The rise of AI chips

Adoption of AI chips has risen, with chipmakers designing different types of these chips to power AI applications such as natural language processing (NLP), computer vision, robotics, and network security across a wide variety of sectors, including automotive, IT, healthcare, and retail.

Recent happenings

• Nvidia recently announced its H100 GPU (graphics processing unit): one of the world’s largest and most powerful AI accelerators, packed with 80 billion transistors.
• Earlier Intel launched new AI chips to provide customers with deep learning compute choices for training and inferencing in data centres.
• The increasing adoption of AI chips in data centres is one of the major factors driving the growth of the market.

What are AI chips?

• They are built with specific architecture and have integrated AI acceleration to support deep learning-based applications.
• Deep learning aka active neural network (ANN) or deep neural network (DNN), is a subset of machine learning and comes under the broader umbrella of AI.
• It combines a series of computer commands or algorithms that stimulate activity and brain structure.
• DNNs go through a training phase, learning new capabilities from existing data.
• It can then inference, by applying these capabilities learned during deep learning training to make predictions against previously unseen data.
• It can make the process of collecting, analysing, and interpreting enormous amounts of data faster and easier.
• These chips, with their hardware architectures and complementary packaging, memory, storage and interconnect technologies, make it possible to infuse AI into a broad spectrum of applications to help turn data into information and then into knowledge.
• Different types of AI chips: application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), central processing units (CPUs) and GPUs, designed for diverse AI applications.

Are they different from traditional chips?

• Traditional chips continuously move commands and data between the two hardware components.
  • These are not ideal for AI applications as they would not be able to handle higher computational necessities of AI workloads which have huge volumes of data.
  • Some of higher-end traditional chips may be able to process certain AI applications.
• AI chips generally contain processor cores as well as several AI-optimised cores (depending on the scale of the chip) that are designed to work in harmony when performing computational tasks.
• They are optimised for demands of heterogeneous enterprise-class AI workloads with low-latency inferencing, due to close integration with the other processor cores, which are designed to handle non-AI applications.
• AI chips, reimagine traditional chips’ architecture, enabling smart devices to perform sophisticated deep learning tasks such as object detection and segmentation in real-time, with minimal power consumption.

What are their applications?

• AI chips are sued for multitude of smart machines and devices, to deliver performance of data centre-class computer to edge devices.
• Some of these chips support in-vehicle computers to run state-of-the-art AI applications more efficiently.
• They power applications of computational imaging in wearable electronics, drones, and robots.
• Use of AI chips for NLP applications has increased due to the rise in demand for chatbots and online channels such as Messenger, Slack, and others.
• NLP is used to analyse user messages and conversational logic.
• They help customers achieve business insights at scale across banking, finance, trading, insurance applications and customer interactions.
• Having a dedicated inference accelerator that includes support for major deep learning frameworks would allow companies to harness the full potential of their data.

Future prospects

• AI company Cerebras Systems set a new standard with its brain-scale AI solution, paving the way for more advanced solutions in the future.
• Its CS-2, powered by Wafer Scale Engine (WSE-2) is a single wafer-scale chip with 2.6 trillion transistors and 8,50,000 AI optimised cores.
• A single CS-2 accelerator can support models of over 120 trillion parameters (synapse equivalents) in size.
• Neuromorphic computing, utilises an engineering method based on the activity of the biological brain.
• Increase in adoption of neuromorphic chips in automotive industry is expected in the next few years.
• Rise in need for smart homes and cities, and the surge in investments in AI start-ups are expected to drive the growth of the global AI chip market

Exam track

Prelims take away

• Artificial intelligence - mechanism, applications
• Semiconductor chip