Reapply #9842: Save some size in dtype_util when dtype selective build is not in use (#10490)

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: compared results of bash test/build_optimized_size_test.sh
before/after this rev.

Before:
```
ExecuTorch with no ops binary size, unstripped:
-rwxr-xr-x  1 swolchok  staff  153928 Apr 25 12:24 cmake-out/test/size_test
ExecuTorch with portable ops binary size, unstripped:
-rwxr-xr-x  1 swolchok  staff  2150960 Apr 25 12:24 cmake-out/test/size_test_all_ops
ExecuTorch with optimized ops binary size, unstripped:
-rwxr-xr-x  1 swolchok  staff  5887368 Apr 25 12:24 cmake-out/test/size_test_all_optimized_ops
(.venv) swolchok@swolchok-mac ~/src/executorch> size cmake-out/test/size_test*
__TEXT	__DATA	__OBJC	others	dec	hex
81920	81920	0	4295049216	4295213056	10003c000	cmake-out/test/size_test
1474560	81920	0	4295655424	4297211904	100224000	cmake-out/test/size_test_all_ops
4489216	98304	0	4296359936	4300947456	1005b4000	cmake-out/test/size_test_all_optimized_ops
```

After:
```
ExecuTorch with no ops binary size, unstripped:
-rwxr-xr-x  1 swolchok  staff  153928 Apr 25 12:51 cmake-out/test/size_test
ExecuTorch with portable ops binary size, unstripped:
-rwxr-xr-x  1 swolchok  staff  1796928 Apr 25 12:51 cmake-out/test/size_test_all_ops
ExecuTorch with optimized ops binary size, unstripped:
-rwxr-xr-x  1 swolchok  staff  5605176 Apr 25 12:51 cmake-out/test/size_test_all_optimized_ops
(.venv) swolchok@swolchok-mac ~/src/executorch> size cmake-out/test/size_test*
__TEXT	__DATA	__OBJC	others	dec	hex
81920	81920	0	4295049216	4295213056	10003c000	cmake-out/test/size_test
1310720	81920	0	4295458816	4296851456	1001cc000	cmake-out/test/size_test_all_ops
4358144	98304	0	4296212480	4300668928	100570000	cmake-out/test/size_test_all_optimized_ops
```

(This was reverted because the diff it was stacked on was a size
regression. Reversing the order instead this time around, and reverted
part of the change that was actually regressing size.)

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) {
@@ -251,6 +251,10 @@ load_to_compute_fn<CTYPE_COMPUTE> get_load_to_compute_fn(
   return nullptr;
 }
 
+// NOTE: applying the #ifdef EXECUTORCH_SELECTIVE_BUILD_DTYPE
+// technique used for get_load_to_compute_fn in this path was a size
+// regression rather than an improvement. Haven't fully investigated
+// why; just be aware when trying to improve size further.
 template <typename CTYPE_COMPUTE, const char* op_name>
 store_compute_to_tensor_fn<CTYPE_COMPUTE> get_store_compute_to_tensor_fn(
     const Tensor& t,
@@ -285,6 +289,29 @@ store_compute_to_tensor_fn<CTYPE_COMPUTE> get_store_compute_to_tensor_fn(
   return nullptr;
 }
 
+#ifndef EXECUTORCH_SELECTIVE_BUILD_DTYPE
+inline 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);
+}
+
 bool check_tensor_dtype(
     const Tensor t,
     SupportedTensorDtypes dtypes,