The heterogeneous plugin enables computing for inference on one network on several devices. Purposes to execute networks in heterogeneous mode
The execution through heterogeneous plugin can be divided to two independent steps:
InferenceEngine::ICNNNetwork
)These steps are decoupled. The setting of affinity can be done automatically using fallback policy or in manual mode.
The fallback automatic policy means greedy behavior and assigns all layers which can be executed on certain device on that device follow priorities.
Some of the topologies are not friendly to heterogeneous execution on some devices or cannot be executed in such mode at all. Example of such networks might be networs having activation layers which are not supported on primary device. If transmitting of data from one part of network to another part in heterogeneous mode takes relatively much time, then it is not much sense to execute them in heterogeneous mode on these devices. In this case you can define heaviest part manually and set affinity thus way to avoid sending of data back and forth many times during one inference.
Default fallback policy decides which layer goes to which device automatically according to the support in dedicated plugins (FPGA,GPU,CPU,VPU).
Another way to annotate a network is setting affinity manually using CNNLayer::affinity
field. This field accepts string values of devices like "CPU" or "FPGA".
The fallback policy does not work if even one layer has initialized affinity. The sequence should be calling of automating affinity settings and then fix manually.
If you rely on default affinity distribution, you can avoid calling IHeteroInferencePlugin::SetAffinity
and just call ICNNNetwork::LoadNetwork
instead:
During loading of the network to heterogeneous plugin, network is divided to separate parts and loaded to dedicated plugins. Intermediate blobs between these sub graphs are allocated automatically in the most efficient way.
Precision for inference in heterogeneous plugin is defined by
Examples:
Samples can be used with the following command:
where:
HETERO
stands for heterogeneous pluginFPGA,CPU
points to fallback policy with priority on FPGA and fallback to CPUYou can point more than two devices: -d HETERO:FPGA,GPU,CPU
After enabling of KEY_HETERO_DUMP_GRAPH_DOT
config key, you can dump GraphViz* .dot
files with annotations of devices per layer.
Heterogeneous plugin can generate two files:
hetero_affinity_<network name>.dot
- annotation of affinities per layer. This file is written to the disk only if default fallback policy was executedhetero_subgraphs_<network name>.dot
- annotation of affinities per graph. This file is written to the disk during execution of ICNNNetwork::LoadNetwork()
for heterogeneous pluginYou can use GraphViz* utility or converters to .png
formats. On Ubuntu* operating system, you can use the following utilities:
sudo apt-get install xdot
xdot hetero_subgraphs.dot
Besides generation of .dot files, you can use error listening mechanism:
If during network loading some layers are deciced to be executed on a fallback plugin, the following message is printed:
You can use performance data (in samples, it is an option -pc
) to get performance data on each subgraph.
Here is an example of the output: for Googlenet v1 running on FPGA with fallback to CPU: