Home
last modified time | relevance | path

Searched refs:executions (Results 1 – 10 of 10) sorted by relevance

/hardware/qcom/neuralnetworks/hvxservice/1.0/hexagon_nn_controller/
Dhexagon_nn_controller.h44 unsigned int executions; member
/hardware/interfaces/neuralnetworks/1.3/
DIDevice.hal124 * prepared models owned by the same client. Higher priority executions may
125 * use more compute resources than lower priority executions, and may
126 * preempt or starve lower priority executions.
149 * executions.
260 * executions.
322 * same buffer may be used for different shapes of outputs on different executions. When the
DIPreparedModel.hal32 * is used to launch executions.
/hardware/interfaces/neuralnetworks/1.0/
DIPreparedModel.hal23 * is used to launch executions.
DIDevice.hal95 * executions.
/hardware/qcom/neuralnetworks/hvxservice/1.0/
DHexagonUtils.cpp274 ", .executions: " + std::to_string(perfinfo.executions) + in toString()
/hardware/interfaces/neuralnetworks/1.1/
DIDevice.hal100 * executions.
/hardware/interfaces/neuralnetworks/1.2/
DIDevice.hal227 * executions.
318 * executions.
DIPreparedModel.hal28 * is used to launch executions.
/hardware/interfaces/renderscript/1.0/
DIContext.hal730 * allocation or RS script executions) to complete.