p47068915
/
mindspore
forked from mindspore-Ecosystem/mindspore
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

!2183 gpu add the graph cache of pynative mode 

Merge pull request !2183 from limingqi107/gpu_pynative_optimize
This commit is contained in:
mindspore-ci-bot 2020-06-17 19:18:38 +08:00 committed by Gitee
parent c3b1814d61 7dca9bfb37
commit 893afd3796
6 changed files with 52 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
mindspore/ccsrc/device/kernel_runtime.cc
View File

@ -153,6 +153,34 @@ void KernelRuntime::RunOpAssignMemory(const std::vector<tensor::TensorPtr> &inpu
UpdateRefNodeOutputMem(graph);
}
void KernelRuntime::RunOpClearMemory(session::KernelGraph *graph) {
MS_EXCEPTION_IF_NULL(graph);
// clear input parameter memory resource
for (const auto &input_node : graph->inputs()) {
MS_EXCEPTION_IF_NULL(input_node);
AnfAlgo::SetOutputAddr(nullptr, 0, input_node.get());
}
// clear input value node memory resource
for (const auto &value_node : graph->graph_value_nodes()) {
MS_EXCEPTION_IF_NULL(value_node);
AnfAlgo::SetOutputAddr(nullptr, 0, value_node.get());
}
for (const auto &cnode : graph->execution_order()) {
MS_EXCEPTION_IF_NULL(cnode);
// clear output memory resource
for (size_t index = 0; index < AnfAlgo::GetOutputTensorNum(cnode); ++index) {
AnfAlgo::SetOutputAddr(nullptr, index, cnode.get());
}
// clear workspace memory resource
auto kernel_mod = AnfAlgo::GetKernelMod(cnode);
MS_EXCEPTION_IF_NULL(kernel_mod);
auto workspace_lists = kernel_mod->GetWorkspaceSizeList();
for (size_t index = 0; index < workspace_lists.size(); ++index) {
AnfAlgo::SetWorkspaceAddr(nullptr, index, cnode.get());
}
}
}
void KernelRuntime::AssignStaticMemory(session::KernelGraph *graph) {
AssignStaticMemoryInput(graph);
AssignStaticMemoryValueNode(graph);

1
mindspore/ccsrc/device/kernel_runtime.h
View File

@ -47,6 +47,7 @@ class KernelRuntime {
virtual bool Init() = 0;
virtual void AssignMemory(session::KernelGraph *graph);
void RunOpAssignMemory(const std::vector<tensor::TensorPtr> &input_tensors, session::KernelGraph *graph);
void RunOpClearMemory(session::KernelGraph *graph);
virtual bool Run(session::KernelGraph *graph);
virtual bool DumpData(session::KernelGraph *graph);
virtual bool RunTask(const session::KernelGraph *graph);

37
mindspore/ccsrc/session/ascend_session.cc
View File

@ -131,34 +131,6 @@ std::vector<BaseRef> GetRealArgs(const KernelGraphPtr graph, const VectorRef &ar
return real_args;
}
void ClearRunOpMemoryResource(const KernelGraphPtr &kernel_graph) {
MS_EXCEPTION_IF_NULL(kernel_graph);
// clear input parameter memory resource
for (const auto &input_node : kernel_graph->inputs()) {
MS_EXCEPTION_IF_NULL(input_node);
AnfAlgo::SetOutputAddr(nullptr, 0, input_node.get());
}
// clear input value node memory resource
for (const auto &value_node : kernel_graph->graph_value_nodes()) {
MS_EXCEPTION_IF_NULL(value_node);
AnfAlgo::SetOutputAddr(nullptr, 0, value_node.get());
}
for (const auto &cnode : kernel_graph->execution_order()) {
MS_EXCEPTION_IF_NULL(cnode);
// clear output memory resource
for (size_t index = 0; index < AnfAlgo::GetOutputTensorNum(cnode); ++index) {
AnfAlgo::SetOutputAddr(nullptr, index, cnode.get());
}
// clear workspace memory resource
auto kernel_mod = AnfAlgo::GetKernelMod(cnode);
MS_EXCEPTION_IF_NULL(kernel_mod);
auto workspace_lists = kernel_mod->GetWorkspaceSizeList();
for (size_t index = 0; index < workspace_lists.size(); ++index) {
AnfAlgo::SetWorkspaceAddr(nullptr, index, cnode.get());
}
}
}
std::vector<CNodePtr> GetCNodes(const std::vector<AnfNodePtr> &anf_nodes) {
std::vector<CNodePtr> cnodes = {};
size_t i = 0;
@ -518,7 +490,7 @@ py::tuple AscendSession::RunOp(const OpRunInfo &op_run_info, const GraphInfo &gr
}
py::object tuple_obj = utils::cast<PyObjectRef>(output_tensors).object_;
py::tuple tuple_tensors = py::cast<py::tuple>(tuple_obj);
ClearRunOpMemoryResource(graph);
RunOpMemoryClear(graph.get());
MS_LOG(INFO) << "Run op " << op_run_info.op_name << " finish!";
return tuple_tensors;
}
@ -652,6 +624,13 @@ void AscendSession::RunOpMemoryAlloc(const std::vector<tensor::TensorPtr> &input
MS_LOG(INFO) << "Finish!";
}
void AscendSession::RunOpMemoryClear(KernelGraph *kernel_graph) const {
MS_EXCEPTION_IF_NULL(kernel_graph);
auto runtime_instance = device::KernelRuntimeManager::Instance().GetKernelRuntime(kAscendDevice, device_id_);
MS_EXCEPTION_IF_NULL(runtime_instance);
runtime_instance->RunOpClearMemory(kernel_graph);
}
void AscendSession::GenerateTaskInfo(const std::shared_ptr<KernelGraph> &kernel_graph) const {
MS_LOG(INFO) << "Start!";
(void)device::KernelAdjust::GetInstance().StepLoadCtrlInputs(kernel_graph);

1
mindspore/ccsrc/session/ascend_session.h
View File

@ -80,6 +80,7 @@ class AscendSession : public SessionBasic {
void BuildKernel(const std::shared_ptr<KernelGraph> &kernel_graph) const;
void MemoryAlloc(KernelGraph *kernel_graph) const;
void RunOpMemoryAlloc(const std::vector<tensor::TensorPtr> &input_tensors, KernelGraph *kernel_graph) const;
void RunOpMemoryClear(KernelGraph *kernel_graph) const;
void GenerateTaskInfo(const std::shared_ptr<KernelGraph> &kernel_graph) const;
void LoadTask(const std::shared_ptr<KernelGraph> &kernel_graph) const;
void ExecTask(const std::shared_ptr<KernelGraph> &kernel_graph) const;

13
mindspore/ccsrc/session/gpu_session.cc
View File

@ -86,6 +86,13 @@ void GPUSession::RunOpAllocateMemory(const std::vector<tensor::TensorPtr> &input
runtime_instance->RunOpAssignMemory(input_tensors, kernel_graph);
}
void GPUSession::RunOpClearMemory(KernelGraph *kernel_graph) const {
MS_EXCEPTION_IF_NULL(kernel_graph);
auto runtime_instance = device::KernelRuntimeManager::Instance().GetSingleKernelRuntime(kGPUDevice, device_id_);
MS_EXCEPTION_IF_NULL(runtime_instance);
runtime_instance->RunOpClearMemory(kernel_graph);
}
void GPUSession::LoadInputData(const std::shared_ptr<KernelGraph> &kernel_graph,
const std::vector<tensor::TensorPtr> &inputs_const) const {
std::vector<tensor::TensorPtr> inputs(inputs_const);
@ -202,6 +209,10 @@ void GPUSession::RunGraph(const GraphId &graph_id, const std::vector<tensor::Ten
void GPUSession::BuildOp(const OpRunInfo &op_run_info, const GraphInfo &graph_info,
const std::vector<tensor::TensorPtr> &input_tensors, const std::vector<int> &tensors_mask) {
// Check if the graph cache exists.
if (run_op_graphs_.find(graph_info) != run_op_graphs_.end()) {
return;
}
// Prepare the graph
auto kernel_graph = ConstructSingleOpGraph(op_run_info, input_tensors, tensors_mask);
MS_EXCEPTION_IF_NULL(kernel_graph);
@ -234,7 +245,7 @@ py::tuple GPUSession::RunOp(const OpRunInfo &op_run_info, const GraphInfo &graph
}
py::object tuple_obj = utils::cast<PyObjectRef>(output_tensors).object_;
py::tuple tuple_tensors = py::cast<py::tuple>(tuple_obj);
run_op_graphs_.clear();
RunOpClearMemory(kernel_graph.get());
return tuple_tensors;
}
} // namespace gpu

2
mindspore/ccsrc/session/gpu_session.h
View File

@ -59,6 +59,8 @@ class GPUSession : public SessionBasic {
void RunOpAllocateMemory(const std::vector<tensor::TensorPtr> &input_tensors, KernelGraph *kernel_graph) const;
void RunOpClearMemory(KernelGraph *kernel_graph) const;
void LoadInputData(const std::shared_ptr<KernelGraph> &kernel_graph,
const std::vector<tensor::TensorPtr> &inputs_const) const override;