Microsoft

PipeThreader: Software-Defined Pipelining for Efficient DNN Execution

To effectively utilize heterogeneous specialized hardware units in modern GPUs, such as TensorCores and Tensor Memory Accelerators, this paper introduces PipeThreader, a new DNN compiler. PipeThreader ...
IEEE

Joint Task Offloading, DNN Pruning, and Computing Resource Allocation for Fault Detection With Dynamic Constraints in Industrial IoT

Abstract: In this paper, we investigate a joint task offloading, deep neural network (DNN) model pruning, and edge computing resource allocation (JOPA) problem for supporting a fault detection service ...
IEEE

Joint Optimization of Device Placement and Model Partitioning for Cooperative DNN Inference in Heterogeneous Edge Computing

Abstract: EdgeAI represents a compelling approach for deploying DNN models at network edge through model partitioning. However, most existing partitioning strategies have primarily concentrated on ...
INSPIRE

Amplitude Reconstruction in n n Scattering at 6-GeV/c: Where Do We Stand and What Measurements Should Be Done?

We study the problem of amplitude reconstruction at a fixed t (−t∼0.3 GeV/c2). The five amplitudes are reconstructed, up to an overall phase, by 9 observables σ, P0, Cnn, Knn, Dnn, Css, Csl, Cll, and ...