diff --git a/ge/graph/load/model_manager/davinci_model.cc b/ge/graph/load/model_manager/davinci_model.cc index 52288673..01ded5a2 100755 --- a/ge/graph/load/model_manager/davinci_model.cc +++ b/ge/graph/load/model_manager/davinci_model.cc @@ -1480,6 +1480,11 @@ Status DavinciModel::GetLabelGotoAddr(uint32_t label_index, rtMemType_t mem_type return SUCCESS; } +void DavinciModel::SetGlobalStep(void *global_step, uint64_t global_step_size) { + global_step_addr_ = global_step; + global_step_size_ = global_step_size; +} + /// @ingroup ge /// @brief LabelSet Op Initialize. /// @param [in] op_desc: LabelSet Op descriptor. @@ -1542,14 +1547,16 @@ Status DavinciModel::InitLabelSet(const OpDescPtr &op_desc) { } Status DavinciModel::InitVariable(const OpDescPtr &op_desc, map &variable_by_name) { - if (op_desc->GetName() == NODE_NAME_GLOBAL_STEP) { - const auto output_sizes = ModelUtils::GetOutputSize(op_desc); - if (!output_sizes.empty()) { - global_step_size_ = output_sizes[0]; - } - const auto output_addrs = ModelUtils::GetOutputDataAddrs(runtime_param_, op_desc); - if (!output_addrs.empty()) { - global_step_addr_ = output_addrs[0]; + if (!known_node_) { + if (op_desc->GetName() == NODE_NAME_GLOBAL_STEP) { + const auto output_sizes = ModelUtils::GetOutputSize(op_desc); + if (!output_sizes.empty()) { + global_step_size_ = output_sizes[0]; + } + const auto output_addrs = ModelUtils::GetOutputDataAddrs(runtime_param_, op_desc); + if (!output_addrs.empty()) { + global_step_addr_ = output_addrs[0]; + } } } @@ -4365,7 +4372,7 @@ void DavinciModel::SetDataDumperArgs(const ComputeGraphPtr &graph, const map void *{ diff --git a/ge/graph/load/model_manager/davinci_model.h b/ge/graph/load/model_manager/davinci_model.h index 4c06ad98..ceabeddb 100755 --- a/ge/graph/load/model_manager/davinci_model.h +++ b/ge/graph/load/model_manager/davinci_model.h @@ -300,6 +300,7 @@ class DavinciModel { return op_list_.at(index); } + void SetGlobalStep(void *global_step, uint64_t global_step_size); void *GetGlobalStep() const { return global_step_addr_; } // get task info for profiling @@ -498,10 +499,6 @@ class DavinciModel { return exception_dumper_.DumpExceptionInfo(exception_infos); } - void SetKnownShapeGlobalStep(void *global_step) { - known_shape_global_step_ = global_step; - } - void DumperShrink() { data_dumper_.DumpShrink(); } @@ -1108,9 +1105,6 @@ class DavinciModel { vector output_descs_; vector output_formats_; - // known shape node for dump - void *known_shape_global_step_; - // op name to attrs mapping std::map>> op_name_to_attrs_; }; diff --git a/ge/hybrid/node_executor/compiledsubgraph/known_node_executor.cc b/ge/hybrid/node_executor/compiledsubgraph/known_node_executor.cc index 8b839849..943b6e15 100755 --- a/ge/hybrid/node_executor/compiledsubgraph/known_node_executor.cc +++ b/ge/hybrid/node_executor/compiledsubgraph/known_node_executor.cc @@ -145,8 +145,6 @@ Status KnownNodeTask::InitDavinciModel(const HybridModel &model, TensorBuffer *w auto dump_properties = DumpManager::GetInstance().GetDumpProperties(model.GetSessionId()); if (dump_properties.IsDumpOpen() || dump_properties.IsOpDebugOpen()) { davinci_model_->SetDumpProperties(dump_properties); - void *global_step = model.GetGlobalStep(); - davinci_model_->SetKnownShapeGlobalStep(global_step); } void *weight = nullptr; @@ -182,6 +180,21 @@ Status KnownNodeExecutor::PrepareTask(NodeTask &task, TaskContext &context) cons return SUCCESS; } +Status KnownNodeExecutor::SetDavinciModel(const HybridModel &model, const NodePtr &node, + std::shared_ptr &davinci_model) const { + // set known node flag as true + davinci_model->SetKnownNode(true); + davinci_model->SetId(model.GetModelId()); + davinci_model->SetDumpModelName(model.GetModelName()); + davinci_model->SetOmName(model.GetOmName()); + void *global_step = model.GetGlobalStep(); + GE_CHECK_NOTNULL(global_step); + davinci_model->SetGlobalStep(global_step, sizeof(int64_t)); + // set model id as root node's node id + davinci_model->SetSubModelId(node->GetOpDesc()->GetId()); + return SUCCESS; +} + Status KnownNodeExecutor::LoadTask(const HybridModel &model, const NodePtr &node, shared_ptr &task) const { GELOGI("[%s] KnownNodeExecutor::LoadTask in.", node->GetName().c_str()); @@ -199,13 +212,7 @@ Status KnownNodeExecutor::LoadTask(const HybridModel &model, const NodePtr &node std::shared_ptr davinci_model = MakeShared(0, nullptr); GE_CHECK_NOTNULL(davinci_model); - // set known node flag as true - davinci_model->SetKnownNode(true); - davinci_model->SetId(model.GetModelId()); - davinci_model->SetDumpModelName(model.GetModelName()); - davinci_model->SetOmName(model.GetOmName()); - // set model id as root node's node id - davinci_model->SetSubModelId(node->GetOpDesc()->GetId()); + GE_CHK_STATUS_RET_NOLOG(SetDavinciModel(model, node, davinci_model)); GELOGD("KnownNodeExecutor::LoadTask node id %ld.", node->GetOpDesc()->GetId()); GE_CHK_STATUS_RET(davinci_model->Assign(ge_model), diff --git a/ge/hybrid/node_executor/compiledsubgraph/known_node_executor.h b/ge/hybrid/node_executor/compiledsubgraph/known_node_executor.h index 11cda846..5e3ea0b9 100644 --- a/ge/hybrid/node_executor/compiledsubgraph/known_node_executor.h +++ b/ge/hybrid/node_executor/compiledsubgraph/known_node_executor.h @@ -59,6 +59,8 @@ class KnownNodeExecutor : public NodeExecutor { const NodePtr &node, GeModelPtr &ge_model, ComputeGraphPtr &graph); + Status SetDavinciModel(const HybridModel &model, const NodePtr &node, + std::shared_ptr &davinci_model) const; }; } // namespace hybrid } // namespace ge diff --git a/ge/offline/main.cc b/ge/offline/main.cc index 65c3c8da..8cbbcd25 100755 --- a/ge/offline/main.cc +++ b/ge/offline/main.cc @@ -1149,9 +1149,9 @@ domi::Status GenerateSingleOp(const std::string& json_file_path) { if (ret != SUCCESS) { DOMI_LOGE("Compile op failed. ge ret = %u, op index = %d", ret, index); ret = domi::FAILED; - break; + } else { + GELOGI("Compile op success. op index = %d, output = %s", index, output_path.c_str()); } - GELOGI("Compile op success. op index = %d, output = %s", index, output_path.c_str()); index += 1; } diff --git a/tests/ut/ge/hybrid/known_node_executor_unittest.cc b/tests/ut/ge/hybrid/known_node_executor_unittest.cc index 98e985f7..b6d06f5d 100644 --- a/tests/ut/ge/hybrid/known_node_executor_unittest.cc +++ b/tests/ut/ge/hybrid/known_node_executor_unittest.cc @@ -27,6 +27,7 @@ #undef protected #include "graph/manager/graph_mem_allocator.h" #include "../graph/passes/graph_builder_utils.h" +#include "../inc/graph/utils/graph_utils.h" using namespace std; using namespace testing; @@ -48,6 +49,34 @@ class KnownNodeTaskMock : public KnownNodeTask { }; } +static ge::OpDescPtr CreateOpDesc(string name = "", string type = "") { + auto op_desc = std::make_shared(name, type); + op_desc->SetStreamId(0); + op_desc->SetId(0); + + op_desc->SetWorkspace({}); + ; + op_desc->SetWorkspaceBytes({}); + op_desc->SetInputOffset({}); + op_desc->SetOutputOffset({}); + + ge::AttrUtils::SetStr(op_desc, ge::TVM_ATTR_NAME_MAGIC, "RT_DEV_BINARY_MAGIC_ELF_AIVEC"); + bool support_dynamic = true; + ge::AttrUtils::GetBool(op_desc, "support_dynamicshape", support_dynamic); + return op_desc; +} + +static ComputeGraphPtr BuildDataDirectConnectGraph() { + const char *kRefIndex = "_parent_node_index"; + ge::ut::GraphBuilder builder("subgraph"); + auto data = builder.AddNode("Data", "Data", 1, 1); + auto netoutput = builder.AddNode("NetOutput", "NetOutput", 1, 1); + (void)AttrUtils::SetInt(netoutput->GetOpDesc()->MutableInputDesc(0), kRefIndex, 0); + + builder.AddDataEdge(data, 0, netoutput, 0); + return builder.GetGraph(); +} + TEST_F(UnknownNodeExecutorTest, test_init_davinci_model) { auto davinci_model = std::make_shared(0, nullptr); davinci_model->SetDeviceId(0); @@ -88,4 +117,29 @@ TEST_F(UnknownNodeExecutorTest, TestParseAttrForAllocatingOutputs) { ASSERT_EQ(node_item.ref_outputs[1], const_node); ASSERT_EQ(node_item.reuse_inputs.size(), 1); ASSERT_EQ(node_item.reuse_inputs[0], 0); -} \ No newline at end of file +} + +TEST_F(UnknownNodeExecutorTest, TestSetGlobalStep) { + OpDescPtr op_desc = CreateOpDesc("PartitionedCall", "PartitionedCall"); + auto root_graph = make_shared("root_graph"); + auto node = root_graph->AddNode(op_desc); + node->SetOwnerComputeGraph(root_graph); + auto sub_graph = BuildDataDirectConnectGraph(); + sub_graph->SetParentGraph(root_graph); + sub_graph->SetParentNode(node); + node->GetOpDesc()->AddSubgraphName("subgraph"); + node->GetOpDesc()->SetSubgraphInstanceName(0, "subgraph"); + root_graph->AddSubgraph("subgraph", sub_graph); + + GeRootModelPtr ge_root_model = make_shared(root_graph); + HybridModel hybrid_model(ge_root_model); + auto *step_id = new int64_t[1]; + step_id[0] = 520; + std::unique_ptr tensor_buf; + tensor_buf = tensor_buf->Create((void *)step_id, sizeof(int64_t)); + hybrid_model.global_step_ = std::move(tensor_buf); + KnownNodeExecutor known_node_executor; + std::shared_ptr davinci_model = MakeShared(0, nullptr); + known_node_executor.SetDaviciModel(hybrid_model, node, davinci_model); + EXPECT_EQ(*(static_cast(davinci_model->global_step_addr_)), 520); +}