Method for measuring performance of neural processing device and device for measuring performance
AssigneeRebellions Inc.
InventorJinseok Kim
Life of this patent
Estimating the term…
Abstract
A method for measuring performance of neural processing devices and devices for measuring performance are provided. The method for measuring performance of neural processing devices comprises receiving hardware information of a neural processing device, modeling hardware components according to the hardware information as agents, dividing a calculation task by events for the agents and modeling the calculation task, thereby generating an event model which includes nodes corresponding to the agents and edges corresponding to the events and measuring a total duration of the calculation task through simulation of the event model.
Claims18
A method for measuring performance of a processing device, comprising:
- receiving, at a processor, hardware information associated with the processing device and a calculation task;
- generating, via the processor, hardware model as agents, according to the hardware information;
- generating, via the processor, an event model by dividing the calculation task by events for the agents based on the hardware model, wherein the event model includes nodes corresponding to the agents and edges corresponding to the events;
- and
- measuring, via the processor, a total duration of the calculation task through simulation of the event model based on durations of the edges, each of the edges is data transmission between nodes, wherein the event model is regenerated after removing an edge,
- wherein measuring the total duration comprises:
- advancing time by a final duration of an edge that is completed earliest among the edges;
- removing the edge that is completed the earliest;
- computing a final duration of each of all the edges again;
- and
- measuring the total duration by summing the advanced time if all the edges have been removed.
A device for measuring performance, comprising processing circuitry, configured to:
- receive hardware information associated with a processing device and a calculation task;
- generate a hardware model as agents;
- generate an event model by dividing the calculation task by events for the agents based on the hardware model, wherein the event model includes nodes corresponding to the agents and edges corresponding to the events;
- and
- measure performance of the processing device by simulating the event model based on durations of the edges, each of the edges is data transmission between nodes, wherein the event model is regenerated after removing an edge,
- wherein the device for measuring performance is further configured to:
- advancing time by on of the final durations, wherein each of the final durations is associated with each of the edges;
- and
- when the final duration of an edge is completed the earliest among the edges of the event model, remove the edge whose final duration is completed the earliest and compute the final durations of each of the edges again.
Dependencies are inferred from the claim text.