allocation is used in scenarios where there is no such file. Space is allocated only when a new file is to be written, which can improve the utilization of storage resources. For example, starting a container does not pre allocate some disk space for the container, but allocates new space as needed when a new file is written.AUFSAufs (another union FS) is a union FS, which is a file level storage driver. Aufs can transparently cover the layered file system of one or more existing file systems, and merge multiple layers into a single-layer representation of the file system. Simply put, it supports mounting different directories to the file system under the same virtual file system. This file system can overlay and modify files layer by layer. No matter how many layers below are read-only, only the top file system is writable. When a file needs to be modified, aufs creates a copy of the file, uses cow to copy the file from the read-only layer to the writable layer for modification, and the results are also saved in the writable layer. In docker, the lower read-only layer is image, and the writable layer is container. The structure is shown in the figure below:OverlayOverlay is supported by Linux kernel after 3.18. It is also a kind of union FS. Unlike aufs, overlay has only two layers: an upper file system and a lower file system, representing the image layer and container layer of docker respectively. When a file needs to be modified, use cow to copy the file from the read-only lower to the writable upper for modification, and the results are also saved in the lower layer. In docker, the lower read-only layer is image, and the writable layer is container. The structure is shown in the figure below:Device mapperDevice mapper is supported by Linux kernel after 2.6.9. It provides a mapping framework mechanism from logical devices to physical devices. Under this mechanism, users can easily formulate and implement storage resource management strategies according to their own needs. Aufs and overlayfs mentioned earlier are file level storage, while device mapper is block level storage. All operations are direct operations on blocks, not files. The device mapper driver will first create a resource pool on the block device, and then create a basic device with a file system on the resource pool. All images are snapshots of the basic device, and the container is a snapshot of the image. Therefore, the file system in the container is a snapshot of the file system of the basic device in the resource pool, and there is no space allocated for the container. When a new file is to be written, a new block is allocated in the container's image and data is written. This is called time allocation. When you want to modify an existing file, use cow to allocate block space for the container snapshot, copy the data to be modified to a new block in the container snapshot, and then modify it. The device mapper driver will create a 100g file by default, including images and containers. Each container is limited to 10g volumes and can be configured and adjusted by itself. The structure is shown in the figure below:BtrfsBtrfs is called the next generation write time copy file system and incorporated into the Linux kernel. It is also a file level storage, but it can directly operate the underlying device like device mapper. Btrfs configures a part of the file system as a complete sub file system, which is called subvolume. With subvolume, a large file system can be divided into multiple sub file systems. These sub file systems share the underlying device space and allocate it from the underlying device when disk space is needed, just like an application calling malloc () to allocate memory. In order to make flexible use of the device space, Btrfs divides the disk space into multiple chunks. Each chunk can use different disk space allocation policies. For example, some chunks only store metadata, and some chunks only store data. This model has many advantages. For example, Btrfs supports dynamic addition of devices. After adding a new disk to the system, you can use the Btrfs command to add the device to the file system. Btrfs regards a large file system as a resource pool and configures it into multiple complete sub file systems. It can also add new sub file systems to the resource pool. The basic image is the snapshot of the sub file system. Each sub image and container has its own snapshot, and these snapshots are the snapshots of subvolume.When a new file is written, a new data block is allocated in the snapshot of the container. The file is written in this space, which is called time allocation. When you want to modify an existing file, use cow copy to allocate a new original data and snapshot, change the data in the newly allocated space, and then update the relevant data structure to point to the new sub file system and snapshot. The original original data and snapshot have no pointer and are overwritten.ZFSZFS file system is a revolutionary new file system. It fundamentally changes the management mode of file system. ZFS completely abandons "volume management" and no longer creates virtual volumes. Instead, it centralizes all devices into one storage pool for management and uses the concept of "storage pool" to manage physical storage space. In the past, file systems were built on physical devices. In order to manage these physical devices and provide redundancy for data, the concept of "volume management" provides a single device image. ZFS is created on a virtual storage pool called "zpools". Each storage pool consists of several virtual devices (vdevs). These virtual devices can be raw disks, a RAID1 mirror device, or multi disk groups with non-standard RAID levels. The file system on zpool can then use the total storage capacity of these virtual devices.Let's take a look at the use of ZFS in docker. First, a ZFS file system is allocated from zpool to the basic layer of the image, while other image layers are clones of the ZFS file system snapshot. The snapshot is read-only and the clone is writable. When the container is started, a writable layer is generated at the top level of the image. As shown in the figure below:When you want to write a new file, use on-demand allocation. A new data is quickly generated from zpool, the new data is written to this block, and the new space is stored in the container (ZFS clone).When you want to modify an existing file, use copy on write to allocate a new space and copy the original data to the new space to complete the modification.AUFS VS OverlayBoth aufs and overlay are federated file systems, but aufs has multiple layers, while overlay has only two layers. Therefore, when copying on write, if the file is large and there are lower layers, Ausf may be slower. Moreover, overlay is incorporated into the Linux kernel mainline, and aufs does not, so it may be faster than aufs. However, overlay is still too young and should be used cautiously in production. As the first storage driver of docker, aufs has a long history, is relatively stable, has been practiced in a large number of production, and has strong community support. Currently, open source DC / OS specifies to use overlay.Overlay VS Device mapperOverlay is a file level storage and device mapper is a block level storage. When a file is very large and the modified content is very small, overlay will copy the whole file regardless of the modified content size. Modifying and displaying a large file takes more time than a small file, while block level only copies the blocks that need to be modified, not the whole file, In this scenario, device mapper is obviously faster. Because the block level directly accesses the logical disk, it is suitable for IO intensive scenarios. The performance of overlay is relatively stronger in the scenario of complex internal program, large concurrency but less io.Device mapper VS Btrfs Driver VS ZFSBoth device mapper and Btrfs operate directly on blocks and do not support shared storage, which means that when multiple containers read the same file, they need to live multiple copies, so this storage driver is not suitable for use on the PAAS platform of high-density containers. Moreover, when many containers are started and stopped, it may lead to disk overflow and make the host unable to work. Device mapper is not recommended for use in production. Btrfs can be very efficient in docker build.ZFS was originally designed for salaris servers with a large amount of memory. It will affect the memory when used. It is suitable for environments with large memory. ZFS cow makes the fragmentation problem more serious. For large files generated by sequential writing, if some of them are randomly changed in the future, the physical address of the file on the hard disk will no longer be continuous, and the performance of sequential reading will become poor in the future. ZFS supports multiple containers to share a cache block, which is suitable for PAAS and high-density user scenarios.Test tool: iozone (a benchmark tool for file systems, which can test the read and write performance of file systems in different operating systems).Test scenario: sequential and random IO performance from 4K to 1g files.Test method: start the container based on different storage drivers, install iozone in the container, and execute the command:.Definition and interpretation of test itemsWrite: tests the performance of writing to a new file.Re write: test the performance of writing to an existing file.Read: test the performance of reading an existing file.Re read: test the validity of reading a recently read file
no data
Contact US

    Bao’an District  Shenzhen City, China

     +86 189 3806 5764

NEWSLETTER SUBSCRIBE
no data
Copyright © 2021 CrowBerry

   

chat online
NEED HELP? WE'RE HERE!