diff options
Diffstat (limited to 'caffe2')
| -rw-r--r-- | caffe2/core/nomnigraph/Representations/NeuralNet.cc | 29 | ||||
| -rw-r--r-- | caffe2/opt/backend_cutting.cc | 14 | ||||
| -rw-r--r-- | caffe2/opt/onnxifi_transformer.cc | 3 |
3 files changed, 32 insertions, 14 deletions
diff --git a/caffe2/core/nomnigraph/Representations/NeuralNet.cc b/caffe2/core/nomnigraph/Representations/NeuralNet.cc index fbac8f1a1f..174e02b0bb 100644 --- a/caffe2/core/nomnigraph/Representations/NeuralNet.cc +++ b/caffe2/core/nomnigraph/Representations/NeuralNet.cc @@ -309,21 +309,26 @@ void coalesceInsertedDataDependencies(repr::NNModule* m) { // Finally we reconcile any data dependency issues (if we can). for (auto& bbNode : m->controlFlow.getMutableNodes()) { auto bb = bbNode->mutableData(); - std::unordered_set<repr::NNGraph::NodeRef> seen; - for (auto instr_iter = bb->getMutableInstructions()->begin(); - instr_iter != bb->getMutableInstructions()->end(); - ++instr_iter) { - // This cannot be auto& because *iter is pure R-ref - auto instr = *instr_iter; - for (auto& output : getOutputs(instr)) { - for (auto& consumer : getConsumers(output)) { - if (seen.count(consumer)) { - bb->moveInstructionBefore(instr, consumer); + int permutation; + do { + permutation = 0; + std::unordered_set<repr::NNGraph::NodeRef> seen; + for (auto instr_iter = bb->getMutableInstructions()->begin(); + instr_iter != bb->getMutableInstructions()->end(); + ++instr_iter) { + // This cannot be auto& because *iter is pure R-ref + auto instr = *instr_iter; + for (auto& output : getOutputs(instr)) { + for (auto& consumer : getConsumers(output)) { + if (seen.count(consumer)) { + bb->moveInstructionBefore(instr, consumer); + ++permutation; + } } } + seen.insert(instr); } - seen.insert(instr); - } + } while (permutation); } } diff --git a/caffe2/opt/backend_cutting.cc b/caffe2/opt/backend_cutting.cc index c4dd792470..b48d4961ce 100644 --- a/caffe2/opt/backend_cutting.cc +++ b/caffe2/opt/backend_cutting.cc @@ -44,12 +44,24 @@ void DumpGraph(NNGraph* g) { assert(node->data() && "Node doesn't have data, can't render it"); if (isa<NeuralNetOperator>(node->data())) { auto* op = dyn_cast<NeuralNetOperator>(node->data().get()); + const auto& op_def = + dyn_cast<Caffe2Annotation>(op->getAnnotation())->getOperatorDef(); + int pos = -1; + for (const auto& arg : op_def.arg()) { + if (arg.name() == "net_pos") { + if (arg.has_i()) { + pos = arg.i(); + } + break; + } + } labelMap["label"] = op->getName() + " (" + c10::to_string((unsigned long long)node) + ")"; auto* annotation = op->getAnnotation(); if (annotation && isa<Caffe2Annotation>(annotation)) { auto device_annotation = dyn_cast<Caffe2Annotation>(annotation); - labelMap["label"] += "\\n[" + device_annotation->getDevice() + "]"; + labelMap["label"] += "\\n[" + device_annotation->getDevice() + + ", pos=" + c10::to_string(pos) + "]"; auto hash = std::hash<std::string>{}(device_annotation->getDevice()); std::stringstream hex_stream; hex_stream << std::hex << hash; diff --git a/caffe2/opt/onnxifi_transformer.cc b/caffe2/opt/onnxifi_transformer.cc index 0c0e8fe357..13b860e1eb 100644 --- a/caffe2/opt/onnxifi_transformer.cc +++ b/caffe2/opt/onnxifi_transformer.cc @@ -841,7 +841,8 @@ NetDef OnnxifiTransformer::TransformViaC2( return SubnetToOnnxifiOpViaC2(net, weights, shape_hints); }; - return opt::OptimizeForBackend(*pred_net, c2_supports, c2_converter); + return opt::OptimizeForBackend( + *pred_net, c2_supports, c2_converter, opts_.debug); } NetDef OnnxifiTransformer::TransformViaOnnx( |