mlir-hlo/lib/Dialect/mhlo/transforms
Lei Zhang 39589add22 Use the correct shape when converting mhlo.reshape
If mhlo.reshape is not purely collapsing some consecutive operand
dimensions into result dimensions, we will generate two linalg
reshape op for it: the first one collapses all operand dimensions
into one dimension, and the second one expands it to all result
dimensions. For this case, the number of collapsed/expanded dimensions
should be coming strictly from the operand/result. It is different
from the case where we can generate one linalg reshape. For that case,
the reassociation map should have rank equal to the largest among
operand/result shape.

PiperOrigin-RevId: 354293826
2021-01-28 05:37:54 -08:00
..
CMakeLists.txt Fix CMakeLists.txt 2021-01-21 12:42:35 -08:00
chlo_legalize_to_hlo.cc [MLIR][CHLO] Add `chlo.lgamma` and lowering to `hlo` 2021-01-28 04:35:03 -08:00
chlo_legalize_to_hlo_pass.cc Fix header include. 2020-12-24 01:40:31 -08:00
chlo_legalize_to_hlo_patterns.td [MLIR][CHLO] Add `is_inf`, `is_pos_inf`, and `is_neg_inf` to CHLO dialect 2021-01-27 09:00:56 -08:00
hlo_legalize_to_lhlo.cc Integrate LLVM at llvm/llvm-project@c85b6bf33c 2021-01-27 11:46:07 -08:00
legalize_control_flow.cc Fix MLIR include paths. 2020-12-17 00:56:04 -08:00
legalize_gather_to_torch_index_select.cc [mlir][NFC] Replace usages of Function.h and Module.h with BuiltinOps.h 2020-12-01 13:18:06 -08:00
legalize_to_linalg.cc Use the correct shape when converting mhlo.reshape 2021-01-28 05:37:54 -08:00
legalize_to_standard.cc Integrate LLVM at llvm/llvm-project@1b97cdf885 2020-12-21 23:49:18 -08:00
legalize_to_standard_patterns.td Lowering for mhlo.ceil to std.ceil 2020-08-12 16:15:35 -07:00
legalize_trigonometric_to_approximation.cc [mlir][NFC] Replace usages of Function.h and Module.h with BuiltinOps.h 2020-12-01 13:18:06 -08:00
lhlo_fuse_linalg.cc Integrate LLVM at llvm/llvm-project@6f4d460762 2021-01-12 16:38:25 -08:00
lhlo_legalize_to_affine.cc [mlir][NFC] Replace usages or mlir/IR/StandardTypes.h with mlir/IR/BuiltinTypes.h 2020-12-15 00:59:29 -08:00
lhlo_legalize_to_gpu.cc [mlir][NFC] Replace usages or mlir/IR/StandardTypes.h with mlir/IR/BuiltinTypes.h 2020-12-15 00:59:29 -08:00
lhlo_legalize_to_parallel_loops.cc [mlir][NFC] Replace usages or mlir/IR/StandardTypes.h with mlir/IR/BuiltinTypes.h 2020-12-15 00:59:29 -08:00
lower_complex.cc Integrate LLVM at llvm/llvm-project@0fc1aa22ee 2020-10-27 06:56:16 -07:00
lower_complex_patterns.td Removed Op(Complex, Real) lowering to address complex type inference issue 2020-11-06 15:24:23 -08:00
lower_general_dot.cc [mlir][NFC] Replace usages or mlir/IR/StandardTypes.h with mlir/IR/BuiltinTypes.h 2020-12-15 00:59:29 -08:00
materialize_broadcasts.cc More cleanup in mlir-hlo to prepare for the standalone build 2020-08-03 19:28:00 -07:00
materialize_broadcasts_pass.cc Integrate LLVM at llvm/llvm-project@0fc1aa22ee 2020-10-27 06:56:16 -07:00
mhlo_control_flow_to_scf.cc Fix MLIR include paths. 2020-12-17 00:56:04 -08:00
mhlo_fusion.cc More cleanup in mlir-hlo to prepare for the standalone build 2020-08-03 19:28:00 -07:00
optimize_mhlo.cc More cleanup in mlir-hlo to prepare for the standalone build 2020-08-03 19:28:00 -07:00
optimize_mhlo_pass.cc Integrate LLVM at llvm/llvm-project@0fc1aa22ee 2020-10-27 06:56:16 -07:00
sink_constants_to_control_flow.cc Enable fallback legalization for MaxPoolGradGrad and MaxPool3DGradGrad ops 2020-11-13 13:49:05 -08:00
test_infer_shaped_type_pass.cc Integrate LLVM at llvm/llvm-project@0fc1aa22ee 2020-10-27 06:56:16 -07:00
transform_unranked_hlo.cc Add template for tf.Cast 2021-01-27 04:49:55 -08:00
unfuse_batch_norm.cc Integrate LLVM at llvm/llvm-project@96ef4f307d 2021-01-20 07:09:47 -08:00
unfuse_batch_norm_pass.cc Integrate LLVM at llvm/llvm-project@0fc1aa22ee 2020-10-27 06:56:16 -07:00