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

!46049 [MS][LITE][STABLE]optimize op performance 

Merge pull request !46049 from chenjianping/r1.8_dev2
This commit is contained in:
i-robot 2022-11-26 01:43:36 +00:00 committed by Gitee
parent e55a5c113e 495afd6d71
commit 335ab321bb
No known key found for this signature in database
GPG Key ID: 173E9B9CA92EEF8F
2 changed files with 17 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
mindspore/lite/src/runtime/kernel/cpu/base/arithmetic_base.cc
View File

@ -96,12 +96,16 @@ int ArithmeticBaseCPUKernel::ResetStatus() {
a_matric_.Reset();
b_matric_.Reset();
c_matric_.Reset();
auto dim_num = shape0.size() >= shape1.size() ? shape0.size() : shape1.size();
for (size_t i = 0; i < dim_num - shape0.size(); ++i) {
auto shape0_size = shape0.size();
auto shape1_size = shape1.size();
auto dim_num = shape0_size >= shape1_size ? shape0_size : shape1_size;
auto a_matric_size = dim_num - shape0_size;
for (size_t i = 0; i < a_matric_size; ++i) {
a_matric_.shape.push_back(1);
}
a_matric_.shape.insert(a_matric_.shape.end(), shape0.begin(), shape0.end());
for (size_t i = 0; i < dim_num - shape1.size(); ++i) {
auto b_matric_size = dim_num - shape1_size;
for (size_t i = 0; i < b_matric_size; ++i) {
b_matric_.shape.push_back(1);
}
b_matric_.shape.insert(b_matric_.shape.end(), shape1.begin(), shape1.end());
@ -120,19 +124,25 @@ int ArithmeticBaseCPUKernel::ResetStatus() {
int ArithmeticBaseCPUKernel::OptimizeShape() {
auto shape0 = a_matric_.shape;
auto shape1 = b_matric_.shape;
auto dim_num = shape0.size() >= shape1.size() ? shape0.size() : shape1.size();
auto shape0_size = shape0.size();
auto shape1_size = shape1.size();
auto dim_num = shape0_size >= shape1_size ? shape0_size : shape1_size;
std::vector<int64_t> shape_0;
std::vector<int64_t> shape_1;
for (size_t i = 0; i < dim_num - shape0.size(); ++i) {
auto shape_0_size = dim_num - shape0_size;
for (size_t i = 0; i < shape_0_size; ++i) {
shape_0.push_back(1);
}
shape_0.insert(shape_0.end(), shape0.begin(), shape0.end());
for (size_t i = 0; i < dim_num - shape1.size(); ++i) {
auto shape_1_size = dim_num - shape1_size;
for (size_t i = 0; i < shape_1_size; ++i) {
shape_1.push_back(1);
}
shape_1.insert(shape_1.end(), shape1.begin(), shape1.end());
std::vector<int64_t> shape0_temp;
shape0_temp.reserve(dim_num);
std::vector<int64_t> shape1_temp;
shape1_temp.reserve(dim_num);
for (size_t i = 0; i < dim_num;) { // horizontal comparison, merge the part of continuous 1.
shape0_temp.push_back(shape_0[i]);
shape1_temp.push_back(shape_1[i]);

2
mindspore/lite/src/runtime/mindrt_executor.cc
View File

@ -280,7 +280,7 @@ int MindrtExecutor::TransferGraphOutput() {
}
void MindrtExecutor::FreeOutputTensor() {
for (auto tensor_map : *isolate_output_map_) {
for (auto &&tensor_map : *isolate_output_map_) {
auto src_tensor = tensor_map.first;
auto dst_tensor = tensor_map.second;
if (dst_tensor->data_type() == kNumberTypeGLUInt && src_tensor->data_type() == kNumberTypeGLUInt) {