[mlir][sparse] Make some integration tests run with vectorization.

[bixia]

Missing enable-buffer-initialization=true for two tests after merging with https://reviews.llvm.org/D139489

[aartbik]

LGTM, post submit ;-)

mlir/test/Integration/Dialect/SparseTensor/CPU/dense_output.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: TENSOR0="%mlir_src_dir/test/Integration/data/test.mtx" \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = enable-runtime-library=false
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 !Filename = !llvm.ptr<i8>
 
 #DenseMatrix = #sparse_tensor.encoding<{
   dimLevelType = [ "dense", "dense" ],
   dimOrdering = affine_map<(i,j) -> (i,j)>
 }>
 

mlir/test/Integration/Dialect/SparseTensor/CPU/dense_output_bf16.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = enable-runtime-library=false
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 // UNSUPPORTED: aarch64
 
 #SparseVector = #sparse_tensor.encoding<{dimLevelType = ["compressed"]}>
 #DenseVector = #sparse_tensor.encoding<{dimLevelType = ["dense"]}>
 
 #trait_vec_op = {
   indexing_maps = [

mlir/test/Integration/Dialect/SparseTensor/CPU/dense_output_f16.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = enable-runtime-library=false
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 #SparseVector = #sparse_tensor.encoding<{dimLevelType = ["compressed"]}>
 #DenseVector = #sparse_tensor.encoding<{dimLevelType = ["dense"]}>
 
 #trait_vec_op = {
   indexing_maps = [
     affine_map<(i) -> (i)>,  // a (in)
     affine_map<(i) -> (i)>,  // b (in)

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_abs.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = enable-runtime-library=false
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
+
 #SparseVector = #sparse_tensor.encoding<{ dimLevelType = [ "compressed" ] }>
 
 #trait_op = {
   indexing_maps = [
     affine_map<(i) -> (i)>, // a
     affine_map<(i) -> (i)>  // x (out)
   ],
   iterator_types = ["parallel"],

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_cast.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = enable-runtime-library=false
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 #SV = #sparse_tensor.encoding<{ dimLevelType = [ "compressed" ] }>
 
 #trait_cast = {
   indexing_maps = [
     affine_map<(i) -> (i)>,  // A (in)
     affine_map<(i) -> (i)>   // X (out)
   ],

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_codegen_dim.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = enable-runtime-library=false
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 #DCSR  = #sparse_tensor.encoding<{
   dimLevelType = [ "compressed", "compressed"]
 }>
 
 module {
   //
   // Main driver.

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_codegen_foreach.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = enable-runtime-library=false
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 #Row = #sparse_tensor.encoding<{
   dimLevelType = [ "compressed", "dense" ]
 }>
 
 #CSR = #sparse_tensor.encoding<{
   dimLevelType = [ "dense", "compressed" ]
 }>

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_complex32.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = "enable-runtime-library=false enable-buffer-initialization=true"
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 #SparseVector = #sparse_tensor.encoding<{dimLevelType = ["compressed"]}>
 
 #trait_op = {
   indexing_maps = [
     affine_map<(i) -> (i)>,  // a (in)
     affine_map<(i) -> (i)>,  // b (in)
     affine_map<(i) -> (i)>   // x (out)

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_complex64.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = enable-runtime-library=false
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 #SparseVector = #sparse_tensor.encoding<{dimLevelType = ["compressed"]}>
 
 #trait_op = {
   indexing_maps = [
     affine_map<(i) -> (i)>,  // a (in)
     affine_map<(i) -> (i)>,  // b (in)
     affine_map<(i) -> (i)>   // x (out)

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_complex_ops.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = enable-runtime-library=false
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 #SparseVector = #sparse_tensor.encoding<{dimLevelType = ["compressed"]}>
 
 #trait_op1 = {
   indexing_maps = [
     affine_map<(i) -> (i)>,  // a (in)
     affine_map<(i) -> (i)>   // x (out)
   ],

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_constant_to_sparse_tensor.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = "enable-runtime-library=false enable-buffer-initialization=true"
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false enable-buffer-initialization=true vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 #Tensor1  = #sparse_tensor.encoding<{
   dimLevelType = [ "compressed", "compressed"]
 }>
 
 //
 // Integration tests for conversions from sparse constants to sparse tensors.
 //

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_conv_1d_nwc_wcf.mlir

-// RUN: mlir-opt %s --sparse-compiler=enable-runtime-library=true | \
-// RUN: mlir-cpu-runner -e entry -entry-point-result=void \
-// RUN:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
-// RUN: FileCheck %s
-
-// RUN: mlir-opt %s --sparse-compiler="enable-runtime-library=false enable-buffer-initialization=true" | \
-// RUN: mlir-cpu-runner \
-// RUN:  -e entry -entry-point-result=void  \
-// RUN:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
-// RUN: FileCheck %s
+// DEFINE: %{option} = enable-runtime-library=true
+// DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
+// DEFINE: mlir-cpu-runner \
+// DEFINE:  -e entry -entry-point-result=void  \
+// DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
+// DEFINE: FileCheck %s
+//
+// RUN: %{command}
+//
+// Do the same run, but now with direct IR generation.
+// REDEFINE: %{option} = "enable-runtime-library=false enable-buffer-initialization=true"
+// RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false enable-buffer-initialization=true vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 #CCC = #sparse_tensor.encoding<{
   dimLevelType = [ "compressed", "compressed", "compressed" ] }>
 
 #CDC = #sparse_tensor.encoding<{
   dimLevelType = [ "compressed", "dense", "compressed" ]
   // FIXME: Still inadmissible might need investigation
   // dimOrdering = affine_map<(i,j,k) -> (j,k,i)>

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_conv_2d_nhwc_hwcf.mlir

-// RUN: mlir-opt %s --sparse-compiler=enable-runtime-library=true | \
-// RUN: mlir-cpu-runner -e entry -entry-point-result=void \
-// RUN:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
-// RUN: FileCheck %s
-
-// RUN: mlir-opt %s --sparse-compiler="enable-runtime-library=false enable-buffer-initialization=true" | \
-// RUN: mlir-cpu-runner \
-// RUN:  -e entry -entry-point-result=void  \
-// RUN:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
-// RUN: FileCheck %s
+// DEFINE: %{option} = enable-runtime-library=true
+// DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
+// DEFINE: mlir-cpu-runner \
+// DEFINE:  -e entry -entry-point-result=void  \
+// DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
+// DEFINE: FileCheck %s
+//
+// RUN: %{command}
+//
+// Do the same run, but now with direct IR generation.
+// REDEFINE: %{option} = "enable-runtime-library=false enable-buffer-initialization=true"
+// RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false enable-buffer-initialization=true vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 #CCCC = #sparse_tensor.encoding<{
   dimLevelType = [ "compressed", "compressed", "compressed", "compressed" ]
 }>
 
 #CDCD = #sparse_tensor.encoding<{
   dimLevelType = [ "compressed", "dense", "compressed", "dense" ]
 }>

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_conv_3d.mlir

-// RUN: mlir-opt %s --sparse-compiler=enable-runtime-library=true | \
-// RUN: mlir-cpu-runner -e entry -entry-point-result=void \
-// RUN:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
-// RUN: FileCheck %s
-
-// RUN: mlir-opt %s --sparse-compiler="enable-runtime-library=false enable-buffer-initialization=true" | \
-// RUN: mlir-cpu-runner \
-// RUN:  -e entry -entry-point-result=void  \
-// RUN:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
-// RUN: FileCheck %s
+// DEFINE: %{option} = enable-runtime-library=true
+// DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
+// DEFINE: mlir-cpu-runner \
+// DEFINE:  -e entry -entry-point-result=void  \
+// DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
+// DEFINE: FileCheck %s
+//
+// RUN: %{command}
+//
+// Do the same run, but now with direct IR generation.
+// REDEFINE: %{option} = "enable-runtime-library=false enable-buffer-initialization=true"
+// RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false enable-buffer-initialization=true vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 #CCC = #sparse_tensor.encoding<{
   dimLevelType = [ "compressed", "compressed", "compressed" ]
 }>
 
 #CDC = #sparse_tensor.encoding<{
   dimLevelType = [ "compressed", "dense", "compressed" ]
 }>

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_conv_3d_ndhwc_dhwcf.mlir

-// RUN: mlir-opt %s --sparse-compiler=enable-runtime-library=true | \
-// RUN: mlir-cpu-runner -e entry -entry-point-result=void \
-// RUN:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
-// RUN: FileCheck %s
-
-// RUN: mlir-opt %s --sparse-compiler="enable-runtime-library=false enable-buffer-initialization=true" | \
-// RUN: mlir-cpu-runner \
-// RUN:  -e entry -entry-point-result=void  \
-// RUN:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
-// RUN: FileCheck %s
+// DEFINE: %{option} = enable-runtime-library=true
+// DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
+// DEFINE: mlir-cpu-runner \
+// DEFINE:  -e entry -entry-point-result=void  \
+// DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
+// DEFINE: FileCheck %s
+//
+// RUN: %{command}
+//
+// Do the same run, but now with direct IR generation.
+// REDEFINE: %{option} = "enable-runtime-library=false enable-buffer-initialization=true"
+// RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false enable-buffer-initialization=true vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 #CCCCC = #sparse_tensor.encoding<{
   dimLevelType = [ "compressed", "compressed", "compressed", "compressed", "compressed" ]
 }>
 
 #CDCDC = #sparse_tensor.encoding<{
   dimLevelType = [ "compressed", "dense", "compressed", "dense", "compressed"]
 }>

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_conversion.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = "enable-runtime-library=false enable-buffer-initialization=true"
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false enable-buffer-initialization=true vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 #Tensor1  = #sparse_tensor.encoding<{
   dimLevelType = [ "compressed", "compressed", "compressed" ],
   dimOrdering = affine_map<(i,j,k) -> (i,j,k)>
 }>
 
 #Tensor2  = #sparse_tensor.encoding<{
   dimLevelType = [ "compressed", "compressed", "compressed" ],

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_conversion_dyn.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = "enable-runtime-library=false enable-buffer-initialization=true"
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false enable-buffer-initialization=true vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 #DCSR  = #sparse_tensor.encoding<{
   dimLevelType = [ "compressed", "compressed" ]
 }>
 
 #DCSC  = #sparse_tensor.encoding<{
   dimLevelType = [ "compressed", "compressed" ],
   dimOrdering = affine_map<(i,j) -> (j,i)>

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_conversion_ptr.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = "enable-runtime-library=false enable-buffer-initialization=true"
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false enable-buffer-initialization=true vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 #DCSR  = #sparse_tensor.encoding<{
   dimLevelType = [ "compressed", "compressed" ],
   pointerBitWidth = 8,
   indexBitWidth = 8
 }>
 
 #DCSC  = #sparse_tensor.encoding<{

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_dot.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = enable-runtime-library=false
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 #SparseVector = #sparse_tensor.encoding<{ dimLevelType = [ "compressed" ] }>
 
 module {
 
   //
   // Sparse kernel.
   //

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_file_io.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: TENSOR0="%mlir_src_dir/test/Integration/data/wide.mtx" \
 // DEFINE: TENSOR1="" \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = enable-runtime-library=false
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 !Filename = !llvm.ptr<i8>
 !TensorReader = !llvm.ptr<i8>
 !TensorWriter = !llvm.ptr<i8>
 
 module {
 
   func.func private @getTensorFilename(index) -> (!Filename)

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_filter_conv2d.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = enable-runtime-library=false
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 #DCSR = #sparse_tensor.encoding<{ dimLevelType = [ "compressed", "compressed" ] }>
 
 // An example of a 2D convolution with a sparse filter.
 module {
 
   func.func @conv2d(%input:  tensor<8x8xi32>,
                %filter: tensor<3x3xi32, #DCSR>,

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_flatten.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: TENSOR0="%mlir_src_dir/test/Integration/data/test.tns" \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = enable-runtime-library=false
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 !Filename = !llvm.ptr<i8>
 
 #SparseTensor = #sparse_tensor.encoding<{
   dimLevelType = [ "compressed", "compressed", "compressed", "compressed",
                    "compressed", "compressed", "compressed", "compressed" ],
   // Note that any dimOrdering permutation should give the same results
   // since, even though it impacts the sparse storage scheme layout,

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_index.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = enable-runtime-library=false
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 #SparseVector = #sparse_tensor.encoding<{
   dimLevelType = ["compressed"]
 }>
 
 #SparseMatrix = #sparse_tensor.encoding<{
   dimLevelType = ["compressed", "compressed"]
 }>

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_index_dense.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = enable-runtime-library=false
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 #SparseVector = #sparse_tensor.encoding<{
   dimLevelType = ["compressed"]
 }>
 
 #SparseMatrix = #sparse_tensor.encoding<{
   dimLevelType = ["compressed", "compressed"]
 }>

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_insert_1d.mlir

-// RUN: mlir-opt %s --sparse-compiler=enable-runtime-library=false | \
-// RUN: mlir-cpu-runner \
-// RUN:  -e entry -entry-point-result=void  \
-// RUN:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
-// RUN: FileCheck %s
+// DEFINE: %{option} = enable-runtime-library=false
+// DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
+// DEFINE: mlir-cpu-runner \
+// DEFINE:  -e entry -entry-point-result=void  \
+// DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
+// DEFINE: FileCheck %s
+//
+// RUN: %{command}
+//
+// Do the same run, but now with vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 // Insertion example using pure codegen (no sparse runtime support lib).
 
 #SparseVector = #sparse_tensor.encoding<{ dimLevelType = [ "compressed" ] }>
 
 #trait_mul_s = {
   indexing_maps = [
     affine_map<(i) -> (i)>   // x (out)

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_insert_2d.mlir

-// RUN: mlir-opt %s --sparse-compiler=enable-runtime-library=false | \
-// RUN: mlir-cpu-runner \
-// RUN:  -e entry -entry-point-result=void  \
-// RUN:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
-// RUN: FileCheck %s
+// DEFINE: %{option} = enable-runtime-library=false
+// DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
+// DEFINE: mlir-cpu-runner \
+// DEFINE:  -e entry -entry-point-result=void  \
+// DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
+// DEFINE: FileCheck %s
+//
+// RUN: %{command}
+//
+// Do the same run, but now with vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 #Dense = #sparse_tensor.encoding<{
   dimLevelType = ["dense", "dense"]
 }>
 
 #SortedCOO = #sparse_tensor.encoding<{
   dimLevelType = [ "compressed-nu", "singleton" ]
 }>

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_insert_3d.mlir

-// RUN: mlir-opt %s --sparse-compiler=enable-runtime-library=false | \
-// RUN: mlir-cpu-runner \
-// RUN:  -e entry -entry-point-result=void  \
-// RUN:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
-// RUN: FileCheck %s
+// DEFINE: %{option} = enable-runtime-library=false
+// DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
+// DEFINE: mlir-cpu-runner \
+// DEFINE:  -e entry -entry-point-result=void  \
+// DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
+// DEFINE: FileCheck %s
+//
+// RUN: %{command}
+//
+// Do the same run, but now with vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 #TensorCSR = #sparse_tensor.encoding<{
   dimLevelType = [ "compressed", "dense", "compressed" ]
 }>
 
 #TensorRow = #sparse_tensor.encoding<{
   dimLevelType = [ "compressed", "compressed", "dense" ]
 }>

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_matmul.mlir

 //
 // Do the same run, but now with parallelization strategy.
 // REDEFINE: %{option} = "enable-runtime-library=true parallelization-strategy=any-storage-any-loop"
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation and parallelization strategy.
 // REDEFINE: %{option} = "enable-runtime-library=false parallelization-strategy=any-storage-any-loop"
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 #CSR = #sparse_tensor.encoding<{
   dimLevelType = [ "dense", "compressed" ],
   dimOrdering = affine_map<(i,j) -> (i,j)>
 }>
 
 #DCSR = #sparse_tensor.encoding<{
   dimLevelType = [ "compressed", "compressed" ],

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_matrix_ops.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = enable-runtime-library=false
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 #DCSR = #sparse_tensor.encoding<{dimLevelType = ["compressed", "compressed"]}>
 
 //
 // Traits for 2-d tensor (aka matrix) operations.
 //
 #trait_scale = {
   indexing_maps = [

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_matvec.mlir

 //
 // Do the same run, but now with parallelization strategy.
 // REDEFINE: %{option} = "enable-runtime-library=true parallelization-strategy=any-storage-any-loop"
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation and parallelization strategy.
 // REDEFINE: %{option} = "enable-runtime-library=false parallelization-strategy=any-storage-any-loop"
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 !Filename = !llvm.ptr<i8>
 
 #SparseMatrix = #sparse_tensor.encoding<{
   dimLevelType = [ "dense", "compressed" ],
   pointerBitWidth = 8,
   indexBitWidth = 8
 }>

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_mttkrp.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: TENSOR0="%mlir_src_dir/test/Integration/data/mttkrp_b.tns" \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = enable-runtime-library=false
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 !Filename = !llvm.ptr<i8>
 
 #SparseTensor = #sparse_tensor.encoding<{
   dimLevelType = [ "compressed", "compressed", "compressed" ]
 }>
 
 #mttkrp = {

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_out_mult_elt.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = "enable-runtime-library=false enable-buffer-initialization=true"
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false enable-buffer-initialization=true vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 #DCSR = #sparse_tensor.encoding<{
   dimLevelType = [ "compressed", "compressed" ]
 }>
 
 #trait_mult_elt = {
   indexing_maps = [
     affine_map<(i,j) -> (i,j)>,  // A

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_out_reduction.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = "enable-runtime-library=false  enable-buffer-initialization=true"
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false enable-buffer-initialization=true vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 #SparseMatrix = #sparse_tensor.encoding<{
   dimLevelType = [ "compressed", "compressed" ]
 }>
 
 #SparseTensor = #sparse_tensor.encoding<{
   dimLevelType = [ "compressed", "compressed", "compressed" ]
 }>

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_out_simple.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: TENSOR0="%mlir_src_dir/test/Integration/data/test.mtx" \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = enable-runtime-library=false
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 !Filename = !llvm.ptr<i8>
 
 #DCSR = #sparse_tensor.encoding<{
   dimLevelType = [ "compressed", "compressed" ],
   dimOrdering = affine_map<(i,j) -> (i,j)>
 }>
 

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_re_im.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = enable-runtime-library=false
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 #SparseVector = #sparse_tensor.encoding<{dimLevelType = ["compressed"]}>
 
 #trait_op = {
   indexing_maps = [
     affine_map<(i) -> (i)>,  // a (in)
     affine_map<(i) -> (i)>   // x (out)
   ],

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_reductions.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = enable-runtime-library=false
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 #SV = #sparse_tensor.encoding<{ dimLevelType = [ "compressed" ] }>
 #DV = #sparse_tensor.encoding<{ dimLevelType = [ "dense"      ] }>
 
 #trait_reduction = {
   indexing_maps = [
     affine_map<(i) -> (i)>,  // a
     affine_map<(i) -> ()>    // x (scalar out)

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_reshape.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = enable-runtime-library=false
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 #SparseVector = #sparse_tensor.encoding<{
   dimLevelType = ["compressed"]
 }>
 
 #SparseMatrix = #sparse_tensor.encoding<{
   dimLevelType = ["compressed", "compressed"]
 }>

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_rewrite_push_back.mlir

-// RUN: mlir-opt %s --sparse-compiler=enable-runtime-library=false | \
-// RUN: mlir-cpu-runner \
-// RUN:  -e entry -entry-point-result=void  \
-// RUN:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
-// RUN: FileCheck %s
+// DEFINE: %{option} = enable-runtime-library=false
+// DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
+// DEFINE: mlir-cpu-runner \
+// DEFINE:  -e entry -entry-point-result=void  \
+// DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
+// DEFINE: FileCheck %s
+//
+// RUN: %{command}
+//
+// Do the same run, but now with vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 module {
   func.func @entry() {
     %c0 = arith.constant 0 : index
     %c1 = arith.constant 1 : index
     %c10 = arith.constant 10 : index
     %d0 = arith.constant 0.0 : f32
     %d1 = arith.constant 1.0 : f32

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_rewrite_sort.mlir

-// RUN: mlir-opt %s --sparse-compiler=enable-runtime-library=false | \
-// RUN: mlir-cpu-runner \
-// RUN:  -e entry -entry-point-result=void  \
-// RUN:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
-// RUN: FileCheck %s
+// DEFINE: %{option} = enable-runtime-library=false
+// DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
+// DEFINE: mlir-cpu-runner \
+// DEFINE:  -e entry -entry-point-result=void  \
+// DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
+// DEFINE: FileCheck %s
+//
+// RUN: %{command}
+//
+// Do the same run, but now with vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 module {
   // Stores 5 values to the memref buffer.
   func.func @storeValuesTo(%b: memref<?xi32>, %v0: i32, %v1: i32, %v2: i32,
     %v3: i32, %v4: i32) -> () {
     %i0 = arith.constant 0 : index
     %i1 = arith.constant 1 : index
     %i2 = arith.constant 2 : index

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_rewrite_sort_coo.mlir

-// RUN: mlir-opt %s --sparse-compiler=enable-runtime-library=false | \
-// RUN: mlir-cpu-runner \
-// RUN:  -e entry -entry-point-result=void  \
-// RUN:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
-// RUN: FileCheck %s
+// DEFINE: %{option} = enable-runtime-library=false
+// DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
+// DEFINE: mlir-cpu-runner \
+// DEFINE:  -e entry -entry-point-result=void  \
+// DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
+// DEFINE: FileCheck %s
+//
+// RUN: %{command}
+//
+// Do the same run, but now with vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 module {
   // Stores 5 values to the memref buffer.
   func.func @storeValuesTo(%b: memref<?xi32>, %v0: i32, %v1: i32, %v2: i32,
     %v3: i32, %v4: i32) -> () {
     %i0 = arith.constant 0 : index
     %i1 = arith.constant 1 : index
     %i2 = arith.constant 2 : index

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_sampled_mm_fusion.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = "enable-runtime-library=false enable-buffer-initialization=true"
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false enable-buffer-initialization=true vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 #SM = #sparse_tensor.encoding<{ dimLevelType = [ "compressed", "compressed" ] }>
 
 #trait_sampled_dense_dense = {
   indexing_maps = [
     affine_map<(i,j,k) -> (i,j)>,  // S
     affine_map<(i,j,k) -> (i,k)>,  // A
     affine_map<(i,j,k) -> (k,j)>,  // B

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_spmm.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: TENSOR0="%mlir_src_dir/test/Integration/data/wide.mtx" \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = enable-runtime-library=false
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 !Filename = !llvm.ptr<i8>
 
 #SparseMatrix = #sparse_tensor.encoding<{
   dimLevelType = [ "dense", "compressed" ]
 }>
 
 #spmm = {

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_storage.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = enable-runtime-library=false
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 //
 // Several common sparse storage schemes.
 //
 
 #Dense  = #sparse_tensor.encoding<{
   dimLevelType = [ "dense", "dense" ]
 }>

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_sum.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: TENSOR0="%mlir_src_dir/test/Integration/data/test_symmetric.mtx" \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = enable-runtime-library=false
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 !Filename = !llvm.ptr<i8>
 
 #SparseMatrix = #sparse_tensor.encoding<{
   dimLevelType = [ "compressed", "compressed" ]
 }>
 
 #trait_sum_reduce = {

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_sum_bf16.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = enable-runtime-library=false
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 // UNSUPPORTED: aarch64
 
 !Filename = !llvm.ptr<i8>
 
 #SparseMatrix = #sparse_tensor.encoding<{
   dimLevelType = [ "compressed", "compressed" ]
 }>

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_sum_c32.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: TENSOR0="%mlir_src_dir/test/Integration/data/test_symmetric_complex.mtx" \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = enable-runtime-library=false
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 !Filename = !llvm.ptr<i8>
 
 #SparseMatrix = #sparse_tensor.encoding<{
   dimLevelType = [ "compressed", "compressed" ]
 }>
 
 #trait_sum_reduce = {

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_sum_f16.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = enable-runtime-library=false
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 !Filename = !llvm.ptr<i8>
 
 #SparseMatrix = #sparse_tensor.encoding<{
   dimLevelType = [ "compressed", "compressed" ]
 }>
 
 #trait_sum_reduce = {

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_tensor_mul.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = enable-runtime-library=false
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 #ST = #sparse_tensor.encoding<{dimLevelType = ["compressed", "compressed", "compressed"]}>
 
 //
 // Trait for 3-d tensor element wise multiplication.
 //
 #trait_mul = {
   indexing_maps = [

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_tensor_ops.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = enable-runtime-library=false
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 #ST1 = #sparse_tensor.encoding<{dimLevelType = ["compressed", "compressed", "compressed"]}>
 #ST2 = #sparse_tensor.encoding<{dimLevelType = ["compressed", "compressed", "dense"]}>
 
 //
 // Trait for 3-d tensor operation.
 //
 #trait_scale = {

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_transpose.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option}
 // DxEFINE: mlir-cpu-runner \
 // DxEFINE:  -e entry -entry-point-result=void  \
 // DxEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DxEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = "enable-runtime-library=false enable-buffer-initialization=true"
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false enable-buffer-initialization=true vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 #DCSR = #sparse_tensor.encoding<{
   dimLevelType = [ "compressed", "compressed" ]
 }>
 
 #DCSC = #sparse_tensor.encoding<{
   dimLevelType = [ "compressed", "compressed" ],
   dimOrdering = affine_map<(i,j) -> (j,i)>

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_unary.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = "enable-runtime-library=false enable-buffer-initialization=true"
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false enable-buffer-initialization=true vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 #SparseVector = #sparse_tensor.encoding<{dimLevelType = ["compressed"]}>
 #DCSR = #sparse_tensor.encoding<{dimLevelType = ["compressed", "compressed"]}>
 
 //
 // Traits for tensor operations.
 //
 #trait_vec_scale = {

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_vector_ops.mlir

 // DEFINE: %{option} = enable-runtime-library=true
 // DEFINE: %{command} = mlir-opt %s --sparse-compiler=%{option} | \
 // DEFINE: mlir-cpu-runner \
 // DEFINE:  -e entry -entry-point-result=void  \
 // DEFINE:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // DEFINE: FileCheck %s
 //
 // RUN: %{command}
 //
 // Do the same run, but now with direct IR generation.
 // REDEFINE: %{option} = "enable-runtime-library=false enable-buffer-initialization=true"
 // RUN: %{command}
+//
+// Do the same run, but now with direct IR generation and vectorization.
+// REDEFINE: %{option} = "enable-runtime-library=false enable-buffer-initialization=true vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
+// RUN: %{command}
 
 #SparseVector = #sparse_tensor.encoding<{dimLevelType = ["compressed"]}>
 #DenseVector = #sparse_tensor.encoding<{dimLevelType = ["dense"]}>
 
 //
 // Traits for 1-d tensor (aka vector) operations.
 //
 #trait_scale = {