HI,
We are trying to run QNN model on SA9000P using QNN SDK version 2.8.0. but getinng following error
0.0ms [VERBOSE] QnnDsp <V> AIC device 0 online. Saving it for QNN use.
0.0ms [VERBOSE] QnnDsp <V> AIC device 1000 online. Saving it for QNN use.
0.0ms [VERBOSE] QnnDsp <V> AIC device 1001 online. Saving it for QNN use.
0.0ms [ INFO ] QnnDsp <I> QnnDevice_getPlatformInfo done. status 0x0
0.0ms [ NFO ] QnnDsp <I> QnnDevice_create started. device = 0x1
0.0ms[ ERROR ] QnnDsp <E> Invalid number of cores passed: 0
0.0ms [ ERROR ] QnnDsp <E> Failed to parse default platform info: 1004
0.0ms [ ERROR ] QnnDsp <E> Failed to parse platform config: 1004
0.0ms [ INFO ] QnnDsp <I> QnnDevice_create done. status 0x3ec
1155.3ms [ ERROR ] Failed to create device: 1004
1155.3ms [ ERROR ] Device Creation failure
0.0ms [ INFO ] QnnDsp <I> terminateClient started. 0x1
Steps Followed:
1. model was created with libQnnHtpMcp.so backend and following config file.
graph_prepare_hw.conf
{
"graph": {
"num_cores" : 1,
"graph_name" : "Inception_v3_quantized"
}
}
graph_prepare_hw.json
{
"backend_extensions": {
"shared_library_path": "/data/local/tmp/lib/libQnnHtpMcpNetRunExtensions.so",
"config_file_path" : "/data/local/tmp/bin/graph_prepare_hw.conf"
}
Please provide necessary steps to execute inference on SA9000P
Thanks,
Panneerselvam N