Computing power and architecture

The types of chips that provide computing power for AI include GPU, FPGA and ASIC

GPU is a kind of microprocessor specialized in image operation on personal computers, workstations, game machines and some mobile devices (such as tablet computers, smart phones, etc.). It is similar to Cu, except that GPU is designed to perform complex mathematical and geometric calculations, which are necessary for graphics rendering

FPGA can complete any digital device function chip, even high-performance CPU can be implemented with FPGA. In 2015, Intel acquired the FPGA long alter head with us $16.1 billion. One of its purposes is to focus on the development of FPGA's special computing power in the field of artificial intelligence in the future

ASIC refers to the integrated circuits designed and manufactured according to the requirements of specific users or the needs of specific electronic systems. Strictly speaking, ASIC is a special chip, which is different from the traditional general chip. It's a chip specially designed for a specific need. The TPU that Google recently exposed for AI deep learning computing is also an ASIC

extended data:

chips are also called integrated circuits. According to different functions, they can be divided into many kinds, including those responsible for power supply voltage output control, audio and video processing, and complex operation processing. The algorithm can only run with the help of chips, and because each chip has different computing power in different scenarios, the processing speed and energy consumption of the algorithm are also different. Today, with the rapid development of the artificial intelligence market, people are looking for chips that can make the deep learning algorithm perform faster and with lower energy consumption

The development of single CPU can not meet the needs of practical applications, and the AI era must rely on parallel computing. At present, the mainstream architecture of parallel computing is heterogeneous parallel computing platform. If you need the service of computing power, you can go to the tenth power

1. Supercomputers:

usually refers to the computer composed of hundreds, thousands or even more processors, which can calculate large and complex tasks that ordinary PC and server cannot complete. Supercomputer is a kind of computer with the strongest function, the fastest computing speed and the largest storage capacity. It is an important symbol of the national scientific and technological development level and comprehensive national strength

2. Server:

refers to some high-performance computers, which can provide services through the network. Compared with ordinary computer, the stability, security, performance and other aspects are higher, so the CPU, chipset, memory, disk system, network and other hardware are different from ordinary computer

the server is the node of the network, which stores and processes 80% of the data and information on the network, and plays an important role in the network. They are high-performance computers that provide various services for client computers. Their high performance mainly includes high-speed computing power, long-time reliable operation, strong external data throughput and so on

3. Desktop:

is a kind of independent and separate computer, which has no connection with other parts. Compared with notebook and netbook, the volume is larger, and the host, display and other devices are generally relatively independent, and generally need to be placed on the computer desk or special workbench. So it's called desktop

as a very popular microcomputer, most of the machines used in homes and companies are desktop computers. The performance of desktop is better than that of laptop

4. Embedded system:

that is, embedded systems
, is an application-oriented, microprocessor-based, software and hardware tailorable special-purpose computer system, which adapts to the application system's strict requirements on function, reliability, cost, volume, power consumption, etc. It is generally composed of embedded microprocessor, peripheral hardware, embedded operating system and user's application program

extended data

computer microprocessor (CPU) takes transistor as the basic component. With the continuous improvement of processor and the acceleration of update speed, computer structure and components will also change greatly. With the development of photoelectric technology, quantum technology and biotechnology, it has a great role in promoting the development of new computers

the working mode of this kind of computer is very intuitive: in a clock cycle, the computer first obtains instructions and data from memory, then executes instructions, stores data, and then obtains the next instruction

this process is repeated until a termination instruction is obtained. Explained by the controller, the instruction set executed by the arithmetic unit is a well-defined and very limited set of simple instructions