Build a global manufacturer and supplier trusted trading platform.

Break through the bottleneck of von Neumann's architecture! The world's first deposit-calculation integrated AI chip was born

12/03/2021 Storage and calculation integrated AI chip, Von Neumann architecture, Processor, memory

representation-of-artificial-intelligence-820x461


  For the past 70 years, computers have been designed according to the von Neumann architecture, and runtime data needs to be transferred back and forth between the processor and the memory.


  With the development of the times, this working mode faces greater challenges: in high-concurrent computing scenarios such as artificial intelligence, data transmission back and forth will generate huge power consumption; the current performance improvement speed of the memory system is significantly behind the performance improvement speed of the processor , Limited memory bandwidth cannot guarantee high-speed data transmission.


  On December 3, Fast Technology learned that DAMO Academy successfully developed a new architecture chip. This chip is the world's first DRAM-based 3D bonded stacked storage and computing integrated AI chip, which can break through the performance bottleneck of the von Neumann architecture and meet the needs of artificial intelligence and other scenarios for high bandwidth, high capacity memory and extreme computing power.


  In certain AI scenarios, the performance of the chip is increased by more than 10 times, and the energy efficiency ratio is increased by up to 300 times.


  In the context of the gradual slowdown of Moore's Law, the integration of storage and computing has become a key technology to solve the bottleneck of computer performance.


  The storage-computing integrated chip is similar to the human brain, and the data storage unit and the computing unit are integrated, which can greatly reduce data handling, thereby greatly improving the parallelism of computing and energy efficiency.


  This technology was proposed as early as the 1990s, but due to the complexity of the technology, high design cost, and lack of application scenarios, the industry's research on integrated storage and computing chips has been slow in the past few decades.


  The integrated storage-calculation chip developed by DAMO Academy integrates a number of innovative technologies and is the world's first chip that uses hybrid bonding 3D stacking technology to achieve integrated storage-calculation. The chip's memory unit uses heterogeneous integrated embedded DRAM (SeDRAM), which has the characteristics of ultra-large bandwidth and ultra-large capacity; in terms of computing units, DAMO Academy has developed and designed a stream-type customized accelerator architecture to "end-to-end" the recommendation system. Acceleration includes tasks such as matching, coarse sorting, neural network calculations, and fine sorting.


  Thanks to the innovation of the overall architecture, the chip achieves both high performance and low system power consumption. In the actual recommended system application, compared with the traditional CPU computing system, the performance of the storage-computing integrated chip is increased by more than 10 times, and the energy efficiency is increased by more than 300 times. The research results of this technology have been included in ISSCC 2022, the top conference in the chip field, and can be applied to scenarios such as VR/AR, unmanned driving, astronomical data calculation, and remote sensing image data analysis in the future.


  Zheng Hongzhong, a scientist at DAMO Academy’s Computing Technology Laboratory, said: “The integration of storage and computing is a disruptive chip technology. It naturally has the advantages of high performance, high bandwidth, and high energy efficiency. In terms of consumption, the chip developed by DAMO Academy closely integrates this technology with the scene, realizing the perfect integration of memory, computing and algorithm applications."


  It is reported that the DAMO Academy Computing Technology Laboratory focuses on the research of chip design methodology and new computer architecture technology. It has already had a number of leading achievements and published many papers at top conferences such as ISSCC, ISCA, MICRO, and HPCA.



  Parts of materials of this site come from the internet, please contact if there is infringement








QR code