Microsoft has added deeper visibility into AI workloads inside Windows Task Manager. On supported newer devices the Processes tab can now show per-process activity for the neural processing unit and the GPU neural engine alongside familiar CPU and GPU figures. The Performance tab displays overall utilisation, including neural engines that form part of a GPU. Optional columns for NPU, NPU engine, and NPU dedicated and shared memory appear on the Processes, Users and Details pages. Microsoft said the metrics help users make better-informed decisions as AI workloads become more common on Windows devices. The data can assist IT teams troubleshooting performance, developers validating that models land on the intended hardware rather than falling back to the CPU, and users diagnosing power consumption on battery-powered laptops. The Register noted that Task Manager continues to expand beyond its original process-management role.
Microsoft has added deeper visibility into AI workloads inside Windows Task Manager. On supported newer devices the Processes tab can now show per-process activity for the neural processing unit and the GPU neural engine alongside familiar CPU and GPU figures. The Performance tab displays overall utilisation, including neural engines that form part of a GPU. Optional columns for NPU, NPU engine, and NPU dedicated and shared memory appear on the Processes, Users and Details pages. Microsoft said the metrics help users make better-informed decisions as AI workloads become more common on Windows devices. The data can assist IT teams troubleshooting performance, developers validating that models land on the intended hardware rather than falling back to the CPU, and users diagnosing power consumption on battery-powered laptops. The Register noted that Task Manager continues to expand beyond its original process-management role.