Save some size in dtype_util when dtype selective build is not in use (#9842)

We duplicate a lot of functions depending on the operator name so that
dtype selective build will work. We can just detect if dtype selective
build is in use and, if not, stop duplicating.

Test Plan: Saves 28288 bytes of text in size_test_all_optimized_ops
compared to previous PR on my Mac.
Pull-Request-resolved: #9742

Author: swolchok

kernels/portable/cpu/util/dtype_util.h

@@ -228,7 +228,7 @@ enum class SupportedTensorDtypes {
 namespace internal {
 
 template <typename CTYPE_COMPUTE, const char* op_name>
-load_to_compute_fn<CTYPE_COMPUTE> get_load_to_compute_fn(
+load_to_compute_fn<CTYPE_COMPUTE> get_load_to_compute_fn_impl(
     const Tensor& t,
     SupportedTensorDtypes dtypes) {
   switch (dtypes) {
@@ -252,7 +252,7 @@ load_to_compute_fn<CTYPE_COMPUTE> get_load_to_compute_fn(
 }
 
 template <typename CTYPE_COMPUTE, const char* op_name>
-store_compute_to_tensor_fn<CTYPE_COMPUTE> get_store_compute_to_tensor_fn(
+store_compute_to_tensor_fn<CTYPE_COMPUTE> get_store_compute_to_tensor_fn_impl(
     const Tensor& t,
     SupportedTensorDtypes dtypes) {
   switch (dtypes) {
@@ -285,6 +285,41 @@ store_compute_to_tensor_fn<CTYPE_COMPUTE> get_store_compute_to_tensor_fn(
   return nullptr;
 }
 
+#ifndef EXECUTORCH_SELECTIVE_BUILD_DTYPE
+constexpr const char kGenericElementwiseOpName[] = "generic_elementwise_op";
+#endif // EXECUTORCH_SELECTIVE_BUILD_DTYPE
+
+template <typename CTYPE_COMPUTE, const char* op_name>
+load_to_compute_fn<CTYPE_COMPUTE> get_load_to_compute_fn(
+    const Tensor& t,
+    SupportedTensorDtypes dtypes) {
+  // NOTE: Selective build relies on the operator name being passed
+  // here. When it's *not* active, using the same operator name
+  // everywhere saves on size because we don't require a new template
+  // instantiation for every operator.
+  return get_load_to_compute_fn_impl<
+      CTYPE_COMPUTE,
+#ifdef EXECUTORCH_SELECTIVE_BUILD_DTYPE
+      op_name
+#else // EXECUTORCH_SELECTIVE_BUILD_DTYPE
+      kGenericElementwiseOpName
+#endif // EXECUTORCH_SELECTIVE_BUILD_DTYPE
+      >(t, dtypes);
+}
+
+template <typename CTYPE_COMPUTE, const char* op_name>
+store_compute_to_tensor_fn<CTYPE_COMPUTE> get_store_compute_to_tensor_fn(
+    const Tensor& t,
+    SupportedTensorDtypes dtypes) {
+  return get_store_compute_to_tensor_fn_impl<
+      CTYPE_COMPUTE,
+#ifdef EXECUTORCH_SELECTIVE_BUILD_DTYPE
+      op_name
+#else // EXECUTORCH_SELECTIVE_BUILD_DTYPE
+      kGenericElementwiseOpName
+#endif // EXECUTORCH_SELECTIVE_BUILD_DTYPE
+      >(t, dtypes);
+}
 bool check_tensor_dtype(
     const Tensor t,
     SupportedTensorDtypes dtypes,