Merge pull request #3731 from shrit/flags

Optimize more mlpack crosscompiled bindings for lower binary footprint
This commit is contained in:
Omar Shrit
2024-07-15 15:33:21 +02:00
committed by GitHub
3 changed files with 55 additions and 27 deletions
+1
View File
@@ -28,6 +28,7 @@ macro(search_openblas version)
get_deps(https://github.com/xianyi/OpenBLAS/releases/download/v${version}/OpenBLAS-${version}.tar.gz OpenBLAS OpenBLAS-${version}.tar.gz)
if (NOT MSVC)
if (NOT EXISTS "${CMAKE_BINARY_DIR}/deps/OpenBLAS-${version}/libopenblas.a")
set(ENV{COMMON_OPT} "${CMAKE_OPENBLAS_FLAGS}") # Pass our flags to OpenBLAS
execute_process(COMMAND make TARGET=${OPENBLAS_TARGET} BINARY=${OPENBLAS_BINARY} HOSTCC=gcc CC=${CMAKE_C_COMPILER} FC=${CMAKE_FORTRAN_COMPILER} NO_SHARED=1
WORKING_DIRECTORY ${CMAKE_BINARY_DIR}/deps/OpenBLAS-${version})
endif()
+7 -3
View File
@@ -249,8 +249,12 @@ if (DEBUG)
else()
add_definitions(-DNDEBUG)
if (NOT MSVC)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -O3")
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -std=c99 -O3")
if (NOT CMAKE_CROSSCOMPILING)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -O3")
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -std=c99 -O3")
else()
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -std=c99")
endif()
else ()
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /O3")
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} /O3")
@@ -283,7 +287,7 @@ endif()
# Download and compile OpenBLAS if we are cross compiling mlpack for a specific
# architecture. The function takes the version of OpenBLAS as variable.
if (CMAKE_CROSSCOMPILING)
search_openblas(0.3.13)
search_openblas(0.3.26)
endif()
if (NOT DOWNLOAD_DEPENDENCIES)
+47 -24
View File
@@ -4,63 +4,86 @@
# footprints.
# Set generic minimization flags for all platforms.
# These flags are the same for all cross-compilation cases.
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Os -fdata-sections -ffunction-sections")
# These flags are the same for all cross-compilation cases and they are
# mainly to reduce the binary footprint.
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Os -s -fdata-sections -ffunction-sections")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fomit-frame-pointer -fno-unwind-tables")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fno-asynchronous-unwind-tables -fvisibility=hidden")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fshort-enums -finline-small-functions")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -findirect-inlining -fno-common")
#-flto -fuse-ld=gold # There is an issue with gold link when compiling on
# Ubuntu 16. At that point gcc linker did not integrate the flto support
# inside and it was a separate plugin that need to be added. Therefore,
# this can be added when mlpack Azure CI moves toward Ubuntu 20.
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fmerge-all-constants -fno-ident")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fno-unroll-loops -fno-math-errno")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fno-stack-protector")
set(CMAKE_OPENBLAS_FLAGS "${CMAKE_CXX_FLAGS}") # OpenBLAS does not supoport flto
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -flto")
set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -Wl,--hash-style=gnu -Wl,--build-id=none")
set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -Wl,-z,norelro")
set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -Wl,--gc-sections")
## Keep the following flag in comment, they might be relevant in the case of MCU's
#set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wl,-nmagic,-Bsymbolic -nostartfiles")
set(BOARD_NAME "" CACHE STRING "Specify Board name to optimize for.")
string(TOUPPER ${BOARD_NAME} BOARD)
# Set specific platforms CMAKE CXX flags.
if(BOARD MATCHES "RPI0" OR BOARD MATCHES "RPI1")
if(BOARD MATCHES "RPI0" OR BOARD MATCHES "RPI1" OR BOARD MATCHES "ARM11")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mtune=arm1176jzf-s")
set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -Wl,--gc-sections")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mcpu=arm1176jzf-s -mfloat-abi=hard -mfpu=vfp")
set(OPENBLAS_TARGET "ARMV6")
set(OPENBLAS_BINARY "32")
elseif(BOARD MATCHES "RPI2")
elseif(BOARD MATCHES "RPI2" OR BOARD MATCHES "CORTEXA7")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mtune=cortex-a7")
set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -Wl,--gc-sections")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mfloat-abi=hard -mfpu=neon-vfpv4")
set(OPENBLAS_TARGET "ARMV7")
set(OPENBLAS_BINARY "32")
elseif(BOARD MATCHES "RPI3")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mtune=cortex-a53")
set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -Wl,--gc-sections")
elseif(BOARD MATCHES "CORTEXA8")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mtune=cortex-a8")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mfloat-abi=hard -mfpu=neon")
set(OPENBLAS_TARGET "ARMV7")
set(OPENBLAS_BINARY "32")
elseif(BOARD MATCHES "CORTEXA9")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mtune=cortex-a9")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mfloat-abi=hard -mfpu=neon")
set(OPENBLAS_TARGET "CORTEXA9")
set(OPENBLAS_BINARY "32")
elseif(BOARD MATCHES "CORTEXA15")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mtune=cortex-a15")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mfloat-abi=hard -mfpu=neon")
set(OPENBLAS_TARGET "CORTEXA15")
set(OPENBLAS_BINARY "32")
elseif(BOARD MATCHES "RPI3" OR BOARD MATCHES "CORTEXA53")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mtune=cortex-a53 -ftree-vectorize")
set(OPENBLAS_TARGET "CORTEXA53")
set(OPENBLAS_BINARY "64")
elseif(BOARD MATCHES "RPI4")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mtune=cortex-a72")
set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -Wl,--gc-sections")
elseif(BOARD MATCHES "RPI4" OR BOARD MATCHES "CORTEXA72")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mtune=cortex-a72 -ftree-vectorize")
set(OPENBLAS_TARGET "CORTEXA72")
set(OPENBLAS_BINARY "64")
elseif(BOARD MATCHES "JETSONAGX" OR BOARD MATCHES "CORTEXA76")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mtune=cortex-a76 -ftree-vectorize")
set(OPENBLAS_TARGET "CORTEXA76")
set(OPENBLAS_BINARY "64")
elseif(BOARD MATCHES "BV")
set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -Wl,--gc-sections")
set(OPENBLAS_TARGET "RISCV64_GENERIC")
set(OPENBLAS_BINARY "64")
elseif(BOARD MATCHES "JETSONAGX")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -matune=cortex-a76")
set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -Wl,--gc-sections")
set(OPENBLAS_TARGET "ARM8")
elseif(BOARD MATCHES "C906")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mtune=thead-c906")
set(OPENBLAS_TARGET "RISCV64_GENERIC")
set(OPENBLAS_BINARY "64")
elseif(BOARD MATCHES "x280")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mtune=sifive-x280")
set(OPENBLAS_TARGET "x280")
set(OPENBLAS_BINARY "64")
elseif(BOARD MATCHES "KATAMI")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=pentium3")
set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -Wl,--gc-sections")
set(OPENBLAS_TARGET "KATAMI")
set(OPENBLAS_BINARY "32")
elseif(BOARD MATCHES "COPPERMINE")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=pentium3")
set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -Wl,--gc-sections")
set(OPENBLAS_TARGET "COPPERMINE")
set(OPENBLAS_BINARY "32")
elseif(BOARD MATCHES "NORTHWOOD")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=pentium4")
set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -Wl,--gc-sections")
set(OPENBLAS_TARGET "NORTHWOOD")
set(OPENBLAS_BINARY "32")
elseif(BOARD)