There is still a certain gap between these domestic enterprises and Nvidia in terms of technology research and development, product lines, market share and so on. For example, Jingjiawei's GPU products are mainly used in the military field, while Biren Technology has launched GPU products for the general computing market, but it still needs to be further improved in terms of ecological construction and market recognition.
Yes, GPU graphics card chips can not only be used for games, 3D rendering, and now AI acceleration is also more and more in need of high-performance Gpus, this field is also the key to domestic catch-up, which Jingjia Micro company's GPU chip released in 2021 has seen itGTX 1050, the company has now also confirmed a new graphics chip.
For comparison, NVIDIA's GeForceGTX1050, which also uses the 14nm process, has a pixel fill rate of 343GPixels/s, a floating-point performance of 733TFlops, and a power consumption of 75W. However, the GTX1050 graphics card was launched in 2016, and Jingjiawei's domestic GPU is more than 5 years behind, and the benefit is that the power consumption is more than half.
Deep technical background and management team JingJiawei's management team comes from National University of Defense TechnologyThis gives the company a deep military electronics industry background and a solid technical foundation. From the successful development of the M9 chip project to the choice of independent research and development of GPU, all reflect the company's pursuit of technological independence and insight into the future of the industry.
Zhongke Shuguang has launched many GPU products, including Kunpeng series, FeiTeng series and Matrix series, etc., with very strong computing power. The GPU products launched by Jingjiawei mainly include JC9200, JC9310 and JC9270 series, but the GPU products of Zhongke Dawning are more powerful in terms of computing powerWhat can be done? '> What Can Nvidia Gpus do?
1, GPU is specialized for processing images and graphics processors, for tasks requiring large-scale parallel processing (such as 3D rendering, video editing, deep learning, etc.), GPU processing power far exceeds the traditional central processing unit (CPU). The Gpus produced by Nvidia are widely used in gaming, film production, scientific computing, artificial intelligence and other fields. In the field of gaming, Nvidia's Gpus are loved by the majority of players for their powerful performance and compatibility.
2, through its CUDA platform, UKVidia enables Gpus to be used for general-purpose computing, accelerating large-scale data processing and simulation in fields such as science, engineering and finance. In addition, Nvidia's Gpus also excel in the field of deep learning, becoming an important tool for training and deploying neural networks. This transformation of Nvidia has transformed it from a hardware company focused on graphics processing into a technology giant with significant influence in multiple computing areas.
3, therefore, NVIDIA's Gpus are also widely used in data centers, autonomous vehicles, medical image analysis and other fields. For example, in medical image analysisWith NVIDIA's Gpus, doctors can process and analyze large amounts of medical image data more quickly, improving diagnostic accuracy and efficiency.
4, A100 graphics card belongs to high-end computing and data center level GPU (graphics processing unit) grade. It is a professional-grade graphics card from NVIDIA for high-performance computing workloads such as deep learning, machine learning, scientific computing, and large-scale data processing. The A100 uses NVIDIA's Ampere architecture and has excellent computing performance, a high degree of parallel processing, and a large memory footprintYes.
This behavior will affect the normal science and technology research and development of domestic science and technology enterprisesIt may even affect the actual progress of cutting-edge technology. Strictly speaking, the United States does not restrict the export of only two chips, but restricts the high-end chips of Nvidia and AMD.
For the global chip market, almost all chips need to be supplied by Nvidia and AMD. In this case, if Nvidia and AMD stop exporting high-end chips to China, it basically means that the middle and high-end areas of many of our industries will be affected accordingly, and our domestic GPU chips will be difficult to achieve technical blockade in a short time. Nvidia CorporationAnd AMD stopped exporting high-end chips to China.
The United States has asked AMD and Nvidia to cut off chip supplies to China. This is a sensational news in the chip industry, because the United States requires AMD and Nvidia to cut off the supply of high-end chips to China, so this matter has directly led to a corresponding negative impact on many industries in China.
1, the release time of the liquid-cooled version of Nvidia B100 has not been officially announced. However, we can learn from Nvidia'sEstimate a possible release window from the perspective of product launch strategies, market trends, and technology developments. As the world's leading graphics processor (GPU) manufacturer, Nvidia's product releases are often closely related to the maturity of the technology and market demand.
2. The NVIDIA B100 is manufactured by TSMC. Nvidia, as the world's well-known graphics processor and artificial intelligence chip manufacturer, its product line has been concerned. As an important chip launched by Nvidia, the B100's manufacturing process has naturally attracted a lot of attention. In the semiconductor industry, many companies will choose to chipManufacturing is outsourced to specialized foundries, and Nvidia has adopted this strategy for the manufacture of the B100. 3. Finally, it's worth mentioning that while Nvidia may rely on some external supply chain partners in the production process, such as suppliers that provide raw materials or specific parts, these are not part of the core of the B100. The core of the B100, its GPU chip and related technology, is entirely designed and controlled by Nvidia itself. Therefore, combining the above points, we can conclude that the core supplier of Nvidia B100 is Nvidia itself.
In summary, it is reasonable for Nvidia, as the designer and intellectual property holder of the B100, to be considered a core supplier of the B100. Although Nvidia may outsource some production, this does not change its core position in the B100 product.1, A100 series is a calculation acceleration displayCard, this series of products for the data center high-performance computer launched for the artificial intelligence science industry and other computing products The GPU chip code is GA100, the core area of 826 square millimeters, with 54 billion transistors, the new maximum equipped with 80GB video memory, using HBM2.
2, chip models and features Nvidia Navi and GA series, stream processor units (SP) are different. Core frequency and manufacturing process: concentrated in 5-8 nm, affecting performance. Graphics card basic parameters Graphics card type: divided into fever levelMainstream and entry-level to meet different needs. Physical size: the weight of the board is about 1500g, and the size is affected by the baffle.
3, "It is Nvidia's most successful product". Huang further introduced that Blackwell has 208 billion transistors, more than double the 80 billion transistors of the previous generation chip "Hopper", and can support AI models with up to 10 trillion parameters. "It will be the cornerstone of new computers and other products deployed by the world's largest data center operators, including Amazon, Microsoft, Google and Oracle." The first paragraph adopts BlThe ackwell chip is called GB200.
4, nvidia graphics card has two series, respectively: GeForce (referred to as GF series), Legacy (referred to as LG series, this series of graphics card is relatively rare). GF series is divided into mobile graphics and desktop video card, including notebook graphics series have a GF 900 m, 800 m GF, GF 700 m, 600 m GF, GF 500 m, 400 m GF, GF 300 m, 200 m, 100 m GF GF,GF 8M, GF GO 7M. 5, Nvidia graphics card has two series, GeForce (referred to as GF series) and Legative (LG series), GF series is divided into notebook graphics card and desktop graphics card, this type of graphics card is for public home users, mainly used for entertainment purposes, compared to professional cards, GF is relatively cheap.