[mlir][bufferization] Update linalg integration tests to lower ops created by bufferization-to-memref pass

[maerhart]

Summary

This commit prepares the linalg integration tests to be run with the new
BufferDeallocation pass which requires the bufferization-to-memref pass
to be run afterwards.
The bufferization-to-memref pass may create ops of the SCF, Func, Arith,
and MemRef dialects. Currently, not all integration tests execute all the
conversion passes necessary to lower these dialects to LLVM.

Depends on D156662

[maerhart]

Rebase on current main

[maerhart]

rebase

[maerhart]

rebase

mlir/test/Integration/Dialect/Linalg/CPU/test-collapse-tensor.mlir

 // RUN: mlir-opt %s -linalg-bufferize \
 // RUN: -arith-bufferize -tensor-bufferize -func-bufferize \
-// RUN: -finalizing-bufferize -buffer-deallocation  \
-// RUN: -expand-strided-metadata -lower-affine \
+// RUN: -finalizing-bufferize -buffer-deallocation -convert-bufferization-to-memref \
+// RUN: -convert-scf-to-cf -expand-strided-metadata -lower-affine -convert-cf-to-llvm -convert-arith-to-llvm \
 // RUN: -finalize-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_runner_utils \
 // RUN: | FileCheck %s
 
 
 func.func @main() {
   %const = arith.constant dense<[[[[-3.9058,0.9072],[-2.9470,-2.2055],[18.3946,8.2997]],[[3.4700,5.9006],[-17.2267,4.9777],[1.0450,-0.8201]]],[[[17.6996,-11.1763],[26.7775,-3.8823],[-4.2492,-5.8966]],[[2.1259,13.1794],[-10.7136,0.8428],[16.4233,9.4589]]]]> : tensor<2x2x3x2xf32>

mlir/test/Integration/Dialect/Linalg/CPU/test-elementwise.mlir

 // RUN: mlir-opt %s -convert-elementwise-to-linalg \
-// RUN: -arith-bufferize -linalg-bufferize -tensor-bufferize \
-// RUN: -func-bufferize -buffer-deallocation -convert-linalg-to-loops \
-// RUN:  --finalize-memref-to-llvm -convert-func-to-llvm \
-// RUN: -reconcile-unrealized-casts | \
+// RUN: -arith-bufferize -linalg-bufferize -tensor-bufferize -func-bufferize \
+// RUN: -canonicalize -buffer-deallocation -convert-bufferization-to-memref -convert-linalg-to-loops \
+// RUN: -convert-scf-to-cf -convert-arith-to-llvm -convert-cf-to-llvm --finalize-memref-to-llvm \
+// RUN: -convert-func-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_runner_utils \
 // RUN: | FileCheck %s
 
 func.func @main() {
   %a = arith.constant dense<[1.0, 2.0, 3.0]> : tensor<3xf32>
   %b = arith.constant dense<[10.0, 20.0, 30.0]> : tensor<3xf32>
 

mlir/test/Integration/Dialect/Linalg/CPU/test-expand-tensor.mlir

 // RUN: mlir-opt %s -linalg-bufferize \
 // RUN: -arith-bufferize -tensor-bufferize -func-bufferize \
-// RUN: -finalizing-bufferize -buffer-deallocation  \
-// RUN: -expand-strided-metadata -lower-affine \
+// RUN: -finalizing-bufferize -buffer-deallocation -convert-bufferization-to-memref \
+// RUN: -convert-scf-to-cf -expand-strided-metadata -lower-affine -convert-cf-to-llvm -convert-arith-to-llvm \
 // RUN: -finalize-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_runner_utils \
 // RUN: | FileCheck %s
 
 
 func.func @main() {
   %const = arith.constant dense<[[[-3.9058,0.9072],[-2.9470,-2.2055],[18.3946,8.2997],[3.4700,5.9006],[-17.2267,4.9777],[1.0450,-0.8201]],[[17.6996,-11.1763],[26.7775,-3.8823],[-4.2492,-5.8966],[2.1259,13.1794],[-10.7136,0.8428],[16.4233,9.4589]]]> : tensor<2x6x2xf32>

mlir/test/Integration/Dialect/Linalg/CPU/test-one-shot-bufferize.mlir

 // RUN: mlir-opt %s -pass-pipeline="builtin.module(func.func(canonicalize,cse),one-shot-bufferize{bufferize-function-boundaries})" |\
 // RUN: mlir-opt -pass-pipeline="builtin.module(func.func(buffer-deallocation,convert-vector-to-scf,lower-affine,convert-linalg-to-loops))" |\
-// RUN: mlir-opt -pass-pipeline="builtin.module(func.func(canonicalize,convert-scf-to-cf),convert-vector-to-llvm,expand-strided-metadata,lower-affine,convert-arith-to-llvm,finalize-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts)" | \
+// RUN: mlir-opt -pass-pipeline="builtin.module(convert-bufferization-to-memref,func.func(canonicalize,convert-scf-to-cf),convert-vector-to-llvm,expand-strided-metadata,lower-affine,convert-arith-to-llvm,finalize-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts)" | \
 
 // RUN: mlir-cpu-runner -O3 -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_runner_utils,%mlir_c_runner_utils |\
 // RUN: FileCheck %s
 
 #map0 = affine_map<(d0, d1)[s0] -> ((d1 - d0) ceildiv s0)>
 #map1 = affine_map<(d0, d1)[s0] -> ((d0 - d1) ceildiv s0)>
 

mlir/test/Integration/Dialect/Linalg/CPU/test-padtensor.mlir

 // RUN: mlir-opt %s -test-linalg-transform-patterns=test-linalg-to-vector-patterns \
 // RUN: -empty-tensor-to-alloc-tensor -linalg-bufferize -arith-bufferize \
 // RUN: -bufferization-bufferize -tensor-bufferize -func-bufferize \
-// RUN: -finalizing-bufferize -buffer-deallocation \
-// RUN: -convert-linalg-to-loops -convert-scf-to-cf  -expand-strided-metadata -lower-affine -convert-arith-to-llvm -finalize-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
+// RUN: -finalizing-bufferize -buffer-deallocation -convert-bufferization-to-memref \
+// RUN: -convert-linalg-to-loops -convert-scf-to-cf -expand-strided-metadata -lower-affine -convert-arith-to-llvm -finalize-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_c_runner_utils,%mlir_runner_utils \
 // RUN: | FileCheck %s
 
 
 func.func @main() {
   %const = arith.constant dense<[[[1.0, 2.0, 3.0], [2.0, 3.0, 4.0]]]> : tensor<1x2x3xf32>
   %dynamic = tensor.cast %const: tensor<1x2x3xf32> to tensor<1x?x3xf32>

mlir/test/Integration/Dialect/Linalg/CPU/test-subtensor-insert-multiple-uses.mlir

 // RUN: mlir-opt %s -linalg-bufferize \
 // RUN: -arith-bufferize -tensor-bufferize -func-bufferize \
-// RUN: -finalizing-bufferize -buffer-deallocation \
-// RUN: -convert-linalg-to-loops -convert-scf-to-cf  -expand-strided-metadata -lower-affine -convert-arith-to-llvm --finalize-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
+// RUN: -finalizing-bufferize -buffer-deallocation -convert-bufferization-to-memref \
+// RUN: -convert-linalg-to-loops -convert-scf-to-cf -expand-strided-metadata -lower-affine -convert-arith-to-llvm --finalize-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_c_runner_utils,%mlir_runner_utils \
 // RUN: | FileCheck %s
 
 func.func @main() {
   %const = arith.constant dense<10.0> : tensor<2xf32>
   %insert_val = arith.constant dense<20.0> : tensor<1xf32>
 

mlir/test/Integration/Dialect/Linalg/CPU/test-subtensor-insert.mlir

 // RUN: mlir-opt %s -linalg-bufferize \
 // RUN: -arith-bufferize -tensor-bufferize -func-bufferize \
-// RUN: -finalizing-bufferize -buffer-deallocation \
-// RUN: -convert-linalg-to-loops -convert-scf-to-cf  -expand-strided-metadata -lower-affine -convert-arith-to-llvm --finalize-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
+// RUN: -finalizing-bufferize -buffer-deallocation -convert-bufferization-to-memref \
+// RUN: -convert-linalg-to-loops -convert-scf-to-cf -expand-strided-metadata -lower-affine -convert-arith-to-llvm --finalize-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_runner_utils \
 // RUN: | FileCheck %s
 
 func.func @main() {
   %const = arith.constant dense<10.0> : tensor<2xf32>
   %insert_val = arith.constant dense<20.0> : tensor<1xf32>
   %inserted = tensor.insert_slice %insert_val into %const[0][1][1] : tensor<1xf32> into tensor<2xf32>

mlir/test/Integration/Dialect/Linalg/CPU/test-tensor-e2e.mlir

 // RUN: mlir-opt %s -arith-bufferize -linalg-bufferize \
-// RUN: -tensor-bufferize -func-bufferize -finalizing-bufferize -buffer-deallocation -convert-linalg-to-loops \
-// RUN:  --finalize-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
+// RUN: -tensor-bufferize -func-bufferize -finalizing-bufferize -buffer-deallocation -convert-bufferization-to-memref -convert-linalg-to-loops \
+// RUN: -convert-arith-to-llvm -convert-scf-to-cf -convert-cf-to-llvm --finalize-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_runner_utils \
 // RUN: | FileCheck %s
 
 func.func @foo() -> tensor<4xf32> {
   %0 = arith.constant dense<[1.0, 2.0, 3.0, 4.0]> : tensor<4xf32>
   return %0 : tensor<4xf32>
 }

mlir/test/Integration/Dialect/Linalg/CPU/test-tensor-matmul.mlir

 // UNSUPPORTED: asan
 // RUN: mlir-opt %s -test-transform-dialect-erase-schedule -linalg-bufferize -arith-bufferize \
-// RUN: -tensor-bufferize -func-bufferize -finalizing-bufferize -buffer-deallocation -convert-linalg-to-loops -convert-scf-to-cf \
-// RUN:  -expand-strided-metadata -lower-affine -convert-arith-to-llvm -convert-scf-to-cf --finalize-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
+// RUN: -tensor-bufferize -func-bufferize -finalizing-bufferize -buffer-deallocation -convert-bufferization-to-memref -convert-linalg-to-loops -convert-scf-to-cf \
+// RUN: -expand-strided-metadata -lower-affine -convert-arith-to-llvm -convert-scf-to-cf --finalize-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_c_runner_utils,%mlir_runner_utils \
 // RUN: | FileCheck %s
 
 // RUN: mlir-opt %s -test-transform-dialect-interpreter -test-transform-dialect-erase-schedule -linalg-bufferize \
 // RUN: -scf-bufferize -arith-bufferize -tensor-bufferize \
 // RUN: -func-bufferize \
 // RUN: -finalizing-bufferize -convert-linalg-to-loops -convert-scf-to-cf -convert-scf-to-cf \