RepoMirrors
/
ceph
mirror of https://github.com/ceph/ceph
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
ceph/m4/ax_arm.m4

42 lines
1.5 KiB
Plaintext
Raw Normal View History

autotools: ARM/AArch64 NEON detection similar to x86
2014-09-09 07:47:16 +00:00
AC_DEFUN([AX_ARM_FEATURES],
[
AC_REQUIRE([AC_CANONICAL_HOST])
case $target_cpu in
arm*)
AX_CHECK_COMPILE_FLAG(-mfpu=neon, ax_cv_support_neon_ext=yes, [])
if test x"$ax_cv_support_neon_ext" = x"yes"; then
ARM_NEON_FLAGS="-mfpu=neon -DARM_NEON"
AC_SUBST(ARM_NEON_FLAGS)
ARM_FLAGS="$ARM_FLAGS $ARM_NEON_FLAGS"
AC_DEFINE(HAVE_NEON,,[Support NEON instructions])
fi
;;
aarch64*)
crc32c: add aarch64 optimized crc32c implementation ARMv8 defines a set of optional CRC32/CRC32C instructions. This patch defines an optimized function that uses these instructions when available rather than table-based lookup. Optimized function based on a Hadoop patch by Ed Nevill. Autotools updated to check for compiler support. Optimized function is selected at runtime based on HWCAP_CRC32. Added crc32c "performance" unit test and arch unit test. Tested on AMD Seattle. Passes all crc32c unit tests. Unit test shows ~4x performance increase versus sctp. Signed-off-by: Yazen Ghannam <yazen.ghannam@linaro.org> Reviewed-by: Steve Capper <steve.capper@linaro.org>
2015-01-21 03:29:05 +00:00
AX_CHECK_COMPILE_FLAG(-march=armv8-a, ax_cv_support_armv8=yes, [])
if test x"$ax_cv_support_armv8" = x"yes"; then
ARM_ARCH_FLAGS="-march=armv8-a"
ARM_DEFINE_FLAGS="-DARCH_AARCH64"
fi
autotools: ARM/AArch64 NEON detection similar to x86
2014-09-09 07:47:16 +00:00
AX_CHECK_COMPILE_FLAG(-march=armv8-a+simd, ax_cv_support_neon_ext=yes, [])
if test x"$ax_cv_support_neon_ext" = x"yes"; then
crc32c: add aarch64 optimized crc32c implementation ARMv8 defines a set of optional CRC32/CRC32C instructions. This patch defines an optimized function that uses these instructions when available rather than table-based lookup. Optimized function based on a Hadoop patch by Ed Nevill. Autotools updated to check for compiler support. Optimized function is selected at runtime based on HWCAP_CRC32. Added crc32c "performance" unit test and arch unit test. Tested on AMD Seattle. Passes all crc32c unit tests. Unit test shows ~4x performance increase versus sctp. Signed-off-by: Yazen Ghannam <yazen.ghannam@linaro.org> Reviewed-by: Steve Capper <steve.capper@linaro.org>
2015-01-21 03:29:05 +00:00
ARM_ARCH_FLAGS="$ARM_ARCH_FLAGS+simd"
ARM_DEFINE_FLAGS="$ARM_DEFINE_FLAGS -DARM_NEON"
autotools: ARM/AArch64 NEON detection similar to x86
2014-09-09 07:47:16 +00:00
ARM_NEON_FLAGS="-march=armv8-a+simd -DARCH_AARCH64 -DARM_NEON"
AC_DEFINE(HAVE_NEON,,[Support NEON instructions])
crc32c: add aarch64 optimized crc32c implementation ARMv8 defines a set of optional CRC32/CRC32C instructions. This patch defines an optimized function that uses these instructions when available rather than table-based lookup. Optimized function based on a Hadoop patch by Ed Nevill. Autotools updated to check for compiler support. Optimized function is selected at runtime based on HWCAP_CRC32. Added crc32c "performance" unit test and arch unit test. Tested on AMD Seattle. Passes all crc32c unit tests. Unit test shows ~4x performance increase versus sctp. Signed-off-by: Yazen Ghannam <yazen.ghannam@linaro.org> Reviewed-by: Steve Capper <steve.capper@linaro.org>
2015-01-21 03:29:05 +00:00
AC_SUBST(ARM_NEON_FLAGS)
fi
AX_CHECK_COMPILE_FLAG(-march=armv8-a+crc, ax_cv_support_crc_ext=yes, [])
if test x"$ax_cv_support_crc_ext" = x"yes"; then
ARM_ARCH_FLAGS="$ARM_ARCH_FLAGS+crc"
ARM_CRC_FLAGS="-march=armv8-a+crc -DARCH_AARCH64"
AC_DEFINE(HAVE_ARMV8_CRC,,[Support ARMv8 CRC instructions])
AC_SUBST(ARM_CRC_FLAGS)
autotools: ARM/AArch64 NEON detection similar to x86
2014-09-09 07:47:16 +00:00
fi
crc32c: add aarch64 optimized crc32c implementation ARMv8 defines a set of optional CRC32/CRC32C instructions. This patch defines an optimized function that uses these instructions when available rather than table-based lookup. Optimized function based on a Hadoop patch by Ed Nevill. Autotools updated to check for compiler support. Optimized function is selected at runtime based on HWCAP_CRC32. Added crc32c "performance" unit test and arch unit test. Tested on AMD Seattle. Passes all crc32c unit tests. Unit test shows ~4x performance increase versus sctp. Signed-off-by: Yazen Ghannam <yazen.ghannam@linaro.org> Reviewed-by: Steve Capper <steve.capper@linaro.org>
2015-01-21 03:29:05 +00:00
ARM_FLAGS="$ARM_ARCH_FLAGS $ARM_DEFINE_FLAGS"
autotools: ARM/AArch64 NEON detection similar to x86
2014-09-09 07:47:16 +00:00
;;
esac
AC_SUBST(ARM_FLAGS)
])