Intel® Gaussian & Neural Accelerator is a low-power neural coprocessor for continuous inference at the edge.
Intel® GNA is not intended to replace classic inference devices such as CPU, graphics processing unit (GPU), or vision processing unit (VPU). It is designed for offloading continuous inference workloads including but not limited to noise reduction or speech recognition to save power and free CPU resources.
The GNA plugin provides a way to run inference on Intel® GNA, as well as in the software execution mode on CPU.
Devices with Intel® GNA support:
NOTE: On platforms where Intel® GNA is not enabled in the BIOS, the driver cannot be installed, so the GNA plugin uses the software emulation mode only.
Intel® GNA hardware requires a driver to be installed on the system.
Because of specifics of hardware architecture, Intel® GNA supports a limited set of layers, their kinds and combinations. For example, you should not expect the GNA Plugin to be able to run computer vision models, except those specifically adapted for the GNA Plugin, because the plugin does not fully support 2D convolutions.
For the list of supported layers, see the GNA column of the Supported Layers section in Supported Devices.
The Intel® GNA hardware natively supports only 1D convolutions.
However, 2D convolutions can be mapped to 1D when a convolution kernel moves in a single direction. GNA Plugin performs such a transformation for Kaldi
nnet1 convolution. From this perspective, the Intel® GNA hardware convolution operation accepts an
NHWC input and produces an
NHWC output. Because OpenVINO™ only supports the
NCHW layout, you may need to insert
Permute layers before or after convolutions.
For example, the Kaldi model optimizer inserts such a permute after convolution for the rm_cnn4a network. This
Permute layer is automatically removed by the GNA Plugin, because the Intel® GNA hardware convolution layer already produces the required
Intel® GNA essentially operates in the low-precision mode, which represents a mix of 8-bit (
I8), 16-bit (
I16), and 32-bit (
I32) integer computations. Outputs calculated using a reduced integer precision are different from the scores calculated using the floating point format, for example,
FP32 outputs calculated on CPU using the Inference Engine CPU Plugin.
Unlike other plugins supporting low-precision execution, the GNA plugin can calculate quantization factors at the model loading time, so you can run a model without calibration using the Post-Training Optimizaton Tool. However, this mode may not provide satisfactory accuracy because the internal quantization algorithm is based on heuristics which may or may not be efficient, depending on the model and dynamic range of input data.
Starting with 2021.4 release of OpenVINO, GNA plugin users are encouraged to use the POT API Usage sample for GNA to get a model with quantization hints based on statistics for the provided dataset.
|Uses Intel® GNA if available, otherwise uses software execution mode on CPU.|
|Uses Intel® GNA if available, otherwise raises an error.|
|Deprecated. Executes the GNA-compiled graph on CPU performing calculations in the same precision as the Intel® GNA, but not in the bit-exact mode.|
|Executes the GNA-compiled graph on CPU performing calculations in the same precision as the Intel® GNA in the bit-exact mode.|
|Executes the GNA-compiled graph on CPU but substitutes parameters and calculations from low precision to floating point (|
The plugin supports the configuration parameters listed below. The parameters are passed as
std::map<std::string, std::string> on
You can change the
KEY_GNA_DEVICE_MODE parameter at run time using
InferenceEngine::ExecutableNetwork::SetConfig, which works for any value excluding
GNA_SW_FP32. This enables you to switch the execution between software emulation mode and hardware emulation mode after the model is loaded.
The parameter names below correspond to their usage through API keys, such as
PluginConfigParams::KEY_PERF_COUNT. When specifying key values as raw strings, that is, when using Python API, omit the
|Parameter Name||Parameter Values||Default Value||Description|
|Enables I/O buffers reuse to save space. Makes debugging harder.|
|1.0||Sets the scale factor to use for input quantization.|
|One of the modes described in Execution Modes|
|Sets the name for the embedded model binary dump file.|
|Sets the preferred integer weight resolution for quantization (ignored for models produced using POT).|
|Turns on performance counters reporting.|
|1-127 integer number||1||Sets the number of GNA accelerator library worker threads used for inference computation in software modes.|
As a result of collecting performance counters using
InferenceEngine::InferRequest::GetPerformanceCounts, you can find various performance data about execution on GNA. Returned map stores a counter description as a key, and a counter value in the
realTime_uSec field of the
InferenceEngineProfileInfo structure. Current GNA implementation calculates counters for the whole utterance scoring and does not provide per-layer information. The API enables you to retrieve counter units in cycles, you can convert cycles to seconds as follows:
Refer to the table below to learn about the frequency of Intel® GNA inside a particular processor.
|Processor||Frequency of Intel® GNA|
|Intel® Ice Lake processors||400MHz|
|Intel® Core™ i3-8121U processor||400MHz|
|Intel® Gemini Lake processors||200MHz|
Performance counters provided for the time being:
The GNA plugin supports the following configuration parameters for multithreading management:
By default, the GNA plugin uses one worker thread for inference computations. This parameter allows you to create up to 127 threads for software modes.
NOTE: Multithreading mode does not guarantee the same computation order as the order of issuing. Additionally, in this case, software modes do not implement any serializations.
Intel® GNA plugin supports the processing of context-windowed speech frames in batches of 1-8 frames in one input blob using
InferenceEngine::ICNNNetwork::setBatchSize. Increasing batch size only improves efficiency of
Fully Connected layers.
NOTE: For networks with
Memorylayers, the only supported batch size is 1.
Heterogeneous plugin was tested with the Intel® GNA as a primary device and CPU as a secondary device. To run inference of networks with layers unsupported by the GNA plugin, such as Softmax, use the Heterogeneous plugin with the
NOTE: Due to limitation of the Intel® GNA backend library, heterogenous support is limited to cases where in the resulted sliced graph, only one subgraph is scheduled to run on GNA_HW or GNA_SW devices.
GNA is designed for real-time workloads such as noise reduction. For such workloads, processing should be time constrained, otherwise extra delays may cause undesired effects such as audio glitches. To make sure that processing can satisfy real-time requirements, the GNA driver provides a Quality of Service (QoS) mechanism, which interrupts requests that might cause high-priority Windows audio processes to miss the schedule, thereby causing long running GNA tasks to terminate early.
Applications should be prepared for this situation. If an inference in the
GNA_HW mode cannot be executed because of such an interruption, then
InferRequest::Wait() returns status code
StatusCode::INFER_NOT_STARTED. In future releases, it will be changed to a more meaningful status code.
Any application working with GNA must properly react to this code. One of the strategies to adapt an application: