p85971406
/
mindspore
forked from mindspore-Ecosystem/mindspore
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

!7166 gpu no broad cast kernel dims exceed 

Merge pull request !7166 from chenweifeng/broadcast-grad-dims-exceed
This commit is contained in:
mindspore-ci-bot 2020-10-14 15:34:07 +08:00 committed by Gitee
parent 520a09c76d 3eae63e4e9
commit b619af917f
2 changed files with 18 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
mindspore/ccsrc/backend/kernel_compiler/gpu/math/broadcast_gpu_kernel.h
View File

@ -83,17 +83,23 @@ class BroadcastOpGpuKernel : public GpuKernel {
rhs_shape_.resize(MAX_DIMS, 1);
output_shape_.resize(MAX_DIMS, 1);
for (size_t i = 0; i < shape3.size(); i++) {
output_shape_[i] = shape3[i];
if (need_broadcast_) {
output_shape_[i] = shape3[i];
}
output_num_ *= shape3[i];
}
int lhs_offset = shape3.size() - shape1.size();
for (size_t j = 0; j < shape1.size(); j++) {
lhs_shape_[j + lhs_offset] = shape1[j];
if (need_broadcast_) {
lhs_shape_[j + lhs_offset] = shape1[j];
}
input1_num_ *= shape1[j];
}
int rhs_offset = shape3.size() - shape2.size();
for (size_t k = 0; k < shape2.size(); k++) {
rhs_shape_[k + rhs_offset] = shape2[k];
if (need_broadcast_) {
rhs_shape_[k + rhs_offset] = shape2[k];
}
input2_num_ *= shape2[k];
}

12
mindspore/ccsrc/backend/kernel_compiler/gpu/math/broadcast_grad_gpu_kernel.h
View File

@ -78,17 +78,23 @@ class BroadcastOpGradGpuKernel : public GpuKernel {
}
for (size_t i = 0; i < shape3.size(); i++) {
dy_shape_[i] = shape3[i];
if (need_broadcast_) {
dy_shape_[i] = shape3[i];
}
output_num_ *= shape3[i];
}
int x1_offset = shape3.size() - shape1.size();
for (size_t i = 0; i < shape1.size(); i++) {
x1_shape_[i + x1_offset] = shape1[i];
if (need_broadcast_) {
x1_shape_[i + x1_offset] = shape1[i];
}
input1_num_ *= shape1[i];
}
int x2_offset = shape3.size() - shape2.size();
for (size_t i = 0; i < shape2.size(); i++) {
x2_shape_[i + x2_offset] = shape2[i];
if (need_broadcast_) {
x2_shape_[i + x2_offset] = shape2[i];
}
input2_num_ *= shape2[i];
}