[mlir][vulkan-runner] Fix testsuite.

[denis13]

Summary

Fix testsuite after D78542.

mlir/test/mlir-vulkan-runner/addf.mlir

 // RUN: mlir-vulkan-runner %s --shared-libs=%vulkan_wrapper_library_dir/libvulkan-runtime-wrappers%shlibext,%linalg_test_lib_dir/libmlir_runner_utils%shlibext --entry-point-result=void | FileCheck %s
 
 // CHECK: [3.3,  3.3,  3.3,  3.3,  3.3,  3.3,  3.3,  3.3]
 module attributes {
   gpu.container_module,
   spv.target_env = #spv.target_env<
     #spv.vce<v1.0, [Shader], [SPV_KHR_storage_buffer_storage_class]>,
     {max_compute_workgroup_invocations = 128 : i32,
      max_compute_workgroup_size = dense<[128, 128, 64]> : vector<3xi32>}>
 } {
   gpu.module @kernels {
     gpu.func @kernel_add(%arg0 : memref<8xf32>, %arg1 : memref<8xf32>, %arg2 : memref<8xf32>)
-      attributes { spv.entry_point_abi = {local_size = dense<[1, 1, 1]>: vector<3xi32>} } kernel {
+      kernel attributes { spv.entry_point_abi = {local_size = dense<[1, 1, 1]>: vector<3xi32> }} {
       %0 = "gpu.block_id"() {dimension = "x"} : () -> index
       %1 = load %arg0[%0] : memref<8xf32>
       %2 = load %arg1[%0] : memref<8xf32>
       %3 = addf %1, %2 : f32
       store %3, %arg2[%0] : memref<8xf32>
       gpu.return
     }
   }
func @main() {
     %arg4 = memref_cast %arg1 : memref<8xf32> to memref<?xf32>
     %arg5 = memref_cast %arg2 : memref<8xf32> to memref<?xf32>
     call @fillResource1DFloat(%arg3, %value1) : (memref<?xf32>, f32) -> ()
     call @fillResource1DFloat(%arg4, %value2) : (memref<?xf32>, f32) -> ()
     call @fillResource1DFloat(%arg5, %value0) : (memref<?xf32>, f32) -> ()
 
     %cst1 = constant 1 : index
     %cst8 = constant 8 : index
-    gpu.launch_func"(%cst8, %cst1, %cst1, %cst1, %cst1, %cst1, %arg0, %arg1, %arg2) { kernel = @kernels::@kernel_add }
+    "gpu.launch_func"(%cst8, %cst1, %cst1, %cst1, %cst1, %cst1, %arg0, %arg1, %arg2) { kernel = @kernels::@kernel_add }
         : (index, index, index, index, index, index, memref<8xf32>, memref<8xf32>, memref<8xf32>) -> ()
     %arg6 = memref_cast %arg5 : memref<?xf32> to memref<*xf32>
     call @print_memref_f32(%arg6) : (memref<*xf32>) -> ()
     return
   }
   func @fillResource1DFloat(%0 : memref<?xf32>, %1 : f32)
   func @print_memref_f32(%ptr : memref<*xf32>)
 }
 

mlir/test/mlir-vulkan-runner/mulf.mlir

 // RUN: mlir-vulkan-runner %s --shared-libs=%vulkan_wrapper_library_dir/libvulkan-runtime-wrappers%shlibext,%linalg_test_lib_dir/libmlir_runner_utils%shlibext --entry-point-result=void | FileCheck %s
 
 // CHECK-COUNT-4: [6, 6, 6, 6]
 module attributes {
   gpu.container_module,
   spv.target_env = #spv.target_env<
     #spv.vce<v1.0, [Shader], [SPV_KHR_storage_buffer_storage_class]>,
     {max_compute_workgroup_invocations = 128 : i32,
      max_compute_workgroup_size = dense<[128, 128, 64]> : vector<3xi32>}>
 } {
   gpu.module @kernels {
     gpu.func @kernel_mul(%arg0 : memref<4x4xf32>, %arg1 : memref<4x4xf32>, %arg2 : memref<4x4xf32>)
-      attributes { spv.entry_point_abi = {local_size = dense<[1, 1, 1]>: vector<3xi32>} } kernel {
+      kernel attributes { spv.entry_point_abi = {local_size = dense<[1, 1, 1]>: vector<3xi32> }} {
       %x = "gpu.block_id"() {dimension = "x"} : () -> index
       %y = "gpu.block_id"() {dimension = "y"} : () -> index
       %1 = load %arg0[%x, %y] : memref<4x4xf32>
       %2 = load %arg1[%x, %y] : memref<4x4xf32>
       %3 = mulf %1, %2 : f32
       store %3, %arg2[%x, %y] : memref<4x4xf32>
       gpu.return
     }

mlir/test/mlir-vulkan-runner/subf.mlir

 // RUN: mlir-vulkan-runner %s --shared-libs=%vulkan_wrapper_library_dir/libvulkan-runtime-wrappers%shlibext,%linalg_test_lib_dir/libmlir_runner_utils%shlibext --entry-point-result=void | FileCheck %s
 
 // CHECK-COUNT-32: [2.2, 2.2, 2.2, 2.2]
 module attributes {
   gpu.container_module,
   spv.target_env = #spv.target_env<
     #spv.vce<v1.0, [Shader], [SPV_KHR_storage_buffer_storage_class]>,
     {max_compute_workgroup_invocations = 128 : i32,
      max_compute_workgroup_size = dense<[128, 128, 64]> : vector<3xi32>}>
 } {
   gpu.module @kernels {
     gpu.func @kernel_sub(%arg0 : memref<8x4x4xf32>, %arg1 : memref<4x4xf32>, %arg2 : memref<8x4x4xf32>)
-      attributes { spv.entry_point_abi = {local_size = dense<[1, 1, 1]>: vector<3xi32>} } kernel {
+      kernel attributes { spv.entry_point_abi = {local_size = dense<[1, 1, 1]>: vector<3xi32> }} {
       %x = "gpu.block_id"() {dimension = "x"} : () -> index
       %y = "gpu.block_id"() {dimension = "y"} : () -> index
       %z = "gpu.block_id"() {dimension = "z"} : () -> index
       %1 = load %arg0[%x, %y, %z] : memref<8x4x4xf32>
       %2 = load %arg1[%y, %z] : memref<4x4xf32>
       %3 = subf %1, %2 : f32
       store %3, %arg2[%x, %y, %z] : memref<8x4x4xf32>
       gpu.return

mlir/test/mlir-vulkan-runner/time.mlir

 // RUN: mlir-vulkan-runner %s --shared-libs=%vulkan_wrapper_library_dir/libvulkan-runtime-wrappers%shlibext,%linalg_test_lib_dir/libmlir_runner_utils%shlibext --entry-point-result=void | FileCheck %s
 
 // CHECK: Compute shader execution time
 // CHECK: Command buffer submit time
 // CHECK: Wait idle time
 
 module attributes {
   gpu.container_module,
   spv.target_env = #spv.target_env<
     #spv.vce<v1.0, [Shader], [SPV_KHR_storage_buffer_storage_class]>,
     {max_compute_workgroup_invocations = 128 : i32,
      max_compute_workgroup_size = dense<[128, 128, 64]> : vector<3xi32>}>
 } {
   gpu.module @kernels {
     gpu.func @kernel_add(%arg0 : memref<16384xf32>, %arg1 : memref<16384xf32>, %arg2 : memref<16384xf32>)
-      attributes { spv.entry_point_abi = {local_size = dense<[128, 1, 1]>: vector<3xi32>} } kernel {
+      kernel attributes { spv.entry_point_abi = {local_size = dense<[128, 1, 1]>: vector<3xi32> }} {
       %bid = "gpu.block_id"() {dimension = "x"} : () -> index
       %tid = "gpu.thread_id"() {dimension = "x"} : () -> index
       %cst = constant 128 : index
       %b = muli %bid, %cst : index
       %0 = addi %b, %tid : index
       %1 = load %arg0[%0] : memref<16384xf32>
       %2 = load %arg1[%0] : memref<16384xf32>
       %3 = addf %1, %2 : f32