[mlir] Update AArch64 integration tests to use mlir-cpu-runner

[awarzynski]

Summary

For consistency with other tests and to simplify the RUN lines, switch
to using mlir-cpu-runner instead of lli in integrations tests
targeting SSVE and SME.

[c-rhodes]

LGTM cheers

mlir/test/Integration/Dialect/Vector/CPU/ArmSME/test-ssve.mlir

-// RUN: mlir-opt %s -test-lower-to-llvm | \
-// RUN: mlir-translate -mlir-to-llvmir | \
-// RUN: %lli_aarch64_cmd --march=aarch64 --mattr="+sve,+sme" \
-// RUN:      -force-streaming-compatible-sve \
-// RUN:      --entry-function=entry \
-// RUN:      --dlopen=%mlir_native_utils_lib_dir/libmlir_c_runner_utils%shlibext | \
-// RUN: FileCheck %s
+// DEFINE: %{entry_point} = entry
+// DEFINE: %{compile} = mlir-opt %s -test-lower-to-llvm
+// DEFINE: %{run} = %mcr_aarch64_cmd \
+// DEFINE:  -march=aarch64 -mattr=+sve,+sme \
+// DEFINE:  --force-streaming-compatible-sve \
+// DEFINE:  -e %{entry_point} -entry-point-result=i32 \
+// DEFINE:  -shared-libs=%mlir_runner_utils,%mlir_c_runner_utils
 
 // NOTE: To run this test, your CPU must support SME.
 
+// RUN: %{compile} | %{run} | FileCheck %s
+
 // VLA memcopy in streaming mode.
 func.func @streaming_kernel_copy(%src : memref<?xi64>, %dst : memref<?xi64>, %size : index) attributes {arm_streaming} {
   %c0 = arith.constant 0 : index
   %c2 = arith.constant 2 : index
   %vscale = vector.vscale
   %step = arith.muli %c2, %vscale : index
   scf.for %i = %c0 to %size step %step {
     %0 = vector.load %src[%i] : memref<?xi64>, vector<[2]xi64>

mlir/test/Integration/Dialect/Vector/CPU/ArmSME/vector-ops.mlir

-// RUN: mlir-opt %s -enable-arm-streaming="mode=locally enable-za" \
-// RUN:   -convert-vector-to-arm-sme -convert-arm-sme-to-scf \
-// RUN:   -convert-vector-to-llvm="enable-arm-sme" \
-// RUN:   -allocate-arm-sme-tiles -test-lower-to-llvm | \
-// RUN: mlir-translate -mlir-to-llvmir | \
-// RUN: %lli_aarch64_cmd --march=aarch64 --mattr="+sve,+sme" \
-// RUN:   --entry-function=entry \
-// RUN:   --dlopen=%mlir_native_utils_lib_dir/libmlir_c_runner_utils%shlibext | \
-// RUN: FileCheck %s
+// DEFINE: %{entry_point} = entry
+// DEFINE: %{compile} = mlir-opt %s -enable-arm-streaming="mode=locally enable-za" \
+// DEFINE:   -convert-vector-to-arm-sme -convert-arm-sme-to-scf \
+// DEFINE:   -convert-vector-to-llvm="enable-arm-sme" \
+// DEFINE:   -allocate-arm-sme-tiles -test-lower-to-llvm
+// DEFINE: %{run} = %mcr_aarch64_cmd \
+// DEFINE:  -march=aarch64 -mattr=+sve,+sme \
+// DEFINE:  -e %{entry_point} -entry-point-result=i32 \
+// DEFINE:  -shared-libs=%mlir_runner_utils,%mlir_c_runner_utils
+
+// RUN: %{compile} | %{run} | FileCheck %s
 
 func.func @entry() -> i32 {
   %c0 = arith.constant 0 : index
   %c1_i8 = arith.constant 1 : i8
   %c1_index = arith.constant 1 : index
 
   %c16 = arith.constant 16 : index
   %vscale = vector.vscale