sfqcyy
/
mindspore
forked from OSSInnovation/mindspore
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

!3105 Save .pb graph file for Mindspore GPU 

Merge pull request !3105 from lichen_101010/lichen_tmp
This commit is contained in:
mindspore-ci-bot 2020-07-21 10:14:37 +08:00 committed by Gitee
parent 3f09439323 515099d0a9
commit aaba62f3fc
1 changed files with 13 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -13,6 +13,7 @@
* See the License for the specific language governing permissions and
* limitations under the License.
*/
#include "debug/anf_ir_utils.h"
#include "backend/session/gpu_session.h"
#include "runtime/device/gpu/kernel_info_setter.h"
#include "runtime/device/gpu/gpu_kernel_build.h"
@ -173,6 +174,10 @@ GraphId GPUSession::CompileGraph(const AnfNodePtrList &lst, const AnfNodePtrList
auto graph_id = graph_sum_;
auto graph = ConstructKernelGraph(lst, outputs);
MS_EXCEPTION_IF_NULL(graph);
// Prepare ms context info for dump .pb graph
auto context_ptr = MsContext::GetInstance();
MS_EXCEPTION_IF_NULL(context_ptr);
bool save_graphs = context_ptr->save_graphs_flag();
// Optimize
Optimize(graph);
// Select kernel build info
@ -185,8 +190,16 @@ GraphId GPUSession::CompileGraph(const AnfNodePtrList &lst, const AnfNodePtrList
predictmodel::StepConvertGraph(graph);
// Start gpu kernel runtime
StartKernelRT();
// Dump .pb graph before hardware optimization
if (save_graphs) {
DumpIRProto(graph, "before_hwopt_" + std::to_string(graph_id));
}
// HardwareOptimize
HardwareOptimize(graph);
// Dump .pb graph after hardware optimization
if (save_graphs) {
DumpIRProto(graph, "after_hwopt_" + std::to_string(graph_id));
}
// Assign CUDA streams
AssignStream(graph);
// Hide NoOp from execution graph