This change reimplements the CUDA autoconfiguration mechanism in Skylark, providing a `cuda_configure` workspace rule. We keep the same user interface, the ./configure script, but rather than modifying source files within the source tree, `cuda_configure` generates a `@local_config_cuda` workspace containing: * Symlinks to the CUDA headers and libraries * BUILD files generated with the correct CUDA and cuDNN versions * CROSSTOOL config with CUDA include dirs populated * crosstool_wrapper_driver_is_not_gcc wrapper script with compiler paths and CUDA compute capabilities set. * cuda_config.h header file with CUDA versions and compute capabilities set, which can be `#include`d by source files. This change also makes the following fixes to `Dockerfile.gpu`: * Change the `CUDNN_INSTALL_PATH` to point to `/usr/lib/x86_64-linux-gnu` rather than `/usr/local/cuda` since NVIDIA's image installs `libcudnn.so` under `/usr/lib/x86_64-linux-gnu`. * Add env variable to set the minimum compute capability to 3.0. Fixes #2873
255 lines
8.7 KiB
Smarty
255 lines
8.7 KiB
Smarty
major_version: "local"
|
|
minor_version: ""
|
|
default_target_cpu: "same_as_host"
|
|
|
|
default_toolchain {
|
|
cpu: "k8"
|
|
toolchain_identifier: "local_linux"
|
|
}
|
|
default_toolchain {
|
|
cpu: "piii"
|
|
toolchain_identifier: "local_linux"
|
|
}
|
|
default_toolchain {
|
|
cpu: "arm"
|
|
toolchain_identifier: "local_linux"
|
|
}
|
|
default_toolchain {
|
|
cpu: "darwin"
|
|
toolchain_identifier: "local_darwin"
|
|
}
|
|
default_toolchain {
|
|
cpu: "ppc"
|
|
toolchain_identifier: "local_linux"
|
|
}
|
|
|
|
toolchain {
|
|
abi_version: "local"
|
|
abi_libc_version: "local"
|
|
builtin_sysroot: ""
|
|
compiler: "compiler"
|
|
host_system_name: "local"
|
|
needsPic: true
|
|
supports_gold_linker: false
|
|
supports_incremental_linker: false
|
|
supports_fission: false
|
|
supports_interface_shared_objects: false
|
|
supports_normalizing_ar: false
|
|
supports_start_end_lib: false
|
|
supports_thin_archives: false
|
|
target_libc: "local"
|
|
target_cpu: "local"
|
|
target_system_name: "local"
|
|
toolchain_identifier: "local_linux"
|
|
|
|
tool_path { name: "ar" path: "/usr/bin/ar" }
|
|
tool_path { name: "compat-ld" path: "/usr/bin/ld" }
|
|
tool_path { name: "cpp" path: "/usr/bin/cpp" }
|
|
tool_path { name: "dwp" path: "/usr/bin/dwp" }
|
|
# As part of the TensorFlow release, we place some cuda-related compilation
|
|
# files in @local_config_cuda//crosstool/clang/bin, and this relative
|
|
# path, combined with the rest of our Bazel configuration causes our
|
|
# compilation to use those files.
|
|
tool_path { name: "gcc" path: "clang/bin/crosstool_wrapper_driver_is_not_gcc" }
|
|
# Use "-std=c++11" for nvcc. For consistency, force both the host compiler
|
|
# and the device compiler to use "-std=c++11".
|
|
cxx_flag: "-std=c++11"
|
|
linker_flag: "-lstdc++"
|
|
linker_flag: "-B/usr/bin/"
|
|
|
|
# TODO(bazel-team): In theory, the path here ought to exactly match the path
|
|
# used by gcc. That works because bazel currently doesn't track files at
|
|
# absolute locations and has no remote execution, yet. However, this will need
|
|
# to be fixed, maybe with auto-detection?
|
|
cxx_builtin_include_directory: "/usr/lib/gcc/"
|
|
cxx_builtin_include_directory: "/usr/local/include"
|
|
cxx_builtin_include_directory: "/usr/include"
|
|
tool_path { name: "gcov" path: "/usr/bin/gcov" }
|
|
|
|
# C(++) compiles invoke the compiler (as that is the one knowing where
|
|
# to find libraries), but we provide LD so other rules can invoke the linker.
|
|
tool_path { name: "ld" path: "/usr/bin/ld" }
|
|
|
|
tool_path { name: "nm" path: "/usr/bin/nm" }
|
|
tool_path { name: "objcopy" path: "/usr/bin/objcopy" }
|
|
objcopy_embed_flag: "-I"
|
|
objcopy_embed_flag: "binary"
|
|
tool_path { name: "objdump" path: "/usr/bin/objdump" }
|
|
tool_path { name: "strip" path: "/usr/bin/strip" }
|
|
|
|
# Anticipated future default.
|
|
unfiltered_cxx_flag: "-no-canonical-prefixes"
|
|
|
|
# Make C++ compilation deterministic. Use linkstamping instead of these
|
|
# compiler symbols.
|
|
unfiltered_cxx_flag: "-Wno-builtin-macro-redefined"
|
|
unfiltered_cxx_flag: "-D__DATE__=\"redacted\""
|
|
unfiltered_cxx_flag: "-D__TIMESTAMP__=\"redacted\""
|
|
unfiltered_cxx_flag: "-D__TIME__=\"redacted\""
|
|
|
|
# Security hardening on by default.
|
|
# Conservative choice; -D_FORTIFY_SOURCE=2 may be unsafe in some cases.
|
|
# We need to undef it before redefining it as some distributions now have
|
|
# it enabled by default.
|
|
compiler_flag: "-U_FORTIFY_SOURCE"
|
|
compiler_flag: "-D_FORTIFY_SOURCE=1"
|
|
compiler_flag: "-fstack-protector"
|
|
compiler_flag: "-fPIE"
|
|
linker_flag: "-pie"
|
|
linker_flag: "-Wl,-z,relro,-z,now"
|
|
|
|
# Enable coloring even if there's no attached terminal. Bazel removes the
|
|
# escape sequences if --nocolor is specified. This isn't supported by gcc
|
|
# on Ubuntu 14.04.
|
|
# compiler_flag: "-fcolor-diagnostics"
|
|
|
|
# All warnings are enabled. Maybe enable -Werror as well?
|
|
compiler_flag: "-Wall"
|
|
# Enable a few more warnings that aren't part of -Wall.
|
|
compiler_flag: "-Wunused-but-set-parameter"
|
|
# But disable some that are problematic.
|
|
compiler_flag: "-Wno-free-nonheap-object" # has false positives
|
|
|
|
# Keep stack frames for debugging, even in opt mode.
|
|
compiler_flag: "-fno-omit-frame-pointer"
|
|
|
|
# Anticipated future default.
|
|
linker_flag: "-no-canonical-prefixes"
|
|
unfiltered_cxx_flag: "-fno-canonical-system-headers"
|
|
# Have gcc return the exit code from ld.
|
|
linker_flag: "-pass-exit-codes"
|
|
# Stamp the binary with a unique identifier.
|
|
linker_flag: "-Wl,--build-id=md5"
|
|
linker_flag: "-Wl,--hash-style=gnu"
|
|
# Gold linker only? Can we enable this by default?
|
|
# linker_flag: "-Wl,--warn-execstack"
|
|
# linker_flag: "-Wl,--detect-odr-violations"
|
|
|
|
# Include directory for cuda headers.
|
|
cxx_builtin_include_directory: "/usr/local/cuda%{cuda_version}/include"
|
|
|
|
compilation_mode_flags {
|
|
mode: DBG
|
|
# Enable debug symbols.
|
|
compiler_flag: "-g"
|
|
}
|
|
compilation_mode_flags {
|
|
mode: OPT
|
|
|
|
# No debug symbols.
|
|
# Maybe we should enable https://gcc.gnu.org/wiki/DebugFission for opt or
|
|
# even generally? However, that can't happen here, as it requires special
|
|
# handling in Bazel.
|
|
compiler_flag: "-g0"
|
|
|
|
# Conservative choice for -O
|
|
# -O3 can increase binary size and even slow down the resulting binaries.
|
|
# Profile first and / or use FDO if you need better performance than this.
|
|
compiler_flag: "-O2"
|
|
|
|
# Disable assertions
|
|
compiler_flag: "-DNDEBUG"
|
|
|
|
# Removal of unused code and data at link time (can this increase binary size in some cases?).
|
|
compiler_flag: "-ffunction-sections"
|
|
compiler_flag: "-fdata-sections"
|
|
linker_flag: "-Wl,--gc-sections"
|
|
}
|
|
linking_mode_flags { mode: DYNAMIC }
|
|
}
|
|
|
|
toolchain {
|
|
abi_version: "local"
|
|
abi_libc_version: "local"
|
|
builtin_sysroot: ""
|
|
compiler: "compiler"
|
|
host_system_name: "local"
|
|
needsPic: true
|
|
target_libc: "macosx"
|
|
target_cpu: "darwin"
|
|
target_system_name: "local"
|
|
toolchain_identifier: "local_darwin"
|
|
|
|
tool_path { name: "ar" path: "/usr/bin/libtool" }
|
|
tool_path { name: "compat-ld" path: "/usr/bin/ld" }
|
|
tool_path { name: "cpp" path: "/usr/bin/cpp" }
|
|
tool_path { name: "dwp" path: "/usr/bin/dwp" }
|
|
tool_path { name: "gcc" path: "clang/bin/crosstool_wrapper_driver_is_not_gcc" }
|
|
cxx_flag: "-std=c++11"
|
|
ar_flag: "-static"
|
|
ar_flag: "-s"
|
|
ar_flag: "-o"
|
|
linker_flag: "-lc++"
|
|
linker_flag: "-undefined"
|
|
linker_flag: "dynamic_lookup"
|
|
# TODO(ulfjack): This is wrong on so many levels. Figure out a way to auto-detect the proper
|
|
# setting from the local compiler, and also how to make incremental builds correct.
|
|
cxx_builtin_include_directory: "/"
|
|
tool_path { name: "gcov" path: "/usr/bin/gcov" }
|
|
tool_path { name: "ld" path: "/usr/bin/ld" }
|
|
tool_path { name: "nm" path: "/usr/bin/nm" }
|
|
tool_path { name: "objcopy" path: "/usr/bin/objcopy" }
|
|
objcopy_embed_flag: "-I"
|
|
objcopy_embed_flag: "binary"
|
|
tool_path { name: "objdump" path: "/usr/bin/objdump" }
|
|
tool_path { name: "strip" path: "/usr/bin/strip" }
|
|
|
|
# Anticipated future default.
|
|
unfiltered_cxx_flag: "-no-canonical-prefixes"
|
|
# Make C++ compilation deterministic. Use linkstamping instead of these
|
|
# compiler symbols.
|
|
unfiltered_cxx_flag: "-Wno-builtin-macro-redefined"
|
|
unfiltered_cxx_flag: "-D__DATE__=\"redacted\""
|
|
unfiltered_cxx_flag: "-D__TIMESTAMP__=\"redacted\""
|
|
unfiltered_cxx_flag: "-D__TIME__=\"redacted\""
|
|
|
|
# Security hardening on by default.
|
|
# Conservative choice; -D_FORTIFY_SOURCE=2 may be unsafe in some cases.
|
|
compiler_flag: "-D_FORTIFY_SOURCE=1"
|
|
compiler_flag: "-fstack-protector"
|
|
|
|
# Enable coloring even if there's no attached terminal. Bazel removes the
|
|
# escape sequences if --nocolor is specified.
|
|
compiler_flag: "-fcolor-diagnostics"
|
|
|
|
# All warnings are enabled. Maybe enable -Werror as well?
|
|
compiler_flag: "-Wall"
|
|
# Enable a few more warnings that aren't part of -Wall.
|
|
compiler_flag: "-Wthread-safety"
|
|
compiler_flag: "-Wself-assign"
|
|
|
|
# Keep stack frames for debugging, even in opt mode.
|
|
compiler_flag: "-fno-omit-frame-pointer"
|
|
|
|
# Anticipated future default.
|
|
linker_flag: "-no-canonical-prefixes"
|
|
|
|
# Include directory for cuda headers.
|
|
cxx_builtin_include_directory: "/usr/local/cuda%{cuda_version}/include"
|
|
|
|
compilation_mode_flags {
|
|
mode: DBG
|
|
# Enable debug symbols.
|
|
compiler_flag: "-g"
|
|
}
|
|
compilation_mode_flags {
|
|
mode: OPT
|
|
# No debug symbols.
|
|
# Maybe we should enable https://gcc.gnu.org/wiki/DebugFission for opt or even generally?
|
|
# However, that can't happen here, as it requires special handling in Bazel.
|
|
compiler_flag: "-g0"
|
|
|
|
# Conservative choice for -O
|
|
# -O3 can increase binary size and even slow down the resulting binaries.
|
|
# Profile first and / or use FDO if you need better performance than this.
|
|
compiler_flag: "-O2"
|
|
|
|
# Disable assertions
|
|
compiler_flag: "-DNDEBUG"
|
|
|
|
# Removal of unused code and data at link time (can this increase binary size in some cases?).
|
|
compiler_flag: "-ffunction-sections"
|
|
compiler_flag: "-fdata-sections"
|
|
}
|
|
}
|