diff --git a/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_cast.mlir b/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_cast.mlir
--- a/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_cast.mlir
+++ b/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_cast.mlir
@@ -13,7 +13,7 @@
 // Do the same run, but now with SIMDization as well. This should not change the outcome.
 //
 // RUN: mlir-opt %s \
-// RUN:   --sparsification="vectorization-strategy=2 vl=2 enable-simd-index32" --sparse-tensor-conversion \
+// RUN:   --sparsification="vectorization-strategy=2 vl=2" --sparse-tensor-conversion \
 // RUN:   --convert-vector-to-scf --convert-scf-to-std \
 // RUN:   --func-bufferize --tensor-constant-bufferize --tensor-bufferize \
 // RUN:   --std-bufferize --finalizing-bufferize --lower-affine \
@@ -23,7 +23,6 @@
 // RUN:  -e entry -entry-point-result=void  \
 // RUN:  -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \
 // RUN: FileCheck %s
-//
 
 #SV = #sparse_tensor.encoding<{ dimLevelType = [ "compressed" ] }>
 
diff --git a/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_flatten.mlir b/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_flatten.mlir
--- a/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_flatten.mlir
+++ b/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_flatten.mlir
@@ -2,7 +2,21 @@
 // RUN:   --sparsification --sparse-tensor-conversion \
 // RUN:   --convert-vector-to-scf --convert-scf-to-std \
 // RUN:   --func-bufferize --tensor-constant-bufferize --tensor-bufferize \
-// RUN:   --std-bufferize --finalizing-bufferize  \
+// RUN:   --std-bufferize --finalizing-bufferize --lower-affine \
+// RUN:   --convert-vector-to-llvm --convert-memref-to-llvm --convert-std-to-llvm --reconcile-unrealized-casts | \
+// RUN: TENSOR0="%mlir_integration_test_dir/data/test.tns" \
+// RUN: mlir-cpu-runner \
+// RUN:  -e entry -entry-point-result=void  \
+// RUN:  -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \
+// RUN: FileCheck %s
+//
+// Do the same run, but now with SIMDization as well. This should not change the outcome.
+//
+// RUN: mlir-opt %s \
+// RUN:   --sparsification="vectorization-strategy=2 vl=4" --sparse-tensor-conversion \
+// RUN:   --convert-vector-to-scf --convert-scf-to-std \
+// RUN:   --func-bufferize --tensor-constant-bufferize --tensor-bufferize \
+// RUN:   --std-bufferize --finalizing-bufferize --lower-affine \
 // RUN:   --convert-vector-to-llvm --convert-memref-to-llvm --convert-std-to-llvm --reconcile-unrealized-casts | \
 // RUN: TENSOR0="%mlir_integration_test_dir/data/test.tns" \
 // RUN: mlir-cpu-runner \
diff --git a/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_mttkrp.mlir b/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_mttkrp.mlir
--- a/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_mttkrp.mlir
+++ b/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_mttkrp.mlir
@@ -2,7 +2,21 @@
 // RUN:   --sparsification --sparse-tensor-conversion \
 // RUN:   --convert-vector-to-scf --convert-scf-to-std \
 // RUN:   --func-bufferize --tensor-constant-bufferize --tensor-bufferize \
-// RUN:   --std-bufferize --finalizing-bufferize  \
+// RUN:   --std-bufferize --finalizing-bufferize --lower-affine \
+// RUN:   --convert-vector-to-llvm --convert-memref-to-llvm --convert-std-to-llvm --reconcile-unrealized-casts | \
+// RUN: TENSOR0="%mlir_integration_test_dir/data/mttkrp_b.tns" \
+// RUN: mlir-cpu-runner \
+// RUN:  -e entry -entry-point-result=void  \
+// RUN:  -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \
+// RUN: FileCheck %s
+//
+// Do the same run, but now with SIMDization as well. This should not change the outcome.
+//
+// RUN: mlir-opt %s \
+// RUN:   --sparsification="vectorization-strategy=2 vl=4" --sparse-tensor-conversion \
+// RUN:   --convert-vector-to-scf --convert-scf-to-std \
+// RUN:   --func-bufferize --tensor-constant-bufferize --tensor-bufferize \
+// RUN:   --std-bufferize --finalizing-bufferize --lower-affine \
 // RUN:   --convert-vector-to-llvm --convert-memref-to-llvm --convert-std-to-llvm --reconcile-unrealized-casts | \
 // RUN: TENSOR0="%mlir_integration_test_dir/data/mttkrp_b.tns" \
 // RUN: mlir-cpu-runner \
diff --git a/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_out_simple.mlir b/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_out_simple.mlir
--- a/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_out_simple.mlir
+++ b/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_out_simple.mlir
@@ -2,7 +2,21 @@
 // RUN:   --sparsification --sparse-tensor-conversion \
 // RUN:   --convert-vector-to-scf --convert-scf-to-std \
 // RUN:   --func-bufferize --tensor-constant-bufferize --tensor-bufferize \
-// RUN:   --std-bufferize --finalizing-bufferize  \
+// RUN:   --std-bufferize --finalizing-bufferize --lower-affine \
+// RUN:   --convert-vector-to-llvm --convert-memref-to-llvm --convert-std-to-llvm --reconcile-unrealized-casts | \
+// RUN: TENSOR0="%mlir_integration_test_dir/data/test.mtx" \
+// RUN: mlir-cpu-runner \
+// RUN:  -e entry -entry-point-result=void  \
+// RUN:  -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \
+// RUN: FileCheck %s
+//
+// Do the same run, but now with SIMDization as well. This should not change the outcome.
+//
+// RUN: mlir-opt %s \
+// RUN:   --sparsification="vectorization-strategy=2 vl=4" --sparse-tensor-conversion \
+// RUN:   --convert-vector-to-scf --convert-scf-to-std \
+// RUN:   --func-bufferize --tensor-constant-bufferize --tensor-bufferize \
+// RUN:   --std-bufferize --finalizing-bufferize --lower-affine \
 // RUN:   --convert-vector-to-llvm --convert-memref-to-llvm --convert-std-to-llvm --reconcile-unrealized-casts | \
 // RUN: TENSOR0="%mlir_integration_test_dir/data/test.mtx" \
 // RUN: mlir-cpu-runner \
diff --git a/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_quantized_matmul.mlir b/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_quantized_matmul.mlir
--- a/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_quantized_matmul.mlir
+++ b/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_quantized_matmul.mlir
@@ -10,6 +10,21 @@
 // RUN:  -e entry -entry-point-result=void  \
 // RUN:  -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \
 // RUN: FileCheck %s
+//
+// Do the same run, but now with SIMDization as well. This should not change the outcome.
+//
+// RUN: mlir-opt %s \
+// RUN:   --linalg-generalize-named-ops --linalg-fuse-elementwise-ops \
+// RUN:   --sparsification="vectorization-strategy=2 vl=2" --sparse-tensor-conversion \
+// RUN:   --convert-vector-to-scf --convert-scf-to-std \
+// RUN:   --func-bufferize --tensor-constant-bufferize --tensor-bufferize \
+// RUN:   --std-bufferize --finalizing-bufferize --lower-affine \
+// RUN:   --convert-vector-to-llvm --convert-memref-to-llvm \
+// RUN:   --convert-std-to-llvm --reconcile-unrealized-casts | \
+// RUN: mlir-cpu-runner \
+// RUN:  -e entry -entry-point-result=void  \
+// RUN:  -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \
+// RUN: FileCheck %s
 
 #DCSR = #sparse_tensor.encoding<{ dimLevelType = [ "compressed", "compressed" ] }>
 
diff --git a/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_sampled_mm_fusion.mlir b/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_sampled_mm_fusion.mlir
--- a/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_sampled_mm_fusion.mlir
+++ b/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_sampled_mm_fusion.mlir
@@ -12,8 +12,7 @@
 // RUN:  -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \
 // RUN: FileCheck %s
 //
-// Do the same run, but now with SIMDization as well.
-// This should not change the outcome.
+// Do the same run, but now with SIMDization as well. This should not change the outcome.
 //
 // RUN: mlir-opt %s \
 // RUN:   --linalg-generalize-named-ops --linalg-fuse-elementwise-ops \
@@ -28,11 +27,10 @@
 // RUN:  -e entry -entry-point-result=void  \
 // RUN:  -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \
 // RUN: FileCheck %s
-//
+
 // Interop between linalg/sparse leaves some issues to be revolved:
 // UNSUPPORTED: asan
 
-
 #SM = #sparse_tensor.encoding<{ dimLevelType = [ "compressed", "compressed" ] }>
 
 #trait_sampled_dense_dense = {
diff --git a/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_scale.mlir b/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_scale.mlir
--- a/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_scale.mlir
+++ b/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_scale.mlir
@@ -2,7 +2,20 @@
 // RUN:   --sparsification --sparse-tensor-conversion \
 // RUN:   --convert-vector-to-scf --convert-scf-to-std \
 // RUN:   --func-bufferize --tensor-constant-bufferize --tensor-bufferize \
-// RUN:   --std-bufferize --finalizing-bufferize  \
+// RUN:   --std-bufferize --finalizing-bufferize --lower-affine \
+// RUN:   --convert-vector-to-llvm --convert-memref-to-llvm --convert-std-to-llvm --reconcile-unrealized-casts | \
+// RUN: mlir-cpu-runner \
+// RUN:  -e entry -entry-point-result=void  \
+// RUN:  -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \
+// RUN: FileCheck %s
+//
+// Do the same run, but now with SIMDization as well. This should not change the outcome.
+//
+// RUN: mlir-opt %s \
+// RUN:   --sparsification="vectorization-strategy=2 vl=4" --sparse-tensor-conversion \
+// RUN:   --convert-vector-to-scf --convert-scf-to-std \
+// RUN:   --func-bufferize --tensor-constant-bufferize --tensor-bufferize \
+// RUN:   --std-bufferize --finalizing-bufferize --lower-affine \
 // RUN:   --convert-vector-to-llvm --convert-memref-to-llvm --convert-std-to-llvm --reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner \
 // RUN:  -e entry -entry-point-result=void  \
diff --git a/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_spmm.mlir b/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_spmm.mlir
--- a/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_spmm.mlir
+++ b/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_spmm.mlir
@@ -2,7 +2,21 @@
 // RUN:   --sparsification --sparse-tensor-conversion \
 // RUN:   --convert-vector-to-scf --convert-scf-to-std \
 // RUN:   --func-bufferize --tensor-constant-bufferize --tensor-bufferize \
-// RUN:   --std-bufferize --finalizing-bufferize  \
+// RUN:   --std-bufferize --finalizing-bufferize --lower-affine \
+// RUN:   --convert-vector-to-llvm --convert-memref-to-llvm --convert-std-to-llvm --reconcile-unrealized-casts | \
+// RUN: TENSOR0="%mlir_integration_test_dir/data/wide.mtx" \
+// RUN: mlir-cpu-runner \
+// RUN:  -e entry -entry-point-result=void  \
+// RUN:  -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \
+// RUN: FileCheck %s
+//
+// Do the same run, but now with SIMDization as well. This should not change the outcome.
+//
+// RUN: mlir-opt %s \
+// RUN:   --sparsification="vectorization-strategy=2 vl=2" --sparse-tensor-conversion \
+// RUN:   --convert-vector-to-scf --convert-scf-to-std \
+// RUN:   --func-bufferize --tensor-constant-bufferize --tensor-bufferize \
+// RUN:   --std-bufferize --finalizing-bufferize --lower-affine \
 // RUN:   --convert-vector-to-llvm --convert-memref-to-llvm --convert-std-to-llvm --reconcile-unrealized-casts | \
 // RUN: TENSOR0="%mlir_integration_test_dir/data/wide.mtx" \
 // RUN: mlir-cpu-runner \
diff --git a/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_sum.mlir b/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_sum.mlir
--- a/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_sum.mlir
+++ b/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_sum.mlir
@@ -2,7 +2,21 @@
 // RUN:   --sparsification --sparse-tensor-conversion \
 // RUN:   --convert-vector-to-scf --convert-scf-to-std \
 // RUN:   --func-bufferize --tensor-constant-bufferize --tensor-bufferize \
-// RUN:   --std-bufferize --finalizing-bufferize  \
+// RUN:   --std-bufferize --finalizing-bufferize --lower-affine \
+// RUN:   --convert-vector-to-llvm --convert-memref-to-llvm --convert-std-to-llvm --reconcile-unrealized-casts | \
+// RUN: TENSOR0="%mlir_integration_test_dir/data/test.mtx" \
+// RUN: mlir-cpu-runner \
+// RUN:  -e entry -entry-point-result=void  \
+// RUN:  -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \
+// RUN: FileCheck %s
+//
+// Do the same run, but now with SIMDization as well. This should not change the outcome.
+//
+// RUN: mlir-opt %s \
+// RUN:   --sparsification="vectorization-strategy=2 vl=2" --sparse-tensor-conversion \
+// RUN:   --convert-vector-to-scf --convert-scf-to-std \
+// RUN:   --func-bufferize --tensor-constant-bufferize --tensor-bufferize \
+// RUN:   --std-bufferize --finalizing-bufferize --lower-affine \
 // RUN:   --convert-vector-to-llvm --convert-memref-to-llvm --convert-std-to-llvm --reconcile-unrealized-casts | \
 // RUN: TENSOR0="%mlir_integration_test_dir/data/test.mtx" \
 // RUN: mlir-cpu-runner \