Can AI computing power become CPU computing power
Publish: 2021-04-17 15:35:18
1.
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
2. I54590 is a four core, four thread, three-level cache is 6MB. The i7 4790 is a 4-core 8-thread, 3-level cache of 8MB. CPU is not only determined by the dominant frequency.
3. You can first right-click in Excel ~ set cell format ~ value ~ currency. Just import it to word
4. Let me explain to you that Tron is the world's largest decentralized blockchain application operating system founded by sun Yuchen. It has become the only Chinese virtual currency with market value among the top ten. At the beginning of 2021, the total number of users of BoChang public chain exceeded 21 million, becoming the only Chinese chain among the three major public chains in the world, with a total of 1.5 billion transactions, running the largest DAPP ecosystem in the world. Did you know that?
5. With the maturity and application of big data, cloud computing, artificial intelligence and other technologies in all walks of life, in the era of artificial intelligence, the emerging term AI server also frequently appears in people's sight. Some people predict that in the era of artificial intelligence, AI server will be widely used in various instries, so what's the difference between AI server and ordinary server? Why can AI server replace most common servers in the era of artificial intelligence
in terms of the hardware architecture of the server, AI server is a heterogeneous server. In terms of heterogeneous mode, different combinations can be adopted according to the application scope, such as CPU + GPU, CPU + TPU, CPU + other accelerators, etc. Compared with ordinary servers, there is no difference in memory, storage and network, mainly in big data, cloud computing, artificial intelligence and other aspects, which need more internal and external memory to meet the needs of various data collection and collation
as we all know, the common server is the provider of computing power based on CPU, which adopts the serial architecture and is good at logical computing and floating-point computing. Because a lot of branch jump processing is needed in logic judgment, the structure of CPU is complex, and the improvement of computing power mainly depends on stacking more cores
however, with the application of network technologies such as big data, cloud computing, artificial intelligence and the Internet of things, the amount of data in the Internet is growing exponentially, which poses a serious challenge to the traditional services with CPU as the main source of computing power. At present, the processing technology of CPU and the number of cores of a single CPU are close to the limit, but the increase of data continues, Therefore, the data processing ability of the server must be improved. Therefore, in this environment, AI server came into being.
in terms of the hardware architecture of the server, AI server is a heterogeneous server. In terms of heterogeneous mode, different combinations can be adopted according to the application scope, such as CPU + GPU, CPU + TPU, CPU + other accelerators, etc. Compared with ordinary servers, there is no difference in memory, storage and network, mainly in big data, cloud computing, artificial intelligence and other aspects, which need more internal and external memory to meet the needs of various data collection and collation
as we all know, the common server is the provider of computing power based on CPU, which adopts the serial architecture and is good at logical computing and floating-point computing. Because a lot of branch jump processing is needed in logic judgment, the structure of CPU is complex, and the improvement of computing power mainly depends on stacking more cores
however, with the application of network technologies such as big data, cloud computing, artificial intelligence and the Internet of things, the amount of data in the Internet is growing exponentially, which poses a serious challenge to the traditional services with CPU as the main source of computing power. At present, the processing technology of CPU and the number of cores of a single CPU are close to the limit, but the increase of data continues, Therefore, the data processing ability of the server must be improved. Therefore, in this environment, AI server came into being.
6. The general CPU is a general-purpose processor, which can do anything, but nothing is the strongest. What can be done depends on the optimization of software. But AI CPU is not. It is a special instrial control chip, which is customized according to the algorithm to achieve a single purpose, such as the CPU used by mining machine, disc machine and other machines. If it is allowed to do other tasks, it can't do anything.
7. In the era of single core, the higher the CPU frequency, the better
in the multi-core era, the higher the frequency of a single core, the better the number of cores
at the same time, we have to consider the CPU manufacturing process, supported instruction set, architecture and so on, so the evaluation of a CPU is not based on the frequency, nor only on the number of cores
the GHz of CPU refers to the dominant frequency of CPU:
the dominant frequency of CPU, that is, the clock speed of CPU core
the megahertz of so and so CPU is usually said, and this megahertz is "the main frequency of CPU"
many people think that the main frequency of CPU is its running speed, but it is not
the dominant frequency of CPU indicates the speed of digital pulse signal oscillation in CPU, which is not directly related to the actual computing power of CPU
since the dominant frequency does not directly represent the operation speed, it is likely that the actual operation speed of CPU with higher dominant frequency will be lower under certain circumstances
in the multi-core era, the higher the frequency of a single core, the better the number of cores
at the same time, we have to consider the CPU manufacturing process, supported instruction set, architecture and so on, so the evaluation of a CPU is not based on the frequency, nor only on the number of cores
the GHz of CPU refers to the dominant frequency of CPU:
the dominant frequency of CPU, that is, the clock speed of CPU core
the megahertz of so and so CPU is usually said, and this megahertz is "the main frequency of CPU"
many people think that the main frequency of CPU is its running speed, but it is not
the dominant frequency of CPU indicates the speed of digital pulse signal oscillation in CPU, which is not directly related to the actual computing power of CPU
since the dominant frequency does not directly represent the operation speed, it is likely that the actual operation speed of CPU with higher dominant frequency will be lower under certain circumstances
8.
on the afternoon of August 23, 2019, Huawei's Shenzhen headquarters released shengteng 910, the most powerful a processor, and launched a full scene AI computing framework Xu Zhijun, chairman of wheel of Huawei, said, Huawei has completed the construction of AI solutions for the whole station and scene, and will launch more AI processors in the future to provide more abundant, more economical and more suitable AI computing power but it gave him a good excuse. He kept shouting that the wolf was coming, the wolf was coming<
9. 1660super silent frequency
Master Lu classic version 5.20
the single running score of graphics card is about 18W
gtx970 is about 13-13.5w
1660s is about 40% faster than the theoretical running score
1660s has the characteristics of low theoretical running score, for example, the theoretical running score is lower than rx590, the actual game is higher than rx590
1660s is about 50-55% faster than gtx970 in the actual game
Master Lu classic version 5.20
the single running score of graphics card is about 18W
gtx970 is about 13-13.5w
1660s is about 40% faster than the theoretical running score
1660s has the characteristics of low theoretical running score, for example, the theoretical running score is lower than rx590, the actual game is higher than rx590
1660s is about 50-55% faster than gtx970 in the actual game
Hot content