[mlir][linalg] Enable insertion of dealloc for end2end tests

[herhut]

Summary

This uses the buffer-deallocation pass or, in case the test case does not use bufferization, has added explicit deallocs.

[herhut]

@mehdi_amini not sure how to test this. Do the builders do this automatically?

[mehdi_amini]

This seems like leaky in test-tensor-matmul.mlir ; can you look into this? Here is the log : https://lab.llvm.org/staging/#/builders/191/builds/1595

[mehdi_amini]

In D111059#3039916, @herhut wrote:

@mehdi_amini not sure how to test this. Do the builders do this automatically?

cmake '-DLLVM_USE_SANITIZER=Address;Undefined'
(using clang as host compiler)

[mehdi_amini]

Ping @herhut ?

mlir/test/Integration/Dialect/Linalg/CPU/lit.local.cfg

-# http://llvm.org/pr52047
-config.environment['ASAN_OPTIONS'] = 'detect_leaks=0'
-

mlir/test/Integration/Dialect/Linalg/CPU/matmul-vs-matvec.mlir

scf.for %j = %c0 to %n step %c1 {
       %e1 = memref.load %C1[%i, %j] : memref<?x?xf32>
       %e2 = memref.load %C2[%i, %j] : memref<?x?xf32>
       %c = arith.cmpf oeq, %e1, %e2 : f32
       assert %c, "Matmul does not produce same output as matvec"
     }
   }
   %C2_ = memref.cast %C2 : memref<?x?xf32> to memref<*xf32>
   call @print_memref_f32(%C2_) : (memref<*xf32>) -> ()
+  memref.dealloc %C1 : memref<?x?xf32>
+  memref.dealloc %C2 : memref<?x?xf32>
   return
 }
 
 // CHECK: Unranked Memref base@ = {{.*}} rank = 2 offset = 0 sizes = [5, 2] strides = [2, 1] data =
 // CHECK-NEXT:      [
 // CHECK-SAME:  [611,   663],
 // CHECK-NEXT:  [611,   663],
 // CHECK-NEXT:  [611,   663],
 // CHECK-NEXT:  [611,   663],
 // CHECK-NEXT:  [611,   663]
 // CHECK-SAME: ]

mlir/test/Integration/Dialect/Linalg/CPU/rank-reducing-subview.mlir

func @main() {
   %B = memref.subview %A[%c1, 0][1, %c2][1, 1] : memref<?x?xf32> to memref<?xf32, offset: ?, strides: [1]>
   %C = memref.subview %A[0, %c1][%c2, 1][1, 1] : memref<?x?xf32> to memref<?xf32, offset: ?, strides: [?]>
   %A_ = memref.cast %A : memref<?x?xf32> to memref<*xf32>
   call @print_memref_f32(%A_) : (memref<*xf32>) -> ()
   %B_ = memref.cast %B : memref<?xf32, offset: ?, strides: [1]> to memref<*xf32>
   call @print_memref_f32(%B_) : (memref<*xf32>) -> ()
   %C_ = memref.cast %C : memref<?xf32, offset: ?, strides: [?]> to memref<*xf32>
   call @print_memref_f32(%C_) : (memref<*xf32>) -> ()
+  memref.dealloc %A : memref<?x?xf32>
   return
 }
 
 // CHECK: Unranked Memref base@ = {{.*}} rank = 2 offset = 0 sizes = [2, 2] strides = [2, 1] data =
 // CHECK-NEXT:      [
 // CHECK-SAME:  [0,   1],
 // CHECK-NEXT:  [2,   3]
 // CHECK-SAME: ]
 // CHECK: [2,  3]
 // CHECK: [1,  3]

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

 // RUN: mlir-opt %s -linalg-bufferize -std-bufferize \
 // RUN: -tensor-constant-bufferize -tensor-bufferize -func-bufferize \
-// RUN: -finalizing-bufferize -convert-linalg-to-llvm \
+// RUN: -finalizing-bufferize -buffer-deallocation -convert-linalg-to-llvm \
 // RUN: -convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
 
 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-comprehensive-bufferize.mlir

 // RUN: mlir-opt %s -canonicalize -cse -linalg-comprehensive-module-bufferize |\
-// RUN: mlir-opt -convert-vector-to-scf -lower-affine -convert-linalg-to-loops |\
+// RUN: mlir-opt -buffer-deallocation -convert-vector-to-scf -lower-affine -convert-linalg-to-loops |\
 // RUN: mlir-opt -canonicalize -convert-scf-to-std -convert-vector-to-llvm -convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
 
 // RUN: mlir-cpu-runner -O3 -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext |\
 // 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-elementwise.mlir

-// RUN: mlir-opt %s -convert-elementwise-to-linalg -std-bufferize -tensor-constant-bufferize -linalg-bufferize -tensor-bufferize -func-bufferize -convert-linalg-to-loops -convert-linalg-to-llvm --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
+// RUN: mlir-opt %s -convert-elementwise-to-linalg -std-bufferize \
+// RUN: -tensor-constant-bufferize -linalg-bufferize -tensor-bufferize \
+// RUN: -func-bufferize -buffer-deallocation -convert-linalg-to-loops \
+// RUN: -convert-linalg-to-llvm --convert-memref-to-llvm -convert-std-to-llvm \
+// RUN: -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
 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 -std-bufferize \
 // RUN: -tensor-constant-bufferize -tensor-bufferize -func-bufferize \
-// RUN: -finalizing-bufferize -convert-linalg-to-llvm \
+// RUN: -finalizing-bufferize -buffer-deallocation -convert-linalg-to-llvm \
 // RUN: -convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
 
 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-padtensor.mlir

 // RUN: mlir-opt %s -linalg-bufferize -std-bufferize \
 // RUN: -tensor-constant-bufferize -tensor-bufferize -func-bufferize \
-// RUN: -finalizing-bufferize \
+// RUN: -finalizing-bufferize -buffer-deallocation \
 // RUN: -convert-linalg-to-loops -convert-scf-to-std -convert-linalg-to-llvm -convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
 
 func @main() {
   %const = arith.constant dense<[[[1.0, 2.0, 3.0], [2.0, 3.0, 4.0]]]> : tensor<1x2x3xf32>

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

 // RUN: mlir-opt %s -linalg-bufferize -std-bufferize \
 // RUN: -tensor-constant-bufferize -tensor-bufferize -func-bufferize \
-// RUN: -finalizing-bufferize \
+// RUN: -finalizing-bufferize -buffer-deallocation \
 // RUN: -convert-linalg-to-loops -convert-scf-to-std -convert-linalg-to-llvm --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
 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 -std-bufferize \
 // RUN: -tensor-constant-bufferize -tensor-bufferize -func-bufferize \
-// RUN: -finalizing-bufferize \
+// RUN: -finalizing-bufferize -buffer-deallocation \
 // RUN: -convert-linalg-to-loops -convert-scf-to-std -convert-linalg-to-llvm --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
 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-tensor-e2e.mlir

 // RUN: mlir-opt %s -tensor-constant-bufferize -std-bufferize -linalg-bufferize \
-// RUN: -tensor-bufferize -func-bufferize -finalizing-bufferize -convert-linalg-to-loops \
+// RUN: -tensor-bufferize -func-bufferize -finalizing-bufferize -buffer-deallocation -convert-linalg-to-loops \
 // RUN: -convert-linalg-to-llvm --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
 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

 // RUN: mlir-opt %s -linalg-bufferize -std-bufferize -tensor-constant-bufferize \
-// RUN: -tensor-bufferize -func-bufferize -finalizing-bufferize  -convert-linalg-to-loops -convert-scf-to-std \
+// RUN: -tensor-bufferize -func-bufferize -finalizing-bufferize -buffer-deallocation -convert-linalg-to-loops -convert-scf-to-std \
 // RUN: -convert-linalg-to-llvm -lower-affine -convert-scf-to-std --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
 // RUN: mlir-opt %s  -linalg-tile="tile-sizes=1,2,3" -linalg-bufferize \
 // RUN: -scf-bufferize -std-bufferize -tensor-constant-bufferize -tensor-bufferize \
 // RUN: -func-bufferize \