According to the website of New Scientist on the 12th, a supercomputer capable of fully simulating human brain synapses will be launched in Australia next year. This neuromorphic supercomputer called "Shennan" can perform 228 trillion synaptic operations per second, which is equivalent to the number of synaptic operations estimated by scientists in the human brain. This will help understand how the human brain processes a large amount of information with relatively less energy consumption. The research team pointed out that similar neuromorphic computers have been introduced before, but "Shennan" will be the largest to date. "Shennan" is manufactured by the International Neuromorphic Systems Center located in Sydney, Australia, in collaboration with Intel and Dell. Unlike ordinary computers, the hardware chips of "Shennan" can implement spike neural networks to model the way synapses process brain information. Andrew Van Scheck, the project leader of the "Shennan" project, pointed out that this will be their first real-time simulation of spike neural network activity the size of the human brain. Although the functions of "Shennan" may not be as powerful as existing supercomputers, it will help advance the understanding of neural morphology computing and biological brain, thereby better understanding the working principles of the brain. Supercomputers are major energy consumers, and the human brain consumes no more energy than light bulbs. This difference is partly attributed to different data processing methods: when traditional computers perform operations, data constantly moves between the processor and memory; The neural morphological architecture performs many operations in parallel, greatly reducing the movement of data. Due to data mobility being one of the most energy consuming components, neural morphological architectures can significantly reduce energy consumption. In addition, spike neural networks are event driven, which means that neural morphological systems only respond to changes in input, unlike traditional computers that run continuously in the background, further reducing energy consumption. Researchers say that "Shennan" will boost research in neuroscience and pave the way for higher computational energy efficiency. If this technology can be miniaturized, it will enhance the autonomous capabilities of drones and robots. (Lai Xin She)