Related papers: Strategies for Optimizing End-to-End Artificial In…
The training of large-scale Mixture of Experts (MoE) models faces a critical memory bottleneck due to severe load imbalance caused by dynamic token routing. This imbalance leads to memory overflow on GPUs with limited capacity, constraining…
Along with the rapid developments in communication technologies and the surge in the use of mobile devices, a brand-new computation paradigm, Edge Computing, is surging in popularity. Meanwhile, Artificial Intelligence (AI) applications are…
Extreme edge-AI systems, such as those in readout ASICs for radiation detection, must operate under stringent hardware constraints such as micron-level dimensions, sub-milliwatt power, and nanosecond-scale speed while providing clear…
We carry out a comparative performance study of multi-core CPUs, GPUs and Intel Xeon Phi (Many Integrated Core - MIC) with a microscopy image analysis application. We experimentally evaluate the performance of computing devices on core…
Topology optimization is a computational method used to determine the optimal material distribution within a prescribed design domain, aiming to minimize structural weight while satisfying load and boundary conditions. For critical…
Matrix multiplication is the bedrock in Deep Learning inference application. When it comes to hardware acceleration on edge computing devices, matrix multiplication often takes up a great majority of the time. To achieve better performance…
When handling large datasets that exceed the capacity of the main memory, movement of data between main memory and external memory (disk), rather than actual (CPU) computation time, is often the bottleneck in the computation. Since data is…
This paper presents a state-of-the-art overview on how to architect, design, and optimize Deep Neural Networks (DNNs) such that performance is improved and accuracy is preserved. The paper covers a set of optimizations that span the entire…
The Crossroads supercomputer was designed to simulate some of the most complex physical devices in the world. These simulations routinely require 1/2 petabyte or more of system memory running on thousands of compute nodes for months at a…
Background: We describe an informatics framework for researchers and clinical investigators to efficiently perform parameter sensitivity analysis and auto-tuning for algorithms that segment and classify image features in a large dataset of…
The development of large-scale foundation models, particularly Large Language Models (LLMs), is constrained by significant computational and memory bottlenecks. These challenges elevate throughput optimization from a mere engineering task…
The "AI for Science, Energy, and Security" report from DOE outlines a significant focus on developing and optimizing artificial intelligence workflows for a foundational impact on a broad range of DOE missions. With the pervasive usage of…
By supporting the access of multiple memory words at the same time, Bit-line Computing (BC) architectures allow the parallel execution of bit-wise operations in-memory. At the array periphery, arithmetic operations are then derived with…
Resource-constrained edge deployments demand AI solutions that balance high performance with stringent compute, memory, and energy limitations. In this survey, we present a comprehensive overview of the primary strategies for accelerating…
Heterogeneous hardware and dynamic workloads worsen long-standing OS bottlenecks in scalability, adaptability, and manageability. At the same time, advances in machine learning (ML), large language models (LLMs), and agent-based methods…
The overall equipment effectiveness (OEE) is a performance measurement metric widely used. Its calculation provides to the managers the possibility to identify the main losses that reduce the machine effectiveness and then take the…
Edge intelligence leverages computing resources on network edge to provide artificial intelligence (AI) services close to network users. As it enables fast inference and distributed learning, edge intelligence is envisioned to be an…
With the ease-of-programming, flexibility and yet efficiency, MapReduce has become one of the most popular frameworks for building big-data applications. MapReduce was originally designed for distributed-computing, and has been extended to…
The time required for training the neural networks increases with size, complexity, and depth. Training model parameters by backpropagation inherently creates feedback loops. These loops hinder efficient pipelining and scheduling of the…
Computer vision on low-power edge devices enables applications including search-and-rescue and security. State-of-the-art computer vision algorithms, such as Deep Neural Networks (DNNs), are too large for inference on low-power edge…