GUGUO CLOUD

  Introduction to Computing in Memory Computing in memory, also known as in-memory computing or computational memory, is a new paradigm that aims to reduce data movement and increase data processing speed by performing computations directly in memory. In contrast to traditional computing architectures that rely on a separation of memory and processing, computing in memory systems leverage the inherently parallel processing capabilities of memory devices to achieve high-throughput and low-latency data processing. Advantages of Computing in Memory Applications Computing in memory has several advantages over traditional computing architectures. One of the biggest advantages is the reduction of data movement, which significantly reduces power consumption and improves overall efficiency. Additionally, computing in memory enables higher bandwidth data processing, faster data transfer rates, and lower latency. These advantages make computing in memory particularly attractive for applicati...

  The principle of producing feedback is that when a microphone and a speaker are used simultaneously, the sound signal captured by the microphone is amplified by the speaker and then output again, forming a feedback loop. Due to the existence of the feedback loop, some specific frequencies of the sound signal can become very strong after multiple amplifications, forming a howling noise. The principle of howling suppression is to use digital signal processing technology to monitor the audio input and output signals in real-time, and identify and eliminate signals that may cause howling. Specifically, the howling suppression algorithm will perform frequency analysis on the input and output signals, and when the strength of the signal in a specific frequency range exceeds a certain threshold, it will recognize that there is howling noise. Then, the howling suppression algorithm will use a certain algorithm model to eliminate or reduce the signals that may cause howling, thereby elimi...

  With the development of TWS technology and intelligence, TWS smart earbuds will play an important role in wireless connectivity, voice interaction, intelligent noise reduction, health monitoring, and hearing enhancement/protection, not just as standard equipment for smartphones, but even becoming an indispensable part of the human body. Noise reduction, hearing protection, intelligent translation, health monitoring, bone conduction+bone sound pattern, anti-loss, etc. will be the key technologies for TWS earbuds. Among them, noise reduction is the top priority, and the two mainstream active noise reduction modes on the market are ANC and ENC. Active noise reduction is achieved through the collaboration of hardware (chips, sensors, microphone arrays, etc.) and software algorithms. Currently, TWS earbuds mainly have two active noise reduction methods: ANC and ENC. (1) ANC noise reduction technology generates reverse sound waves equal to external noise through the internal noise redu...

For decades, headphones have been a crucial tool for people from all walks of life. From listening to music and podcasts to gaming and taking calls, headphones have become an indispensable accessory for many individuals. However, with advancements in technology, it's time to take headphones to the next level. This is where the concept of computing in memory comes in. Computing in memory (CIM), also known as in-memory computing, is a new technology that merges memory and processing capabilities into one device, offering significant speed and efficiency improvements over traditional computing architectures. The ability to integrate processing power and memory into a single device has enormous implications for the headphone industry. The technology opens up new possibilities for real-time audio processing, including noise reduction, equalization, and spatial audio, leading to a significant improvement in the overall listening experience. CIM technology allows for the integration of ad...

  WTM2101 is a speech recognition and wake-up chip based on computing in-memory technology, with a core consisting of a set of low-power processors specifically designed for speech recognition. Compared to traditional speech processors, WTM2101 adopts a series of optimization measures for speech wake-up and recognition scenarios, significantly reducing power consumption. One of the most important optimization measures is the full phoneme algorithm model. Traditional speech recognition algorithms require a large amount of acoustic and linguistic knowledge to build complex acoustic and language models to achieve high-precision recognition. The full phoneme algorithm model uses a simpler speech unit, namely a single phoneme, to avoid complex acoustic and language modeling, thereby greatly reducing the complexity and power consumption of the algorithm. Offline speech wake-up and recognition technology has been widely used in smart homes and smart speakers. The balance between AI speech...

  As consumers increasingly demand diversified and intelligent functions from smart wearable devices, the smart wearable industry needs to invest more in research and development and production costs to achieve product feature stacking or performance improvement. Constrained by the small form factor and cost control, the demand for high computing power and low power consumption, as well as the contradiction with the traditional von Neumann architecture, has become increasingly prominent. In this context, with the mass production of the world's first computing in-memory SoC chip WTM2101 in 2022, many manufacturers have begun to seek a breakthrough in this new type of computing architecture and have successfully developed and launched products, entering the lives of consumers. 1.Chip model: WTM2101 2.Chip type: ultra-low power AI SoC chip 3.Application: intelligent voice and intelligent health 4.Package: WLCSP (2.6x3.2mm²) 5.Power consumption: 5uA-3mA 6.AI computing power: 50Gops 7.M...

  Currently, most TWS devices use traditional dual or triple microphone ENC-based algorithms for voice enhancement and noise reduction. These algorithms can pick up sound directionally and reduce noise from other directions, but they also have significant drawbacks. Traditional noise reduction algorithms can cause some damage to human speech when directional pickup is achieved through phase manipulation, resulting in a muffled sound. They cannot effectively reduce noise from the same direction as the human voice, and they are not effective in high-noise environments, such as subways, trains, cafes, and roads. NN-based environment noise reduction algorithms are more versatile and can analyze collected audio directly using the characteristics of deep learning to separate human speech from noise, improve signal-to-noise ratio, reduce environmental noise, and preserve human speech. NN environment noise reduction can work alone with a single microphone, without requiring custom tuning a...

  Recently, ChatGPT4 has become the new hot spot with Microsoft office and google products, with the AI tools generation, which kind of new computation technology support that? Computing in Memory (CIM) technology is an emerging computing architecture that integrates storage and computing functions into the same chip. This technology has a wide range of applications in big data processing, artificial intelligence, and machine learning. For large natural language processing models like ChatGPT4, CIM technology is one of the key factors for performance improvement. It helps companies reduce energy consumption, increase computing efficiency, and achieve higher performance.   Firstly, CIM technology can help reduce data transfer time and energy consumption. In traditional computer architectures, data needs to be transferred from storage units to computing units, which consumes a lot of time and energy. In CIM technology, storage and computing units are directly integrated int...

  The WTM8000 series is a high-performance, low-power, all-in-one AI processing chip for video enhancement processing. It has the core advantages of high computing power, low power consumption, increased energy efficiency, and low cost.   1. it can implement various AI-based video enhancement processing, including object recognition, classification and detection, and video enhancement algorithms, and is suitable for multiple energy-efficient and complex edge computing scenarios.   2. 4K/8K@60/120FPS frame interpolation, super scoring, HDR wide dynamic and noise reduction capabilities for video display.   3. 4K@60FPS power-efficient NPU and HD video enhancement capabilities for AI-ISP, such as HDR wide dynamic, noise reduction processing, etc.   4. The WTM8000 series combines power-efficient in-store computing with advanced logic processes through 3D ICs to achieve high-power, low-power, and cost-effective AI solution.

  WTM2101 has both ultra-low power consumption and high computing power and can realize multiple application scenarios. With high computing power in-memory computing core, compared with NPU, DSP, and MCU computing platforms, the AI computing power of WTM2101 has increased by 10-200 times. At the same time, WTM2101 also has outstanding performance in terms of low power consumption. The deep Learning Network Inference Operation only consumes 0.1 mA current. At present, the WTM2101 chip covers eight major application scenarios and solutions, including speech recognition, speech enhancement, health monitoring, environmental recognition, far-field wake-up, motion recognition, visual recognition, and event detection. Various intelligent wearable devices with high requirements for diversification.   WTM2101 chip has four significant advantages   1. Based on the integration of storage and computing technology, realize NN VAD and recognition of hundreds of voice command words 2. U...

  Computing in memory is not a new concept. As early as the 1990s, there were discussions on the prototype of computing in memory, but the development of hardware was limited at that time, and no further research was carried out. There is no unified definition of the concept of computing in memory. GridGrain gives this explanation about memory computing: by using a middleware software, data is stored in memory in a distributed cluster and processed in parallel. Techopedia believes that as memory prices drop sharply and memory capacity increases, it is better to store information in dedicated server memory instead of slower storage disks. It can help business users quickly perform pattern recognition and timely analysis Big data is the so-called computing in memory. Computing in memory is not only about storing data in memory, but also requires special design of software systems and computing models. Therefore, it can be seen that memory computing mainly has...

  Thanks to the rapid development of the semiconductor industry over the past half century driven by Moore's Law, computing power has been experiencing significant leaps. The integration density of integrated circuits doubles every two years, and then this cycle shortens to 18 months. The performance of microprocessors increases by 1 times every 18 months. However, as the economic cost of silicon chips approaches its physical limit, Moore's Law may become invalid in the future. The processing logic based on the Von Neumann architecture, which is based on the instruction set pattern, requires data to be transmitted back and forth between the processor and memory at runtime, resulting in significant power consumption. Nowadays, the shortcoming of processing massive data, especially irregular massive data, is increasingly evident in high-performance computing environments such as artificial intelligence. Solving the "storage wall" bottleneck has become urgent. In this co...

  In the foreseeable future, performance improvements based on process miniaturization will be very limited, and the inability to improve computing power will lead to a bottleneck in innovation in the application market. The computing in memory technology that effectively overcomes the bottleneck of the von Neumann architecture and achieves a significant improvement in computing energy efficiency is the focus of industry expectations and attention. In March 2022, the international first computing in memory (SoC) chip WTM2101 produced by Witmem Technology was officially launched on the market. Less than a year later, WTM2101 has been successfully commercialized at the end, providing AI processing solutions for voice, video, and other applications, helping products achieve more than 10 times energy efficiency improvement. With the successful accumulation of research and development and market experience of computing in memory products, Witmem Technology's computing in memory products...

  On January 6, 36 Krypton learned that Witmem Technology, a storage and computing chip company, announced completing a 200 million RMB Series B2 financing round. This funding round was led by Guotou Venture, followed by Shuimu Chunjin Capital, LH Ventures continued additional investment, and Index Capital acted as the exclusive financial advisor. This funding will be mainly used for mass production of in-store computing chips and new product development to expand the scale of industrialization on the ground. Witmem Technology was founded in 2017 and is a company 36 Krypton has been following for a long time. Witmem Technology has now released and mass-produced two generations of products, the WTM1001, a storage and computing accelerator, and the WTM2101, a storage in-computing SoC chip. In 2022, Witmem Technology announced the completion of a 200 million RMB B1 round of financing and a 100 million RMB B1+ round of funding in January and September, respectively....

  On January 12, 2023, the 2022 SHOWTECH2022-WIM Innovators Annual Conference, jointly organized by Zhongguancun National Independent Innovation Demonstration Zone Exhibition Center, Zhongguancun Exhibition and Service Industry Alliance and Equal Ocean, was officially launched in Beijing. At the conference, Equal Ocean and IC Ranks released the World Innovation Awards 2022 (WIA2022) series of lists, Witmem Technology was honored to be listed as one of the "Top 20 Best Employers for Emerging Semiconductor companies in 2022".     The selection process took more than a month and was based on the company's application status and the Equal Ocean database. The list was based on the key aspects and elements of the upstream and downstream semiconductor industry chain, including company size, team background, technology level, revenue capacity, development potential, visibility, and other core dimensions, and combined with in-depth interviews, expert scores, user ratings, field re...

  On November 10, 2022, the International IC & Component Exhibition and Conference (IIC)  official opened in Shenzhen, China, and Shaodi Wang, Founder and CEO of Witmem Technology, was invited to attend the Global CEO Summit and the Global e-Achievement Award Ceremony. Mr. Wang Shaodi, the founder and CEO of Witmem Technology, was invited to participate in the Global CEO Summit and the Global e-Achievement Awards ceremony to receive the 2022 Global e-Achievement Award for Outstanding Emerging Company. The World Electronics Achievement Awards, sponsored by AspenCore, a leading global electronics media group, and judged by a panel of AspenCore's senior industry analysts and website users from Asia, the US, and Europe, is one of the most highly regarded annual awards in the IC sector. It is one of the most highly regarded annual awards in the IC sector, and its nomination is a testament to its leadership and outstanding performance in the industry. Being nominated f...

  On December 11, 2022, the China Mobile Global Partner Conference held the "China Mobile Industry Chain Innovation and Arithmetic Network Sub-Forum," it focused on chain innovation, a joint creation of the future, and the era of arithmetic. It shows the ecology of industry chain integration, group breakthrough achievements, and the effectiveness of arithmetic network innovation. Among them, the industry's first "White Paper on Computing in Memory. Integration," jointly released by various units of industry, academia, and research, has attracted intense attention and will become an authoritative treasure book to guide all sectors of industry, academia, and research to standardize their understanding of computing in-memory integration and its development. ·CMCC, ZTE Corporation, Huawei Technologies, Tsinghua University, Peking University, and Beijing Witmem Technology Co jointly prepared the White Paper. The book explains the core technology, development route, a...