torch-mlir/lib/Dialect/Torch/Transforms
Tanyo Kwok 1ee865983b
[MHLO] fix tensor mode aten.div op pattern (#1160)
* [MHLO] fix tensor mode aten.div op pattern

See RFC #999
Co-authored-by: Bairen Yi <yibairen.byron@bytedance.com>
Co-authored-by: Jiawei Wu <xremold@gmail.com>
Co-authored-by: Tianyou Guo <tianyou.gty@alibaba-inc.com>
Co-authored-by: Xu Yan <yancey.yx@alibaba-inc.com>
Co-authored-by: Ziheng Jiang <ziheng.jiang@bytedance.com>
2022-08-06 23:38:06 +08:00
..
AdjustCallingConventions.cpp llvm: bump tag to e1318078 (#781) 2022-04-26 12:27:51 -07:00
CMakeLists.txt torch: add pass to catch non-value tensors (#1052) 2022-07-13 17:11:15 -07:00
DecomposeComplexOps.cpp [MHLO] fix tensor mode aten.div op pattern (#1160) 2022-08-06 23:38:06 +08:00
DropShapeCalculations.cpp torch: allow torch dialect ops after running drop-shape pass (#979) 2022-06-25 07:27:47 -07:00
GlobalizeObjectGraph.cpp torch: [nfc] use `WalkResult::isInterrupted()` instead of booleans (#1081) 2022-07-19 10:17:57 -07:00
InlineGlobalSlots.cpp Dual license the torch-mlir project. 2021-10-01 10:46:08 -07:00
MaximizeValueSemantics.cpp Implemented a decomposition of aten::narrow 2022-08-01 18:32:14 +05:30
PassDetail.h llvm: bump tag to e1318078 (#781) 2022-04-26 12:27:51 -07:00
Passes.cpp torch: add pass to catch non-value tensors (#1052) 2022-07-13 17:11:15 -07:00
PrepareForGlobalizeObjectGraph.cpp llvm: bump tag to e1318078 (#781) 2022-04-26 12:27:51 -07:00
ReduceOpVariants.cpp Undo shape lib changes + update function signature of sum + zero (#1035) 2022-07-11 10:56:12 -07:00
RefinePublicReturn.cpp llvm: bump tag to e1318078 (#781) 2022-04-26 12:27:51 -07:00
RefineTypes.cpp add e2e support for aten.atan2 (#1117) 2022-08-02 11:39:41 -04:00
ReifyShapeCalculations.cpp llvm: bump tag to e1318078 (#781) 2022-04-26 12:27:51 -07:00
ShapeLibrary.cpp [MLIR][TORCH] Add support for dim=None to Aten[Var|Std]DimOp 2022-08-05 20:28:56 +05:30
SimplifyShapeCalculations.cpp [MLIR][TORCH] Add support for multiple indexing tensors for aten.index.Tensor (#1097) 2022-07-28 19:00:02 -04:00
VerifyConversionToValueSemantics.cpp torch: [nfc] use `WalkResult::isInterrupted()` instead of booleans (#1081) 2022-07-19 10:17:57 -07:00