[upstream #2779] Accuracy failures in logspace op#18
Draft
Stonepia wants to merge 1 commit into
Draft
Conversation
[upstream pytorch#2779] Accuracy failures in logspace op
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
[upstream pytorch#2779] Accuracy failures in logspace op
Fixes https://github.com/intel-sandbox/torch-xpu-ops-exp/issues/191
Root Cause: The logspace decomposition in torch/_refs/init.py computes pow(base, linspace(...)) in float64 then truncates to integer dtype via _maybe_convert_to_dtype. For integer dtypes, floating-point precision errors in pow() produce values like 99.99999999 which truncate to 99 instead of 100, causing one-off accuracy failures.
Failed Tests:
test_decomp_xpu.py::TestDecompXPU::test_comprehensive_logspace_tensor_overload_xpu_int16test_decomp_xpu.py::TestDecompXPU::test_comprehensive_logspace_tensor_overload_xpu_int32test_decomp_xpu.py::TestDecompXPU::test_comprehensive_logspace_tensor_overload_xpu_int64test_decomp_xpu.py::TestDecompXPU::test_comprehensive_logspace_xpu_int16test_decomp_xpu.py::TestDecompXPU::test_comprehensive_logspace_xpu_int32test_decomp_xpu.py::TestDecompXPU::test_comprehensive_logspace_xpu_int64test_decomp_xpu.py::TestDecompXPU::test_quick_logspace_tensor_overload_xpu_int16test_decomp_xpu.py::TestDecompXPU::test_quick_logspace_tensor_overload_xpu_int32test_decomp_xpu.py::TestDecomXPU::test_quick_logspace_tensor_overload_xpu_int64test_decomp_xpu.py::TestDecompXPU::test_quick_logspace_xpu_int16test_decomp_xpu.py::TestDecompXPU::test_quick_logspace_xpu_int32test_decomp_xpu.py::TestDecompXPU::test_quick_logspace_xpu_int64Diff stat: