xref: /aosp_15_r20/hardware/interfaces/neuralnetworks/1.2/IDevice.hal (revision 4d7e907c777eeecc4c5bd7cf640a754fac206ff7)

/*
 * Copyright (C) 2018 The Android Open Source Project
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 *      http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

package [email protected];

import @1.0::ErrorStatus;
import @1.1::ExecutionPreference;
import @1.1::IDevice;
import IPreparedModelCallback;

/**
 * This interface represents a device driver.
 */
interface IDevice extends @1.1::IDevice {
    /**
     * Get the version string of the driver implementation.
     *
     * The version string must be a unique token among the set of version strings of
     * drivers of a specific device. The token identifies the device driver's
     * implementation. The token must not be confused with the feature level which is solely
     * defined by the interface version. This API is opaque to the Android framework, but the
     * Android framework may use the information for debugging or to pass on to NNAPI applications.
     *
     * Application developers sometimes have specific requirements to ensure good user experiences,
     * and they need more information to make intelligent decisions when the Android framework cannot.
     * For example, combined with the device name and other information, the token can help
     * NNAPI applications filter devices based on their needs:
     *     - An application demands a certain level of performance, but a specific version of
     *       the driver cannot meet that requirement because of a performance regression.
     *       The application can disallow the driver based on the version provided.
     *     - An application has a minimum precision requirement, but certain versions of
     *       the driver cannot meet that requirement because of bugs or certain optimizations.
     *       The application can filter out versions of these drivers.
     *
     * @return status Error status returned from querying the version string. Must be:
     *     - NONE if the query was successful
     *     - DEVICE_UNAVAILABLE if driver is offline or busy
     *     - GENERAL_FAILURE if the query resulted in an
     *       unspecified error
     * @return version The version string of the device implementation.
     *     Must have nonzero length
     */
    getVersionString() generates (ErrorStatus status, string version);

    /**
     * Get the type of a given device.
     *
     * The device type can be used to help application developers to distribute
     * Machine Learning workloads and other workloads such as graphical rendering.
     * E.g., for an app which renders AR scenes based on real time object detection
     * results, the developer could choose an ACCELERATOR type device for ML
     * workloads, and reserve GPU for graphical rendering.
     *
     * @return status Error status returned from querying the device type. Must be:
     *                - NONE if the query was successful
     *                - DEVICE_UNAVAILABLE if driver is offline or busy
     *                - GENERAL_FAILURE if the query resulted in an
     *                  unspecified error
     * @return type The DeviceType of the device. Please note, this is not a
     *              bitfield of DeviceTypes. Each device must only be of a
     *              single DeviceType.
     */
    getType() generates (ErrorStatus status, DeviceType type);

    /**
     * Gets the capabilities of a driver.
     *
     * @return status Error status of the call, must be:
     *                - NONE if successful
     *                - DEVICE_UNAVAILABLE if driver is offline or busy
     *                - GENERAL_FAILURE if there is an unspecified error
     * @return capabilities Capabilities of the driver.
     */
    getCapabilities_1_2() generates (ErrorStatus status, Capabilities capabilities);

    /**
     * Gets information about extensions supported by the driver implementation.
     *
     * All extension operations and operands must be fully supported for the
     * extension to appear in the list of supported extensions.
     *
     * @return status Error status of the call, must be:
     *     - NONE if successful
     *     - DEVICE_UNAVAILABLE if driver is offline or busy
     *     - GENERAL_FAILURE if there is an unspecified error
     * @return extensions A list of supported extensions.
     */
    getSupportedExtensions()
        generates (ErrorStatus status, vec<Extension> extensions);

    /**
     * Gets the supported operations in a model.
     *
     * getSupportedOperations indicates which operations of a model are fully
     * supported by the vendor driver. If an operation may not be supported for
     * any reason, getSupportedOperations must return false for that operation.
     *
     * @param model A model whose operations--and their corresponding operands--
     *     are to be verified by the driver.
     * @return status Error status of the call, must be:
     *     - NONE if successful
     *     - DEVICE_UNAVAILABLE if driver is offline or busy
     *     - GENERAL_FAILURE if there is an unspecified error
     *     - INVALID_ARGUMENT if provided model is invalid
     * @return supportedOperations A list of supported operations, where true
     *     indicates the operation is supported and false indicates the
     *     operation is not supported. The index of "supported" corresponds with
     *     the index of the operation it is describing.
     */
    getSupportedOperations_1_2(Model model)
            generates (ErrorStatus status, vec<bool> supportedOperations);

    /**
     * Gets the caching requirements of the driver implementation.
     *
     * There are two types of cache file descriptors provided to the driver: model cache
     * and data cache.
     *
     * The data cache is for caching constant data, possibly including preprocessed
     * and transformed tensor buffers. Any modification to the data cache should
     * have no worse effect than generating bad output values at execution time.
     *
     * The model cache is for caching security-sensitive data such as compiled
     * executable machine code in the device's native binary format. A modification
     * to the model cache may affect the driver's execution behavior, and a malicious
     * client could make use of this to execute beyond the granted permission. Thus,
     * the driver must always check whether the model cache is corrupted before
     * preparing the model from cache.
     *
     * getNumberOfCacheFilesNeeded returns how many of each type of cache files the driver
     * implementation needs to cache a single prepared model. Returning 0 for both types
     * indicates compilation caching is not supported by this driver. The driver may
     * still choose not to cache certain compiled models even if it reports that caching
     * is supported.
     *
     * If the device reports that caching is not supported, the user may avoid calling
     * IDevice::prepareModelFromCache or providing cache file descriptors to
     * IDevice::prepareModel_1_2.
     *
     * @return status Error status of the call, must be:
     *     - NONE if successful
     *     - DEVICE_UNAVAILABLE if driver is offline or busy
     *     - GENERAL_FAILURE if there is an unspecified error
     * @return numModelCache An unsigned integer indicating how many files for model cache
     *                       the driver needs to cache a single prepared model. It must
     *                       be less than or equal to Constant::MAX_NUMBER_OF_CACHE_FILES.
     * @return numDataCache An unsigned integer indicating how many files for data cache
     *                      the driver needs to cache a single prepared model. It must
     *                      be less than or equal to Constant::MAX_NUMBER_OF_CACHE_FILES.
     */
    getNumberOfCacheFilesNeeded()
            generates (ErrorStatus status, uint32_t numModelCache, uint32_t numDataCache);

    /**
     * Asynchronously creates a prepared model for execution and optionally saves it
     * into cache files.
     *
     * prepareModel is used to make any necessary transformations to or alternative
     * representations to a model for execution, possibly including
     * transformations on the constant data, optimization on the model's graph,
     * or compilation into the device's native binary format. The model itself
     * is not changed.
     *
     * Optionally, caching information may be provided for the driver to save
     * the prepared model to cache files for faster model compilation time
     * when the same model preparation is requested in the future. There are
     * two types of cache file handles provided to the driver: model cache
     * and data cache. For more information on the two types of cache handles,
     * refer to getNumberOfCacheFilesNeeded.
     *
     * The file descriptors must be opened with read and write permission. A file may
     * have any size, and the corresponding file descriptor may have any offset. The
     * driver must truncate a file to zero size before writing to that file. The file
     * descriptors may be closed by the client once the asynchronous preparation has
     * finished. The driver must dup a file descriptor if it wants to get access to
     * the cache file later.
     *
     * The model is prepared asynchronously with respect to the caller. The
     * prepareModel function must verify the inputs to the preparedModel function
     * related to preparing the model (as opposed to saving the prepared model to
     * cache) are correct. If there is an error, prepareModel must immediately invoke
     * the callback with the appropriate ErrorStatus value and nullptr for the
     * IPreparedModel, then return with the same ErrorStatus. If the inputs to the
     * prepareModel function that are related to preparing the model are valid and
     * there is no error, prepareModel must launch an asynchronous task
     * to prepare the model in the background, and immediately return from
     * prepareModel with ErrorStatus::NONE. If the asynchronous task fails to launch,
     * prepareModel must immediately invoke the callback with
     * ErrorStatus::GENERAL_FAILURE and nullptr for the IPreparedModel, then return
     * with ErrorStatus::GENERAL_FAILURE.
     *
     * When the asynchronous task has finished preparing the model, it must
     * immediately invoke the callback function provided as an input to
     * prepareModel. If the model was prepared successfully, the callback object
     * must be invoked with an error status of ErrorStatus::NONE and the
     * produced IPreparedModel object. If an error occurred preparing the model,
     * the callback object must be invoked with the appropriate ErrorStatus
     * value and nullptr for the IPreparedModel.
     *
     * Optionally, the driver may save the prepared model to cache during the
     * asynchronous preparation. Any error that occurs when saving to cache must
     * not affect the status of preparing the model. Even if the input arguments
     * related to the cache may be invalid, or the driver may fail to save to cache,
     * the prepareModel function must finish preparing the model. The driver
     * may choose not to save to cache even if the caching information is
     * provided and valid.
     *
     * The only information that may be unknown to the model at this stage is
     * the shape of the tensors, which may only be known at execution time. As
     * such, some driver services may return partially prepared models, where
     * the prepared model may only be finished when it is paired with a set of
     * inputs to the model. Note that the same prepared model object may be
     * used with different shapes of inputs on different (possibly concurrent)
     * executions.
     *
     * Multiple threads may call prepareModel on the same model concurrently.
     *
     * @param model The model to be prepared for execution.
     * @param preference Indicates the intended execution behavior of a prepared
     *     model.
     * @param modelCache A vector of handles with each entry holding exactly one
     *     cache file descriptor for the security-sensitive cache. The length of
     *     the vector must either be 0 indicating that caching information is not provided,
     *     or match the numModelCache returned from getNumberOfCacheFilesNeeded. The cache
     *     handles will be provided in the same order when retrieving the
     *     preparedModel from cache files with prepareModelFromCache.
     * @param dataCache A vector of handles with each entry holding exactly one
     *     cache file descriptor for the constants' cache. The length of
     *     the vector must either be 0 indicating that caching information is not provided,
     *     or match the numDataCache returned from getNumberOfCacheFilesNeeded. The cache
     *     handles will be provided in the same order when retrieving the
     *     preparedModel from cache files with prepareModelFromCache.
     * @param token A caching token of length Constant::BYTE_SIZE_OF_CACHE_TOKEN
     *     identifying the prepared model. The same token will be provided when retrieving
     *     the prepared model from the cache files with prepareModelFromCache.
     *     Tokens should be chosen to have a low rate of collision for a particular
     *     application. The driver cannot detect a collision; a collision will result
     *     in a failed execution or in a successful execution that produces incorrect
     *     output values. If both modelCache and dataCache are empty indicating that
     *     caching information is not provided, this token must be ignored.
     * @param callback A callback object used to return the error status of
     *     preparing the model for execution and the prepared model if
     *     successful, nullptr otherwise. The callback object's notify function
     *     must be called exactly once, even if the model could not be prepared.
     * @return status Error status of launching a task which prepares the model
     *     in the background; must be:
     *     - NONE if preparation task is successfully launched
     *     - DEVICE_UNAVAILABLE if driver is offline or busy
     *     - GENERAL_FAILURE if there is an unspecified error
     *     - INVALID_ARGUMENT if one of the input arguments related to preparing the
     *       model is invalid
     */
    prepareModel_1_2(Model model, ExecutionPreference preference,
                     vec<handle> modelCache, vec<handle> dataCache,
                     uint8_t[Constant:BYTE_SIZE_OF_CACHE_TOKEN] token,
                     IPreparedModelCallback callback)
          generates (ErrorStatus status);

    /**
     * Creates a prepared model from cache files for execution.
     *
     * prepareModelFromCache is used to retrieve a prepared model directly from
     * cache files to avoid slow model compilation time. There are
     * two types of cache file handles provided to the driver: model cache
     * and data cache. For more information on the two types of cache handles,
     * refer to getNumberOfCacheFilesNeeded.
     *
     * The file descriptors must be opened with read and write permission. A file may
     * have any size, and the corresponding file descriptor may have any offset. The
     * driver must truncate a file to zero size before writing to that file. The file
     * descriptors may be closed by the client once the asynchronous preparation has
     * finished. The driver must dup a file descriptor if it wants to get access to
     * the cache file later.
     *
     * The model is prepared asynchronously with respect to the caller. The
     * prepareModelFromCache function must verify the inputs to the
     * prepareModelFromCache function are correct, and that the security-sensitive
     * cache has not been modified since it was last written by the driver.
     * If there is an error, or if compilation caching is not supported, or if the
     * security-sensitive cache has been modified, prepareModelFromCache must
     * immediately invoke the callback with the appropriate ErrorStatus value and
     * nullptr for the IPreparedModel, then return with the same ErrorStatus. If
     * the inputs to the prepareModelFromCache function are valid, the security-sensitive
     * cache is not modified, and there is no error, prepareModelFromCache must launch an
     * asynchronous task to prepare the model in the background, and immediately return
     * from prepareModelFromCache with ErrorStatus::NONE. If the asynchronous task
     * fails to launch, prepareModelFromCache must immediately invoke the callback
     * with ErrorStatus::GENERAL_FAILURE and nullptr for the IPreparedModel, then
     * return with ErrorStatus::GENERAL_FAILURE.
     *
     * When the asynchronous task has finished preparing the model, it must
     * immediately invoke the callback function provided as an input to
     * prepareModelFromCache. If the model was prepared successfully, the
     * callback object must be invoked with an error status of ErrorStatus::NONE
     * and the produced IPreparedModel object. If an error occurred preparing
     * the model, the callback object must be invoked with the appropriate
     * ErrorStatus value and nullptr for the IPreparedModel.
     *
     * The only information that may be unknown to the model at this stage is
     * the shape of the tensors, which may only be known at execution time. As
     * such, some driver services may return partially prepared models, where
     * the prepared model may only be finished when it is paired with a set of
     * inputs to the model. Note that the same prepared model object may be
     * used with different shapes of inputs on different (possibly concurrent)
     * executions.
     *
     * @param modelCache A vector of handles with each entry holding exactly one
     *     cache file descriptor for the security-sensitive cache. The length of
     *     the vector must match the numModelCache returned from getNumberOfCacheFilesNeeded.
     *     The cache handles will be provided in the same order as with prepareModel_1_2.
     * @param dataCache A vector of handles with each entry holding exactly one
     *     cache file descriptor for the constants' cache. The length of the vector
     *     must match the numDataCache returned from getNumberOfCacheFilesNeeded.
     *     The cache handles will be provided in the same order as with prepareModel_1_2.
     * @param token A caching token of length Constant::BYTE_SIZE_OF_CACHE_TOKEN
     *     identifying the prepared model. It is the same token provided when saving
     *     the cache files with prepareModel_1_2. Tokens should be chosen
     *     to have a low rate of collision for a particular application. The driver
     *     cannot detect a collision; a collision will result in a failed execution
     *     or in a successful execution that produces incorrect output values.
     * @param callback A callback object used to return the error status of
     *     preparing the model for execution and the prepared model if
     *     successful, nullptr otherwise. The callback object's notify function
     *     must be called exactly once, even if the model could not be prepared.
     * @return status Error status of launching a task which prepares the model
     *     in the background; must be:
     *     - NONE if preparation task is successfully launched
     *     - DEVICE_UNAVAILABLE if driver is offline or busy
     *     - GENERAL_FAILURE if caching is not supported or if there is an
     *       unspecified error
     *     - INVALID_ARGUMENT if one of the input arguments is invalid
     */
    prepareModelFromCache(vec<handle> modelCache, vec<handle> dataCache,
                          uint8_t[Constant:BYTE_SIZE_OF_CACHE_TOKEN] token,
                          IPreparedModelCallback callback)
            generates (ErrorStatus status);
};