Related papers: A Novel SIMD-Optimized Implementation for Fast and…
Depthwise convolutions are widely used in lightweight convolutional neural networks (CNNs). The performance of depthwise convolutions is mainly bounded by the memory access rather than the arithmetic operations for classic convolutions so…
The research interest in specialized hardware accelerators for deep neural networks (DNN) spikes recently owing to their superior performance and efficiency. However, today's DNN accelerators primarily focus on accelerating specific…
Geometric numerical integration has recently been exploited to design symplectic accelerated optimization algorithms by simulating the Lagrangian and Hamiltonian systems from the variational framework introduced in Wibisono et al. In this…
`In-memory computing' is being widely explored as a novel computing paradigm to mitigate the well known memory bottleneck. This emerging paradigm aims at embedding some aspects of computations inside the memory array, thereby avoiding…
Over the last ten years, graphics processors have become the de facto accelerator for data-parallel tasks in various branches of high-performance computing, including machine learning and computational sciences. However, with the recent…
Reconfigurable architectures like Field Programmable Gate Arrays (FPGAs) have been used for accelerating computations in several domains because of their unique combination of flexibility, performance, and power efficiency. However, FPGAs…
In-memory computing (IMC) with single instruction multiple data (SIMD) setup enables memory to perform operations on the stored data in parallel to achieve high throughput and energy saving. To instruct a SIMD IMC hardware to compute a…
Thermodynamic computing has emerged as a promising paradigm for accelerating computation by harnessing the thermalization properties of physical systems. This work introduces a novel approach to solving quadratic programming problems using…
We describe a modified SIMD architecture suitable for single-chip integration of a large number of processing elements, such as 1,000 or more. Important differences from traditional SIMD designs are: a) The size of the memory per processing…
Neural networks (NNs) are growing in importance and complexity. A neural network's performance (and energy efficiency) can be bound either by computation or memory resources. The processing-in-memory (PIM) paradigm, where computation is…
Transformer-based models are becoming more and more intelligent and are revolutionizing a wide range of human tasks. To support their deployment, AI labs offer inference services that consume hundreds of GWh of energy annually and charge…
We present a strategy to speed up Runge-Kutta-based ODE simulations of large systems with nearest-neighbor coupling. We identify the cache/memory bandwidth as the crucial performance bottleneck. To reduce the required bandwidth, we…
While deep neural network (DNN)-based video denoising has demonstrated significant performance, deploying state-of-the-art models on edge devices remains challenging due to stringent real-time and energy efficiency requirements.…
We propose to express the forward-backward algorithm in terms of operations between sparse matrices in a specific semiring. This new perspective naturally leads to a GPU-friendly algorithm which is easy to implement in Julia or any…
Tensor decomposition has been widely used in machine learning and high-volume data analysis. However, large-scale tensor factorization often consumes huge memory and computing cost. Meanwhile, modernized computing hardware such as tensor…
As a promising solution to boost the performance of distance-related algorithms (e.g., K-means and KNN), FPGA-based acceleration attracts lots of attention, but also comes with numerous challenges. In this work, we propose AccD, a…
Large Language Models (LLMs) have become essential in a variety of applications due to their advanced language understanding and generation capabilities. However, their computational and memory requirements pose significant challenges to…
Memory tiering provides a cost-effective solution to increase memory capacity, utilization, and even bandwidth. Memory tiering relies on system software for memory profiling, detection of frequently accessed pages, and page migration. Such…
This paper describes our experience developing polynomial approximations for trigonometric functions that produce correctly rounded results for multiple representations and rounding modes using the RLIBM approach. A key challenge with…
This paper is concerned with developing an efficient numerical algorithm for fast implementation of the sparse grid method for computing the $d$-dimensional integral of a given function. The new algorithm, called the MDI-SG ({\em multilevel…