colin
/
onnx-mlir
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
onnx-mlir/test/mlir/onnx/onnx_structure.mlir

28 lines
1.8 KiB
MLIR
Raw Normal View History

Revert "Emit allocs at the top of functions (#222)" (#226) This reverts commit b27e57cc4f4fdc3ba955639a44026265592e5e09.
2020-07-22 06:30:39 +08:00
// RUN: onnx-mlir-opt %s -split-input-file | FileCheck %s
support map and seq in tablegen (#159) * support map and seq in tablegen * register MLONNX for testing * format * remove the unwanted test * add a test Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-06-18 21:49:40 +08:00
//===----------------------------------------------------------------------===//
String type (Ready for Review) (#182) * string type from tensorflow * simplify type * parser and print * gen StringType for tablegen * onnx to onnx-mlir type * add namespace * allow all integer type * dialect document * add test case * format * more precise type for ONNXOp * format * enable the failed test * update comment * update onnx.md Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-06-26 04:34:37 +08:00
// CHECK-LABEL: @check_map1(%arg0: tuple<i64, f32>) -> tensor<*xf32> {
func @check_map1(%arg0: tuple<i64, f32>) -> tensor<*xf32> {
Support LLVM as of 7dcd0042 (#309) * Update to support LLVM as of 7dcd0042 Fixes for upstream changes to mlir. - New pass registration method from https://reviews.llvm.org/D85622 - Integer attributes are now C types when possible https://reviews.llvm.org/D86739 Signed-off-by: Nathaniel McVicar <namcvica@microsoft.com> * Fix for checkclang * Windows incremental build fix from @max-ku * Remove MLIRShapeToSCF lib * Missed a getSExtValue on now c type * Rebuild prereq docker. * Bump CircleCI cache version. * Update hash for Windows build Signed-off-by: Nathaniel McVicar <namcvica@microsoft.com> * Bump CircieCI cache version again. * Rebuild prereq docker. * Update README.md * Update README.md * Undo edits to ONNXOps.td.inc. * Undo changes to ONNXOps.td.inc. * Fix cast op TableGen. * Tweak tablegen definition of Cast. * Use explicitly signed integer as attributes. * Move all signless attribute to explicitly signed attribute. * Import ONNX int attribute as SI64 attribute. * Make Conv.group attr use SI64 attr. * Fix conv test. * Fix DocCheck complaint. Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-09-23 00:42:50 +08:00
%0 = "onnx.CastMap"(%arg0) {cast_to = "TO_FLOAT", map_form = "DENSE", max_map = 1 : si64} : (tuple<i64, f32>) -> tensor<*xf32>
String type (Ready for Review) (#182) * string type from tensorflow * simplify type * parser and print * gen StringType for tablegen * onnx to onnx-mlir type * add namespace * allow all integer type * dialect document * add test case * format * more precise type for ONNXOp * format * enable the failed test * update comment * update onnx.md Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-06-26 04:34:37 +08:00
return %0 : tensor<*xf32>
Support LLVM as of 7dcd0042 (#309) * Update to support LLVM as of 7dcd0042 Fixes for upstream changes to mlir. - New pass registration method from https://reviews.llvm.org/D85622 - Integer attributes are now C types when possible https://reviews.llvm.org/D86739 Signed-off-by: Nathaniel McVicar <namcvica@microsoft.com> * Fix for checkclang * Windows incremental build fix from @max-ku * Remove MLIRShapeToSCF lib * Missed a getSExtValue on now c type * Rebuild prereq docker. * Bump CircleCI cache version. * Update hash for Windows build Signed-off-by: Nathaniel McVicar <namcvica@microsoft.com> * Bump CircieCI cache version again. * Rebuild prereq docker. * Update README.md * Update README.md * Undo edits to ONNXOps.td.inc. * Undo changes to ONNXOps.td.inc. * Fix cast op TableGen. * Tweak tablegen definition of Cast. * Use explicitly signed integer as attributes. * Move all signless attribute to explicitly signed attribute. * Import ONNX int attribute as SI64 attribute. * Make Conv.group attr use SI64 attr. * Fix conv test. * Fix DocCheck complaint. Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-09-23 00:42:50 +08:00
// CHECK-NEXT: %0 = "onnx.CastMap"(%arg0) {cast_to = "TO_FLOAT", map_form = "DENSE", max_map = 1 : si64} : (tuple<i64, f32>) -> tensor<*xf32>
support map and seq in tablegen (#159) * support map and seq in tablegen * register MLONNX for testing * format * remove the unwanted test * add a test Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-06-18 21:49:40 +08:00
}
String type (Ready for Review) (#182) * string type from tensorflow * simplify type * parser and print * gen StringType for tablegen * onnx to onnx-mlir type * add namespace * allow all integer type * dialect document * add test case * format * more precise type for ONNXOp * format * enable the failed test * update comment * update onnx.md Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-06-26 04:34:37 +08:00
// CHECK-LABEL: @check_string(%arg0: tensor<10x20x!onnx.String>) -> tensor<10x20x!onnx.String> {
func @check_string(%arg0: tensor<10x20x!onnx.String>) -> tensor<10x20x!onnx.String> {
return %arg0 : tensor<10x20x!onnx.String>
// CHECK-NEXT: return %arg0 : tensor<10x20x!onnx.String>
}
Seq type (#199) * base implementation * add example * change table gen * docs * small change for review Co-authored-by: Alexandre Eichenberger <alexe@us.ibm.com> Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-07-31 20:05:59 +08:00
// CHECK-LABEL: @check_seq(%arg0: tensor<10x20xf32>, %arg1: tensor<5x20xf32>) -> tensor<*xf32> {
func @check_seq(%arg0: tensor<10x20xf32>, %arg1: tensor<5x20xf32>) -> tensor<*xf32> {
%cst = "onnx.Constant"() {value = dense<[0]> : tensor<1xi32>} : () -> tensor<1xi32>
%0 = "onnx.SequenceConstruct"(%arg0, %arg1) : (tensor<10x20xf32>, tensor<5x20xf32>) -> !onnx.Seq<tensor<10x20xf32>, tensor<5x20xf32>>
%1 = "onnx.SequenceAt"(%0, %cst) : (!onnx.Seq<tensor<10x20xf32>, tensor<5x20xf32>>, tensor<1xi32>) -> tensor<*xf32>
return %1 : tensor<*xf32>
// CHECK-NEXT: %0 = "onnx.Constant"() {value = dense<0> : tensor<1xi32>} : () -> tensor<1xi32>
// CHECK-NEXT: %1 = "onnx.SequenceConstruct"(%arg0, %arg1) : (tensor<10x20xf32>, tensor<5x20xf32>) -> !onnx.Seq<tensor<10x20xf32>, tensor<5x20xf32>>
// CHECK-NEXT: %2 = "onnx.SequenceAt"(%1, %0) : (!onnx.Seq<tensor<10x20xf32>, tensor<5x20xf32>>, tensor<1xi32>) -> tensor<*xf32>
}