Samsung Electronics Co., Ltd.

Uiseok Song

Wooseok Chang

Jaehyung Ahn

Seongbeom Kim

Junyeon Lee

Byungwoo Bang

Hun Seong Choi

A processor-implemented neural network model reconfiguration method is provided. The method calculates required resource information of each of a plurality of layers of a neural network model, determines whether a layer of the plurality of layers is a reconfiguration target layer based on the required resource information and hardware information, determines reconfiguration layers, with respect to the reconfiguration target layer, based on required resource information of the reconfiguration target layer and the hardware information, selects one of the reconfiguration target layer and the determined reconfiguration layers based on performance information of the reconfiguration target layer and performance information of each of the determined reconfiguration layers, and implements one of the determined reconfigured layers in the neural network model based on the selecting of the determined reconfiguration layers.

Apparatus and method with neural network model reconfiguration

A method and apparatus with cosmic ray fault protection is included. A method includes obtaining cosmic ray information indicating at least one cosmic ray event, determining a soft error mitigation policy based on the cosmic ray information, accessing the soft error mitigation policy by a device, and based on the soft error mitigation policy, performing, by the device, a mitigation action that mitigates for soft errors related to the cosmic ray event.

Method and apparatus with cosmic ray fault protection

An electronic device and method with on-demand accelerator checkpointing are provided. In one general aspect, an electronic device includes a host processor, and an accelerator configured to operate according to instructions transmitted by the host processor to the accelerator, wherein, a memory of the host processor and a memory of the accelerator are respectively checkpointed to a storage at respective different intervals, and in response to a determination that a failure has occurred in the host processor, the memory of the accelerator is checkpointed to the storage.

Growing community of inventors

Suwon-si, South Korea

Uiseok Song