gnu: python-pytorch: Update to 2.2.1 and unbundle dependencies.

Autogenerated files are also regenerated. The tests can be run, but are
disabled, as they require a long time.

* gnu/packages/machine-learning.scm (python-pytorch): Update to 2.2.1.
[version]: Use %python-pytorch-version.
[source]: Use %python-pytorch-src.
[arguments]: Remove 'make-things-writable phase.  Add 'cmake-patches,
'disable-avx-dependencies, 'set-max-jobs, 'codegen1, 'codegen2, 'build2,
'install2 phases. Adjust 'use-system-libraries and 'check phases.
[native-inputs]: Add doxygen, ideep-pytorch, pocketfft-cpp, python-expecttest,
python-pytest-flakefinder, python-pytest-rerunfailures-13,
python-pytest-shard, python-pytest-xdist, python-hypothesis,
python-types-dataclasses, python-typing-extensions-4.10 and valgrind.
[inputs]: Add asmjit, clog, flatbuffers-next, foxi, fxdiv, libuv,
miniz-for-pytorch, qnnpack, qnnpack-pytorch and oneapi-dnnl. Use nnpack,
oneapi-dnnl, qnnpack, qnnpack-pytorch and xnnpack only for supported systems.
[propagated-inputs]: Add python-filelock, python-fsspec, python-jinja2,
python-networkx, python-opt-einsum, python-optree, python-packaging,
python-psutil and python-sympy. Remove python-cffi and python-six. Use cpuinfo
only for supported systems.
(%python-pytorch-src)[source]: Add patches.
(python-pytorch2): Remove variable.
* gnu/packages/patches/python-pytorch-runpath.patch: Adjust patch.
* gnu/packages/patches/python-pytorch-system-libraries.patch: Adjust patch.
* gnu/packages/patches/python-pytorch-1.9.0-system-libraries.patch: Remove file.
* gnu/packages/patches/python-pytorch-fix-codegen.patch: New file.
* gnu/packages/patches/python-pytorch-without-kineto: New file.
* gnu/local.mk (dist_patch_DATA): Register them.

1 files changed, 279 insertions, 38 deletions

diff --git a/gnu/packages/patches/python-pytorch-system-libraries.patch b/gnu/packages/patches/python-pytorch-system-libraries.patch
index fd849fd9e22..99f999f32f6 100644
--- a/gnu/packages/patches/python-pytorch-system-libraries.patch
+++ b/gnu/packages/patches/python-pytorch-system-libraries.patch
@@ -1,38 +1,104 @@
-Use our own googletest rather than the bundled one.
-Get NNPACK to use our own PeachPy rather than the bundled one.
+Patch build files to also system libraries instead of bundled ones for the
+libraries not supported or working only by specifying USE_SYSTEM_LIBS.  This
+includes using the clog, cpuinfo, fbgemm, foxi, fp16, fxdiv, googletest,
+ideep, miniz, nnpack, oneapi-dnnl, pocketfft, pthreadpool, qnnpack,
+qnnpack-pytorch, tensorpipe, valgrind and xnnpack packages.
+For QNNPACK, two versions were bundled and are required: The upstream one and
+an internal fork (now in the package qnnpack-pytorch).
 
+diff --git a/aten/src/ATen/CMakeLists.txt b/aten/src/ATen/CMakeLists.txt
+index 2c2b967..5ac5fa6 100644
+--- a/aten/src/ATen/CMakeLists.txt
++++ b/aten/src/ATen/CMakeLists.txt
+@@ -371,9 +371,9 @@ if(AT_NNPACK_ENABLED)
+   list(APPEND ATen_CPU_DEPENDENCY_LIBS nnpack) # cpuinfo is added below
+ endif()
+ 
+-if(MKLDNN_FOUND)
+-  list(APPEND ATen_CPU_DEPENDENCY_LIBS ${MKLDNN_LIBRARIES})
+-endif(MKLDNN_FOUND)
++if(USE_MKLDNN)
++  list(APPEND ATen_CPU_DEPENDENCY_LIBS DNNL::dnnl)
++endif(USE_MKLDNN)
+ 
+ if(NOT CMAKE_SYSTEM_PROCESSOR MATCHES "^(s390x|ppc64le)$")
+   list(APPEND ATen_CPU_DEPENDENCY_LIBS cpuinfo)
 diff --git a/caffe2/CMakeLists.txt b/caffe2/CMakeLists.txt
-index d57d7ebb..5b5622f0 100644
+index 7483637..093de40 100644
 --- a/caffe2/CMakeLists.txt
 +++ b/caffe2/CMakeLists.txt
-@@ -1736,7 +1736,7 @@ if(BUILD_TEST)
+@@ -111,9 +111,6 @@ if(NOT MSVC AND USE_XNNPACK)
+   if(NOT TARGET fxdiv)
+     set(FXDIV_BUILD_TESTS OFF CACHE BOOL "")
+     set(FXDIV_BUILD_BENCHMARKS OFF CACHE BOOL "")
+-    add_subdirectory(
+-      "${FXDIV_SOURCE_DIR}"
+-      "${CMAKE_BINARY_DIR}/FXdiv")
+   endif()
+ endif()
+ 
+@@ -1055,7 +1052,6 @@ elseif(USE_CUDA)
+ endif()
+ 
+ if(NOT MSVC AND USE_XNNPACK)
+-  TARGET_LINK_LIBRARIES(torch_cpu PRIVATE fxdiv)
+ endif()
+ 
+ # ==========================================================
+@@ -1396,6 +1392,7 @@ target_link_libraries(torch_cpu PUBLIC c10)
+ target_link_libraries(torch_cpu PUBLIC ${Caffe2_PUBLIC_DEPENDENCY_LIBS})
+ target_link_libraries(torch_cpu PRIVATE ${Caffe2_DEPENDENCY_LIBS})
+ target_link_libraries(torch_cpu PRIVATE ${Caffe2_DEPENDENCY_WHOLE_LINK_LIBS})
++target_link_libraries(torch_cpu PRIVATE miniz clog)
+ if(USE_MPI)
+   target_link_libraries(torch_cpu PRIVATE MPI::MPI_CXX)
+ endif()
+@@ -1653,7 +1650,7 @@ if(BUILD_STATIC_RUNTIME_BENCHMARK)
+   add_executable(static_runtime_bench "${STATIC_RUNTIME_BENCHMARK_SRCS}")
+   add_executable(static_runtime_test "${STATIC_RUNTIME_TEST_SRCS}")
+   target_link_libraries(static_runtime_bench torch_library benchmark)
+-  target_link_libraries(static_runtime_test torch_library gtest_main)
++  target_link_libraries(static_runtime_test torch_library gtest_main gtest)
+ endif()
+ 
+ if(BUILD_TENSOREXPR_BENCHMARK)
+@@ -1680,7 +1677,7 @@ if(BUILD_MOBILE_TEST)
+   foreach(test_src ${ATen_MOBILE_TEST_SRCS})
+     get_filename_component(test_name ${test_src} NAME_WE)
+     add_executable(${test_name} "${test_src}")
+-    target_link_libraries(${test_name} torch_library gtest_main)
++    target_link_libraries(${test_name} torch_library gtest_main gtest)
+     target_include_directories(${test_name} PRIVATE $<INSTALL_INTERFACE:include>)
+     target_include_directories(${test_name} PRIVATE $<BUILD_INTERFACE:${CMAKE_BINARY_DIR}/include>)
+     target_include_directories(${test_name} PRIVATE ${ATen_CPU_INCLUDE})
+@@ -1701,7 +1698,7 @@ if(BUILD_TEST)
          if(NOT MSVC)
-           add_executable(${test_name}_${CPU_CAPABILITY} "${test_src}" ../aten/src/ATen/native/quantized/affine_quantizer_base.cpp)
+           add_executable(${test_name}_${CPU_CAPABILITY} "${test_src}" ../aten/src/ATen/native/quantized/AffineQuantizerBase.cpp)
            # TODO: Get rid of c10 dependency (which is only needed for the implementation of AT_ERROR)
 -          target_link_libraries(${test_name}_${CPU_CAPABILITY} c10 sleef gtest_main)
 +          target_link_libraries(${test_name}_${CPU_CAPABILITY} c10 sleef gtest_main gtest)
            if(USE_FBGEMM)
              target_link_libraries(${test_name}_${CPU_CAPABILITY} fbgemm)
            endif()
-@@ -1759,7 +1759,7 @@ if(BUILD_TEST)
+@@ -1715,7 +1712,7 @@ if(BUILD_TEST)
+           endif()
+         else()
+           add_executable(${test_name}_${CPU_CAPABILITY} "${test_src}")
+-          target_link_libraries(${test_name}_${CPU_CAPABILITY} torch_library gtest_main)
++          target_link_libraries(${test_name}_${CPU_CAPABILITY} torch_library gtest_main gtest)
+         endif()
+         target_include_directories(${test_name}_${CPU_CAPABILITY} PRIVATE $<INSTALL_INTERFACE:include>)
+         target_include_directories(${test_name}_${CPU_CAPABILITY} PRIVATE $<BUILD_INTERFACE:${CMAKE_BINARY_DIR}/include>)
+@@ -1732,7 +1729,7 @@ if(BUILD_TEST)
    foreach(test_src ${Caffe2_CPU_TEST_SRCS})
      get_filename_component(test_name ${test_src} NAME_WE)
      add_executable(${test_name} "${test_src}")
 -    target_link_libraries(${test_name} torch_library gtest_main)
 +    target_link_libraries(${test_name} torch_library gtest_main gtest)
-     if(USE_OPENMP)
-       # -fopenmp is a compile time flag and as result not guaranteed
-       # to link executable against OpenMP runtime library
-@@ -1785,7 +1785,7 @@ if(BUILD_TEST)
-     foreach(test_src ${Caffe2_GPU_TEST_SRCS})
-       get_filename_component(test_name ${test_src} NAME_WE)
-       add_executable(${test_name} "${test_src}")
--      target_link_libraries(${test_name} torch_library gtest_main)
-+      target_link_libraries(${test_name} torch_library gtest_main gtest)
-       target_include_directories(${test_name} PRIVATE $<INSTALL_INTERFACE:include>)
-       target_include_directories(${test_name} PRIVATE ${Caffe2_CPU_INCLUDE})
-       add_test(NAME ${test_name} COMMAND $<TARGET_FILE:${test_name}>)
-@@ -1803,7 +1803,7 @@ if(BUILD_TEST)
+     target_include_directories(${test_name} PRIVATE $<INSTALL_INTERFACE:include>)
+     target_include_directories(${test_name} PRIVATE $<BUILD_INTERFACE:${CMAKE_BINARY_DIR}/include>)
+     target_include_directories(${test_name} PRIVATE ${Caffe2_CPU_INCLUDE})
+@@ -1795,7 +1792,7 @@ if(BUILD_TEST)
      foreach(test_src ${Caffe2_VULKAN_TEST_SRCS})
        get_filename_component(test_name ${test_src} NAME_WE)
        add_executable(${test_name} "${test_src}")
@@ -41,20 +107,66 @@ index d57d7ebb..5b5622f0 100644
        target_include_directories(${test_name} PRIVATE $<INSTALL_INTERFACE:include>)
        target_include_directories(${test_name} PRIVATE ${Caffe2_CPU_INCLUDE})
        add_test(NAME ${test_name} COMMAND $<TARGET_FILE:${test_name}>)
-@@ -1821,7 +1821,7 @@ if(BUILD_TEST)
-     foreach(test_src ${Caffe2_HIP_TEST_SRCS})
-       get_filename_component(test_name ${test_src} NAME_WE)
-       add_executable(${test_name} "${test_src}")
--      target_link_libraries(${test_name} torch_library gtest_main)
-+      target_link_libraries(${test_name} torch_library gtest_main gtest)
-       target_include_directories(${test_name} PRIVATE $<INSTALL_INTERFACE:include>)
-       target_include_directories(${test_name} PRIVATE ${Caffe2_CPU_INCLUDE} ${Caffe2_HIP_INCLUDE})
-       target_compile_options(${test_name} PRIVATE ${HIP_CXX_FLAGS})
+diff --git a/caffe2/serialize/CMakeLists.txt b/caffe2/serialize/CMakeLists.txt
+index 1552b59..67e1a9a 100644
+--- a/caffe2/serialize/CMakeLists.txt
++++ b/caffe2/serialize/CMakeLists.txt
+@@ -2,7 +2,6 @@ file(GLOB tmp *_test.cc)
+ 
+ set(Caffe2_CPU_TEST_SRCS ${Caffe2_CPU_TEST_SRCS} ${tmp})
+ list(APPEND Caffe2_CPU_SRCS
+-  ${PROJECT_SOURCE_DIR}/third_party/miniz-2.1.0/miniz.c
+   ${CMAKE_CURRENT_SOURCE_DIR}/inline_container.cc
+   ${CMAKE_CURRENT_SOURCE_DIR}/istream_adapter.cc
+   ${CMAKE_CURRENT_SOURCE_DIR}/file_adapter.cc
 diff --git a/cmake/Dependencies.cmake b/cmake/Dependencies.cmake
-index 557ab649..ee9cf410 100644
+index acc9584..97275bf 100644
 --- a/cmake/Dependencies.cmake
 +++ b/cmake/Dependencies.cmake
-@@ -732,11 +732,6 @@ if(BUILD_TEST OR BUILD_MOBILE_BENCHMARK OR BUILD_MOBILE_TEST)
+@@ -283,7 +283,7 @@ endif()
+ # --- [ PocketFFT
+ set(AT_POCKETFFT_ENABLED 0)
+ if(NOT AT_MKL_ENABLED)
+-  set(POCKETFFT_INCLUDE_DIR "${Torch_SOURCE_DIR}/third_party/pocketfft/")
++  set(POCKETFFT_INCLUDE_DIR "#POCKETFFT_INCLUDE_DIR")
+   if(NOT EXISTS "${POCKETFFT_INCLUDE_DIR}")
+     message(FATAL_ERROR "pocketfft directory not found, expected ${POCKETFFT_INCLUDE_DIR}")
+   elif(NOT EXISTS "${POCKETFFT_INCLUDE_DIR}/pocketfft_hdronly.h")
+@@ -489,19 +489,6 @@ if(USE_QNNPACK)
+     set(QNNPACK_BUILD_TESTS OFF CACHE BOOL "")
+     set(QNNPACK_BUILD_BENCHMARKS OFF CACHE BOOL "")
+     set(QNNPACK_LIBRARY_TYPE "static" CACHE STRING "")
+-    add_subdirectory(
+-      "${QNNPACK_SOURCE_DIR}"
+-      "${CONFU_DEPENDENCIES_BINARY_DIR}/QNNPACK")
+-
+-    # TODO: See https://github.com/pytorch/pytorch/issues/56285
+-    if(CMAKE_CXX_COMPILER_ID MATCHES "Clang" OR CMAKE_CXX_COMPILER_ID STREQUAL "GNU")
+-      target_compile_options(qnnpack PRIVATE -Wno-deprecated-declarations)
+-    endif()
+-
+-    # We build static versions of QNNPACK and pthreadpool but link
+-    # them into a shared library for Caffe2, so they need PIC.
+-    set_property(TARGET qnnpack PROPERTY POSITION_INDEPENDENT_CODE ON)
+-    set_property(TARGET cpuinfo PROPERTY POSITION_INDEPENDENT_CODE ON)
+ 
+     if(QNNPACK_CUSTOM_THREADPOOL)
+       target_compile_definitions(
+@@ -550,13 +537,6 @@ if(USE_PYTORCH_QNNPACK)
+       set(PYTORCH_QNNPACK_BUILD_TESTS OFF CACHE BOOL "")
+       set(PYTORCH_QNNPACK_BUILD_BENCHMARKS OFF CACHE BOOL "")
+       set(PYTORCH_QNNPACK_LIBRARY_TYPE "static" CACHE STRING "")
+-      add_subdirectory(
+-        "${PYTORCH_QNNPACK_SOURCE_DIR}"
+-        "${CONFU_DEPENDENCIES_BINARY_DIR}/pytorch_qnnpack")
+-      # We build static versions of QNNPACK and pthreadpool but link
+-      # them into a shared library for Caffe2, so they need PIC.
+-      set_property(TARGET pytorch_qnnpack PROPERTY POSITION_INDEPENDENT_CODE ON)
+-      set_property(TARGET cpuinfo PROPERTY POSITION_INDEPENDENT_CODE ON)
+ 
+       if(PYTORCH_QNNPACK_CUSTOM_THREADPOOL)
+         target_compile_definitions(
+@@ -728,11 +708,6 @@ if(BUILD_TEST OR BUILD_MOBILE_BENCHMARK OR BUILD_MOBILE_TEST)
    # this shouldn't be necessary anymore.
    get_property(INC_DIR_temp DIRECTORY PROPERTY INCLUDE_DIRECTORIES)
    set_property(DIRECTORY PROPERTY INCLUDE_DIRECTORIES "")
@@ -66,7 +178,49 @@ index 557ab649..ee9cf410 100644
  
    # We will not need to test benchmark lib itself.
    set(BENCHMARK_ENABLE_TESTING OFF CACHE BOOL "Disable benchmark testing as we don't need it.")
-@@ -1543,7 +1538,7 @@ if(CAFFE2_CMAKE_BUILDING_WITH_MAIN_REPO AND NOT INTERN_DISABLE_ONNX)
+@@ -810,16 +785,6 @@ if(USE_FBGEMM)
+     if(USE_ASAN)
+       set(USE_SANITIZER "address,undefined" CACHE STRING "-fsanitize options for FBGEMM")
+     endif()
+-    add_subdirectory("${FBGEMM_SOURCE_DIR}")
+-    set_property(TARGET fbgemm_generic PROPERTY POSITION_INDEPENDENT_CODE ON)
+-    set_property(TARGET fbgemm_avx2 PROPERTY POSITION_INDEPENDENT_CODE ON)
+-    set_property(TARGET fbgemm_avx512 PROPERTY POSITION_INDEPENDENT_CODE ON)
+-    set_property(TARGET fbgemm PROPERTY POSITION_INDEPENDENT_CODE ON)
+-    if("${CMAKE_CXX_COMPILER_ID}" MATCHES "Clang" AND CMAKE_CXX_COMPILER_VERSION VERSION_GREATER 13.0.0)
+-      # See https://github.com/pytorch/pytorch/issues/74352
+-      target_compile_options_if_supported(asmjit -Wno-deprecated-copy)
+-      target_compile_options_if_supported(asmjit -Wno-unused-but-set-variable)
+-    endif()
+   endif()
+ 
+   if(USE_FBGEMM)
+@@ -979,7 +944,7 @@ if(NOT TARGET fp16 AND NOT USE_SYSTEM_FP16)
+     "${FP16_SOURCE_DIR}"
+     "${CONFU_DEPENDENCIES_BINARY_DIR}/FP16")
+ elseif(NOT TARGET fp16 AND USE_SYSTEM_FP16)
+-  add_library(fp16 STATIC "/usr/include/fp16.h")
++  add_library(fp16 STATIC "#FP16_INCLUDE_DIR")
+   set_target_properties(fp16 PROPERTIES LINKER_LANGUAGE C)
+ endif()
+ list(APPEND Caffe2_DEPENDENCY_LIBS fp16)
+@@ -1362,7 +1327,6 @@ if(USE_DISTRIBUTED AND USE_TENSORPIPE)
+ 
+     # Tensorpipe uses cuda_add_library
+     torch_update_find_cuda_flags()
+-    add_subdirectory(${PROJECT_SOURCE_DIR}/third_party/tensorpipe)
+ 
+     list(APPEND Caffe2_DEPENDENCY_LIBS tensorpipe)
+     if(USE_CUDA)
+@@ -1529,7 +1493,6 @@ if(CAFFE2_CMAKE_BUILDING_WITH_MAIN_REPO AND NOT INTERN_DISABLE_ONNX)
+       set_target_properties(onnx_proto PROPERTIES CXX_STANDARD 17)
+     endif()
+   endif()
+-  add_subdirectory(${CMAKE_CURRENT_LIST_DIR}/../third_party/foxi EXCLUDE_FROM_ALL)
+ 
+   add_definitions(-DONNX_NAMESPACE=${ONNX_NAMESPACE})
+   if(NOT USE_SYSTEM_ONNX)
+@@ -1560,7 +1523,7 @@ if(CAFFE2_CMAKE_BUILDING_WITH_MAIN_REPO AND NOT INTERN_DISABLE_ONNX)
      endif()
      set_property(TARGET onnx_proto PROPERTY IMPORTED_LOCATION ${ONNX_PROTO_LIBRARY})
      message("-- Found onnx: ${ONNX_LIBRARY} ${ONNX_PROTO_LIBRARY}")
@@ -75,8 +229,36 @@ index 557ab649..ee9cf410 100644
    endif()
    include_directories(${FOXI_INCLUDE_DIRS})
    list(APPEND Caffe2_DEPENDENCY_LIBS foxi_loader)
+@@ -1739,9 +1702,8 @@ if(NOT INTERN_BUILD_MOBILE)
+   endif()
+   if(USE_MKLDNN)
+     include(${CMAKE_CURRENT_LIST_DIR}/public/mkldnn.cmake)
+-    if(MKLDNN_FOUND)
++    if(DNNL_FOUND)
+       set(AT_MKLDNN_ENABLED 1)
+-      include_directories(AFTER SYSTEM ${MKLDNN_INCLUDE_DIR})
+       if(BUILD_CAFFE2_OPS)
+         list(APPEND Caffe2_DEPENDENCY_LIBS caffe2::mkldnn)
+       endif(BUILD_CAFFE2_OPS)
+@@ -1796,7 +1758,7 @@ endif()
+ #
+ set(TEMP_BUILD_SHARED_LIBS ${BUILD_SHARED_LIBS})
+ set(BUILD_SHARED_LIBS OFF CACHE BOOL "Build shared libs" FORCE)
+-add_subdirectory(${PROJECT_SOURCE_DIR}/third_party/fmt)
++find_package(fmt)
+ 
+ # Disable compiler feature checks for `fmt`.
+ #
+@@ -1805,7 +1767,6 @@ add_subdirectory(${PROJECT_SOURCE_DIR}/third_party/fmt)
+ # CMAKE_CXX_FLAGS in ways that break feature checks. Since we already know
+ # `fmt` is compatible with a superset of the compilers that PyTorch is, it
+ # shouldn't be too bad to just disable the checks.
+-set_target_properties(fmt-header-only PROPERTIES INTERFACE_COMPILE_FEATURES "")
+ 
+ list(APPEND Caffe2_DEPENDENCY_LIBS fmt::fmt-header-only)
+ set(BUILD_SHARED_LIBS ${TEMP_BUILD_SHARED_LIBS} CACHE BOOL "Build shared libs" FORCE)
 diff --git a/cmake/External/nnpack.cmake b/cmake/External/nnpack.cmake
-index a41343cb..6075bdd0 100644
+index 9d5f064..c3624e5 100644
 --- a/cmake/External/nnpack.cmake
 +++ b/cmake/External/nnpack.cmake
 @@ -40,7 +40,7 @@ endif()
@@ -88,7 +270,7 @@ index a41343cb..6075bdd0 100644
    message(STATUS "Brace yourself, we are building NNPACK")
    set(CAFFE2_THIRD_PARTY_ROOT ${PROJECT_SOURCE_DIR}/third_party)
  
-@@ -114,6 +114,5 @@ endif()
+@@ -112,6 +112,5 @@ endif()
  # (4) Catch-all: not supported.
  ##############################################################################
  
@@ -97,8 +279,45 @@ index a41343cb..6075bdd0 100644
 -set(USE_NNPACK OFF)
 +set(NNPACK_FOUND TRUE)
 +set(USE_NNPACK ON)
+diff --git a/cmake/public/mkldnn.cmake b/cmake/public/mkldnn.cmake
+index 8793562..9f8fa3d 100644
+--- a/cmake/public/mkldnn.cmake
++++ b/cmake/public/mkldnn.cmake
+@@ -4,7 +4,7 @@ if(CPU_AARCH64)
+   include(${CMAKE_CURRENT_LIST_DIR}/ComputeLibrary.cmake)
+ endif()
+ 
+-find_package(MKLDNN QUIET)
++find_package(DNNL REQUIRED)
+ 
+ if(NOT TARGET caffe2::mkldnn)
+   add_library(caffe2::mkldnn INTERFACE IMPORTED)
+@@ -15,4 +15,4 @@ set_property(
+   ${MKLDNN_INCLUDE_DIR})
+ set_property(
+   TARGET caffe2::mkldnn PROPERTY INTERFACE_LINK_LIBRARIES
+-  ${MKLDNN_LIBRARIES})
++  DNNL::dnnl)
+diff --git a/setup.py b/setup.py
+index 81f3c6c..3251cab 100644
+--- a/setup.py
++++ b/setup.py
+@@ -482,13 +482,9 @@ def build_deps():
+     # Windows has very poor support for them.
+     sym_files = [
+         "tools/shared/_utils_internal.py",
+-        "torch/utils/benchmark/utils/valgrind_wrapper/callgrind.h",
+-        "torch/utils/benchmark/utils/valgrind_wrapper/valgrind.h",
+     ]
+     orig_files = [
+         "torch/_utils_internal.py",
+-        "third_party/valgrind-headers/callgrind.h",
+-        "third_party/valgrind-headers/valgrind.h",
+     ]
+     for sym_file, orig_file in zip(sym_files, orig_files):
+         same = False
 diff --git a/test/cpp/c10d/CMakeLists.txt b/test/cpp/c10d/CMakeLists.txt
-index bf91460c..ef56948f 100644
+index 5c89748..ef84c57 100644
 --- a/test/cpp/c10d/CMakeLists.txt
 +++ b/test/cpp/c10d/CMakeLists.txt
 @@ -16,14 +16,14 @@ function(c10d_add_test test_src)
@@ -133,7 +352,29 @@ index bf91460c..ef56948f 100644
    endif()
    if(USE_NCCL AND USE_C10D_NCCL)
      # NCCL is a private dependency of libtorch, but the tests include some
-@@ -56,7 +56,7 @@ if(USE_CUDA)
+@@ -44,10 +44,10 @@ if(USE_CUDA)
+     # a private dependency of the tests as well.
+     c10d_add_test(
+       ProcessGroupNCCLTest.cpp
+-      torch_cpu c10d_cuda_test gtest_main __caffe2_nccl)
++      torch_cpu c10d_cuda_test gtest_main gtest __caffe2_nccl)
+     c10d_add_test(
+       ProcessGroupNCCLErrorsTest.cpp
+-      torch_cpu c10d_cuda_test gtest_main __caffe2_nccl)
++      torch_cpu c10d_cuda_test gtest_main gtest __caffe2_nccl)
+     if(INSTALL_TEST)
+       install(TARGETS ProcessGroupNCCLTest DESTINATION bin)
+       install(TARGETS ProcessGroupNCCLErrorsTest DESTINATION bin)
+@@ -61,7 +61,7 @@ if(USE_CUDA)
+     # a private dependency of the tests as well.
+     c10d_add_test(
+       ProcessGroupUCCTest.cpp
+-      torch_cpu c10d_cuda_test gtest_main __caffe2_ucc)
++      torch_cpu c10d_cuda_test gtest_main gtest __caffe2_ucc)
+     if(INSTALL_TEST)
+       install(TARGETS ProcessGroupUCCTest DESTINATION bin)
+       install(TARGETS c10d_cuda_test DESTINATION lib)
+@@ -69,7 +69,7 @@ if(USE_CUDA)
    endif()
  else()
    if(USE_GLOO AND USE_C10D_GLOO)
@@ -143,10 +384,10 @@ index bf91460c..ef56948f 100644
  endif()
  
 diff --git a/test/cpp/tensorexpr/CMakeLists.txt b/test/cpp/tensorexpr/CMakeLists.txt
-index 8fc5a0a1..643202f6 100644
+index 012471d..d39b625 100644
 --- a/test/cpp/tensorexpr/CMakeLists.txt
 +++ b/test/cpp/tensorexpr/CMakeLists.txt
-@@ -53,7 +53,7 @@ target_include_directories(tutorial_tensorexpr PRIVATE ${ATen_CPU_INCLUDE})
+@@ -54,7 +54,7 @@ target_include_directories(tutorial_tensorexpr PRIVATE ${ATen_CPU_INCLUDE})
  # pthreadpool header. For some build environment we need add the dependency
  # explicitly.
  if(USE_PTHREADPOOL)
@@ -154,4 +395,4 @@ index 8fc5a0a1..643202f6 100644
 +  target_link_libraries(test_tensorexpr PRIVATE pthreadpool)
  endif()
  if(USE_CUDA)
-   target_link_libraries(test_tensorexpr PRIVATE
+   target_compile_definitions(test_tensorexpr PRIVATE USE_CUDA)