hls4ml.backends.quartus package
Subpackages
- hls4ml.backends.quartus.passes package
- Submodules
- hls4ml.backends.quartus.passes.bn_quant module
- hls4ml.backends.quartus.passes.convolution_templates module
- hls4ml.backends.quartus.passes.convolution_winograd module
- hls4ml.backends.quartus.passes.core_templates module
ActivationConfigTemplate
ActivationFunctionTemplate
BatchNormalizationConfigTemplate
BatchNormalizationFunctionTemplate
DenseConfigTemplate
DenseFunctionTemplate
HardActivationConfigTemplate
PReLUFunctionTemplate
ParamActivationConfigTemplate
ParametrizedActivationFunctionTemplate
SoftmaxConfigTemplate
- hls4ml.backends.quartus.passes.merge_templates module
- hls4ml.backends.quartus.passes.pointwise module
- hls4ml.backends.quartus.passes.pooling_templates module
- hls4ml.backends.quartus.passes.quantization_templates module
- hls4ml.backends.quartus.passes.recurrent_templates module
- hls4ml.backends.quartus.passes.reshaping_templates module
- hls4ml.backends.quartus.passes.resource_strategy module
- hls4ml.backends.quartus.passes.transform_types module
- Module contents
Submodules
hls4ml.backends.quartus.quartus_backend module
- class hls4ml.backends.quartus.quartus_backend.QuartusBackend
Bases:
FPGABackend
- build(model, synth=True, fpgasynth=False, log_level=1, cont_if_large_area=False)
Builds the project using Intel HLS compiler.
- Parameters:
model (ModelGraph) – The model to build
synth – Whether to run HLS synthesis
optional – Whether to run HLS synthesis
fpgasynth – Whether to run FPGA synthesis (Quartus Compile)
optional – Whether to run FPGA synthesis (Quartus Compile)
log_level – Logging level to be displayed during HLS synthesis (0, 1, 2)
optional – Logging level to be displayed during HLS synthesis (0, 1, 2)
cont_if_large_area – Instruct the HLS compiler to continue synthesis if the estimated resource usage exceeds device resources
Errors raise exceptions
- create_initial_config(part='Arria10', clock_period=5, io_type='io_parallel', **_)
Create the minimal conversion config for the backend.
Subclasses should implement this method to provide the initial configuration for the conversion.
- get_default_flow()
The name of the default flow of the backend.
Default flow is used as the conversion target if the target flow has not been specified.
- get_writer_flow()
- init_activation(layer)
- init_base_layer(layer)
- init_conv1d(layer)
- init_conv2d(layer)
- init_dense(layer)
- init_embed(layer)
- init_gru(layer)
- init_lstm(layer)
- init_simple_rnn(layer)
- init_softmax(layer)
- hls4ml.backends.quartus.quartus_backend.chdir(newdir)
hls4ml.backends.quartus.quartus_types module
- class hls4ml.backends.quartus.quartus_types.QuartusArrayVariableConverter(type_converter)
Bases:
ArrayVariableConverter
- class hls4ml.backends.quartus.quartus_types.QuartusArrayVariableDefinition
Bases:
VariableDefinition
- definition_cpp(name_suffix='', as_reference=False)
- class hls4ml.backends.quartus.quartus_types.QuartusInplaceArrayVariableConverter(type_converter)
Bases:
ArrayVariableConverter
- class hls4ml.backends.quartus.quartus_types.QuartusInplaceArrayVariableDefinition
Bases:
VariableDefinition
- definition_cpp()
- class hls4ml.backends.quartus.quartus_types.QuartusInplaceStreamVariableConverter(type_converter)
- class hls4ml.backends.quartus.quartus_types.QuartusInplaceStreamVariableDefinition
Bases:
VariableDefinition
- definition_cpp()
- class hls4ml.backends.quartus.quartus_types.QuartusStreamVariableConverter(type_converter)
Bases:
StreamVariableConverter
- class hls4ml.backends.quartus.quartus_types.QuartusStreamVariableDefinition
Bases:
VariableDefinition
- definition_cpp(name_suffix='', as_reference=False)
- class hls4ml.backends.quartus.quartus_types.QuartusStructMemberVariableConverter(type_converter)
- class hls4ml.backends.quartus.quartus_types.QuartusStructMemberVariableDefinition
Bases:
VariableDefinition
- definition_cpp(name_suffix='', as_reference=False)