Basic scalar implementation of CHW-to-HWC Depth-to-Space.

PiperOrigin-RevId: 340764018
diff --git a/BUILD.bazel b/BUILD.bazel
index d9cad9f..cd66815 100644
--- a/BUILD.bazel
+++ b/BUILD.bazel
@@ -498,6 +498,7 @@
     "src/x8-zip/x3-scalar.c",
     "src/x8-zip/x4-scalar.c",
     "src/x8-zip/xm-scalar.c",
+    "src/x32-depth-to-space-chw2hwc/scalar.c",
     "src/x32-fill/scalar-float.c",
     "src/x32-fill/scalar-int.c",
     "src/x32-packx/x2-scalar.c",
@@ -3077,6 +3078,7 @@
     "src/xnnpack/clamp.h",
     "src/xnnpack/common.h",
     "src/xnnpack/conv.h",
+    "src/xnnpack/depthtospace.h",
     "src/xnnpack/dwconv.h",
     "src/xnnpack/fill.h",
     "src/xnnpack/gavgpool.h",
@@ -6313,6 +6315,15 @@
 )
 
 xnnpack_unit_test(
+    name = "x32_depth_to_space_chw2hwc_test",
+    srcs = [
+        "test/x32-depth-to-space-chw2hwc.cc",
+        "test/depth-to-space-microkernel-tester.h",
+    ] + MICROKERNEL_TEST_HDRS,
+    deps = MICROKERNEL_TEST_DEPS,
+)
+
+xnnpack_unit_test(
     name = "x32_fill_test",
     srcs = [
         "test/x32-fill.cc",