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 ...
Microsoft

Uncovering Nested Data Parallelism and Data Reuse in DNN Computation with FractalTensor

To speed up computation, deep neural networks (DNNs) usually rely on highly optimized tensor operators. Despite the effectiveness, tensor operators are often defined empirically with ad hoc semantics.
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

Dynamic Flow Scheduling for DNN Training Workloads in Data Centers

Abstract: Distributed deep learning (DL) training constitutes a significant portion of workloads in modern data centers that are equipped with high computational capacities, such as GPU servers.
MacRumors

iOS 26.3 Adds Notification Forwarding Option for Third-Party Wearables

iOS 26.3 adds a new "Notification Forwarding" setting that allows incoming notifications on an iPhone to be forwarded to a third-party device. The setting is located in the Notification section of the ...