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

28 lines
2.4 KiB
MLIR
Raw Normal View History

[NFC] Rename passes for stylistic consistency. (#232) * lower-frontend -> convert-onnx-to-krnl * lower-all-llvm -> convert-krnl-to-llvm * lower-krnl -> convert-krnl-to-affine * Name fix.
2020-07-31 21:37:35 +08:00
// RUN: onnx-mlir-opt --shape-inference --convert-onnx-to-krnl --convert-krnl-to-affine --convert-krnl-to-llvm %s -split-input-file | FileCheck %s
Revert "Emit allocs at the top of functions (#222)" (#226) This reverts commit b27e57cc4f4fdc3ba955639a44026265592e5e09.
2020-07-22 06:30:39 +08:00
// -----
Add the split marker to test files (#90) Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-04-16 15:17:27 +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
func @test_reshape(%arg0 : tensor<?x10xf32>, %arg1 : tensor<4xi64>) -> tensor<*xf32> {
%0 = "onnx.Reshape"(%arg0, %arg1) : (tensor<?x10xf32>, tensor<4xi64>) -> tensor<*xf32>
[MLIR] Add support for reshape (#390) * Add reshape op handling. * Lower reshape to KRNL dialect. * Add comments. * Propagate reshape to KRNL IR. * Lower KRNL reshape to affine and standard ops level dialects. * Add lowering of reshape operation to Krnl and LLVM Dialects. * Add test for LLVM IR dialect output for reshape. * Fix rebase. * Fix test variable. * Emit errors during reshape shape inference. Address other reviewer comments.
2019-12-14 04:28:56 +08:00
"std.return"(%0) : (tensor<*xf32>) -> ()
Update LLVM commit ID to the version that corresponds to MLIR News, 13th edition (8/7/2020) (#248) * Update LLVM commit ID to include to the new modeling of LLVM type in MLIR * Fix commit id discrepancy * Update README.md * Update MLIR version * Force rebuild prereq dockers and see what happens. * Use LLVM commit ID that corresponds to MLIR News, 13th edition (8/7/2020) Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-08-14 12:52:48 +08:00
// CHECK: llvm.func @llvm.memcpy.p0i8.p0i8.i64(!llvm.ptr<i8>, !llvm.ptr<i8>, !llvm.i64, !llvm.i1)
// CHECK: [[TMP:%.+]] = llvm.mlir.undef : !llvm.struct<(ptr<float>, ptr<float>, i64, array<2 x i64>, array<2 x i64>)>
// CHECK: llvm.insertvalue %arg0, %0[0] : !llvm.struct<(ptr<float>, ptr<float>, i64, array<2 x i64>, array<2 x i64>)>
// CHECK: llvm.insertvalue %arg1, %1[1] : !llvm.struct<(ptr<float>, ptr<float>, i64, array<2 x i64>, array<2 x i64>)>
// CHECK: llvm.insertvalue %arg2, %2[2] : !llvm.struct<(ptr<float>, ptr<float>, i64, array<2 x i64>, array<2 x i64>)>
// CHECK: llvm.insertvalue %arg3, %3[3, 0] : !llvm.struct<(ptr<float>, ptr<float>, i64, array<2 x i64>, array<2 x i64>)>
// CHECK: llvm.insertvalue %arg5, %4[4, 0] : !llvm.struct<(ptr<float>, ptr<float>, i64, array<2 x i64>, array<2 x i64>)>
// CHECK: llvm.insertvalue %arg4, %5[3, 1] : !llvm.struct<(ptr<float>, ptr<float>, i64, array<2 x i64>, array<2 x i64>)>
// CHECK: [[TMP1:%.+]] = llvm.insertvalue %arg6, %6[4, 1] : !llvm.struct<(ptr<float>, ptr<float>, i64, array<2 x i64>, array<2 x i64>)>
// CHECK: [[RES:%.+]] = llvm.insertvalue {{.*}}[4, 3] : !llvm.struct<(ptr<float>, ptr<float>, i64, array<4 x i64>, array<4 x i64>)>
// CHECK: [[EXT_VAL_0:%.+]] = llvm.extractvalue [[RES]][1] : !llvm.struct<(ptr<float>, ptr<float>, i64, array<4 x i64>, array<4 x i64>)>
// CHECK: [[DST:%.+]] = llvm.bitcast [[EXT_VAL_0]] : !llvm.ptr<float> to !llvm.ptr<i8>
// CHECK: [[EXT_VAL_1:%.+]] = llvm.extractvalue [[TMP1]][1] : !llvm.struct<(ptr<float>, ptr<float>, i64, array<2 x i64>, array<2 x i64>)>
// CHECK: [[SRC:%.+]] = llvm.bitcast [[EXT_VAL_1]] : !llvm.ptr<float> to !llvm.ptr<i8>
[MLIR] Add support for reshape (#390) * Add reshape op handling. * Lower reshape to KRNL dialect. * Add comments. * Propagate reshape to KRNL IR. * Lower KRNL reshape to affine and standard ops level dialects. * Add lowering of reshape operation to Krnl and LLVM Dialects. * Add test for LLVM IR dialect output for reshape. * Fix rebase. * Fix test variable. * Emit errors during reshape shape inference. Address other reviewer comments.
2019-12-14 04:28:56 +08:00
// CHECK: [[SIZE:%.+]] = llvm.sext %{{.*}} : !llvm.i64 to !llvm.i64
Update llvm version (#187) * Update llvm version * Update git hash for llvm-project * Update option handling * Update LLVM version * Update tests * Update git hash * Update docs * clang-format * Fix operand adaptor * Fix dim with constant * Update LSTM.cpp Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-07-07 21:26:00 +08:00
// CHECK: [[VOLATILE:%.+]] = llvm.mlir.constant(false) : !llvm.i1
Using onnx-mlir through incremental stages (#257) * Add lowering of Vector dialect for lower-all-llvm pass * Fix generating CallOp instructions when return type is void * Fix lowering of memref * Reformat using clang-format * Record more context. * Reflow comments. Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-09-10 10:29:55 +08:00
// CHECK: llvm.call @llvm.memcpy.p0i8.p0i8.i64([[DST]], [[SRC]], [[SIZE]], [[VOLATILE]]) : (!llvm.ptr<i8>, !llvm.ptr<i8>, !llvm.i64, !llvm.i1) -> ()
Update LLVM commit ID to the version that corresponds to MLIR News, 13th edition (8/7/2020) (#248) * Update LLVM commit ID to include to the new modeling of LLVM type in MLIR * Fix commit id discrepancy * Update README.md * Update MLIR version * Force rebuild prereq dockers and see what happens. * Use LLVM commit ID that corresponds to MLIR News, 13th edition (8/7/2020) Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-08-14 12:52:48 +08:00
// CHECK: llvm.return [[RES]] : !llvm.struct<(ptr<float>, ptr<float>, i64, array<4 x i64>, array<4 x i64>)>
[MLIR] Add support for reshape (#390) * Add reshape op handling. * Lower reshape to KRNL dialect. * Add comments. * Propagate reshape to KRNL IR. * Lower KRNL reshape to affine and standard ops level dialects. * Add lowering of reshape operation to Krnl and LLVM Dialects. * Add test for LLVM IR dialect output for reshape. * Fix rebase. * Fix test variable. * Emit errors during reshape shape inference. Address other reviewer comments.
2019-12-14 04:28:56 +08:00
}