manupa-arm commented on PR #60: URL: https://github.com/apache/tvm-rfcs/pull/60#issuecomment-1122520135
@areusch and @MichaelJKlaiber, I agree with using [Target-registered compilation flow customization](https://github.com/apache/tvm-rfcs/blob/main/rfcs/0010-target-registered-compiler-flow-customisation.md). I am struggling to how to connect that with : ``` TVM_REGISTER_GLOBAL("relay.backend.contrib.uma.RegisterTarget") .set_body_typed([](String target_name){ ::tvm::TargetKindRegEntry::RegisterOrGet(target_name) .set_name() .set_device_type(kDLCPU) .add_attr_option<Array<String>>("keys") .add_attr_option<String>("tag") .add_attr_option<String>("device") .add_attr_option<String>("model") .add_attr_option<Array<String>>("libs") .add_attr_option<Target>("host") .add_attr_option<Integer>("from_device") .set_attr<FTVMRelayToTIR>("RelayToTIR", relay::contrib::uma::RelayToTIR(target_name)) .set_attr<FTVMTIRToRuntime>("TIRToRuntime", relay::contrib::uma::TIRToRuntime); }); ``` What would be the API to add an option ? e.g. from here ``` class UltraTrailBackend(UMABackend): def __init__(self): super(UltraTrailBackend, self).__init__() # Relay to Relay function registration self._register_pattern("conv1d_relu", conv1d_relu_pattern()) self._register_relay_pass(1, ConfigGenerator()) self._register_relay_pass(2, BufferScopeAnnotator()) # Relay to TIR function registration self._register_operator_strategy("nn.conv1d", custom_conv1d_strategy) self._register_tir_pass(0, CodegenGenerateConfig()) self._register_tir_pass(0, CodegenGenerateExternCalls()) # TIR to runtime function registration self._register_codegen(format="c", includes=gen_includes, replace_call_extern=None) @property def target_name(self): return "ultra_trail" ``` -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
