➀ Jensen Huang discusses the current state of AI development and the issue of AI hallucinations; ➁ He emphasizes the rapid increase in AI computing power demand over the past decade; ➃ Huang shares personal anecdotes about his career and his early promises.
Recent #Computing Power news in the semiconductor industry
➀ Computing power is an important indicator of a computer's information processing capability, with AI computing power focusing on AI applications, commonly measured in TOPS and TFLOPS, and provided by dedicated chips such as GPU, ASIC, and FPGA for algorithm model training and inference.
➁ AI chip accuracy is a way to measure computing power level, with FP16 and FP32 used in model training, and FP16 and INT8 used in model inference.
➂ AI chips typically use GPU and ASIC architectures. GPUs are the key components in AI computing due to their advantages in computation and parallel task processing.
➃ Tensor Core, an enhanced AI computing core compared to the parallel computation performance of Cuda Core, is more focused on the deep learning field and accelerates AI deep learning training and inference tasks through optimized matrix operations.
➄ TPUs, a type of ASIC designed for machine learning, stand out in high energy efficiency in machine learning tasks compared to CPUs and GPUs.
➀ Overview of the Lightwave Expo and its focus on new optical transmission technologies; ➁ Detailed schedules and keynotes of various forums such as the Power of Light Forum, Innovation and Development Forum of Optical Innovation in Computing Centers, and Forum on Integrated Circuit Design and Manufacturing of Optoelectronics; ➂ Discussion on the progress and future prospects of full-optical network technology in the era of computing power, trends and challenges in data center optical interconnects, and the development of 5G and beyond; ➃ Release of the next-generation wireless front-haul standard and its impact on the optical industry.