中文 English

New Neural Processors Address Emerging Neural Networks


It’s been ten years since AlexNet, a deep learning convolutional neural network (CNN) model running on GPUs, displaced more traditional vision processing algorithms to win the ImageNet Large Scale Visual Recognition Competition (ILSVRC). AlexNet, and its successors, provided significant improvements in object classification accuracy at the cost of intense computational complexity and large da... » read more

The Past Predicting The Future


It is often said that you cannot predict the future by looking at the past, but that isn't always correct. There are many clues provided by digging into change. Those changes are a prelude to what may happen in the future. One way we can do that here at Semiconductor Engineering is by looking at changes in reading habits. What types of articles are attracting the most attention? This is a sure ... » read more

Power/Performance Bits: Aug. 24


Low power AI Engineers at the Swiss Center for Electronics and Microtechnology (CSEM) designed an SoC for edge AI applications that can run on solar power or a small battery. The SoC consists of an ASIC chip with RISC-V processor developed at CSEM along with two tightly coupled machine-learning accelerators: one for face detection, for example, and one for classification. The first is a bin... » read more

Timing Challenges In The Age Of AI Hardware


In recent years, we have seen a clear market trend towards dedicated integrated circuits (ASICs) that are much more efficient in performance and energy consumption than traditional general-purpose computers for processing AI workloads. These AI accelerators harden deep learning algorithm kernels into circuits, enable higher data ingestion bandwidth with local memory, and perform massively paral... » read more

Addressing Power Challenges In AI Hardware


Artificial intelligence (AI) accelerators are essential for tackling AI workloads like neural networks. These high-performance parallel computation machines provide the processing efficiency that such high data volumes demand. With AI playing increasingly larger roles in our lives—from consumer devices like smart speakers to industrial applications like automated factories—it’s paramount ... » read more

Tapping Into Purpose-Built Neural Network Models For Even Bigger Efficiency Gains


Neural networks can be categorized as a set of algorithms modelled loosely after the human brain that can ‘learn’ by incorporating new data. Indeed, many benefits can be derived from developing purpose-built “computationally efficient” neural network models. However, to ensure your model is effective, there are several key requirements that need to be considered. One critical conside... » read more

Convolutional Neural Network With INT4 Optimization


Xilinx provides an INT8 AI inference accelerator on Xilinx hardware platforms — Deep Learning Processor Unit (XDPU). However, in some resource-limited, high-performance and low-latency scenarios (such as the resource-power-sensitive edge side and low-latency ADAS scenario), low bit quantization of neural networks is required to achieve lower power consumption and higher performance than provi... » read more

The Benefits Of Using Embedded Sensing Fabrics In AI Devices


AI chips, regardless of the application, are not regular ASICs and tend to be very large, this essentially means that AI chips are reaching the reticle limits in-terms of their size. They are also usually dominated by an array of regular structures and this helps to mitigate yield issues by building in tolerance to defect density due to the sheer number of processor blocks. The reason behind... » read more

ResNet-50 Does Not Predict Inference Throughput For MegaPixel Neural Network Models


Customers are considering applications for AI inference and want to evaluate multiple inference accelerators. As we discussed last month, TOPS do NOT correlate with inference throughput and you should use real neural network models to benchmark accelerators. So is ResNet-50 a good benchmark for evaluating relative performance of inference accelerators? If your application is going to p... » read more

AI & IP In Edge Computing For Faster 5G And The IoT


Edge computing, which is the concept of processing and analyzing data in servers closer to the applications they serve, is growing in popularity and opening new markets for established telecom providers, semiconductor startups, and new software ecosystems. It’s brilliant how technology has come together over the last several decades to enable this new space starting with Big Data and the idea... » read more

← Older posts