Accelerated CPU
On Artpec-9, there are three backends you may use to execute your model;
- DLPU -- fast, limited operator support
- CPU -- slow, large operator support
- Accelerated CPU -- moderately fast, moderate operator support
The Accelerated CPU is a good backend to use if you have the need to run your model faster than what the regular CPU allows, but struggle to fit all (or most) of your model operators on the DLPU.
Simply use the "armnn-cpu-tflite" backend to run your model on the accelerated CPU:
larod-client -g <my-model>.tflite -c armnn-cpu-tflite -i ""
Supported Ops
| Operator | Known limitations |
|---|---|
| ABS | |
| ADD | |
| ARG_MAX | |
| ARG_MIN | |
| AVERAGE_POOL_2D | Supported Fused Activation: RELU, RELU6, RELU_N1_TO_1, SIGMOID, TANH, NONE |
| AVERAGE_POOL_3D | Supported Fused Activation: RELU, RELU6, RELU_N1_TO_1, SIGMOID, SIGN_BIT, TANH, NONE |
| BATCH_MATMUL | |
| BATCH_TO_SPACE_ND | |
| BROADCAST_TO | |
| CAST | |
| CEIL | |
| CONCATENATION | Supported Fused Activation: RELU, RELU6, RELU_N1_TO_1, SIGMOID, TANH, NONE |
| CONV_2D | Supported Fused Activation: RELU, RELU6, RELU_N1_TO_1, SIGMOID, TANH, NONE |
| CONV_3D | Supported Fused Activation: RELU, RELU6, RELU_N1_TO_1, SIGMOID, TANH, NONE |
| DEPTH_TO_SPACE | |
| DEPTHWISE_CONV_2D | Supported Fused Activation: RELU, RELU6, RELU_N1_TO_1, SIGMOID, TANH, NONE |
| DEQUANTIZE | |
| DIV | |
| EQUAL | |
| ELU | |
| EXP | |
| EXPAND_DIMS | |
| FILL | |
| FLOOR | |
| FLOOR_DIV | |
| FULLY_CONNECTED | Supported Fused Activation: RELU, RELU6, RELU_N1_TO_1, SIGMOID, TANH, NONE |
| GATHER | |
| GATHER_ND | |
| GELU | |
| GREATER | |
| GREATER_EQUAL | |
| HARD_SWISH | |
| L2_NORMALIZATION | |
| L2_POOL_2D | |
| LESS | |
| LESS_EQUAL | |
| LOCAL_RESPONSE_NORMALIZATION | |
| LOG | |
| LOGICAL_AND | |
| LOGICAL_NOT | |
| LOGICAL_OR | |
| LOGISTIC | |
| LOG_SOFTMAX | |
| LSTM | |
| MAXIMUM | |
| MAX_POOL_2D | Supported Fused Activation: RELU, RELU6, RELU_N1_TO_1, SIGMOID, TANH, NONE |
| MAX_POOL_3D | Supported Fused Activation: RELU, RELU6, RELU_N1_TO_1, SIGMOID, SIGN_BIT, TANH, NONE |
| MEAN | |
| MINIMUM | |
| MIRROR_PAD | |
| MUL | |
| NEG | |
| NOT_EQUAL | |
| PACK | |
| PAD | |
| PADV2 | |
| POW | |
| PRELU | |
| QUANTIZE | |
| RANK | |
| REDUCE_MAX | |
| REDUCE_MIN | |
| REDUCE_PROD | |
| RELU | |
| RELU6 | |
| RELU_N1_TO_1 | |
| RESHAPE | |
| RESIZE_BILINEAR | |
| RESIZE_NEAREST_NEIGHBOR | |
| REVERSEV2 | |
| RSQRT | |
| SCATTERND | |
| SHAPE | |
| SIN | |
| SOFTMAX | |
| SPACE_TO_BATCH_ND | |
| SPACE_TO_DEPTH | |
| SPLIT | |
| SPLIT_V | |
| SQRT | |
| SQUARE_DIFFERENCE | |
| SQUEEZE | |
| SLICE | |
| STRIDED_SLICE | |
| SUB | |
| SUM | |
| TANH | |
| TILE | |
| TRANSPOSE | |
| TRANSPOSE_CONV | |
| UNIDIRECTIONAL_SEQUENCE_LSTM | |
| UNPACK |