[mlir] Don't mix -pass-pipeline with other pass options

[rkayaith]

Summary

These are test updates required for D135745

[rkayaith]

rebase

mlir/test/Conversion/VectorToGPU/vector-to-mma-ops.mlir

-// RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-gpu)" -canonicalize | FileCheck %s
+// RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-gpu),canonicalize" | FileCheck %s
 
 #map0 = affine_map<(d0, d1) -> (d1, d0)>
 #map1 = affine_map<(d0, d1, d2) -> (d0, d2)>
 #map2 = affine_map<(d0, d1, d2) -> (d1, d2)>
 #map3 = affine_map<(d0, d1, d2) -> (d0, d1)>
 #map4 = affine_map<(d0) -> (d0, 0)>
 
 // CHECK-LABEL: func @matmul

mlir/test/Dialect/GPU/promotion.mlir

-// RUN: mlir-opt -allow-unregistered-dialect -test-gpu-memory-promotion -pass-pipeline='gpu.module(gpu.func(test-gpu-memory-promotion))' -split-input-file %s | FileCheck %s
+// RUN: mlir-opt -allow-unregistered-dialect -pass-pipeline='gpu.module(gpu.func(test-gpu-memory-promotion))' -split-input-file %s | FileCheck %s
 
 gpu.module @foo {
 
   // Verify that the attribution was indeed introduced
   // CHECK-LABEL: @memref3d
   // CHECK-SAME: (%[[arg:.*]]: memref<5x4xf32>
   // CHECK-SAME: workgroup(%[[promoted:.*]] : memref<5x4xf32, 3>)
   gpu.func @memref3d(%arg0: memref<5x4xf32> {gpu.test_promote_workgroup}) kernel {

mlir/test/Integration/Dialect/Vector/GPU/CUDA/test-reduction-distribute.mlir

 // RUN: mlir-opt %s -test-vector-warp-distribute="hoist-uniform distribute-transfer-write propagate-distribution" -canonicalize |\
 // RUN: mlir-opt -test-vector-warp-distribute=rewrite-warp-ops-to-scf-if |\
 // RUN: mlir-opt  -lower-affine -convert-scf-to-cf -convert-vector-to-llvm \
-// RUN:  -convert-arith-to-llvm -gpu-kernel-outlining \
-// RUN:  -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,reconcile-unrealized-casts,gpu-to-cubin)' \
-// RUN:  -gpu-to-llvm -reconcile-unrealized-casts |\
+// RUN:  -convert-arith-to-llvm -gpu-kernel-outlining |\
+// RUN: mlir-opt -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,reconcile-unrealized-casts,gpu-to-cubin)' |\
+// RUN: mlir-opt -gpu-to-llvm -reconcile-unrealized-casts |\
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
 // RUN:   -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext \
 // RUN:   -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext | \
 // RUN: FileCheck %s
 
 // Run a tiled reduction fused with an elementwise op.
 

mlir/test/Integration/Dialect/Vector/GPU/CUDA/test-warp-distribute.mlir

 // Run the test cases without distributing ops to test default lowering. Run
 // everything on the same thread.
 // RUN: mlir-opt %s -test-vector-warp-distribute=rewrite-warp-ops-to-scf-if -canonicalize | \
 // RUN: mlir-opt -convert-scf-to-cf -convert-cf-to-llvm -convert-vector-to-llvm -convert-arith-to-llvm \
-// RUN:  -gpu-kernel-outlining \
-// RUN:  -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,reconcile-unrealized-casts,gpu-to-cubin)' \
-// RUN:  -gpu-to-llvm -reconcile-unrealized-casts |\
+// RUN:  -gpu-kernel-outlining |\
+// RUN: mlir-opt -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,reconcile-unrealized-casts,gpu-to-cubin)' |\
+// RUN: mlir-opt -gpu-to-llvm -reconcile-unrealized-casts |\
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
 // RUN:   -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext \
 // RUN:   -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext | \
 // RUN: FileCheck %s
 
 // Run the same test cases with distribution and propagation.
 // RUN: mlir-opt %s  -test-vector-warp-distribute="hoist-uniform distribute-transfer-write" \
 // RUN:   -test-vector-warp-distribute=rewrite-warp-ops-to-scf-if -canonicalize | \
 // RUN: mlir-opt -convert-scf-to-cf -convert-cf-to-llvm -convert-vector-to-llvm -convert-arith-to-llvm \
-// RUN:  -gpu-kernel-outlining \
-// RUN:  -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,reconcile-unrealized-casts,gpu-to-cubin)' \
-// RUN:  -gpu-to-llvm -reconcile-unrealized-casts |\
+// RUN:  -gpu-kernel-outlining |\
+// RUN: mlir-opt -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,reconcile-unrealized-casts,gpu-to-cubin)' |\
+// RUN: mlir-opt -gpu-to-llvm -reconcile-unrealized-casts |\
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
 // RUN:   -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext \
 // RUN:   -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext | \
 // RUN: FileCheck %s
 
 // RUN: mlir-opt %s  -test-vector-warp-distribute="hoist-uniform distribute-transfer-write propagate-distribution" \
 // RUN:   -test-vector-warp-distribute=rewrite-warp-ops-to-scf-if -canonicalize | \
 // RUN: mlir-opt -convert-scf-to-cf -convert-cf-to-llvm -convert-vector-to-llvm -convert-arith-to-llvm \
-// RUN:  -gpu-kernel-outlining \
-// RUN:  -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,reconcile-unrealized-casts,gpu-to-cubin)' \
-// RUN:  -gpu-to-llvm -reconcile-unrealized-casts |\
+// RUN:  -gpu-kernel-outlining |\
+// RUN: mlir-opt -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,reconcile-unrealized-casts,gpu-to-cubin)' |\
+// RUN: mlir-opt -gpu-to-llvm -reconcile-unrealized-casts |\
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
 // RUN:   -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext \
 // RUN:   -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext | \
 // RUN: FileCheck %s
 
 func.func @gpu_func(%arg1: memref<32xf32>, %arg2: memref<32xf32>) {
   %c1 = arith.constant 1 : index

mlir/test/Integration/GPU/CUDA/TensorCore/wmma-matmul-f16.mlir

 // RUN: mlir-opt %s \
-// RUN: -gpu-kernel-outlining \
-// RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin{chip=sm_70})' \
-// RUN: --convert-scf-to-cf -gpu-to-llvm \
+// RUN: | mlir-opt -gpu-kernel-outlining \
+// RUN: | mlir-opt -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin{chip=sm_70})' \
+// RUN: | mlir-opt --convert-scf-to-cf -gpu-to-llvm \
 // RUN: | mlir-cpu-runner \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
 // RUN:   --entry-point-result=void \
 // RUN: | FileCheck %s
 // Test case to check the working of Tensor cores on Nvidia GPUs. The kernel has already
 // been outlined to prevent crashing due to introduction of an empty basic block by --gpu-
 // kernel-outling.

mlir/test/Integration/GPU/CUDA/TensorCore/wmma-matmul-f32.mlir

 // RUN: mlir-opt %s \
-// RUN: -gpu-kernel-outlining \
-// RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin{chip=sm_70})' \
-// RUN: --convert-scf-to-cf -gpu-to-llvm \
+// RUN: | mlir-opt -gpu-kernel-outlining \
+// RUN: | mlir-opt -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin{chip=sm_70})' \
+// RUN: | mlir-opt --convert-scf-to-cf -gpu-to-llvm \
 // RUN: | mlir-cpu-runner \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
 // RUN:   --entry-point-result=void \
 // RUN: | FileCheck %s
 
 func.func @main() {
   %0 = memref.alloc() : memref<16x16xf16>

mlir/test/Integration/GPU/CUDA/all-reduce-and.mlir

 // RUN: mlir-opt %s \
-// RUN:   -gpu-kernel-outlining \
-// RUN:   -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
-// RUN:   -gpu-to-llvm \
+// RUN: | mlir-opt -gpu-kernel-outlining \
+// RUN: | mlir-opt -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
+// RUN: | mlir-opt -gpu-to-llvm \
 // RUN: | mlir-cpu-runner \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
 // RUN:   --entry-point-result=void \
 // RUN: | FileCheck %s
 
 func.func @main() {
   %data = memref.alloc() : memref<2x6xi32>

mlir/test/Integration/GPU/CUDA/all-reduce-max.mlir

 // RUN: mlir-opt %s \
-// RUN:   -gpu-kernel-outlining \
-// RUN:   -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
-// RUN:   -gpu-to-llvm \
+// RUN: | mlir-opt -gpu-kernel-outlining \
+// RUN: | mlir-opt -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
+// RUN: | mlir-opt -gpu-to-llvm \
 // RUN: | mlir-cpu-runner \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
 // RUN:   --entry-point-result=void \
 // RUN: | FileCheck %s
 
 func.func @main() {
   %data = memref.alloc() : memref<2x6xi32>

mlir/test/Integration/GPU/CUDA/all-reduce-min.mlir

 // RUN: mlir-opt %s \
-// RUN:   -gpu-kernel-outlining \
-// RUN:   -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
-// RUN:   -gpu-to-llvm \
+// RUN: | mlir-opt -gpu-kernel-outlining \
+// RUN: | mlir-opt -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
+// RUN: | mlir-opt -gpu-to-llvm \
 // RUN: | mlir-cpu-runner \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
 // RUN:   --entry-point-result=void \
 // RUN: | FileCheck %s
 
 func.func @main() {
   %data = memref.alloc() : memref<2x6xi32>

mlir/test/Integration/GPU/CUDA/all-reduce-op.mlir

 // RUN: mlir-opt %s \
-// RUN:   -gpu-kernel-outlining \
-// RUN:   -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
-// RUN:   -gpu-to-llvm \
+// RUN: | mlir-opt -gpu-kernel-outlining \
+// RUN: | mlir-opt -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
+// RUN: | mlir-opt -gpu-to-llvm \
 // RUN: | mlir-cpu-runner \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
 // RUN:   --entry-point-result=void \
 // RUN: | FileCheck %s
 
 // CHECK-COUNT-8: [{{(5356, ){12}5356}}]
 func.func @main() {

mlir/test/Integration/GPU/CUDA/all-reduce-or.mlir

 // RUN: mlir-opt %s \
-// RUN:   -gpu-kernel-outlining \
-// RUN:   -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
-// RUN:   -gpu-to-llvm \
+// RUN: | mlir-opt -gpu-kernel-outlining \
+// RUN: | mlir-opt -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
+// RUN: | mlir-opt -gpu-to-llvm \
 // RUN: | mlir-cpu-runner \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
 // RUN:   --entry-point-result=void \
 // RUN: | FileCheck %s
 
 func.func @main() {
   %data = memref.alloc() : memref<2x6xi32>

mlir/test/Integration/GPU/CUDA/all-reduce-region.mlir

 // RUN: mlir-opt %s \
-// RUN:   -gpu-kernel-outlining \
-// RUN:   -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
-// RUN:   -gpu-to-llvm \
+// RUN: | mlir-opt -gpu-kernel-outlining \
+// RUN: | mlir-opt -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
+// RUN: | mlir-opt -gpu-to-llvm \
 // RUN: | mlir-cpu-runner \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
 // RUN:   --entry-point-result=void \
 // RUN: | FileCheck %s
 
 // CHECK: [{{(35, ){34}35}}]
 func.func @main() {

mlir/test/Integration/GPU/CUDA/all-reduce-xor.mlir

 // RUN: mlir-opt %s \
-// RUN:   -gpu-kernel-outlining \
-// RUN:   -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
-// RUN:   -gpu-to-llvm \
+// RUN: | mlir-opt -gpu-kernel-outlining \
+// RUN: | mlir-opt -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
+// RUN: | mlir-opt -gpu-to-llvm \
 // RUN: | mlir-cpu-runner \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
 // RUN:   --entry-point-result=void \
 // RUN: | FileCheck %s
 
 func.func @main() {
   %data = memref.alloc() : memref<2x6xi32>

mlir/test/Integration/GPU/CUDA/async.mlir

 // RUN: mlir-opt %s \
-// RUN:   -gpu-kernel-outlining \
-// RUN:   -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
-// RUN:   -gpu-async-region -gpu-to-llvm \
-// RUN:   -async-to-async-runtime -async-runtime-ref-counting \
-// RUN:   -convert-async-to-llvm -convert-func-to-llvm \
+// RUN: | mlir-opt -gpu-kernel-outlining \
+// RUN: | mlir-opt -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
+// RUN: | mlir-opt -gpu-async-region -gpu-to-llvm \
+// RUN: | mlir-opt -async-to-async-runtime -async-runtime-ref-counting \
+// RUN: | mlir-opt -convert-async-to-llvm -convert-func-to-llvm \
 // RUN: | mlir-cpu-runner \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_async_runtime%shlibext \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
 // RUN:   --entry-point-result=void -O0 \
 // RUN: | FileCheck %s
 
 func.func @main() {

mlir/test/Integration/GPU/CUDA/gpu-to-cubin.mlir

 // RUN: mlir-opt %s \
-// RUN:   -gpu-kernel-outlining \
-// RUN:   -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
-// RUN:   -gpu-to-llvm \
+// RUN: | mlir-opt -gpu-kernel-outlining \
+// RUN: | mlir-opt -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
+// RUN: | mlir-opt -gpu-to-llvm \
 // RUN: | mlir-cpu-runner \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext \
 // RUN:   --entry-point-result=void \
 // RUN: | FileCheck %s
 
 func.func @other_func(%arg0 : f32, %arg1 : memref<?xf32>) {

mlir/test/Integration/GPU/CUDA/multiple-all-reduce.mlir

 // RUN: mlir-opt %s \
-// RUN:   -gpu-kernel-outlining \
-// RUN:   -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
-// RUN:   -gpu-to-llvm \
+// RUN: | mlir-opt -gpu-kernel-outlining \
+// RUN: | mlir-opt -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
+// RUN: | mlir-opt -gpu-to-llvm \
 // RUN: | mlir-cpu-runner \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
 // RUN:   --entry-point-result=void \
 // RUN: | FileCheck %s
 
 func.func @main() {
   %data = memref.alloc() : memref<2x6xf32>

mlir/test/Integration/GPU/CUDA/shuffle.mlir

 // RUN: mlir-opt %s \
-// RUN:   -gpu-kernel-outlining \
-// RUN:   -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
-// RUN:   -gpu-to-llvm \
+// RUN: | mlir-opt -gpu-kernel-outlining \
+// RUN: | mlir-opt -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
+// RUN: | mlir-opt -gpu-to-llvm \
 // RUN: | mlir-cpu-runner \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
 // RUN:   --entry-point-result=void \
 // RUN: | FileCheck %s
 
 // CHECK: [4, 5, 6, 7, 0, 1, 2, 3, 12, -1, -1, -1, 8]
 func.func @main() {

mlir/test/Integration/GPU/CUDA/two-modules.mlir

 // RUN: mlir-opt %s \
-// RUN:   -gpu-kernel-outlining \
-// RUN:   -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
-// RUN:   -gpu-to-llvm \
+// RUN: | mlir-opt -gpu-kernel-outlining \
+// RUN: | mlir-opt -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
+// RUN: | mlir-opt -gpu-to-llvm \
 // RUN: | mlir-cpu-runner \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
 // RUN:   --entry-point-result=void \
 // RUN: | FileCheck %s
 
 // CHECK: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]
 func.func @main() {

mlir/test/Integration/GPU/ROCM/gpu-to-hsaco.mlir

 // RUN: mlir-opt %s \
-// RUN:   -gpu-kernel-outlining \
-// RUN:   -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-rocdl,gpu-to-hsaco{chip=%chip})' \
-// RUN:   -gpu-to-llvm \
+// RUN: | mlir-opt -gpu-kernel-outlining \
+// RUN: | mlir-opt -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-rocdl,gpu-to-hsaco{chip=%chip})' \
+// RUN: | mlir-opt -gpu-to-llvm \
 // RUN: | mlir-cpu-runner \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_rocm_runtime%shlibext \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
 // RUN:   --entry-point-result=void \
 // RUN: | FileCheck %s
 
 func.func @other_func(%arg0 : f32, %arg1 : memref<?xf32>) {
   %c0 = arith.constant 0 : index

mlir/test/Integration/GPU/ROCM/printf.mlir

 // RUN: mlir-opt %s \
-// RUN:   -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-rocdl{index-bitwidth=32 runtime=HIP},gpu-to-hsaco{chip=%chip})' \
-// RUN:   -gpu-to-llvm \
+// RUN: | mlir-opt -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-rocdl{index-bitwidth=32 runtime=HIP},gpu-to-hsaco{chip=%chip})' \
+// RUN: | mlir-opt -gpu-to-llvm \
 // RUN: | mlir-cpu-runner \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_rocm_runtime%shlibext \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
 // RUN:   --entry-point-result=void \
 // RUN: | FileCheck %s
 
 // CHECK: Hello from 0
 // CHECK: Hello from 1

mlir/test/Integration/GPU/ROCM/two-modules.mlir

 // RUN: mlir-opt %s \
-// RUN:   -gpu-kernel-outlining \
-// RUN:   -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-rocdl,gpu-to-hsaco{chip=%chip})' \
-// RUN:   -gpu-to-llvm \
+// RUN: | mlir-opt -gpu-kernel-outlining \
+// RUN: | mlir-opt -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-rocdl,gpu-to-hsaco{chip=%chip})' \
+// RUN: | mlir-opt -gpu-to-llvm \
 // RUN: | mlir-cpu-runner \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_rocm_runtime%shlibext \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
 // RUN:   --entry-point-result=void \
 // RUN: | FileCheck %s
 
 // CHECK: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]
 func.func @main() {

mlir/test/Integration/GPU/ROCM/vecadd.mlir

 // RUN: mlir-opt %s \
-// RUN:   -convert-scf-to-cf \
-// RUN:   -gpu-kernel-outlining \
-// RUN:   -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-rocdl{use-bare-ptr-memref-call-conv=true},gpu-to-hsaco{chip=%chip})' \
-// RUN:   -gpu-to-llvm=use-bare-pointers-for-kernels=true \
+// RUN: | mlir-opt -convert-scf-to-cf \
+// RUN: | mlir-opt -gpu-kernel-outlining \
+// RUN: | mlir-opt -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-rocdl{use-bare-ptr-memref-call-conv=true},gpu-to-hsaco{chip=%chip})' \
+// RUN: | mlir-opt -gpu-to-llvm=use-bare-pointers-for-kernels=true \
 // RUN: | mlir-cpu-runner \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_rocm_runtime%shlibext \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
 // RUN:   --entry-point-result=void \
 // RUN: | FileCheck %s
 
 func.func @vecadd(%arg0 : memref<5xf32>, %arg1 : memref<5xf32>, %arg2 : memref<5xf32>) {
   %c0 = arith.constant 0 : index

mlir/test/Integration/GPU/ROCM/vector-transferops.mlir

 // RUN: mlir-opt %s \
-// RUN:   -convert-scf-to-cf \
-// RUN:   -gpu-kernel-outlining \
-// RUN:   -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-rocdl{chipset=%chip index-bitwidth=32},gpu-to-hsaco{chip=%chip})' \
-// RUN:   -gpu-to-llvm \
+// RUN: | mlir-opt -convert-scf-to-cf \
+// RUN: | mlir-opt -gpu-kernel-outlining \
+// RUN: | mlir-opt -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-rocdl{chipset=%chip index-bitwidth=32},gpu-to-hsaco{chip=%chip})' \
+// RUN: | mlir-opt -gpu-to-llvm \
 // RUN: | mlir-cpu-runner \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_rocm_runtime%shlibext \
 // RUN:   --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
 // RUN:   --entry-point-result=void \
 // RUN: | FileCheck %s
 
 // TODO: swap for vector transfer reads if we ever create a --vector-to-amdgpu
 func.func @vectransferx2(%arg0 : memref<?xf32>, %arg1 : memref<?xf32>) {

mlir/test/Pass/pipeline-parsing.mlir

-// RUN: mlir-opt %s -mlir-disable-threading -pass-pipeline='builtin.module(test-module-pass,func.func(test-function-pass)),func.func(test-function-pass)' -pass-pipeline="func.func(cse,canonicalize)" -verify-each=false -mlir-timing -mlir-timing-display=tree 2>&1 | FileCheck %s
+// RUN: mlir-opt %s -mlir-disable-threading -pass-pipeline='builtin.module(test-module-pass,func.func(test-function-pass)),func.func(test-function-pass),func.func(cse,canonicalize)' -verify-each=false -mlir-timing -mlir-timing-display=tree 2>&1 | FileCheck %s
 // RUN: mlir-opt %s -mlir-disable-threading -test-textual-pm-nested-pipeline -verify-each=false -mlir-timing -mlir-timing-display=tree 2>&1 | FileCheck %s --check-prefix=TEXTUAL_CHECK
 // RUN: mlir-opt %s -mlir-disable-threading -pass-pipeline='builtin.module(test-module-pass),any(test-interface-pass),any(test-interface-pass),func.func(test-function-pass),any(canonicalize),func.func(cse)' -verify-each=false -mlir-timing -mlir-timing-display=tree 2>&1 | FileCheck %s --check-prefix=GENERIC_MERGE_CHECK
 // RUN: not mlir-opt %s -pass-pipeline='builtin.module(test-module-pass' 2>&1 | FileCheck --check-prefix=CHECK_ERROR_1 %s
 // RUN: not mlir-opt %s -pass-pipeline='builtin.module(test-module-pass))' 2>&1 | FileCheck --check-prefix=CHECK_ERROR_2 %s
 // RUN: not mlir-opt %s -pass-pipeline='builtin.module()(' 2>&1 | FileCheck --check-prefix=CHECK_ERROR_3 %s
 // RUN: not mlir-opt %s -pass-pipeline=',' 2>&1 | FileCheck --check-prefix=CHECK_ERROR_4 %s
 // RUN: not mlir-opt %s -pass-pipeline='func.func(test-module-pass)' 2>&1 | FileCheck --check-prefix=CHECK_ERROR_5 %s
 

mlir/test/mlir-cpu-runner/bare-ptr-call-conv.mlir

-// RUN: mlir-opt %s -pass-pipeline="func.func(convert-scf-to-cf,convert-arith-to-llvm),convert-memref-to-llvm,convert-func-to-llvm{use-bare-ptr-memref-call-conv=1}" -reconcile-unrealized-casts | mlir-cpu-runner -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext -entry-point-result=void | FileCheck %s
+// RUN: mlir-opt %s -pass-pipeline="func.func(convert-scf-to-cf,convert-arith-to-llvm),convert-memref-to-llvm,convert-func-to-llvm{use-bare-ptr-memref-call-conv=1},reconcile-unrealized-casts" | mlir-cpu-runner -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext -entry-point-result=void | FileCheck %s
 
 // Verify bare pointer memref calling convention. `simple_add1_add2_test`
 // gets two 2xf32 memrefs, adds 1.0f to the first one and 2.0f to the second
 // one. 'main' calls 'simple_add1_add2_test' with {1, 1} and {2, 2} so {2, 2}
 // and {4, 4} are the expected outputs.
 
 func.func @simple_add1_add2_test(%arg0: memref<2xf32>, %arg1: memref<2xf32>) {
   %c2 = arith.constant 2 : index