Add XPU enabled jagged tensor operators - #96
Draft
aagalleg wants to merge 122 commits into
Draft
Conversation
Remove .gitkeep placeholders
- Add invert_permute kernel to CMake build - Implement invert_permute Python wrapper in ops.py - Register invert_permute operator with schema existence check - Add torch_library.h utility for schema validation
Add SYCL/XPU kernel implementation for invert_permute operation.
Add complete test coverage for invert_permute operator on XPU devices, covering correctness, validation, parity, and performance. Test coverage includes: - Correctness tests for int32/int64 with edge cases (empty, single element, identity, reverse, random permutations) - Input validation tests for invalid dimensions and dtypes - Meta function tests for torch.compile compatibility - PyTorch opcheck validation for operator conventions - Parametric tests with varying sizes (1 to 1M elements) - CPU-XPU parity tests to ensure consistent results - Performance benchmarks measuring execution time and bandwidth
- CMakeLists: add permute_1d_sparse_data.cpp to build sources - ops.py: add Python wrapper with type hints - ops_registry.cpp: register operator schema in fbgemm namespace
Implement SYCL/XPU kernel implementation of permute_1D_sparse_data operator for sparse jagged/1D format data permutation.
Replace the custom standalone test_invert_permute.py with a git-am patch applied to upstream FBGEMM v1.7.0 misc_ops_test.py, following the torchcodec-xpu convention. The patch makes test_invert_permute run on XPU (permute.xpu(), gated on torch.xpu.is_available()) and skips the remaining operator tests that are not implemented on XPU.
Collapse the two type-specific kernel functors (InvertPermuteKernelInt32, InvertPermuteKernelInt64) into a single templated functor InvertPermuteKernel<index_t>, mirroring the reference CUDA kernel invert_permute_kernel<index_t>.
Replaced test for upstream patched FBGEMM tests that enables testing XPU. This file is no longer needed.
Add SYCL port of FBGEMM's asynchronous_complete_cumsum operator for Intel XPU devices. The operator computes a complete cumulative sum with a leading zero (e.g., [a, b, c] → [0, a, a+b, a+b+c]).
Integrate asynchronous_complete_cumsum operator into fbgemm-xpu: - Add Python wrapper with complete cumsum documentation - Register operator schema in torch library - Include implementation in CMake build
Add comprehensive test suite for asynchronous_complete_cumsum operator covering: - Basic functionality with int32 and int64 dtypes - Empty tensor handling - Random input validation with numpy reference
Delete the accidentally tracked submodule reference to FBGEMM-v1.7.0.
Add SYCL infrastructure headers from intel/torch-xpu-ops/ to support advanced kernel implementations: - DeviceProperties.h: Device capability queries and work group sizing - SYCLContext.h: SYCL context management and namespace aliases - SYCLHelpers.h: SYCL kernel submission and utility functions - TensorInfo.h: Tensor metadata and dimension handling structures - TensorOptions.h: Tensor configuration and options management - Runtime.h: SYCL runtime utilities - Macros.h: Common macro definitions - Scalar.h: Scalar type conversion utilities These headers provide the foundation for implementing 2D sparse data permutation and other complex SYCL operations on XPU devices.
Add foundational utility headers and implementations to support complex SYCL kernel operations: - utils.h/cpp: Core constants, type definitions, kernel launch helpers, and device property queries - dispatch_macros.h: Type dispatch macros for handling multiple data types (int32, int64, float, etc.) - tensor_utils.h: Tensor manipulation and metadata utilities - function_types.h: Symbol visibility definitions for shared library exports These utilities provide essential infrastructure for implementing 2D sparse data permutation and other advanced operators on XPU devices, including work group sizing, kernel launch helpers, and type-safe dispatching mechanisms.
Add SYCL port of FBGEMM's permute_2D_sparse_data operator for Intel XPU devices. This operator permutes 2D sparse data including lengths [T, B], indices, and optional weights according to a permutation vector, commonly used for reordering embedding table features. Implementation includes: - SYCL kernels: permute_2D_lengths_kernel and permute_2D_data_kernel - Host function: permute_2D_sparse_data_xpu
Integrate permute_2D_sparse_data operator into fbgemm-xpu: - Add Python wrapper with type hints and documentation - Register operator schema in torch library - Include implementation files in CMake build (utils.cpp, SYCL kernels, and operator implementation)
Add comprehensive test suite for permute_2D_sparse_data operator covering: - Basic functionality with int32 and int64 data types - Sparse data with and without weights - Permutations with repeated indices - Exact value validation - CPU-XPU consistency verification
Signed-off-by: Felipe Leza Alvarez <felipe.leza.alvarez@intel.com>
Signed-off-by: Felipe Leza Alvarez <felipe.leza.alvarez@intel.com>
Signed-off-by: Felipe Leza Alvarez <felipe.leza.alvarez@intel.com>
The permute_2d_sparse_data_op.cpp file was incorrectly emptied. Restore the SYCL implementation.
Signed-off-by: Felipe Leza Alvarez <felipe.leza.alvarez@intel.com>
…ng standards Signed-off-by: Felipe Leza Alvarez <felipe.leza.alvarez@intel.com>
Signed-off-by: Felipe Leza Alvarez <felipe.leza.alvarez@intel.com>
Integrate asynchronous_complete_cumsum operator into fbgemm-xpu: - Add Python wrapper with complete cumsum documentation - Register operator schema in torch library - Include implementation in CMake build
Integrate permute_2D_sparse_data operator into fbgemm-xpu: - Add Python wrapper with type hints and documentation - Register operator schema in torch library - Include implementation files in CMake build (utils.cpp, SYCL kernels, and operator implementation)
Fixes CMake configuration and import ordering to properly build and load the block_bucketize_sparse_features XPU operator. - Configure CMake for XPU-only PyTorch builds - Import torch before _C extension to load libtorch.so dependencies - Adjust test imports for consistency All 18 tests passing.
Register operator schemas and add Python bindings for split and dense embedding lookup functions. Changes span ops_registry.cpp and ops.py.
Add src/codegen/CMakeLists.txt to drive code generation and build the _C_training Python extension module, and wire it into the top-level build.
aagalleg
force-pushed
the
feat/jagged_ops
branch
from
July 22, 2026 22:08
2a071ef to
5cf2df9
Compare
Signed-off-by: Felipe Leza Alvarez <felipe.leza.alvarez@intel.com>
Signed-off-by: Felipe Leza Alvarez <felipe.leza.alvarez@intel.com>
Update device selection order in the test patch to check for XPU
availability first, then fall back to CPU or CUDA. This ensures XPU
tests run on XPU hardware when available, rather than defaulting to
CPU even when XPU is present.
Changes the device logic from:
"cpu" if use_cpu else ("xpu" if xpu_available else "cuda")
to:
"xpu" if xpu_available else ("cpu" if use_cpu else "cuda")
Integrate asynchronous_complete_cumsum operator into fbgemm-xpu: - Add Python wrapper with complete cumsum documentation - Register operator schema in torch library - Include implementation in CMake build
Integrate permute_2D_sparse_data operator into fbgemm-xpu: - Add Python wrapper with type hints and documentation - Register operator schema in torch library - Include implementation files in CMake build (utils.cpp, SYCL kernels, and operator implementation)
Fixes CMake configuration and import ordering to properly build and load the block_bucketize_sparse_features XPU operator. - Configure CMake for XPU-only PyTorch builds - Import torch before _C extension to load libtorch.so dependencies - Adjust test imports for consistency All 18 tests passing.
Register operator schemas and add Python bindings for split and dense embedding lookup functions. Changes span ops_registry.cpp and ops.py.
Add src/codegen/CMakeLists.txt to drive code generation and build the _C_training Python extension module, and wire it into the top-level build.
Port dense_to_jagged, jagged_to_padded_dense, jagged_dense_elementwise_add_jagged_output and jagged_2d_to_dense from custom_operator_xpu to fbgemm-xpu with SYCL/XPU kernels.
Declare the operator schemas, add the Python wrappers and build the new SYCL sources for the jagged tensor family (dense_to_jagged, jagged_to_padded_dense, jagged_dense_elementwise_add_jagged_output and jagged_2d_to_dense).
aagalleg
force-pushed
the
feat/jagged_ops
branch
from
July 23, 2026 18:27
5cf2df9 to
a6ebc1e
Compare
Implement autograd backward kernels and wire up gradient computation for dense_to_jagged, jagged_to_padded_dense, and jagged_dense_elementwise_add_jagged_output operators on XPU.
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
2 participants
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.
The operators enable conversion between dense and jagged representations and support in-place element-wise operations:
dense_to_jagged: Convert dense padded tensors to compact jagged formatjagged_to_padded_dense: Convert jagged tensors back to padded dense formatjagged_dense_elementwise_add_jagged_output: Element-wise addition with jagged outputjagged_2d_to_dense: Convert 2D jagged tensors to dense formatDepends on: #92
Changes
Operator Implementation
•
jagged_tensorOps.cpp: Top-level operator implementations with autograd support for XPU.SYCL Kernel Implementation
•
sycl_kernels/jagged_tensor_ops_kernels.h: Header for SYCL kernel interfaces.•
sycl_kernels/jagged_tensor_ops_kernels.cpp: SYCL kernel implementations for dense-to-jagged conversion, jagged-to-padded-dense conversion, and element-wise operations.Build System Integration
•
CMakeLists.txt: Addsjagged_tensor_ops_kernels.cppandjagged_tensorOps.cppto thehost_sourceslist, ensuring SYCL compilation with theicpxcompiler and AOT targets.•
ops_registry.cpp: Registers operator schemas for all four jagged tensor operators with the PyTorch dispatcher.•
ops.py: Exposes Python wrappers for the operators, making them accessible viafbgemm_xpu.dense_to_jagged(), etc.Testing
•
test_jagged_ops.py: