[NPU] add broadcast supporting for elementwise_add_op_npu #34057
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Thanks for your contribution! |
ronny1996
force-pushed
the
npu_elementwise_add
branch
from
d66a446
to
18ea729
Compare
ronny1996
force-pushed
the
npu_elementwise_add
branch
from
18ea729
to
14647a9
Compare
ronny1996
force-pushed
the
npu_elementwise_add
branch
from
14647a9
to
e14fdf7
Compare
qili93
requested changes
Jul 13, 2021
| ops::ElementwiseAddGradNPUKernel<float>, | ||
| ops::ElementwiseAddGradNPUKernel<plat::float16>); | ||
| ops::ElementwiseAddGradWithAxisNPUKernel<float>, | ||
| ops::ElementwiseAddGradWithAxisNPUKernel<plat::float16>); |
There was a problem hiding this comment.
原有的ElementwiseAddGradNPUKernel是不是不再被调用了，是的话可以删掉，避免冗余代码。
| See the License for the specific language governing permissions and | ||
| limitations under the License. */ | ||
| #pragma once | ||
| #ifdef PADDLE_WITH_ASCEND_CL |
There was a problem hiding this comment.
#ifdef PADDLE_WITH_ASCEND_CL 可以删掉
| self.y = np.random.rand(10, 1, 12, 1).astype(self.dtype) | ||
| self.out = self.x + self.y | ||
|
|
||
|
|
There was a problem hiding this comment.
单测问题不大，如果可以的话，最好能参考test_elementwise_add_op.py里面的单测case把，里面的case都加上，不支持最好注释一下说明原因，方便以后debug。
ronny1996
changed the title
ronny1996
force-pushed
the
npu_elementwise_add
branch
from
fa454c3
to
8cd53cf
Compare
ronny1996
force-pushed
the
npu_elementwise_add
branch
from
f421c5b
to
e690f19
Compare
ronny1996
force-pushed
the
npu_elementwise_add
branch
from
e812419
to
79a4d2a
Compare
ronny1996
changed the title
zhangting2020
approved these changes
Aug 9, 2021
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
PR types
Others
PR changes
OPs
Describe
add broadcast supporting for elementwise_add_op_npu
elementwise_add_grad使用NPU算子ReduceSumD在训练resnet50时，发现会在几个epoch之后挂掉（acl error code 507015）