rocm_jax/.bazelrc

# #############################################################################
# All default build options below. These apply to all build commands.
# #############################################################################
# Make Bazel print out all options from rc files.
build --announce_rc

# By default, execute all actions locally.
build --spawn_strategy=local

# Enable host OS specific configs. For instance, "build:linux" will be used
# automatically when building on Linux.
build --enable_platform_specific_config

build --experimental_cc_shared_library

# Do not use C-Ares when building gRPC.
build --define=grpc_no_ares=true

build --define=tsl_link_protobuf=true

# Enable optimization.
build -c opt

# Suppress all warning messages.
build --output_filter=DONT_MATCH_ANYTHING

build --copt=-DMLIR_PYTHON_PACKAGE_PREFIX=jaxlib.mlir.

# #############################################################################
# Platform Specific configs below. These are automatically picked up by Bazel
# depending on the platform that is running the build.
# #############################################################################
build:linux --config=posix
build:linux --copt=-Wno-unknown-warning-option

# Workaround for gcc 10+ warnings related to upb.
# See https://github.com/tensorflow/tensorflow/issues/39467
build:linux --copt=-Wno-stringop-truncation
build:linux --copt=-Wno-array-parameter

build:macos --config=posix
build:macos --apple_platform_type=macos

# Windows has a relatively short command line limit, which JAX has begun to hit.
# See https://docs.bazel.build/versions/main/windows.html
build:windows --features=compiler_param_file
build:windows --features=archive_param_file

# XLA uses M_* math constants that only get defined by MSVC headers if
# _USE_MATH_DEFINES is defined.
build:windows --copt=/D_USE_MATH_DEFINES
build:windows --host_copt=/D_USE_MATH_DEFINES
# Make sure to include as little of windows.h as possible
build:windows --copt=-DWIN32_LEAN_AND_MEAN
build:windows --host_copt=-DWIN32_LEAN_AND_MEAN
build:windows --copt=-DNOGDI
build:windows --host_copt=-DNOGDI
# https://devblogs.microsoft.com/cppblog/announcing-full-support-for-a-c-c-conformant-preprocessor-in-msvc/
# otherwise, there will be some compiling error due to preprocessing.
build:windows --copt=/Zc:preprocessor
build:windows --cxxopt=/std:c++17
build:windows --host_cxxopt=/std:c++17
# Generate PDB files, to generate useful PDBs, in opt compilation_mode
# --copt /Z7 is needed.
build:windows --linkopt=/DEBUG
build:windows --host_linkopt=/DEBUG
build:windows --linkopt=/OPT:REF
build:windows --host_linkopt=/OPT:REF
build:windows --linkopt=/OPT:ICF
build:windows --host_linkopt=/OPT:ICF
build:windows --incompatible_strict_action_env=true

# #############################################################################
# Feature-specific configurations. These are used by the CI configs below
# depending on the type of build. E.g. `ci_linux_x86_64` inherits the Linux x86
# configs such as `avx_linux` and `mkl_open_source_only`, `ci_linux_x86_64_cuda`
# inherits `cuda` and `build_cuda_with_nvcc`, etc.
# #############################################################################
build:nonccl --define=no_nccl_support=true

build:posix --copt=-fvisibility=hidden
build:posix --copt=-Wno-sign-compare
build:posix --cxxopt=-std=c++17
build:posix --host_cxxopt=-std=c++17

build:avx_posix --copt=-mavx
build:avx_posix --host_copt=-mavx

build:native_arch_posix --copt=-march=native
build:native_arch_posix --host_copt=-march=native

build:avx_linux --copt=-mavx
build:avx_linux --host_copt=-mavx

build:avx_windows --copt=/arch:AVX

build:mkl_open_source_only --define=tensorflow_mkldnn_contraction_kernel=1

# Config setting to build oneDNN with Compute Library for the Arm Architecture (ACL).
build:mkl_aarch64_threadpool --define=build_with_mkl_aarch64=true
build:mkl_aarch64_threadpool --@compute_library//:openmp=false
build:mkl_aarch64_threadpool -c opt

# Disable clang extention that rejects type definitions within offsetof.
# This was added in clang-16 by https://reviews.llvm.org/D133574.
# Can be removed once upb is updated, since a type definition is used within
# offset of in the current version of ubp.
# See https://github.com/protocolbuffers/upb/blob/9effcbcb27f0a665f9f345030188c0b291e32482/upb/upb.c#L183.
build:clang --copt=-Wno-gnu-offsetof-extensions
# Disable clang extention that rejects unknown arguments.
build:clang --copt=-Qunused-arguments
# Error on struct/class mismatches, since this causes link failures on Windows.
build:clang --copt=-Werror=mismatched-tags

# Configs for CUDA
build:cuda --repo_env TF_NEED_CUDA=1
build:cuda --repo_env TF_NCCL_USE_STUB=1
# "sm" means we emit only cubin, which is forward compatible within a GPU generation.
# "compute" means we emit both cubin and PTX, which is larger but also forward compatible to future GPU generations.
build:cuda --repo_env HERMETIC_CUDA_COMPUTE_CAPABILITIES="sm_50,sm_60,sm_70,sm_80,compute_90"
build:cuda --crosstool_top=@local_config_cuda//crosstool:toolchain
build:cuda --@local_config_cuda//:enable_cuda

# Default hermetic CUDA and CUDNN versions.
build:cuda --repo_env=HERMETIC_CUDA_VERSION="12.3.2"
build:cuda --repo_env=HERMETIC_CUDNN_VERSION="9.1.1"
build:cuda --@local_config_cuda//cuda:include_cuda_libs=true

# This config is used for building targets with CUDA libraries from stubs.
build:cuda_libraries_from_stubs --@local_config_cuda//cuda:include_cuda_libs=false

# Force the linker to set RPATH, not RUNPATH. When resolving dynamic libraries,
# ld.so prefers in order: RPATH, LD_LIBRARY_PATH, RUNPATH. JAX sets RPATH to
# point to the $ORIGIN-relative location of the pip-installed NVIDIA CUDA
# packages.
# This has pros and cons:
# * pro: we'll ignore other CUDA installations, which has frequently confused
#   users in the past. By setting RPATH, we'll always use the NVIDIA pip
#   packages if they are installed.
# * con: the user cannot override the CUDA installation location
#   via LD_LIBRARY_PATH, if the nvidia-... pip packages are installed. This is
#   acceptable, because the workaround is "remove the nvidia-..." pip packages.
# The list of CUDA pip packages that JAX depends on are present in setup.py.
build:cuda --linkopt=-Wl,--disable-new-dtags

# Build CUDA and other C++ targets with Clang
build:build_cuda_with_clang --@local_config_cuda//:cuda_compiler=clang

# Build CUDA with NVCC and other C++ targets with Clang
build:build_cuda_with_nvcc --action_env=TF_NVCC_CLANG="1"
build:build_cuda_with_nvcc --@local_config_cuda//:cuda_compiler=nvcc

# Requires MSVC and LLVM to be installed
build:win_clang --extra_toolchains=@local_config_cc//:cc-toolchain-x64_windows-clang-cl
build:win_clang --extra_execution_platforms=//jax/tools/toolchains:x64_windows-clang-cl
build:win_clang --compiler=clang-cl

build:rocm_base --crosstool_top=@local_config_rocm//crosstool:toolchain
build:rocm_base --define=using_rocm=true --define=using_rocm_hipcc=true
build:rocm_base --repo_env TF_NEED_ROCM=1
build:rocm_base --action_env TF_ROCM_AMDGPU_TARGETS="gfx900,gfx906,gfx908,gfx90a,gfx940,gfx941,gfx942,gfx1030,gfx1100,gfx1200,gfx1201"

# Build with hipcc for ROCm and clang for the host.
build:rocm --config=rocm_base
build:rocm --action_env=TF_ROCM_CLANG="1"
build:rocm --action_env=CLANG_COMPILER_PATH="/usr/lib/llvm-18/bin/clang"
build:rocm --copt=-Wno-gnu-offsetof-extensions
build:rocm --copt=-Qunused-arguments
build:rocm --action_env=TF_HIPCC_CLANG="1"

# #############################################################################
# Cache options below.
# #############################################################################
# Public read-only cache
build:public_cache --remote_cache="https://storage.googleapis.com/jax-bazel-cache/" --remote_upload_local_results=false
# Cache pushes are limited to JAX's CI system.
build:public_cache_push --config=public_cache --remote_upload_local_results=true --google_default_credentials

# Note: the following cache configs are deprecated and will be removed soon.
# Public read-only cache for Mac builds. JAX uses a GCS bucket to store cache
# from JAX's Mac CI build. By applying --config=macos_cache, any local Mac build
# should be able to read from this cache and potentially see a speedup. The
# "oct2023" in the URL is just the date when the bucket was created and can be
# disregarded. It still contains the latest cache that is being used.
build:macos_cache --remote_cache="https://storage.googleapis.com/tensorflow-macos-bazel-cache/oct2023" --remote_upload_local_results=false

# Cache pushes are limited to JAX's CI system.
build:macos_cache_push --config=macos_cache --remote_upload_local_results=true --google_default_credentials

# #############################################################################
# CI Build config options below.
# JAX uses these configs in CI builds for building artifacts and when running
# Bazel tests.
# #############################################################################
# Linux x86 CI configs
build:ci_linux_x86_64 --config=avx_linux --config=avx_posix
build:ci_linux_x86_64 --config=mkl_open_source_only
build:ci_linux_x86_64 --config=clang --verbose_failures=true
build:ci_linux_x86_64 --color=yes

# TODO(b/356695103): We do not have a CPU only toolchain so we use the CUDA
# toolchain for both CPU and GPU builds.
build:ci_linux_x86_64 --host_crosstool_top="@local_config_cuda//crosstool:toolchain"
build:ci_linux_x86_64 --crosstool_top="@local_config_cuda//crosstool:toolchain"
build:ci_linux_x86_64 --extra_toolchains="@local_config_cuda//crosstool:toolchain-linux-x86_64"
build:ci_linux_x86_64 --repo_env=TF_SYSROOT="/dt9"

# Clang path needs to be set for remote toolchain to be configured correctly.
build:ci_linux_x86_64 --action_env=CLANG_CUDA_COMPILER_PATH="/usr/lib/llvm-18/bin/clang"

# The toolchain in `--config=cuda` needs to be read before the toolchain in
# `--config=ci_linux_x86_64`. Otherwise, we run into issues with manylinux
# compliance.
build:ci_linux_x86_64_cuda --config=cuda --config=build_cuda_with_nvcc
build:ci_linux_x86_64_cuda --config=ci_linux_x86_64

# Linux Aarch64 CI configs
build:ci_linux_aarch64_base --config=clang --verbose_failures=true
build:ci_linux_aarch64_base --action_env=TF_SYSROOT="/dt10"
build:ci_linux_aarch64_base --color=yes

build:ci_linux_aarch64 --config=ci_linux_aarch64_base
build:ci_linux_aarch64 --host_crosstool_top="@ml2014_clang_aarch64_config_aarch64//crosstool:toolchain"
build:ci_linux_aarch64 --crosstool_top="@ml2014_clang_aarch64_config_aarch64//crosstool:toolchain"

# CUDA configs for Linux Aarch64 do not pass in the crosstool_top flag from
# above because the Aarch64 toolchain rule does not support building with NVCC.
# Instead, we use `@local_config_cuda//crosstool:toolchain` from --config=cuda
# and set `CLANG_CUDA_COMPILER_PATH` to define the toolchain so that we can
# use Clang for the C++ targets and NVCC to build CUDA targets.
build:ci_linux_aarch64_cuda --config=ci_linux_aarch64_base
build:ci_linux_aarch64_cuda --config=cuda --config=build_cuda_with_nvcc
build:ci_linux_aarch64_cuda --action_env=CLANG_CUDA_COMPILER_PATH="/usr/lib/llvm-18/bin/clang"

# Mac x86 CI configs
build:ci_darwin_x86_64 --macos_minimum_os=11.0
build:ci_darwin_x86_64 --config=macos_cache_push
build:ci_darwin_x86_64 --verbose_failures=true
build:ci_darwin_x86_64 --color=yes

# Mac Arm64 CI configs
build:ci_darwin_arm64 --macos_minimum_os=11.0
build:ci_darwin_arm64 --config=macos_cache_push
build:ci_darwin_arm64 --verbose_failures=true
build:ci_darwin_arm64 --color=yes

# Windows x86 CI configs
build:ci_windows_amd64 --config=avx_windows
build:ci_windows_amd64 --compiler=clang-cl --config=clang --verbose_failures=true
build:ci_windows_amd64 --crosstool_top="@xla//tools/toolchains/win/20240424:toolchain"
build:ci_windows_amd64 --extra_toolchains="@xla//tools/toolchains/win/20240424:cc-toolchain-x64_windows-clang-cl"
build:ci_windows_amd64 --host_linkopt=/FORCE:MULTIPLE --linkopt=/FORCE:MULTIPLE
build:ci_windows_amd64 --color=yes

# #############################################################################
# RBE config options below. These inherit the CI configs above and set the
# remote execution backend and authentication options required to run builds
# with RBE. Linux x86 and Windows builds use RBE.
# #############################################################################
# Flag to enable remote config
common --experimental_repo_remote_exec

# Allow creation of resultstore URLs for any bazel invocation
build:resultstore --google_default_credentials
build:resultstore --bes_backend=buildeventservice.googleapis.com
build:resultstore --bes_instance_name="tensorflow-testing"
build:resultstore --bes_results_url="https://source.cloud.google.com/results/invocations"
build:resultstore --bes_timeout=600s

build:rbe --config=resultstore
build:rbe --repo_env=BAZEL_DO_NOT_DETECT_CPP_TOOLCHAIN=1
build:rbe --define=EXECUTOR=remote
build:rbe --flaky_test_attempts=3
build:rbe --jobs=200
build:rbe --remote_executor=grpcs://remotebuildexecution.googleapis.com
build:rbe --remote_timeout=3600
build:rbe --spawn_strategy=remote,worker,standalone,local
# Attempt to minimize the amount of data transfer between bazel and the remote
# workers:
build:rbe --remote_download_toplevel
test:rbe --test_env=USER=anon

# RBE configs for Linux x86
# Set the remote worker pool
common:rbe_linux_x86_64_base --remote_instance_name=projects/tensorflow-testing/instances/default_instance

build:rbe_linux_x86_64_base --config=rbe
build:rbe_linux_x86_64_base --action_env=PATH="/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/local/go/bin"
build:rbe_linux_x86_64_base --linkopt=-lrt
build:rbe_linux_x86_64_base --host_linkopt=-lrt
build:rbe_linux_x86_64_base --linkopt=-lm
build:rbe_linux_x86_64_base --host_linkopt=-lm

# Set the host, execution, and target platform
build:rbe_linux_x86_64_base --host_platform="@ubuntu20.04-clang_manylinux2014-cuda12.3-cudnn9.1_config_platform//:platform"
build:rbe_linux_x86_64_base --extra_execution_platforms="@ubuntu20.04-clang_manylinux2014-cuda12.3-cudnn9.1_config_platform//:platform"
build:rbe_linux_x86_64_base --platforms="@ubuntu20.04-clang_manylinux2014-cuda12.3-cudnn9.1_config_platform//:platform"

build:rbe_linux_x86_64 --config=rbe_linux_x86_64_base
build:rbe_linux_x86_64 --config=ci_linux_x86_64

build:rbe_linux_x86_64_cuda --config=rbe_linux_x86_64_base
build:rbe_linux_x86_64_cuda --config=ci_linux_x86_64_cuda
build:rbe_linux_x86_64_cuda --repo_env=REMOTE_GPU_TESTING=1

# RBE configs for Windows
# Set the remote worker pool
common:rbe_windows_amd64 --remote_instance_name=projects/tensorflow-testing/instances/windows

build:rbe_windows_amd64 --config=rbe

# Set the host, execution, and target platform
build:rbe_windows_amd64 --host_platform="@xla//tools/toolchains/win:x64_windows-clang-cl"
build:rbe_windows_amd64 --extra_execution_platforms="@xla//tools/toolchains/win:x64_windows-clang-cl"
build:rbe_windows_amd64 --platforms="@xla//tools/toolchains/win:x64_windows-clang-cl"

build:rbe_windows_amd64 --shell_executable=C:\\tools\\msys64\\usr\\bin\\bash.exe
build:rbe_windows_amd64 --enable_runfiles
build:rbe_windows_amd64 --define=override_eigen_strong_inline=true

# Don't build the python zip archive in the RBE build.
build:rbe_windows_amd64 --nobuild_python_zip

build:rbe_windows_amd64 --config=ci_windows_amd64

# #############################################################################
# Cross-compile config options below. Native RBE support does not exist for
# Linux Aarch64 and Mac x86. So, we use a cross-compile toolchain to build
# targets for Linux Aarch64 and Mac x86 on the Linux x86 RBE pool.
# #############################################################################
# Set execution platform to Linux x86
# Note: Lot of the "host_" flags such as "host_cpu" and "host_crosstool_top"
# flags seem to be actually used to specify the execution platform details. It
# seems it is this way because these flags are old and predate the distinction
# between host and execution platform.
build:cross_compile_base --host_cpu=k8
build:cross_compile_base --host_crosstool_top=@xla//tools/toolchains/cross_compile/cc:cross_compile_toolchain_suite
build:cross_compile_base --extra_execution_platforms=@xla//tools/toolchains/cross_compile/config:linux_x86_64

# Linux Aarch64
build:cross_compile_linux_aarch64 --config=cross_compile_base

# Set the target CPU to Aarch64
build:cross_compile_linux_aarch64 --platforms=@xla//tools/toolchains/cross_compile/config:linux_aarch64
build:cross_compile_linux_aarch64 --cpu=aarch64
build:cross_compile_linux_aarch64 --crosstool_top=@xla//tools/toolchains/cross_compile/cc:cross_compile_toolchain_suite

build:rbe_cross_compile_base --config=rbe
build:rbe_cross_compile_base --remote_instance_name=projects/tensorflow-testing/instances/default_instance

# RBE cross-compile configs for Linux Aarch64
build:rbe_cross_compile_linux_aarch64 --config=cross_compile_linux_aarch64
build:rbe_cross_compile_linux_aarch64 --config=rbe_cross_compile_base

# Mac x86
build:cross_compile_darwin_x86_64 --config=cross_compile_base
build:cross_compile_darwin_x86_64 --config=nonccl
# Target Catalina (10.15) as the minimum supported OS
build:cross_compile_darwin_x86_64 --action_env  MACOSX_DEPLOYMENT_TARGET=10.15

# Set the target CPU to Darwin x86
build:cross_compile_darwin_x86_64 --platforms=@xla//tools/toolchains/cross_compile/config:darwin_x86_64
build:cross_compile_darwin_x86_64 --cpu=darwin
build:cross_compile_darwin_x86_64 --crosstool_top=@xla//tools/toolchains/cross_compile/cc:cross_compile_toolchain_suite
# When RBE cross-compiling for macOS, we need to explicitly register the
# toolchain. Otherwise, oddly, RBE complains that a "docker container must be
# specified".
build:cross_compile_darwin_x86_64 --extra_toolchains=@xla//tools/toolchains/cross_compile/config:macos-x86-cross-compile-cc-toolchain
# Map --platforms=darwin_x86_64 to --cpu=darwin and vice-versa to make selects()
# and transistions that use these flags work. The flag --platform_mappings needs
# to be set to a file that exists relative to the package path roots.
build:cross_compile_darwin_x86_64 --platform_mappings=platform_mappings

# RBE cross-compile configs for Darwin x86
build:rbe_cross_compile_darwin_x86_64 --config=cross_compile_darwin_x86_64
build:rbe_cross_compile_darwin_x86_64 --config=rbe_cross_compile_base

#############################################################################
# Some configs to make getting some forms of debug builds. In general, the
# codebase is only regularly built with optimizations. Use 'debug_symbols' to
# just get symbols for the parts of XLA/PJRT that jaxlib uses.
# Or try 'debug' to get a build with assertions enabled and minimal
# optimizations.
# Include these in a local .bazelrc.user file as:
#   build --config=debug_symbols
# Or:
#   build --config=debug
#
# Additional files can be opted in for debug symbols by adding patterns
# to a per_file_copt similar to below.
#############################################################################

build:debug_symbols --strip=never --per_file_copt="xla/pjrt|xla/python@-g3"
build:debug --config debug_symbols -c fastbuild

# Load `.jax_configure.bazelrc` file written by build.py
try-import %workspace%/.jax_configure.bazelrc

# Load rc file with user-specific options.
try-import %workspace%/.bazelrc.user