GUGUO CLOUD

  Witmem Technology, a leading computing-in-memory chip startup, debuted on April 29 its upgraded brand campaign with a new logo and a 2022 corporate video. The in-memory computing unit of the WTM2101 enables the running of different types of deep learning algorithms, ranging from tens of Mops to several Gops, with power consumption as low as sub-milliamps. It is capable of running multiple deep learning algorithms simultaneously and can be applied in various applications such as speech recognition, voice enhancement, health monitoring, environment recognition, far-field wake-up, and event detection.Founded in October 2017, the Beijing-based Witmem Technology (知存科技) started mass production of its first computing-in-memory SoC chip WTM2101 in March this year. Compared with mainstream digital NPU and DSP, WTM2101 can increase computing power more effectively. With its breakthrough in application competitiveness and marketing...

  With the landing and large-scale application of artificial intelligence, AI chips have also become a common chip category. Compared with traditional chips, the main competitive advantage of AI chips lies in high computing power and high energy efficiency ratio. High computing power refers to the ability to complete AI calculations faster than traditional chips, while high energy efficiency ratio refers to the ability to complete calculations with less energy than traditional chips. In the early days of the birth of AI chips, the AI chip architecture was mainly optimized for computing parallelism, thereby enhancing computing power. At present, there are many players in global in-memory computing. A major problem with traditional in-memory computing is the contradiction between computing accuracy and application scenarios. If we want to solve this contradiction, we hope to have a low-power in-memory computing product for the mobile terminal, and its calculation accuracy can meet th...

  Keywords: integration of storage and computing, integration of computing and storage, PIM (processing-in-memory), in-memory computing, Computational RAM, Resistive random-access memory According to a market analysis report on " in-memory computing " from 2018 to 2026, in-memory computing is quite promising. In today's AI technology, as the amount of data increases and the amount of calculation increases, the original von Neumann structure is being challenged more and more. The hardware architecture cannot be expected to expand the CPU if the amount of calculation is large, and to use memory stacking if the amount of storage is large; this is a heavy reliance on the past architecture, and this method is very unsuitable for AI. When the capacity is large to a certain extent, it can only indicate that some technologies need to be innovated. From a biological point of view, the brain stores a large amount of knowledge, which can be quickly retrieved and accessed. However, t...

  Since the development of applications, the emergence of AI has driven the development of computational storage/integrated storage and computing/in-memory computing. The application of storage and calculation integration technology in AI includes Voice cmds,Voice enhancement,Health monitoring,Environment identification,Gesture controls,Sports classification,Object detection,Positioning, etc. The memory-intensive (big data demand) and computing-intensive (low-precision regular operation) characteristics of AI algorithms provide powerful conditions for the realization of computational storage/integration of storage and computing/in-memory computing: 1) The AI algorithm is a very large and complex network, which contains a large amount of image data and weight parameters, and a large amount of data will be generated during the calculation process. Taking the VGG-16 network as an example, the number of weights is about 1.4*108, processing a 3-channel image with a size of 224*224 requi...

  In the von Neumann system, CPU computing and memory storage are separated, and data movement between the two will cause high latency and high energy consumption. With the development of memory-intensive and computing-intensive applications such as AI in recent years, the problems of high latency and high energy consumption have become urgent problems to be solved. Strictly speaking, in memory computing can be divided into two categories: process using memory: It is biased towards circuit innovation, such as allowing the memory itself to have computing power, but this method currently has limited calculation accuracy. process near memory : The memory integrates additional computing units, such as 3D-stacked memory, logic in memory controllers. Samsung will release the industry's first in-memory computing chip based on MRAM (Magnetic Random Access Memory) on Nature in 2022. Using MRAM for in-memory computing is a huge leap forward. However, there are still many factors hindering P...