What to use to speed up the calculation? Heterogeneous processor to help

Computer development today, has dramatically changed our lives, we have entered the era of intelligent. But if you want to achieve the full interactive artificial intelligence and human-computer interaction system in film and television works, you have to mention deep learning.

Deep learning

The concept of deep learning stems from the study of artificial neural networks. A multilayer sensor with multiple hidden layers is a deep learning structure. Deep learning creates more abstract high-level representation attribute categories or features by combining low-level features to discover distributed representations of data.

The concept of deep learning was proposed by Hinton et al. in 2006. Based on deep trust network (DBN) proposed non-supervised greedy layer-by-layer training algorithm, in order to solve the deep structure related optimization problems bring hope, followed by a multi-layer automatic encoder deep structure. In addition, the convolutional neural network proposed by Lecun et al. is the first true multi-layer structure learning algorithm, which uses the spatial relative relationship to reduce the number of parameters to improve training performance.

Deep learning is a new field in machine learning research. Its motivation lies in building and simulating the neural network of the human brain for analytical learning. It imitates the mechanism of the human brain to interpret data such as images, sounds, and texts.

As with machine learning methods, in-depth machine learning methods also have the distinction between supervised learning and unsupervised learning. The learning model established under different learning frameworks is very different.

For example, Convolutional Neural Networks (CNNs) is a deep machine learning model under supervised learning, and Deep Belief Nets (DBNs) is a machine learning model under unsupervised learning. .

Artificial Intelligence, also known as artificial intelligence, is like one's best dreams, like immortality and interplanetary roaming. Although computer technology has made great progress, so far, there is not a computer that can generate "self" consciousness. Yes, with the help of humans and a large amount of ready-made data, the computer can perform very powerfully, but leaving the two, it can't even tell a comet and a Wangxing.

Turing (Turing, we all know it. The originators of computers and artificial intelligence, corresponding to their famous Turing machines and Turing tests, respectively) proposed in the 1950 paper that the Turing experiment envisaged Dialogue with the wall, you will not know whether to talk to you, people or computers. This undoubtedly gives computers, especially artificial intelligence, a preset high expectation. But half a century has passed and the progress of artificial intelligence is far from reaching the Turing test standard. This is not only disappointing people who have been waiting for years, but also believes that artificial intelligence is a flicker and related fields are "pseudoscience."

However, since 2006, the field of machine learning has made breakthrough progress. The Turing experiment was at least not as far-reaching as possible. As for technical means, not only rely on the ability of cloud computing for parallel processing of big data, but also rely on algorithms. The algorithm is, Deep Learning. With the help of the Deep Learning algorithm, humans have finally found a way to deal with the ancient concept of "abstract concept."

In June 2012, the "New York Times" disclosed the Google Brain project and attracted wide public attention. The project was led by Andrew Ng, a renowned Stanford University professor of machine learning, and Jeff Dean, a world-leading expert in large-scale computer systems. He trained a so-called “deep neural network” (DNN) with a parallel computing platform of 16,000 CPU Cores. , Deep Neural Networks' machine learning model (having a total of 1 billion nodes internally. This network naturally cannot be compared with human neural networks. It should be noted that there are more than 15 billion neurons in the human brain, interconnected nodes That is, the number of synapses is more like the number of galactic sands. It has been estimated that if the axons and dendrites of all nerve cells in a person’s brain are connected in sequence and pulled into a straight line, they can be connected from the earth to the moon. Returning to Earth from the Moon, it achieved great success in the fields of speech recognition and image recognition.

Andrew, one of the project leaders, said: "We didn't frame our boundaries like we usually do, but we put a lot of data directly into the algorithm, let the data speak for itself, and the system will automatically learn from the data." Another person in charge Jeff said: "We never told the machine when we were training that: 'This is a cat.' The system actually invented or understood the concept of 'cat'."

In November 2012, Microsoft publicly demonstrated a fully automated simultaneous interpretation system at an event in Tianjin, China. The lecturer gave a speech in English. The computer in the background automatically completed speech recognition, English-Chinese machine translation, and Chinese speech synthesis. Very smooth. According to reports, the key technology behind the support is also DNN, or Deep Learning (DL, DeepLearning).

What to use to speed up the calculation? Heterogeneous processor

Under the influence of Moore's Law, the performance of single-core scalar processors continues to increase. Software developers only need to write good software, and performance waits for the next hardware update. In the decades before 2003, this kind of "free of charge." The "lunch" mode has continued. After 2003, this "free lunch" has ceased to exist due to power consumption. In order to survive, all hardware manufacturers have to adopt various methods to increase the computing power of the hardware. The following are the most popular methods.

(1) Let the processor handle multiple instructions in one cycle. These multiple instructions can be the same or different. For example, an Intel Haswell processor can perform 4 integer addition instructions and 2 floating-point multiplication instructions in one cycle, and simultaneous fetch and operation instructions can also be executed simultaneously.

(2) Using vector instructions, mainly SIMD and VLIW techniques. SIMD technology increases the number of data bits that a processor can process at one time from word size to 128 or 256 bits, which also increases the computing power.

(3) Multiple processing units are integrated in the same chip, and divided into multi-core processors or multi-processors according to different integration methods. Multi-core processors are so important that even now embedded ARM processors on mobile phones are already quad-core or eight-core.

(4) Using heterogeneous processors, processors with different architectures have different characteristics. For example, the X86 processor is optimized for delay to reduce the instruction execution latency as the main design considerations (of course, there are many X86 processor designs today. Designed for throughput.) NVIDIA GPUs and AMD GPUs are designed for throughput, with the overall hardware throughput being the primary design goal.