diff --git a/mlir/test/Integration/GPU/CUDA/shuffle.mlir b/mlir/test/Integration/GPU/CUDA/shuffle.mlir
@@ -3,8 +3,8 @@
 // RUN:   -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
 // RUN:   -gpu-to-llvm \
 // RUN: | mlir-cpu-runner \
-// RUN:   --shared-libs=%linalg_test_lib_dir/libmlir_cuda_runtime%shlibext \
-// RUN:   --shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext \
+// 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
 

diff --git a/mlir/test/Integration/GPU/CUDA/two-modules.mlir b/mlir/test/Integration/GPU/CUDA/two-modules.mlir
@@ -3,8 +3,8 @@
 // RUN:   -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
 // RUN:   -gpu-to-llvm \
 // RUN: | mlir-cpu-runner \
-// RUN:   --shared-libs=%linalg_test_lib_dir/libmlir_cuda_runtime%shlibext \
-// RUN:   --shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext \
+// 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
 

diff --git a/mlir/test/Integration/GPU/ROCM/gpu-to-hsaco.mlir b/mlir/test/Integration/GPU/ROCM/gpu-to-hsaco.mlir
@@ -3,8 +3,8 @@
 // RUN:   -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-rocdl,gpu-to-hsaco{chip=%chip})' \
 // RUN:   -gpu-to-llvm \
 // RUN: | mlir-cpu-runner \
-// RUN:   --shared-libs=%linalg_test_lib_dir/libmlir_rocm_runtime%shlibext \
-// RUN:   --shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext \
+// 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
 

diff --git a/mlir/test/Integration/GPU/ROCM/printf.mlir b/mlir/test/Integration/GPU/ROCM/printf.mlir
@@ -2,8 +2,8 @@
 // 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-cpu-runner \
-// RUN:   --shared-libs=%linalg_test_lib_dir/libmlir_rocm_runtime%shlibext \
-// RUN:   --shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext \
+// 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
 

diff --git a/mlir/test/Integration/GPU/ROCM/two-modules.mlir b/mlir/test/Integration/GPU/ROCM/two-modules.mlir
@@ -3,8 +3,8 @@
 // RUN:   -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-rocdl,gpu-to-hsaco{chip=%chip})' \
 // RUN:   -gpu-to-llvm \
 // RUN: | mlir-cpu-runner \
-// RUN:   --shared-libs=%linalg_test_lib_dir/libmlir_rocm_runtime%shlibext \
-// RUN:   --shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext \
+// 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
 

diff --git a/mlir/test/Integration/GPU/ROCM/vecadd.mlir b/mlir/test/Integration/GPU/ROCM/vecadd.mlir
@@ -4,8 +4,8 @@
 // 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-cpu-runner \
-// RUN:   --shared-libs=%linalg_test_lib_dir/libmlir_rocm_runtime%shlibext \
-// RUN:   --shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext \
+// 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
 

diff --git a/mlir/test/Integration/GPU/ROCM/vector-transferops.mlir b/mlir/test/Integration/GPU/ROCM/vector-transferops.mlir
@@ -4,8 +4,8 @@
 // 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-cpu-runner \
-// RUN:   --shared-libs=%linalg_test_lib_dir/libmlir_rocm_runtime%shlibext \
-// RUN:   --shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext \
+// 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
 

diff --git a/mlir/test/lit.cfg.py b/mlir/test/lit.cfg.py
@@ -77,6 +77,7 @@
     ToolSubst('toy-ch4', unresolved='ignore'),
     ToolSubst('toy-ch5', unresolved='ignore'),
     ToolSubst('%mlir_lib_dir', config.mlir_lib_dir, unresolved='ignore'),
+    ToolSubst('%mlir_src_dir', config.mlir_src_root, unresolved='ignore'),
     # The substitutions below will be replaced by '%mlir_lib_dir' shortly.
     ToolSubst('%linalg_test_lib_dir', config.mlir_lib_dir, unresolved='ignore'),
     ToolSubst('%mlir_runner_utils_dir', config.mlir_lib_dir, unresolved='ignore'),
@@ -111,33 +112,33 @@
 # binaries come from the build tree. This should be unified to the build tree
 # by copying/linking sources to build.
 if config.enable_bindings_python:
-    llvm_config.with_environment('PYTHONPATH', [
-        os.path.join(config.mlir_obj_root, 'python_packages', 'mlir_core'),
-        os.path.join(config.mlir_obj_root, 'python_packages', 'mlir_test'),
-    ], append_path=True)
+  llvm_config.with_environment('PYTHONPATH', [
+      os.path.join(config.mlir_obj_root, 'python_packages', 'mlir_core'),
+      os.path.join(config.mlir_obj_root, 'python_packages', 'mlir_test'),
+  ], append_path=True)
 
 if config.enable_assertions:
-    config.available_features.add('asserts')
+  config.available_features.add('asserts')
 else:
-    config.available_features.add('noasserts')
+  config.available_features.add('noasserts')
 
 def have_host_jit_feature_support(feature_name):
-    mlir_cpu_runner_exe = lit.util.which('mlir-cpu-runner', config.mlir_tools_dir)
+  mlir_cpu_runner_exe = lit.util.which('mlir-cpu-runner', config.mlir_tools_dir)
 
-    if not mlir_cpu_runner_exe:
-        return False
+  if not mlir_cpu_runner_exe:
+    return False
 
-    try:
-        mlir_cpu_runner_cmd = subprocess.Popen(
-            [mlir_cpu_runner_exe, '--host-supports-' + feature_name], stdout=subprocess.PIPE)
-    except OSError:
-        print('could not exec mlir-cpu-runner')
-        return False
+  try:
+    mlir_cpu_runner_cmd = subprocess.Popen(
+        [mlir_cpu_runner_exe, '--host-supports-' + feature_name], stdout=subprocess.PIPE)
+  except OSError:
+    print('could not exec mlir-cpu-runner')
+    return False
 
-    mlir_cpu_runner_out = mlir_cpu_runner_cmd.stdout.read().decode('ascii')
-    mlir_cpu_runner_cmd.wait()
+  mlir_cpu_runner_out = mlir_cpu_runner_cmd.stdout.read().decode('ascii')
+  mlir_cpu_runner_cmd.wait()
 
-    return 'true' in mlir_cpu_runner_out
+  return 'true' in mlir_cpu_runner_out
 
 if have_host_jit_feature_support('jit'):
-    config.available_features.add('host-supports-jit')
+  config.available_features.add('host-supports-jit')
diff --git a/mlir/test/mlir-cpu-runner/X86Vector/math-polynomial-approx-avx2.mlir b/mlir/test/mlir-cpu-runner/X86Vector/math-polynomial-approx-avx2.mlir
@@ -6,8 +6,8 @@
 // RUN:               -reconcile-unrealized-casts                              \
 // RUN: | mlir-cpu-runner                                                      \
 // RUN:     -e main -entry-point-result=void -O0                               \
-// RUN:     -shared-libs=%linalg_test_lib_dir/libmlir_c_runner_utils%shlibext  \
-// RUN:     -shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%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
 
 // -------------------------------------------------------------------------- //

diff --git a/mlir/test/mlir-cpu-runner/async-error.mlir b/mlir/test/mlir-cpu-runner/async-error.mlir
@@ -1,9 +1,9 @@
 // RUN:   mlir-opt %s -pass-pipeline="async-to-async-runtime,func.func(async-runtime-ref-counting,async-runtime-ref-counting-opt),convert-async-to-llvm,func.func(convert-linalg-to-loops,convert-scf-to-cf),convert-linalg-to-llvm,convert-vector-to-llvm,func.func(convert-arith-to-llvm),convert-func-to-llvm,reconcile-unrealized-casts" \
 // RUN: | mlir-cpu-runner                                                      \
 // RUN:     -e main -entry-point-result=void -O0                               \
-// RUN:     -shared-libs=%linalg_test_lib_dir/libmlir_c_runner_utils%shlibext  \
-// RUN:     -shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext    \
-// RUN:     -shared-libs=%linalg_test_lib_dir/libmlir_async_runtime%shlibext   \
+// RUN:     -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext  \
+// RUN:     -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext    \
+// RUN:     -shared-libs=%mlir_lib_dir/libmlir_async_runtime%shlibext   \
 // RUN: | FileCheck %s --dump-input=always
 
 // FIXME: https://github.com/llvm/llvm-project/issues/57231

diff --git a/mlir/test/mlir-cpu-runner/async-group.mlir b/mlir/test/mlir-cpu-runner/async-group.mlir
@@ -1,9 +1,9 @@
 // RUN:   mlir-opt %s -pass-pipeline="async-to-async-runtime,func.func(async-runtime-ref-counting,async-runtime-ref-counting-opt),convert-async-to-llvm,func.func(convert-arith-to-llvm),convert-func-to-llvm,reconcile-unrealized-casts" \
 // RUN: | mlir-cpu-runner                                                      \
 // RUN:     -e main -entry-point-result=void -O0                               \
-// RUN:     -shared-libs=%linalg_test_lib_dir/libmlir_c_runner_utils%shlibext  \
-// RUN:     -shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext    \
-// RUN:     -shared-libs=%linalg_test_lib_dir/libmlir_async_runtime%shlibext   \
+// RUN:     -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext  \
+// RUN:     -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext    \
+// RUN:     -shared-libs=%mlir_lib_dir/libmlir_async_runtime%shlibext   \
 // RUN: | FileCheck %s
 
 // This is crashing in CI "most of the time" on a AMD Rome CPU VM on GCP with:

diff --git a/mlir/test/mlir-cpu-runner/async-value.mlir b/mlir/test/mlir-cpu-runner/async-value.mlir
@@ -1,9 +1,9 @@
 // RUN:   mlir-opt %s -pass-pipeline="async-to-async-runtime,func.func(async-runtime-ref-counting,async-runtime-ref-counting-opt),convert-async-to-llvm,func.func(convert-arith-to-llvm),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" \
 // RUN: | mlir-cpu-runner                                                      \
 // RUN:     -e main -entry-point-result=void -O0                               \
-// RUN:     -shared-libs=%linalg_test_lib_dir/libmlir_c_runner_utils%shlibext  \
-// RUN:     -shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext    \
-// RUN:     -shared-libs=%linalg_test_lib_dir/libmlir_async_runtime%shlibext   \
+// RUN:     -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext  \
+// RUN:     -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext    \
+// RUN:     -shared-libs=%mlir_lib_dir/libmlir_async_runtime%shlibext   \
 // RUN: | FileCheck %s --dump-input=always
 
 // FIXME: https://github.com/llvm/llvm-project/issues/57231

diff --git a/mlir/test/mlir-cpu-runner/async.mlir b/mlir/test/mlir-cpu-runner/async.mlir
@@ -1,9 +1,9 @@
 // RUN:   mlir-opt %s -pass-pipeline="async-to-async-runtime,func.func(async-runtime-ref-counting,async-runtime-ref-counting-opt),convert-async-to-llvm,func.func(convert-linalg-to-loops,convert-scf-to-cf),convert-linalg-to-llvm,convert-memref-to-llvm,func.func(convert-arith-to-llvm),convert-func-to-llvm,reconcile-unrealized-casts" \
 // RUN: | mlir-cpu-runner                                                      \
 // RUN:     -e main -entry-point-result=void -O0                               \
-// RUN:     -shared-libs=%linalg_test_lib_dir/libmlir_c_runner_utils%shlibext  \
-// RUN:     -shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext    \
-// RUN:     -shared-libs=%linalg_test_lib_dir/libmlir_async_runtime%shlibext   \
+// RUN:     -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext  \
+// RUN:     -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext    \
+// RUN:     -shared-libs=%mlir_lib_dir/libmlir_async_runtime%shlibext   \
 // RUN: | FileCheck %s
 
 // FIXME: https://github.com/llvm/llvm-project/issues/57231

diff --git a/mlir/test/mlir-cpu-runner/bare-ptr-call-conv.mlir b/mlir/test/mlir-cpu-runner/bare-ptr-call-conv.mlir
@@ -1,4 +1,4 @@
-// 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=%linalg_test_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

diff --git a/mlir/test/mlir-cpu-runner/copy.mlir b/mlir/test/mlir-cpu-runner/copy.mlir
@@ -1,6 +1,6 @@
 // RUN: mlir-opt %s -pass-pipeline="func.func(convert-scf-to-cf,convert-arith-to-llvm),convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" \
 // RUN: | mlir-cpu-runner -e main -entry-point-result=void \
-// RUN: -shared-libs=%mlir_runner_utils_dir/libmlir_runner_utils%shlibext,%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext \
+// RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext,%mlir_lib_dir/libmlir_c_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
 func.func private @printMemrefF32(memref<*xf32>) attributes { llvm.emit_c_interface }

diff --git a/mlir/test/mlir-cpu-runner/global-memref.mlir b/mlir/test/mlir-cpu-runner/global-memref.mlir
@@ -1,4 +1,4 @@
-// RUN: mlir-opt %s -pass-pipeline="func.func(convert-arith-to-llvm),convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | mlir-cpu-runner -e main -entry-point-result=void -shared-libs=%mlir_runner_utils_dir/libmlir_runner_utils%shlibext,%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext | FileCheck %s
+// RUN: mlir-opt %s -pass-pipeline="func.func(convert-arith-to-llvm),convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | mlir-cpu-runner -e main -entry-point-result=void -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext,%mlir_lib_dir/libmlir_c_runner_utils%shlibext | FileCheck %s
 
 func.func private @printMemrefF32(memref<*xf32>) attributes { llvm.emit_c_interface }
 func.func private @printMemrefI32(memref<*xi32>) attributes { llvm.emit_c_interface }

diff --git a/mlir/test/mlir-cpu-runner/math-polynomial-approx.mlir b/mlir/test/mlir-cpu-runner/math-polynomial-approx.mlir
@@ -1,8 +1,8 @@
 // RUN:   mlir-opt %s -pass-pipeline="func.func(test-math-polynomial-approximation,convert-arith-to-llvm),convert-vector-to-llvm,func.func(convert-math-to-llvm),convert-func-to-llvm,reconcile-unrealized-casts" \
 // RUN: | mlir-cpu-runner                                                      \
 // RUN:     -e main -entry-point-result=void -O0                               \
-// RUN:     -shared-libs=%linalg_test_lib_dir/libmlir_c_runner_utils%shlibext  \
-// RUN:     -shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%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
 
 // -------------------------------------------------------------------------- //

diff --git a/mlir/test/mlir-cpu-runner/memref-reinterpret-cast.mlir b/mlir/test/mlir-cpu-runner/memref-reinterpret-cast.mlir
@@ -1,6 +1,6 @@
 // RUN: mlir-opt %s -pass-pipeline="func.func(convert-scf-to-cf),convert-memref-to-llvm,func.func(convert-arith-to-llvm),convert-func-to-llvm,reconcile-unrealized-casts" \
 // RUN: | mlir-cpu-runner -e main -entry-point-result=void \
-// RUN: -shared-libs=%mlir_runner_utils_dir/libmlir_runner_utils%shlibext,%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext \
+// RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext,%mlir_lib_dir/libmlir_c_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
 func.func private @printMemrefF32(memref<*xf32>) attributes { llvm.emit_c_interface }

diff --git a/mlir/test/mlir-cpu-runner/memref-reshape.mlir b/mlir/test/mlir-cpu-runner/memref-reshape.mlir
@@ -1,6 +1,6 @@
 // RUN: mlir-opt %s -pass-pipeline="func.func(convert-scf-to-cf,memref-expand,convert-arith-to-llvm),convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" \
 // RUN: | mlir-cpu-runner -e main -entry-point-result=void \
-// RUN: -shared-libs=%mlir_runner_utils_dir/libmlir_runner_utils%shlibext,%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext \
+// RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext,%mlir_lib_dir/libmlir_c_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
 

diff --git a/mlir/test/mlir-cpu-runner/print.mlir b/mlir/test/mlir-cpu-runner/print.mlir
@@ -1,6 +1,6 @@
 // RUN: mlir-opt %s -pass-pipeline="convert-func-to-llvm,reconcile-unrealized-casts" \
 // RUN: | mlir-cpu-runner -e main -entry-point-result=void \
-// RUN:   -shared-libs=%mlir_runner_utils_dir/libmlir_runner_utils%shlibext,%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext \
+// RUN:   -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext,%mlir_lib_dir/libmlir_c_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
 

diff --git a/mlir/test/mlir-cpu-runner/sgemm-naive-codegen.mlir b/mlir/test/mlir-cpu-runner/sgemm-naive-codegen.mlir
@@ -1,4 +1,4 @@
-// RUN: mlir-opt -pass-pipeline="func.func(convert-linalg-to-loops,lower-affine,convert-scf-to-cf,convert-arith-to-llvm),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" %s | mlir-cpu-runner -O3 -e main -entry-point-result=void -shared-libs=%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext | FileCheck %s
+// RUN: mlir-opt -pass-pipeline="func.func(convert-linalg-to-loops,lower-affine,convert-scf-to-cf,convert-arith-to-llvm),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" %s | mlir-cpu-runner -O3 -e main -entry-point-result=void -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | FileCheck %s
 
 func.func @main() {
   %A = memref.alloc() : memref<16x16xf32>

diff --git a/mlir/test/mlir-cpu-runner/unranked-memref.mlir b/mlir/test/mlir-cpu-runner/unranked-memref.mlir
@@ -1,6 +1,6 @@
 // RUN: mlir-opt %s -pass-pipeline="func.func(convert-linalg-to-loops,convert-scf-to-cf,convert-arith-to-llvm),convert-linalg-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" |        \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
-// RUN: -shared-libs=%mlir_runner_utils_dir/libmlir_runner_utils%shlibext,%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext | FileCheck %s
+// RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext,%mlir_lib_dir/libmlir_c_runner_utils%shlibext | FileCheck %s
 
 // CHECK: rank = 2
 // CHECK-SAME: sizes = [10, 3]

diff --git a/mlir/test/mlir-cpu-runner/utils.mlir b/mlir/test/mlir-cpu-runner/utils.mlir
@@ -1,7 +1,7 @@
-// RUN: mlir-opt %s -pass-pipeline="func.func(convert-linalg-to-loops,convert-scf-to-cf,convert-arith-to-llvm),convert-linalg-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | mlir-cpu-runner -e print_0d -entry-point-result=void -shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext -shared-libs=%linalg_test_lib_dir/libmlir_c_runner_utils%shlibext | FileCheck %s --check-prefix=PRINT-0D
-// RUN: mlir-opt %s -pass-pipeline="func.func(convert-linalg-to-loops,convert-scf-to-cf,convert-arith-to-llvm),convert-linalg-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | mlir-cpu-runner -e print_1d -entry-point-result=void -shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext -shared-libs=%linalg_test_lib_dir/libmlir_c_runner_utils%shlibext | FileCheck %s --check-prefix=PRINT-1D
-// RUN: mlir-opt %s -pass-pipeline="func.func(convert-linalg-to-loops,convert-scf-to-cf,convert-arith-to-llvm),convert-linalg-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | mlir-cpu-runner -e print_3d -entry-point-result=void -shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext -shared-libs=%linalg_test_lib_dir/libmlir_c_runner_utils%shlibext | FileCheck %s --check-prefix=PRINT-3D
-// RUN: mlir-opt %s -pass-pipeline="func.func(convert-linalg-to-loops,convert-scf-to-cf,convert-arith-to-llvm),convert-linalg-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | mlir-cpu-runner -e vector_splat_2d -entry-point-result=void -shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext -shared-libs=%linalg_test_lib_dir/libmlir_c_runner_utils%shlibext | FileCheck %s --check-prefix=PRINT-VECTOR-SPLAT-2D
+// RUN: mlir-opt %s -pass-pipeline="func.func(convert-linalg-to-loops,convert-scf-to-cf,convert-arith-to-llvm),convert-linalg-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | mlir-cpu-runner -e print_0d -entry-point-result=void -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | FileCheck %s --check-prefix=PRINT-0D
+// RUN: mlir-opt %s -pass-pipeline="func.func(convert-linalg-to-loops,convert-scf-to-cf,convert-arith-to-llvm),convert-linalg-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | mlir-cpu-runner -e print_1d -entry-point-result=void -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | FileCheck %s --check-prefix=PRINT-1D
+// RUN: mlir-opt %s -pass-pipeline="func.func(convert-linalg-to-loops,convert-scf-to-cf,convert-arith-to-llvm),convert-linalg-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | mlir-cpu-runner -e print_3d -entry-point-result=void -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | FileCheck %s --check-prefix=PRINT-3D
+// RUN: mlir-opt %s -pass-pipeline="func.func(convert-linalg-to-loops,convert-scf-to-cf,convert-arith-to-llvm),convert-linalg-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | mlir-cpu-runner -e vector_splat_2d -entry-point-result=void -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | FileCheck %s --check-prefix=PRINT-VECTOR-SPLAT-2D
 
 func.func @print_0d() {
   %f = arith.constant 2.00000e+00 : f32

diff --git a/mlir/test/mlir-spirv-cpu-runner/double.mlir b/mlir/test/mlir-spirv-cpu-runner/double.mlir
@@ -1,4 +1,4 @@
-// RUN: mlir-spirv-cpu-runner %s -e main --entry-point-result=void --shared-libs=%mlir_runner_utils_dir/libmlir_runner_utils%shlibext,%spirv_wrapper_library_dir/libmlir_test_spirv_cpu_runner_c_wrappers%shlibext
+// RUN: mlir-spirv-cpu-runner %s -e main --entry-point-result=void --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext,%mlir_lib_dir/libmlir_test_spirv_cpu_runner_c_wrappers%shlibext
 
 // CHECK: [8,  8,  8,  8,  8,  8]
 module attributes {

diff --git a/mlir/test/mlir-spirv-cpu-runner/simple_add.mlir b/mlir/test/mlir-spirv-cpu-runner/simple_add.mlir
@@ -1,4 +1,4 @@
-// RUN: mlir-spirv-cpu-runner %s -e main --entry-point-result=void --shared-libs=%mlir_runner_utils_dir/libmlir_runner_utils%shlibext,%spirv_wrapper_library_dir/libmlir_test_spirv_cpu_runner_c_wrappers%shlibext
+// RUN: mlir-spirv-cpu-runner %s -e main --entry-point-result=void --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext,%mlir_lib_dir/libmlir_test_spirv_cpu_runner_c_wrappers%shlibext
 
 // CHECK: [[[7.7,    0,    0], [7.7,    0,    0], [7.7,    0,    0]], [[0,    7.7,    0], [0,    7.7,    0], [0,    7.7,    0]], [[0,    0,    7.7], [0,    0,    7.7], [0,    0,    7.7]]]
 module attributes {

diff --git a/mlir/test/mlir-vulkan-runner/addf.mlir b/mlir/test/mlir-vulkan-runner/addf.mlir
@@ -1,4 +1,4 @@
-// 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
+// RUN: mlir-vulkan-runner %s --shared-libs=%mlir_lib_dir/libvulkan-runtime-wrappers%shlibext,%mlir_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 {

diff --git a/mlir/test/mlir-vulkan-runner/addi.mlir b/mlir/test/mlir-vulkan-runner/addi.mlir
@@ -1,4 +1,4 @@
-// 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
+// RUN: mlir-vulkan-runner %s --shared-libs=%mlir_lib_dir/libvulkan-runtime-wrappers%shlibext,%mlir_lib_dir/libmlir_runner_utils%shlibext --entry-point-result=void | FileCheck %s
 
 // CHECK-COUNT-64: [3, 3, 3, 3, 3, 3, 3, 3]
 module attributes {

diff --git a/mlir/test/mlir-vulkan-runner/addi8.mlir b/mlir/test/mlir-vulkan-runner/addi8.mlir
@@ -1,4 +1,4 @@
-// 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
+// RUN: mlir-vulkan-runner %s --shared-libs=%mlir_lib_dir/libvulkan-runtime-wrappers%shlibext,%mlir_lib_dir/libmlir_runner_utils%shlibext --entry-point-result=void | FileCheck %s
 
 // CHECK-COUNT-64: [3, 3, 3, 3, 3, 3, 3, 3]
 module attributes {

diff --git a/mlir/test/mlir-vulkan-runner/mulf.mlir b/mlir/test/mlir-vulkan-runner/mulf.mlir
@@ -1,4 +1,4 @@
-// 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
+// RUN: mlir-vulkan-runner %s --shared-libs=%mlir_lib_dir/libvulkan-runtime-wrappers%shlibext,%mlir_lib_dir/libmlir_runner_utils%shlibext --entry-point-result=void | FileCheck %s
 
 // CHECK-COUNT-4: [6, 6, 6, 6]
 module attributes {

diff --git a/mlir/test/mlir-vulkan-runner/subf.mlir b/mlir/test/mlir-vulkan-runner/subf.mlir
@@ -1,4 +1,4 @@
-// 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
+// RUN: mlir-vulkan-runner %s --shared-libs=%mlir_lib_dir/libvulkan-runtime-wrappers%shlibext,%mlir_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 {

diff --git a/mlir/test/mlir-vulkan-runner/time.mlir b/mlir/test/mlir-vulkan-runner/time.mlir
@@ -1,4 +1,4 @@
-// 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
+// RUN: mlir-vulkan-runner %s --shared-libs=%mlir_lib_dir/libvulkan-runtime-wrappers%shlibext,%mlir_lib_dir/libmlir_runner_utils%shlibext --entry-point-result=void | FileCheck %s
 
 // CHECK: Compute shader execution time
 // CHECK: Command buffer submit time

diff --git a/utils/bazel/llvm-project-overlay/mlir/BUILD.bazel b/utils/bazel/llvm-project-overlay/mlir/BUILD.bazel
@@ -6471,7 +6471,36 @@ cc_library(
 )
 
 cc_library(
-    name = "mlir_c_runner_utils",
+    name = "mlir_async_runtime_api",
+    hdrs = ["include/mlir/ExecutionEngine/AsyncRuntime.h"],
+    includes = ["include"],
+)
+
+cc_library(
+    name = "_mlir_async_runtime",
+    srcs = ["lib/ExecutionEngine/AsyncRuntime.cpp"],
+    copts = ["-Dmlir_async_runtime_EXPORTS"],
+    deps = [
+        ":mlir_async_runtime_api",
+        "//llvm:Support",
+    ],
+)
+
+# Indirection to avoid output filename clash between cc_library and cc_binary.
+alias(
+    name = "mlir_async_runtime",
+    actual = "_mlir_async_runtime",
+)
+
+cc_binary(
+    name = "libmlir_async_runtime.so",
+    linkshared = True,
+    linkstatic = False,
+    deps = [":mlir_async_runtime"],
+)
+
+cc_library(
+    name = "_mlir_c_runner_utils",
     srcs = [
         "lib/ExecutionEngine/CRunnerUtils.cpp",
         "lib/ExecutionEngine/Float16bits.cpp",
@@ -6486,30 +6515,40 @@ cc_library(
     includes = ["include"],
 )
 
-cc_library(
-    name = "mlir_async_runtime_api",
-    hdrs = ["include/mlir/ExecutionEngine/AsyncRuntime.h"],
-    includes = ["include"],
+# Indirection to avoid output filename clash between cc_library and cc_binary.
+alias(
+    name = "mlir_c_runner_utils",
+    actual = "_mlir_c_runner_utils",
 )
 
-cc_library(
-    name = "mlir_async_runtime",
-    srcs = ["lib/ExecutionEngine/AsyncRuntime.cpp"],
-    copts = ["-Dmlir_async_runtime_EXPORTS"],
-    deps = [
-        ":mlir_async_runtime_api",
-        "//llvm:Support",
-    ],
+cc_binary(
+    name = "libmlir_c_runner_utils.so",
+    linkshared = True,
+    linkstatic = False,
+    deps = [":mlir_c_runner_utils"],
 )
 
 cc_library(
-    name = "mlir_runner_utils",
+    name = "_mlir_runner_utils",
     srcs = ["lib/ExecutionEngine/RunnerUtils.cpp"],
     hdrs = ["include/mlir/ExecutionEngine/RunnerUtils.h"],
     includes = ["include"],
     deps = [":mlir_c_runner_utils"],
 )
 
+# Indirection to avoid output filename clash between cc_library and cc_binary.
+alias(
+    name = "mlir_runner_utils",
+    actual = "_mlir_runner_utils",
+)
+
+cc_binary(
+    name = "libmlir_runner_utils.so",
+    linkshared = True,
+    linkstatic = False,
+    deps = [":mlir_runner_utils"],
+)
+
 cc_binary(
     name = "mlir-cpu-runner",
     srcs = ["tools/mlir-cpu-runner/mlir-cpu-runner.cpp"],
@@ -6546,7 +6585,7 @@ cc_headers_only(
 )
 
 cc_library(
-    name = "mlir_cuda_runtime",
+    name = "_mlir_cuda_runtime",
     srcs = ["lib/ExecutionEngine/CudaRuntimeWrappers.cpp"],
     # Prevent needing EnableABIBreakingChecks symbol from LLVMSupport.
     copts = ["-DLLVM_DISABLE_ABI_BREAKING_CHECKS_ENFORCING=1"],
@@ -6562,6 +6601,27 @@ cc_library(
     ],
 )
 
+# Indirection to avoid output filename clash between cc_library and cc_binary.
+alias(
+    name = "mlir_cuda_runtime",
+    actual = "_mlir_cuda_runtime",
+    tags = [
+        "manual",  # External dependency
+        "nobuildkite",  # TODO(gcmn): Add support for this target
+    ],
+)
+
+cc_binary(
+    name = "libmlir_cuda_runtime.so",
+    linkshared = True,
+    linkstatic = False,
+    tags = [
+        "manual",  # External dependency
+        "nobuildkite",  # TODO(gcmn): Add support for this target
+    ],
+    deps = [":mlir_cuda_runtime"],
+)
+
 cc_library(
     name = "VulkanRuntime",
     srcs = ["tools/mlir-vulkan-runner/VulkanRuntime.cpp"],
@@ -6583,7 +6643,7 @@ cc_library(
 )
 
 cc_binary(
-    name = "tools/libvulkan-runtime-wrappers.so",
+    name = "libvulkan-runtime-wrappers.so",
     srcs = ["tools/mlir-vulkan-runner/vulkan-runtime-wrappers.cpp"],
     linkshared = True,
     tags = [