Sync shape info between dil tensor and aten tensor #12
Conversation
This file contains hidden or 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
…e buffer of input tensor is dnnl
pinzhenx
reviewed
May 18, 2020
| @@ -38,7 +38,6 @@ dil::tensor try_gen_dil_tensor(const at::Tensor &input) { | |||
| if (cpu::ShadeDataContext::isDilTensor(input)) { | |||
| return cpu::ShadeDataContext::getDilTensor(input); | |||
There was a problem hiding this comment.
getDilTensor will lose aten metadata when gen dil tensor
zhuhaozhe
pushed a commit
to zhuhaozhe/intel-extension-for-pytorch
that referenced
this pull request
Apr 23, 2021
…uild_flag Add USE_TORCH_CCL Build Flag
EikanWang
pushed a commit
that referenced
this pull request
Oct 4, 2021
…and adaptive_avg_pool2d (#12) * input quantization parameters propagate to the output for max_pool2d and adaptive_avg_pool2d * [LLGA] add UT for int8 max_pool2d * [LLGA] add skipped UT for adap_avg_pool Co-authored-by: chunyuan <chunyuan.wu@intel.com>
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Outdated suggestions cannot be applied.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.
@pinzhenx @hongzhen1 @jiayisunx @XiaobingSuper , Please review the patch to make sure the shape of aten tensor and its dil tensor buffer is consistent. The dil tensor is just a buffer of aten tensor, all shape info for the computation should come from the aten tensor.
@pinzhenx , I'm not sure which DNNL OP requires its input tensors should be contiguous. Could you help to check it?
After that, each DNNL op needs to do "contiguous" explicitly if it requires its input tensors are contiguous.