colin
/
mlir-hlo
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
mlir-hlo/tests
History
Rahul Joshi 8134bff98d [XLA:GPU] Add layout attributes to LHLO_GPU Convolution operations. 
- MLIR MemRefs do not preserve layout information correctly when unit dimensions
  are involved. Operations like convolution that use cuDNN however need the correct
  layout to be preserved so that we do not end up creating an incompatible combination
  of input/filter/output layout that is not supported by cuDNN.
- Add these layouts to convolution attributes in the form of I32ArrayAttr for representing
  the layout in "minor_to_major" form similar to XLA.

PiperOrigin-RevId: 348034757
 		2020-12-17 09:26:28 -08:00
..
end2end Integrate LLVM at llvm/llvm-project@0cf7e4b252 2020-12-16 20:30:17 -08:00
CMakeLists.txt Add CMake files and lit configurations, enough for `ninja check-mlir-hlo` to pass on all the tests 2020-08-07 22:14:34 -07:00
canonicalize.mlir Fix folding of HLO SliceOp with zero elements 2020-12-10 20:22:48 -08:00
chlo_infer_shape_type_methods.mlir [MLIR][KernelGen] Implement InferShapedTypeOpInterface for `mhlo.compare/select` 2020-09-17 07:10:10 -07:00
chlo_legalize_to_hlo_broadcasts.mlir Move unranked chlo lowering to transform_unranked_hlo. 2020-10-30 02:56:44 -07:00
chlo_legalize_to_mhlo.mlir [KERNEL_GEN] Add unranked Conj kernel. 2020-11-25 06:37:26 -08:00
concatenate.mlir Rename `xla_hlo` dialect to `mhlo` 2020-07-30 22:32:50 +00:00
convert.mlir Fix constant folding of mhlo.convert op with i1 element types 2020-11-23 14:18:28 -08:00
hlo-legalize-gather-to-torch-index-select.mlir Add a transform for Gathers to torch_index_select. 2020-07-30 22:34:32 +00:00
hlo-legalize-to-lhlo-unranked.mlir [HLO] Delete LHLO memref cast ops and migrate to STD ones. 2020-11-04 09:26:34 -08:00
hlo-legalize-to-lhlo.mlir Integrate LLVM at llvm/llvm-project@0cf7e4b252 2020-12-16 20:30:17 -08:00
hlo-legalize-to-linalg.mlir [KERNEL_GEN] Convert LHLO AddOp, SubOp (ComplexType) to complex ops. 2020-12-16 05:45:06 -08:00
hlo-transform-unranked.mlir [kernel_gen] Lower max rank specialization from 6 to 5 2020-12-07 02:18:38 -08:00
inlining.mlir Rename `xla_hlo` dialect to `mhlo` 2020-07-30 22:32:50 +00:00
legalize-control-flow.mlir Integrate LLVM at llvm/llvm-project@0cf7e4b252 2020-12-16 20:30:17 -08:00
legalize-to-std.mlir Folders for mhlo.compare 2020-09-23 12:03:48 -07:00
legalize-trigonometric-to-approximation.mlir [MLIR][KernelGen] Legalize `atan` to approximation 2020-10-05 08:05:52 -07:00
legalize_to_scf.mlir Integrate LLVM at llvm/llvm-project@0cf7e4b252 2020-12-16 20:30:17 -08:00
lhlo-fuse-linalg.mlir Extend fusion root heuristic to also work in partially bufferized programs. 2020-11-17 06:34:48 -08:00
lhlo-legalize-select-and-scatter.mlir Cleanup build rule names in compiler/mlir/hlo to remove the redundant/obsolete xla_ prefix 2020-07-30 22:33:29 +00:00
lhlo-legalize-to-affine.mlir Make LMHLO's Dot have the same power as MHLO's DotGeneral. 2020-10-15 15:09:06 -07:00
lhlo-legalize-to-gpu.mlir Integrate LLVM at llvm/llvm-project@72ddd559b8 2020-11-02 12:29:52 -08:00
lhlo-legalize-to-linalg.mlir Fix SignOp lowering for floating point values. 2020-12-17 01:45:54 -08:00
lhlo-legalize-to-parallel-loops.mlir Allow running tests with FILECHECK_OPTS=-enable-var-scope 2020-08-03 19:27:38 -07:00
lhlo_gpu_ops.mlir [XLA:GPU] Add layout attributes to LHLO_GPU Convolution operations. 2020-12-17 09:26:28 -08:00
lhlo_ops.mlir [HLO] Delete LHLO memref cast ops and migrate to STD ones. 2020-11-04 09:26:34 -08:00
lit.cfg.py Add CMake files and lit configurations, enough for `ninja check-mlir-hlo` to pass on all the tests 2020-08-07 22:14:34 -07:00
lit.site.cfg.py.in Add license header to lit.site.cfg.py.in 2020-08-07 22:22:24 -07:00
lower-complex.mlir Removed Op(Complex, Real) lowering to address complex type inference issue 2020-11-06 15:24:23 -08:00
lower-general-dot.mlir Cleanup build rule names in compiler/mlir/hlo to remove the redundant/obsolete xla_ prefix 2020-07-30 22:33:29 +00:00
materialize-broadcasts.mlir Cleanup build rule names in compiler/mlir/hlo to remove the redundant/obsolete xla_ prefix 2020-07-30 22:33:29 +00:00
mhlo-fusion.mlir Cleanup build rule names in compiler/mlir/hlo to remove the redundant/obsolete xla_ prefix 2020-07-30 22:33:29 +00:00
mhlo_infer_shape_type_methods.mlir Add compare_type optional attribute to CompareOp in HLO dialects 2020-10-26 12:58:29 -07:00
ops.mlir [MLIR] Update tests to eliminate public function declarations. 2020-11-12 10:42:59 -08:00
optimize-hlo.mlir Add an optimization that converts some Gathers to Slices. 2020-07-30 22:34:10 +00:00
reduce.mlir Rename `xla_hlo` dialect to `mhlo` 2020-07-30 22:32:50 +00:00
reshape.mlir Rename `xla_hlo` dialect to `mhlo` 2020-07-30 22:32:50 +00:00
reverse.mlir Rename `xla_hlo` dialect to `mhlo` 2020-07-30 22:32:50 +00:00
sink-constants-to-control-flow.mlir Sink standard dialect constants in sink_constants_to_control_flow pass 2020-08-03 19:30:29 -07:00
transpose.mlir Rename `xla_hlo` dialect to `mhlo` 2020-07-30 22:32:50 +00:00
tuple.mlir Rename `xla_hlo` dialect to `mhlo` 2020-07-30 22:32:50 +00:00
unfuse_batch_norm.mlir Integrate LLVM at llvm/llvm-project@52f0837778 2020-09-10 08:14:23 -07:00