Revert "Optimize scale-factor-2 nearest-neighbor upsampling portable op" (pytorch#23260)

Reverts pytorch#22999

Many buck failures on internal CI: D122355607

cc @JakeStevens

Author: metascroy

kernels/optimized/CMakeLists.txt

@@ -1,6 +1,5 @@
 # Copyright (c) Meta Platforms, Inc. and affiliates.
 # All rights reserved.
-# Copyright 2026 Arm Limited and/or its affiliates.
 #
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
@@ -108,25 +107,6 @@ if(CMAKE_SYSTEM_PROCESSOR MATCHES "aarch64|arm64" OR ANDROID_ABI STREQUAL
   )
 endif()
 
-# The nearest-2x fast path uses only baseline AArch64 Advanced SIMD. Keep
-# arm_neon.h and its implementation out of all other architecture builds.
-if(CMAKE_SYSTEM_PROCESSOR MATCHES "aarch64|arm64" OR ANDROID_ABI STREQUAL
-                                                     "arm64-v8a"
-)
-  add_library(
-    upsample_nearest2d_neon_impl OBJECT
-    ${EXECUTORCH_ROOT}/kernels/optimized/cpu/op_upsample_nearest2d_neon.cpp
-  )
-  target_compile_options(
-    upsample_nearest2d_neon_impl PRIVATE ${_common_compile_options}
-  )
-  target_link_libraries(upsample_nearest2d_neon_impl PRIVATE executorch_core)
-  target_link_libraries(
-    optimized_kernels
-    PRIVATE $<BUILD_LOCAL_INTERFACE:upsample_nearest2d_neon_impl>
-  )
-endif()
-
 # Build a library for _optimized_kernels_srcs
 #
 # optimized_ops_lib: Register optimized ops kernels into Executorch runtime

kernels/optimized/cpu/op_upsample_nearest2d.cpp

@@ -109,19 +109,6 @@ def define_common_targets():
         ],
     )
 
-    runtime.cxx_library(
-        name = "upsample_nearest2d_neon_impl",
-        srcs = select({
-            "DEFAULT": [],
-            "ovr_config//cpu:arm64": ["op_upsample_nearest2d_neon.cpp"],
-        }),
-        exported_headers = ["op_upsample_nearest2d_neon.h"],
-        visibility = ["PUBLIC"],
-        exported_deps = [
-            "//executorch/runtime/kernel:kernel_includes",
-        ],
-    )
-
     # Used for dtype selective build. Collect source and header files.
     runtime.filegroup(
         name = "optimized_source_files",

kernels/optimized/cpu/op_upsample_nearest2d_neon.cpp

@@ -1,5 +1,4 @@
 # Copyright (c) Meta Platforms, Inc. and affiliates.
-# Copyright 2026 Arm Limited and/or its affiliates.
 #
 # This yaml file contains operators that have optimized kernels available.
 
@@ -122,8 +121,3 @@
   kernels:
     - arg_meta: null
       kernel_name: torch::executor::opt_where_out
-
-- op: upsample_nearest2d.vec_out
-  kernels:
-    - arg_meta: null
-      kernel_name: torch::executor::opt_upsample_nearest2d_vec_out

kernels/optimized/cpu/op_upsample_nearest2d_neon.h

@@ -1,95 +1,25 @@
 /*
  * Copyright (c) Meta Platforms, Inc. and affiliates.
  * All rights reserved.
- * Copyright 2026 Arm Limited and/or its affiliates.
  *
  * This source code is licensed under the BSD-style license found in the
  * LICENSE file in the root directory of this source tree.
  */
 
 #include <executorch/kernels/portable/cpu/util/upsample_util.h>
 #include <executorch/runtime/kernel/kernel_includes.h>
-#include <executorch/runtime/kernel/thread_parallel_interface.h>
-
-#include <cstring>
 
 namespace torch {
 namespace executor {
 namespace native {
 
 namespace {
-
-template <typename CTYPE>
-bool upsample_nearest2d_2x_nchw_fast_path(
-    const Tensor& in,
-    const float scale_h,
-    const float scale_w,
-    Tensor& out) {
-  if (scale_h != 0.5f || scale_w != 0.5f || out.size(2) != in.size(2) * 2 ||
-      out.size(3) != in.size(3) * 2) {
-    return false;
-  }
-
-  const int64_t in_h = in.size(2);
-  const int64_t in_w = in.size(3);
-  const int64_t out_h = out.size(2);
-  const int64_t out_w = out.size(3);
-
-  const bool in_contiguous_nchw = in.strides()[3] == 1 &&
-      in.strides()[2] == in_w && in.strides()[1] == in_h * in_w &&
-      in.strides()[0] == in.size(1) * in_h * in_w;
-  const bool out_contiguous_nchw = out.strides()[3] == 1 &&
-      out.strides()[2] == out_w && out.strides()[1] == out_h * out_w &&
-      out.strides()[0] == out.size(1) * out_h * out_w;
-  if (!in_contiguous_nchw || !out_contiguous_nchw) {
-    return false;
-  }
-
-  const auto in_data = in.const_data_ptr<CTYPE>();
-  auto out_data = out.mutable_data_ptr<CTYPE>();
-  const int64_t planes = in.size(0) * in.size(1);
-  const int64_t in_plane_size = in_h * in_w;
-  const int64_t out_plane_size = out_h * out_w;
-  int64_t grain_size =
-      ::executorch::extension::internal::GRAIN_SIZE / out_plane_size;
-  if (grain_size < 1) {
-    grain_size = 1;
-  }
-
-  const bool success = ::executorch::extension::parallel_for(
-      0, planes, grain_size, [&](const auto begin, const auto end) {
-        for (const auto plane : c10::irange(begin, end)) {
-          const CTYPE* in_plane = in_data + plane * in_plane_size;
-          CTYPE* out_plane = out_data + plane * out_plane_size;
-
-          for (int64_t h = 0; h < in_h; ++h) {
-            const CTYPE* in_row = in_plane + h * in_w;
-            CTYPE* out_row0 = out_plane + (2 * h) * out_w;
-            CTYPE* out_row1 = out_row0 + out_w;
-
-            for (int64_t w = 0; w < in_w; ++w) {
-              const CTYPE value = in_row[w];
-              out_row0[2 * w] = value;
-              out_row0[2 * w + 1] = value;
-            }
-            std::memcpy(out_row1, out_row0, out_w * sizeof(CTYPE));
-          }
-        }
-      });
-
-  return success;
-}
-
 template <typename CTYPE>
 void upsample_nearest2d_kernel_impl_nchw(
     const Tensor& in,
     const float scale_h,
     const float scale_w,
     Tensor& out) {
-  if (upsample_nearest2d_2x_nchw_fast_path<CTYPE>(in, scale_h, scale_w, out)) {
-    return;
-  }
-
   const auto in_data = in.const_data_ptr<CTYPE>();
   auto out_data = out.mutable_data_ptr<CTYPE>();
 

kernels/optimized/cpu/targets.bzl

@@ -1,6 +1,5 @@
 # Copyright (c) Meta Platforms, Inc. and affiliates.
 # All rights reserved.
-# Copyright 2026 Arm Limited and/or its affiliates.
 #
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
@@ -364,7 +363,6 @@ if(EXECUTORCH_BUILD_KERNELS_OPTIMIZED)
       "op_native_layer_norm_test.cpp"
       "op_neg_test.cpp"
       "op_sub_test.cpp"
-      "op_upsample_nearest2d_test.cpp"
       "op_where_test.cpp"
       "UnaryUfuncRealHBBF16ToFloatHBF16Test.cpp"
       ${CMAKE_CURRENT_BINARY_DIR}/include/optimized/executorch/kernels/test/supported_features.cpp