onnx-mlir/test/mlir/onnx
Alexandre Eichenberger 742e817722
Constprop2 (#167)
* initial const prop attempt

* added support for broadcast ops

* adde all binary broadcast ops into custom builders with precise type

* added test example

* working

* format

* fixed suggestion by Tung, start woring on unary

* added subtraction and neg the right way, and added elementwise mul too

* formatting changes

* format

* format

* added instructions to add new optimizations

* added propagation rules that always migrate constants toward the root of the expression, using assoc and commutativity

* format comment
2020-06-15 14:56:15 -04:00
..
onnx_canonicalization.mlir Implement PadOp based on attribute promotion (#71) 2020-05-15 13:19:28 +08:00
onnx_constprop.mlir Constprop2 (#167) 2020-06-15 14:56:15 -04:00
onnx_decompose.mlir Add the split marker to test files (#90) 2020-04-16 15:17:27 +08:00
onnx_elide_constants.mlir Rework output to improve readability of intermediate MLIR code. (#87) 2020-04-24 16:15:36 -04:00
onnx_enable_memory_pool.mlir Add basic support for memory pool (#161) 2020-06-09 16:48:33 -04:00
onnx_krnl_global_elision.mlir Compiling Models with Large Constant Arrays (#146) 2020-06-12 10:27:05 +08:00
onnx_lowering.mlir Lower SplitOp to Krnl dialect (#155) 2020-06-11 10:57:20 +08:00
onnx_lowering_with_dealloc.mlir Add AffineScope trait to KrnlIterateOp and enable affine-loop-fusion pass (#140) 2020-06-08 15:36:27 +08:00
onnx_shape_inference.mlir Add shape inference for several ops (#163) 2020-06-09 14:55:49 +08:00
onnx_shape_inference_maxpool.mlir Add the split marker to test files (#90) 2020-04-16 15:17:27 +08:00