Create NeuralNetworks HAL v1.1 for new OperationTypes

Test: mm
Change-Id: I08efaba79ec28a2f89e94a84ab88b0fa701b7d98
(cherry picked from commit 5c6ee9ecefa53efe5f5ac2525196ed5e0ace7170)

3 files changed, 463 insertions, 0 deletions

diff --git a/neuralnetworks/1.1/Android.bp b/neuralnetworks/1.1/Android.bp
new file mode 100644
index 0000000000..9365d4ead1
--- /dev/null
+++ b/neuralnetworks/1.1/Android.bp
@@ -0,0 +1,24 @@
+// This file is autogenerated by hidl-gen -Landroidbp.
+
+hidl_interface {
+    name: "android.hardware.neuralnetworks@1.1",
+    root: "android.hardware",
+    vndk: {
+        enabled: true,
+    },
+    srcs: [
+        "types.hal",
+        "IDevice.hal",
+    ],
+    interfaces: [
+        "android.hardware.neuralnetworks@1.0",
+        "android.hidl.base@1.0",
+    ],
+    types: [
+        "Model",
+        "Operation",
+        "OperationType",
+    ],
+    gen_java: false,
+}
+
diff --git a/neuralnetworks/1.1/IDevice.hal b/neuralnetworks/1.1/IDevice.hal
new file mode 100644
index 0000000000..9d3fc312a6
--- /dev/null
+++ b/neuralnetworks/1.1/IDevice.hal
@@ -0,0 +1,106 @@
+/*
+ * 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 android.hardware.neuralnetworks@1.1;
+
+import @1.0::ErrorStatus;
+import @1.0::IDevice;
+import @1.0::IPreparedModelCallback;
+
+/**
+ * This interface represents a device driver.
+ */
+interface IDevice extends @1.0::IDevice {
+    /**
+     * Gets the supported operations in a model.
+     *
+     * getSupportedSubgraph 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_1(Model model)
+            generates (ErrorStatus status, vec<bool> supportedOperations);
+
+    /**
+     * Creates a prepared model for execution.
+     *
+     * prepareModel is used to make any necessary transformations or alternative
+     * representations to a model for execution, possiblly 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.
+     *
+     * The model is prepared asynchronously with respect to the caller. The
+     * prepareModel function must verify the inputs to the prepareModel function
+     * 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 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.
+     *
+     * 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 can only be finished when it is paired with a set of
+     * inputs to the model. Note that the same prepared model object can be
+     * used with different shapes of inputs on different (possibly concurrent)
+     * executions.
+     *
+     * Multiple threads can call prepareModel on the same model concurrently.
+     *
+     * @param model The model to be prepared for execution.
+     * @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 is
+     *                  invalid
+     */
+    prepareModel_1_1(Model model, IPreparedModelCallback callback)
+          generates (ErrorStatus status);
+};
diff --git a/neuralnetworks/1.1/types.hal b/neuralnetworks/1.1/types.hal
new file mode 100644
index 0000000000..18863d3e89
--- /dev/null
+++ b/neuralnetworks/1.1/types.hal
@@ -0,0 +1,333 @@
+/*
+ * 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 android.hardware.neuralnetworks@1.1;
+
+import @1.0::Operand;
+import @1.0::OperationType;
+
+/**
+ * Operation types.
+ *
+ * The type of an operation in a model.
+ */
+enum OperationType : @1.0::OperationType {
+    /**
+     * BatchToSpace for N-D tensors.
+     *
+     * This operation reshapes the "batch" dimension 0 into M + 1 dimensions of shape
+     * block_shape + [batch], interleaves these blocks back into the grid defined by the
+     * spatial dimensions [1, ..., M], to obtain a result with the same rank as the input.
+     * The spatial dimensions of this intermediate result are then optionally cropped
+     * according to the amount to crop to produce the output.
+     * This is the reverse of SpaceToBatch.
+     *
+     * Supported tensor types: {@link OperandType::TENSOR_FLOAT32}
+     *                         {@link OperandType::TENSOR_QUANT8_ASYMM}
+     * Supported tensor rank: up to 4
+     *
+     * Inputs:
+     * 0: An n-D tensor, specifying the input.
+     * 1: A 1-D Tensor of type TENSOR_INT32, the block sizes for each spatial dimension of the
+     *    input tensor. All values must be >= 1.
+     * 2: A 1-D Tensor of type TENSOR_INT32, the amount to crop for each spatial diemension of the
+     *    input tensor. All values must be >= 0.
+     *
+     * Outputs:
+     * 0: A tensor of the same type as input0.
+     */
+    BATCH_TO_SPACE_ND = 29,
+
+    /**
+     * Divides the second tensor from the first tensor, element-wise.
+     *
+     * Takes two input tensors of identical OperandType and compatible dimensions. The output
+     * is the result of dividing the first input tensor by the second, optionally
+     * modified by an activation function.
+     *
+     * Two dimensions are compatible when:
+     *     1. they are equal, or
+     *     2. one of them is 1
+     *
+     * The size of the output is the maximum size along each dimension of the input operands.
+     * It starts with the trailing dimensions, and works its way forward.
+     *
+     * Example:
+     *     input1.dimension =    {4, 1, 2}
+     *     input2.dimension = {5, 4, 3, 1}
+     *     output.dimension = {5, 4, 3, 2}
+     *
+     * Supported tensor types: {@link OperandType::TENSOR_FLOAT32}
+     * Supported tensor rank: up to 4
+     *
+     * Inputs:
+     * 0: An n-D tensor, specifying the first input.
+     * 1: A tensor of the same type, and compatible dimensions as input0.
+     * 2: An INT32 value, and has to be one of the {@link FusedActivationFunc} values.
+     *    Specifies the activation to invoke on the result of each addition.
+     *
+     * Outputs:
+     * 0: A tensor of the same type as input0.
+     */
+    DIV = 30,
+
+    /**
+     * Computes the mean of elements across dimensions of a tensor.
+     *
+     * Reduces input tensor along the dimensions given in axis. Unless keep_dims is true,
+     * the rank of the tensor is reduced by 1 for each entry in axis. If keep_dims is
+     * true, the reduced dimensions are retained with length 1.
+     *
+     * If axis has no entries, all dimensions are reduced, and a tensor with a single
+     * element is returned.
+     *
+     * Supported tensor types: {@link OperandType::TENSOR_FLOAT32}
+     *                         {@link OperandType::TENSOR_QUANT8_ASYMM}
+     * Supported tensor rank: up to 4
+     *
+     * Inputs:
+     * 0: A tensor, specifying the input.
+     * 1: A 1-D Tensor of type TENSOR_INT32. The dimensions to reduce. If None (the default),
+     *    reduces all dimensions. Must be in the range [-rank(input_tensor), rank(input_tensor)).
+     * 2: An INT32 value, keep_dims. If positive, retains reduced dimensions with length 1.
+     *
+     * Outputs:
+     * 0: A tensor of the same type as input0.
+     */
+    MEAN = 31,
+
+    /**
+     * Pads a tensor.
+     *
+     * This operation pads a tensor according to the specified paddings.
+     *
+     * Supported tensor types: {@link OperandType::TENSOR_FLOAT32}
+     *                         {@link OperandType::TENSOR_QUANT8_ASYMM}
+     * Supported tensor rank: up to 4
+     *
+     * Inputs:
+     * 0: An n-D tensor, specifying the input.
+     * 1: A 2-D Tensor of type TENSOR_INT32. The paddings, before and after for each spatial dimension
+     *    of the input tensor.
+     *
+     * Outputs:
+     * 0: A tensor of the same type as input0.
+     */
+    PAD = 32,
+
+    /**
+     * SpaceToBatch for N-D tensors.
+     *
+     * This operation divides "spatial" dimensions [1, ..., M] of the input into a grid of blocks
+     * of shape block_shape, and interleaves these blocks with the "batch" dimension (0) such that
+     * in the output, the spatial dimensions [1, ..., M] correspond to the position within the grid,
+     * and the batch dimension combines both the position within a spatial block and the original
+     * batch position. Prior to division into blocks, the spatial dimensions of the input are
+     * optionally zero padded according to paddings.
+     *
+     * Supported tensor types: {@link OperandType::TENSOR_FLOAT32}
+     *                         {@link OperandType::TENSOR_QUANT8_ASYMM}
+     * Supported tensor rank: up to 4
+     *
+     * Inputs:
+     * 0: An n-D tensor, specifying the input.
+     * 1: A 1-D Tensor of type TENSOR_INT32, the block sizes for each spatial dimension of the
+     *    input tensor. All values must be >= 1.
+     * 2: A 2-D Tensor of type TENSOR_INT32, the paddings for each spatial diemension of the
+     *    input tensor. All values must be >= 0.
+     *
+     * Outputs:
+     * 0: A tensor of the same type as input0.
+     */
+    SPACE_TO_BATCH_ND = 33,
+
+    /**
+     * Removes dimensions of size 1 from the shape of a tensor.
+     *
+     * Given a tensor input, this operation returns a tensor of the same type with all
+     * dimensions of size 1 removed. If you don't want to remove all size 1 dimensions,
+     * you can remove specific size 1 dimensions by specifying axis.
+     *
+     * Supported tensor types: {@link OperandType::TENSOR_FLOAT32}
+     *                         {@link OperandType::TENSOR_QUANT8_ASYMM}
+     * Supported tensor rank: up to 4
+     *
+     * Inputs:
+     * 0: An n-D tensor, specifying the input.
+     * 1: An 1-D Tensor of type TENSOR_INT32. The dimensions to squeeze. If None (the default),
+     *    squeezes all dimensions. If specified, only squeezes the dimensions listed. The dimension
+     *    index starts at 0. It is an error to squeeze a dimension that is not 1.
+     *
+     * Outputs:
+     * 0: A tensor of the same type as input0. Contains the same data as input, but has one or more
+     *    dimensions of size 1 removed.
+     */
+    SQUEEZE = 34,
+
+    /**
+     * Extracts a strided slice of a tensor.
+     *
+     * This op extracts a slice of size (end-begin)/stride from the given input tensor.
+    *  Starting at the location specified by begin the slice continues by adding
+     * stride to the index until all dimensions are not less than end. Note that a stride can
+     * be negative, which causes a reverse slice.
+     *
+     * Supported tensor types: {@link OperandType::TENSOR_FLOAT32}
+     *                         {@link OperandType::TENSOR_QUANT8_ASYMM}
+     * Supported tensor rank: up to 4
+     *
+     * Inputs:
+     * 0: An n-D tensor, specifying the input.
+     * 1: A 1-D Tensor of type TENSOR_INT32, the starts of the dimensions of the input
+     *    tensor to be sliced.
+     * 2: A 1-D Tensor of type TENSOR_INT32, the ends of the dimensions of the input
+     *    tensor to be sliced.
+     * 3: A 1-D Tensor of type TENSOR_INT32, the strides of the dimensions of the input
+     *    tensor to be sliced.
+     *
+     * Outputs:
+     * 0: A tensor of the same type as input0.
+     */
+    STRIDED_SLICE = 35,
+
+    /**
+     * Subtracts the second tensor from the first tensor, element-wise.
+     *
+     * Takes two input tensors of identical type and compatible dimensions. The output
+     * is the result of subtracting the second input tensor from the first one, optionally
+     * modified by an activation function.
+     *
+     * Two dimensions are compatible when:
+     *     1. they are equal, or
+     *     2. one of them is 1
+     *
+     * The size of the output is the maximum size along each dimension of the input operands.
+     * It starts with the trailing dimensions, and works its way forward.
+     *
+     * Example:
+     *     input1.dimension =    {4, 1, 2}
+     *     input2.dimension = {5, 4, 3, 1}
+     *     output.dimension = {5, 4, 3, 2}
+     *
+     * Supported tensor types: {@link OperandType::TENSOR_FLOAT32}
+     * Supported tensor rank: up to 4
+     *
+     * Inputs:
+     * 0: An n-D tensor, specifying the first input.
+     * 1: A tensor of the same type, and compatible dimensions as input0.
+     * 2: An INT32 value, and has to be one of the {@link FusedActivationFunc} values.
+     *    Specifies the activation to invoke on the result of each addition.
+     *
+     * Outputs:
+     * 0: A tensor of the same type as input0.
+     */
+    SUB = 36,
+
+    /**
+     * Transposes the input tensor, permuting the dimensions according to the perm tensor.
+     *
+     * The returned tensor's dimension i must correspond to the input dimension perm[i].
+     * If perm is not given, it is set to (n-1...0), where n is the rank of the input tensor.
+     * Hence by default, this operation performs a regular matrix transpose on 2-D input Tensors.
+     *
+     * Supported tensor types: {@link OperandType::TENSOR_FLOAT32}
+     *                         {@link OperandType::TENSOR_QUANT8_ASYMM}
+     * Supported tensor rank: up to 4
+     *
+     * Inputs:
+     * 0: An n-D tensor, specifying the input.
+     * 1: A 1-D Tensor of type TENSOR_INT32, the permutation of the dimensions of the input
+     *    tensor.
+     *
+     * Outputs:
+     * 0: A tensor of the same type as input0.
+     */
+    TRANSPOSE = 37,
+};
+
+/**
+ * Describes one operation of the model's graph.
+ */
+struct Operation {
+    /**
+     * The operation type.
+     */
+    OperationType type;
+
+    /**
+     * Describes the table that contains the indexes of the inputs of the
+     * operation. The offset is the index in the operandIndexes table.
+     */
+    vec<uint32_t> inputs;
+
+    /**
+     * Describes the table that contains the indexes of the outputs of the
+     * operation. The offset is the index in the operandIndexes table.
+     */
+    vec<uint32_t> outputs;
+};
+
+/**
+ * A Neural Network Model.
+ *
+ * This includes not only the execution graph, but also constant data such as
+ * weights or scalars added at construction time. The only information that
+ * may not be known is the shape of the input tensors.
+ */
+struct Model {
+    /**
+     * All operands included in the model.
+     */
+    vec<Operand> operands;
+
+    /**
+     * All operations included in the model.
+     *
+     * The operations are sorted into execution order.
+     */
+    vec<Operation> operations;
+
+    /**
+     * Input indexes of the model.
+     *
+     * Each value corresponds to the index of the operand in "operands".
+     */
+    vec<uint32_t> inputIndexes;
+
+    /**
+     * Output indexes of the model.
+     *
+     * Each value corresponds to the index of the operand in "operands".
+     */
+    vec<uint32_t> outputIndexes;
+
+    /**
+     * A byte buffer containing operand data that were copied into the model.
+     *
+     * An operand's value must be located here if and only if Operand::lifetime
+     * equals OperandLifeTime::CONSTANT_COPY.
+     */
+    vec<uint8_t> operandValues;
+
+    /**
+     * A collection of shared memory pools containing operand data that were
+     * registered by the model.
+     *
+     * An operand's value must be located here if and only if Operand::lifetime
+     * equals OperandLifeTime::CONSTANT_REFERENCE.
+     */
+    vec<memory> pools;
+};