Google is committed to advancing racial equity for Black communities. See how.

Memory Pools

This page describes the data structures and methods used to efficiently communicate operand buffers between the driver and the framework.

At model compilation time, the framework provides the values of the constant operands to the driver. Depending on the lifetime of the constant operand, its values are located either in a HIDL vector or a shared memory pool.

  • If the lifetime is CONSTANT_COPY, the values are located in the operandValues field of the model structure. Because the values in the HIDL vector are copied during interprocess communication (IPC), this is typically used only to hold a small amount of data such as scalar operands (for example, the activation scalar in ADD) and small tensor parameters (for example, the shape tensor in RESHAPE).
  • If the lifetime is CONSTANT_REFERENCE, the values are located in the pools field of the model structure. Only the handles of the shared memory pools are duplicated during IPC rather than copying the raw values. Therefore, it's more efficient to hold a large amount of data (for example, the weight parameters in convolutions) using shared memory pools than HIDL vectors.

At model execution time, the framework provides the buffers of the input and output operands to the driver. Unlike the compile-time constants that might be sent in a HIDL vector, the input and output data of an execution is always communicated through a collection of memory pools.

The HIDL data type hidl_memory is used in both compilation and execution to represent an unmapped shared memory pool. The driver should map the memory accordingly to make it usable based on the name of the hidl_memory data type. The supported memory names are:

  • ashmem: Android shared memory. For more details, see memory.
  • mmap_fd: Shared memory backed by a file descriptor through mmap.
  • hardware_buffer_blob: Shared memory backed by a AHardwareBuffer with the format AHARDWARE_BUFFER_FORMAT_BLOB. Available from Neural Networks (NN) HAL 1.2. For more details, see AHardwareBuffer.
  • hardware_buffer: Shared memory backed by a general AHardwareBuffer that doesn't use the format AHARDWARE_BUFFER_FORMAT_BLOB. The non-BLOB mode hardware buffer is only supported in model execution.Available from NN HAL 1.2. For more details, see AHardwareBuffer.

From NN HAL 1.3, NNAPI supports memory domains that provide allocator interfaces for driver-managed buffers. The driver-managed buffers can also be used as execution inputs or outputs. For more details, see Memory domains.

NNAPI drivers must support mapping of ashmem and mmap_fd memory names. From NN HAL 1.3, drivers must also support mapping of hardware_buffer_blob. Support for general non-BLOB mode hardware_buffer and memory domains is optional.


AHardwareBuffer is a type of shared memory that wraps a Gralloc buffer. In Android 10, the Neural Networks API (NNAPI) supports using AHardwareBuffer, allowing the driver to perform executions without copying data, which improves performance and power consumption for apps. For example, a camera HAL stack can pass AHardwareBuffer objects to the NNAPI for machine learning workloads using AHardwareBuffer handles generated by camera NDK and media NDK APIs. For more information, see ANeuralNetworksMemory_createFromAHardwareBuffer.

AHardwareBuffer objects used in NNAPI are passed to the driver through a hidl_memory struct named either hardware_buffer or hardware_buffer_blob. The hidl_memory struct hardware_buffer_blob represents only AHardwareBuffer objects with the AHARDWAREBUFFER_FORMAT_BLOB format.

The information required by the framework is encoded in the hidl_handle field of the hidl_memory struct. The hidl_handle field wraps native_handle, which encodes all of the required metadata about AHardwareBuffer or Gralloc buffer.

The driver must properly decode the provided hidl_handle field and access the memory described by hidl_handle. When the getSupportedOperations_1_2, getSupportedOperations_1_1, or getSupportedOperations method is called, the driver should detect whether it can decode the provided hidl_handle and access the memory described by hidl_handle. The model preparation must fail if the hidl_handle field used for a constant operand isn't supported. The execution must fail if the hidl_handle field used for an input or output operand of the execution isn't supported. It's recommended for the driver to return a GENERAL_FAILURE error code if the model preparation or execution fails.

Memory domains

For devices running Android 11 or higher, NNAPI supports memory domains that provide allocator interfaces for driver-managed buffers. This allows for passing device native memories across executions, suppressing unnecessary data copying and transformation between consecutive executions on the same driver. This flow is illustrated in Figure 1.

Buffer data flow with and without memory domains
Figure 1. Buffer data flow using memory domains

The memory domain feature is intended for tensors that are mostly internal to the driver and don't need frequent access on the client side. Examples of such tensors include the state tensors in sequence models. For tensors that need frequent CPU access on the client side, it's preferable to use shared memory pools.

To support the memory domain feature, implement IDevice::allocate to allow the framework to request for driver-managed buffer allocation. During the allocation, the framework provides the following properties and usage patterns for the buffer:

  • BufferDesc describes the required properties of the buffer.
  • BufferRole describes the potential usage pattern of the buffer as an input or output of a prepared model. Multiple roles can be specified during the buffer allocation, and the allocated buffer can be used only as those specified roles.

The allocated buffer is internal to the driver. A driver can choose any buffer location or data layout. When the buffer is successfully allocated, the client of the driver can reference or interact with the buffer using the returned token or the IBuffer object.

The token from IDevice::allocate is provided when referencing the buffer as one of the MemoryPool objects in the Request structure of an execution. To prevent a process from trying to access the buffer allocated in another process, the driver must apply proper validation upon every use of the buffer. The driver must validate that the buffer usage is one of the BufferRole roles provided during the allocation and must fail the execution immediately if the usage is illegal.

The IBuffer object is used for explicit memory copying. In certain situations, the client of the driver must initialize the driver-managed buffer from a shared memory pool or copy the buffer out to a shared memory pool. Example use cases include:

  • Initialization of the state tensor
  • Caching intermediate results
  • Fallback execution on CPU

To support these use cases, the driver must implement IBuffer::copyTo and IBuffer::copyFrom with ashmem, mmap_fd, and hardware_buffer_blob if it supports memory domain allocation. It's optional for the driver to support non-BLOB mode hardware_buffer.

During buffer allocation, the dimensions of the buffer can be deduced from the corresponding model operands of all the roles specified by BufferRole, and the dimensions provided in BufferDesc. With all the dimensional information combined, the buffer might have unknown dimensions or rank. In such a case, the buffer is in a flexible state where the dimensions are fixed when used as a model input and in a dynamic state when used as a model output. The same buffer can be used with different shapes of outputs in different executions and the driver must handle the buffer resizing properly.

Memory domain is an optional feature. A driver can determine that it can't support a given allocation request for a number of reasons. For example:

  • The requested buffer has a dynamic size.
  • The driver has memory constraints preventing it from handling large buffers.

It's possible for several different threads to read from the driver-managed buffer concurrently. Accessing the buffer simultaneously for write or read/write is undefined, but it must not crash the driver service or block the caller indefinitely. The driver can return an error or leave the buffer's content in an indeterminate state.