Automatic Device Selection

This article introduces how Automatic Device Selection works and how to use it for inference.

How AUTO Works

The Automatic Device Selection mode, or AUTO for short, uses a “virtual” or a “proxy” device, which does not bind to a specific type of hardware, but rather selects the processing unit for inference automatically. It detects available devices, picks the one best-suited for the task, and configures its optimization settings. This way, you can write the application once and deploy it anywhere.

The selection also depends on your performance requirements, defined by the “hints” configuration API, as well as device priority list limitations, if you choose to exclude some hardware from the process.

The logic behind the choice is as follows:

  1. Check what supported devices are available.

  2. Check precisions of the input model (for detailed information on precisions read more on the ov::device::capabilities)

  3. Select the highest-priority device capable of supporting the given model, as listed in the table below.

  4. If model’s precision is FP32 but there is no device capable of supporting it, offload the model to a device supporting FP16.

Device Priority

Supported
Device
Supported
model precision

1

dGPU
(e.g. Intel® Iris® Xe MAX)

FP32, FP16, INT8, BIN

2

iGPU
(e.g. Intel® UHD Graphics 620 (iGPU))

FP32, FP16, BIN

3

Intel® Movidius™ Myriad™ X VPU
(e.g. Intel® Neural Compute Stick 2 (Intel® NCS2))

FP16

4

Intel® CPU
(e.g. Intel® Core™ i7-1165G7)

FP32, FP16, INT8, BIN

To put it simply, when loading the model to the first device on the list fails, AUTO will try to load it to the next device in line, until one of them succeeds. What is important, AUTO always starts inference with the CPU of the system, as it provides very low latency and can start inference with no additional delays. While the CPU is performing inference, AUTO continues to load the model to the device best suited for the purpose and transfers the task to it when ready. This way, the devices which are much slower in compiling models, GPU being the best example, do not impede inference at its initial stages. For example, if you use a CPU and a GPU, the first-inference latency of AUTO will be better than that of using GPU alone.

Note that if you choose to exclude CPU from the priority list, it will be unable to support the initial model compilation stage.

_images/autoplugin_accelerate.png

This mechanism can be easily observed in the Using AUTO with Benchmark app sample section, showing how the first-inference latency (the time it takes to compile the model and perform the first inference) is reduced when using AUTO. For example:

benchmark_app -m ../public/alexnet/FP32/alexnet.xml -d GPU -niter 128
benchmark_app -m ../public/alexnet/FP32/alexnet.xml -d AUTO -niter 128

Note

The longer the process runs, the closer realtime performance will be to that of the best-suited device.

Using AUTO

Following the OpenVINO™ naming convention, the Automatic Device Selection mode is assigned the label of “AUTO.” It may be defined with no additional parameters, resulting in defaults being used, or configured further with the following setup options:

Property
Values and Description
<device candidate list>








Values:
empty
AUTO
AUTO: <device names> (comma-separated, no spaces)

Lists the devices available for selection.
The device sequence will be taken as priority from high to low.
If not specified, AUTO will be used as default,
and all devices will be “viewed” as candidates.
ov::device:priorities





Values:
<device names> (comma-separated, no spaces)

Specifies the devices for AUTO to select.
The device sequence will be taken as priority from high to low.
This configuration is optional.
ov::hint::performance_mode





Values:
ov::hint::PerformanceMode::LATENCY
ov::hint::PerformanceMode::THROUGHPUT
ov::hint::PerformanceMode::CUMULATIVE_THROUGHPUT

Specifies the performance option preferred by the application.
ov::hint::model_priority






Values:
ov::hint::Priority::HIGH
ov::hint::Priority::MEDIUM
ov::hint::Priority::LOW

Indicates the priority for a model.
IMPORTANT: This property is not fully supported yet.

Inference with AUTO is configured similarly to when device plugins are used: you compile the model on the plugin with configuration and execute inference.

Device Candidates and Priority

The device candidate list enables you to customize the priority and limit the choice of devices available to AUTO.

  • If <device candidate list> is not specified, AUTO assumes all the devices present in the system can be used.

  • If AUTO without any device names is specified, AUTO assumes all the devices present in the system can be used, and will load the network to all devices and run inference based on their default priorities, from high to low.

To specify the priority of devices, enter the device names in the priority order (from high to low) in AUTO: <device names>, or use the ov::device:priorities property.

See the following code for using AUTO and specifying devices:

ov::Core core;

// Read a network in IR, PaddlePaddle, or ONNX format:
std::shared_ptr<ov::Model> model = core.read_model("sample.xml");

// compile a model on AUTO using the default list of device candidates.
// The following lines are equivalent:
ov::CompiledModel model0 = core.compile_model(model);
ov::CompiledModel model1 = core.compile_model(model, "AUTO");

// Optional
// You can also specify the devices to be used by AUTO.
// The following lines are equivalent:
ov::CompiledModel model3 = core.compile_model(model, "AUTO:GPU,CPU");
ov::CompiledModel model4 = core.compile_model(model, "AUTO", ov::device::priorities("GPU,CPU"));

//Optional
// the AUTO plugin is pre-configured (globally) with the explicit option:
core.set_property("AUTO", ov::device::priorities("GPU,CPU"));
    core = Core()

    # Read a network in IR, PaddlePaddle, or ONNX format:
    model = core.read_model(model_path)

    #  compile a model on AUTO using the default list of device candidates.
    #  The following lines are equivalent:
    compiled_model = core.compile_model(model=model)
    compiled_model = core.compile_model(model=model, device_name="AUTO")

    # Optional
    # You can also specify the devices to be used by AUTO.
    # The following lines are equivalent:
    compiled_model = core.compile_model(model=model, device_name="AUTO:GPU,CPU")
    compiled_model = core.compile_model(model=model, device_name="AUTO", config={"MULTI_DEVICE_PRIORITIES": "GPU,CPU"})

    # Optional
    # the AUTO plugin is pre-configured (globally) with the explicit option:
    core.set_property(device_name="AUTO", properties={"MULTI_DEVICE_PRIORITIES":"GPU,CPU"})

Note that OpenVINO Runtime lets you use “GPU” as an alias for “GPU.0” in function calls. More details on enumerating devices can be found in Working with devices.

Checking Available Devices

To check what devices are present in the system, you can use Device API, as listed below. For information on how to use it, see Query device properties and configuration.

ov::runtime::Core::get_available_devices()

See the Hello Query Device C++ Sample for reference.

openvino.runtime.Core.available_devices

See the Hello Query Device Python Sample for reference.

Excluding Devices from Device Candidate List

You can also exclude hardware devices from AUTO, for example, to reserve CPU for other jobs. AUTO will not use the device for inference then. To do that, add a minus sign (-) before CPU in AUTO: <device names>, as in the following example:

ov::CompiledModel compiled_model = core.compile_model(model, "AUTO:-CPU");
compiled_model = core.compile_model(model=model, device_name="AUTO:-CPU")

AUTO will then query all available devices and remove CPU from the candidate list.

Note that if you choose to exclude CPU from device candidate list, CPU will not be able to support the initial model compilation stage. See more information in How AUTO Works.

Performance Hints for AUTO

The ov::hint::performance_mode property enables you to specify a performance option for AUTO to be more efficient for particular use cases.

Note

Currently, the ov::hint property is supported by CPU and GPU devices only.

THROUGHPUT

This option prioritizes high throughput, balancing between latency and power. It is best suited for tasks involving multiple jobs, such as inference of video feeds or large numbers of images.

Note

If no performance hint is set explicitly, AUTO will set THROUGHPUT for devices that have not set ov::device::properties. For example, if you have both a CPU and a GPU in the system, this command core.compile_model("AUTO", ov::device::properties("CPU", ov::enable_profiling(true))) will set THROUGHPUT for the GPU only. No hint will be set for the CPU although it’s the selected device.

LATENCY

This option prioritizes low latency, providing short response time for each inference job. It performs best for tasks where inference is required for a single input image, e.g. a medical analysis of an ultrasound scan image. It also fits the tasks of real-time or nearly real-time applications, such as an industrial robot’s response to actions in its environment or obstacle avoidance for autonomous vehicles.

CUMULATIVE_THROUGHPUT

While LATENCY and THROUGHPUT can select one target device with your preferred performance option, the CUMULATIVE_THROUGHPUT option enables running inference on multiple devices for higher throughput. With CUMULATIVE_THROUGHPUT, AUTO loads the network model to all available devices in the candidate list, and then runs inference on them based on the default or specified priority.

CUMULATIVE_THROUGHPUT has similar behavior as the Multi-Device execution mode (MULTI). The only difference is that CUMULATIVE_THROUGHPUT uses the devices specified by AUTO, which means that it’s not mandatory to add devices manually, while with MULTI, you need to specify the devices before inference.

With the CUMULATIVE_THROUGHPUT option:

  • If AUTO without any device names is specified, and the system has more than two GPU devices, AUTO will remove CPU from the device candidate list to keep GPU running at full capacity.

  • If device priority is specified, AUTO will run inference requests on devices based on the priority. In the following example, AUTO will always try to use GPU first, and then use CPU if GPU is busy:

    ov::CompiledModel compiled_model = core.compile_model(model, "AUTO:GPU,CPU", ov::hint::performance_mode(ov::hint::PerformanceMode::CUMULATIVE_THROUGHPUT));

Code Examples

To enable performance hints for your application, use the following code:

ov::Core core;

// Read a network in IR, PaddlePaddle, or ONNX format:
std::shared_ptr<ov::Model> model = core.read_model("sample.xml");

// Compile a model on AUTO with Performance Hint enabled:
// To use the “THROUGHPUT” option:
ov::CompiledModel compiled_model = core.compile_model(model, "AUTO",
    ov::hint::performance_mode(ov::hint::PerformanceMode::THROUGHPUT));
// To use the “LATENCY” option:
ov::CompiledModel compiled_mode2 = core.compile_model(model, "AUTO",
    ov::hint::performance_mode(ov::hint::PerformanceMode::LATENCY));
// To use the “CUMULATIVE_THROUGHPUT” option:
ov::CompiledModel compiled_mode3 = core.compile_model(model, "AUTO",
    ov::hint::performance_mode(ov::hint::PerformanceMode::CUMULATIVE_THROUGHPUT));    
    core = Core()
    # Read a network in IR, PaddlePaddle, or ONNX format:
    model = core.read_model(model_path)
    # Compile a model on AUTO with Performance Hints enabled:
    # To use the “THROUGHPUT” mode:
    compiled_model = core.compile_model(model=model, device_name="AUTO", config={"PERFORMANCE_HINT":"THROUGHPUT"})
    # To use the “LATENCY” mode:
    compiled_model = core.compile_model(model=model, device_name="AUTO", config={"PERFORMANCE_HINT":"LATENCY"})
    # To use the “CUMULATIVE_THROUGHPUT” mode:
    compiled_model = core.compile_model(model=model, device_name="AUTO", config={"PERFORMANCE_HINT":"CUMULATIVE_THROUGHPUT"})

Disabling Auto-Batching for THROUGHPUT and CUMULATIVE_THROUGHPUT

The ov::hint::PerformanceMode::THROUGHPUT mode and the ov::hint::PerformanceMode::CUMULATIVE_THROUGHPUT mode will trigger Auto-Batching (for example, for the GPU device) by default. You can disable it by setting ov::hint::allow_auto_batching(false), or change the default timeout value to a large number, e.g. ov::auto_batch_timeout(1000). See Automatic Batching for more details.

Configuring Model Priority

The ov::hint::model_priority property enables you to control the priorities of models in the Auto-Device plugin. A high-priority model will be loaded to a supported high-priority device. A lower-priority model will not be loaded to a device that is occupied by a higher-priority model.

// Example 1
ov::CompiledModel compiled_model0 = core.compile_model(model, "AUTO",
    ov::hint::model_priority(ov::hint::Priority::HIGH));
ov::CompiledModel compiled_model1 = core.compile_model(model, "AUTO",
    ov::hint::model_priority(ov::hint::Priority::MEDIUM));
ov::CompiledModel compiled_model2 = core.compile_model(model, "AUTO",
    ov::hint::model_priority(ov::hint::Priority::LOW));
/************
  Assume that all the devices (CPU, GPU, and MYRIAD) can support all the networks.
  Result: compiled_model0 will use GPU, compiled_model1 will use MYRIAD, compiled_model2 will use CPU.
 ************/

// Example 2
ov::CompiledModel compiled_model3 = core.compile_model(model, "AUTO",
    ov::hint::model_priority(ov::hint::Priority::LOW));
ov::CompiledModel compiled_model4 = core.compile_model(model, "AUTO",
    ov::hint::model_priority(ov::hint::Priority::MEDIUM));
ov::CompiledModel compiled_model5 = core.compile_model(model, "AUTO",
    ov::hint::model_priority(ov::hint::Priority::LOW));
/************
  Assume that all the devices (CPU, GPU, and MYRIAD) can support all the networks.
  Result: compiled_model3 will use GPU, compiled_model4 will use GPU, compiled_model5 will use MYRIAD.
 ************/
    core = Core()
    model = core.read_model(model_path)

    # Example 1
    compiled_model0 = core.compile_model(model=model, device_name="AUTO", config={"MODEL_PRIORITY":"HIGH"})
    compiled_model1 = core.compile_model(model=model, device_name="AUTO", config={"MODEL_PRIORITY":"MEDIUM"})
    compiled_model2 = core.compile_model(model=model, device_name="AUTO", config={"MODEL_PRIORITY":"LOW"})
    # Assume that all the devices (CPU, GPU, and MYRIAD) can support all the networks.
    # Result: compiled_model0 will use GPU, compiled_model1 will use MYRIAD, compiled_model2 will use CPU.

    # Example 2
    compiled_model3 = core.compile_model(model=model, device_name="AUTO", config={"MODEL_PRIORITY":"HIGH"})
    compiled_model4 = core.compile_model(model=model, device_name="AUTO", config={"MODEL_PRIORITY":"MEDIUM"})
    compiled_model5 = core.compile_model(model=model, device_name="AUTO", config={"MODEL_PRIORITY":"LOW"})
    # Assume that all the devices (CPU, GPU, and MYRIAD) can support all the networks.
    # Result: compiled_model3 will use GPU, compiled_model4 will use GPU, compiled_model5 will use MYRIAD.

Configuring Individual Devices and Creating the Auto-Device plugin on Top

Although the methods described above are currently the preferred way to execute inference with AUTO, the following steps can be also used as an alternative. It is currently available as a legacy feature and used if the device candidate list includes Myriad devices, uncapable of utilizing the Performance Hints option.

ov::Core core;

// Read a network in IR, PaddlePaddle, or ONNX format:
std::shared_ptr<ov::Model> model = core.read_model("sample.xml");

// Configure  CPU and the MYRIAD devices when compiled model
ov::CompiledModel compiled_model = core.compile_model(model, "AUTO",
    ov::device::properties("CPU", cpu_config),
    ov::device::properties("MYRIAD", myriad_config));
    core = Core()
    model = core.read_model(model_path)
    core.set_property(device_name="CPU", properties={})
    core.set_property(device_name="MYRIAD", properties={})
    compiled_model = core.compile_model(model=model)
    compiled_model = core.compile_model(model=model, device_name="AUTO")

Using AUTO with OpenVINO Samples and Benchmark app

To see how the Auto-Device plugin is used in practice and test its performance, take a look at OpenVINO™ samples. All samples supporting the “-d” command-line option (which stands for “device”) will accept the plugin out-of-the-box. The Benchmark Application will be a perfect place to start – it presents the optimal performance of the plugin without the need for additional settings, like the number of requests or CPU threads. To evaluate the AUTO performance, you can use the following commands:

For unlimited device choice:

benchmark_app d AUTO m <model> -i <input> -niter 1000

For limited device choice:

benchmark_app d AUTO:CPU,GPU,MYRIAD m <model> -i <input> -niter 1000

For more information, refer to the C++ or Python version instructions.

Note

The default CPU stream is 1 if using “-d AUTO”.

You can use the FP16 IR to work with auto-device.

No demos are yet fully optimized for AUTO, by means of selecting the most suitable device, using the GPU streams/throttling, and so on.