From 5980f1884fc911af120c98ad440b9546ed9012c5 Mon Sep 17 00:00:00 2001 From: Tom Lane Date: Mon, 25 Nov 2024 12:50:17 -0500 Subject: [PATCH] Update configure probes for CFLAGS needed for ARM CRC instructions. On ARM platforms where the baseline CPU target lacks CRC instructions, we need to supply a -march flag to persuade the compiler to compile such instructions. It turns out that our existing choice of "-march=armv8-a+crc" has not worked for some time, because recent gcc will interpret that as selecting software floating point, and then will spit up if the platform requires hard-float ABI, as most do nowadays. The end result was to silently fall back to software CRC, which isn't very desirable since in practice almost all currently produced ARM chips do have hardware CRC. We can fix this by using "-march=armv8-a+crc+simd" to enable the correct ABI choice. (This has no impact on the code actually generated, since neither of the files we compile with this flag does any floating-point stuff, let alone SIMD.) Keep the test for "-march=armv8-a+crc" since that's required for soft-float ABI, but try that second since most platforms we're likely to build on use hard-float. Since this isn't working as-intended on the last several years' worth of gcc releases, back-patch to all supported branches. Discussion: https://postgr.es/m/4496616.iHFcN1HehY@portable-bastien --- configure | 47 +++++++++++++++++++++++++++++++++++++++++++++-- configure.ac | 8 ++++++-- meson.build | 7 +++++++ 3 files changed, 58 insertions(+), 4 deletions(-) diff --git a/configure b/configure index 62bf4c7655b..199d666aa73 100755 --- a/configure +++ b/configure @@ -17482,7 +17482,8 @@ rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext # Check for ARMv8 CRC Extension intrinsics to do CRC calculations. # # First check if __crc32c* intrinsics can be used with the default compiler -# flags. If not, check if adding -march=armv8-a+crc flag helps. +# flags. If not, check if adding "-march=armv8-a+crc+simd" flag helps. +# On systems using soft-float ABI, "-march=armv8-a+crc" is required instead. # CFLAGS_CRC is set if the extra flag is required. { $as_echo "$as_me:${as_lineno-$LINENO}: checking for __crc32cb, __crc32ch, __crc32cw, and __crc32cd with CFLAGS=" >&5 $as_echo_n "checking for __crc32cb, __crc32ch, __crc32cw, and __crc32cd with CFLAGS=... " >&6; } @@ -17525,7 +17526,48 @@ if test x"$pgac_cv_armv8_crc32c_intrinsics_" = x"yes"; then fi if test x"$pgac_armv8_crc32c_intrinsics" != x"yes"; then - { $as_echo "$as_me:${as_lineno-$LINENO}: checking for __crc32cb, __crc32ch, __crc32cw, and __crc32cd with CFLAGS=-march=armv8-a+crc" >&5 + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for __crc32cb, __crc32ch, __crc32cw, and __crc32cd with CFLAGS=-march=armv8-a+crc+simd" >&5 +$as_echo_n "checking for __crc32cb, __crc32ch, __crc32cw, and __crc32cd with CFLAGS=-march=armv8-a+crc+simd... " >&6; } +if ${pgac_cv_armv8_crc32c_intrinsics__march_armv8_apcrcpsimd+:} false; then : + $as_echo_n "(cached) " >&6 +else + pgac_save_CFLAGS=$CFLAGS +CFLAGS="$pgac_save_CFLAGS -march=armv8-a+crc+simd" +cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ +#include +int +main () +{ +unsigned int crc = 0; + crc = __crc32cb(crc, 0); + crc = __crc32ch(crc, 0); + crc = __crc32cw(crc, 0); + crc = __crc32cd(crc, 0); + /* return computed value, to prevent the above being optimized away */ + return crc == 0; + ; + return 0; +} +_ACEOF +if ac_fn_c_try_link "$LINENO"; then : + pgac_cv_armv8_crc32c_intrinsics__march_armv8_apcrcpsimd=yes +else + pgac_cv_armv8_crc32c_intrinsics__march_armv8_apcrcpsimd=no +fi +rm -f core conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +CFLAGS="$pgac_save_CFLAGS" +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_armv8_crc32c_intrinsics__march_armv8_apcrcpsimd" >&5 +$as_echo "$pgac_cv_armv8_crc32c_intrinsics__march_armv8_apcrcpsimd" >&6; } +if test x"$pgac_cv_armv8_crc32c_intrinsics__march_armv8_apcrcpsimd" = x"yes"; then + CFLAGS_CRC="-march=armv8-a+crc+simd" + pgac_armv8_crc32c_intrinsics=yes +fi + + if test x"$pgac_armv8_crc32c_intrinsics" != x"yes"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for __crc32cb, __crc32ch, __crc32cw, and __crc32cd with CFLAGS=-march=armv8-a+crc" >&5 $as_echo_n "checking for __crc32cb, __crc32ch, __crc32cw, and __crc32cd with CFLAGS=-march=armv8-a+crc... " >&6; } if ${pgac_cv_armv8_crc32c_intrinsics__march_armv8_apcrc+:} false; then : $as_echo_n "(cached) " >&6 @@ -17565,6 +17607,7 @@ if test x"$pgac_cv_armv8_crc32c_intrinsics__march_armv8_apcrc" = x"yes"; then pgac_armv8_crc32c_intrinsics=yes fi + fi fi # Check for LoongArch CRC intrinsics to do CRC calculations. diff --git a/configure.ac b/configure.ac index c7d01168814..4f56bb5062e 100644 --- a/configure.ac +++ b/configure.ac @@ -2088,11 +2088,15 @@ AC_COMPILE_IFELSE([AC_LANG_PROGRAM([], [ # Check for ARMv8 CRC Extension intrinsics to do CRC calculations. # # First check if __crc32c* intrinsics can be used with the default compiler -# flags. If not, check if adding -march=armv8-a+crc flag helps. +# flags. If not, check if adding "-march=armv8-a+crc+simd" flag helps. +# On systems using soft-float ABI, "-march=armv8-a+crc" is required instead. # CFLAGS_CRC is set if the extra flag is required. PGAC_ARMV8_CRC32C_INTRINSICS([]) if test x"$pgac_armv8_crc32c_intrinsics" != x"yes"; then - PGAC_ARMV8_CRC32C_INTRINSICS([-march=armv8-a+crc]) + PGAC_ARMV8_CRC32C_INTRINSICS([-march=armv8-a+crc+simd]) + if test x"$pgac_armv8_crc32c_intrinsics" != x"yes"; then + PGAC_ARMV8_CRC32C_INTRINSICS([-march=armv8-a+crc]) + fi fi # Check for LoongArch CRC intrinsics to do CRC calculations. diff --git a/meson.build b/meson.build index 26b8b47d3ef..b55faea7f5f 100644 --- a/meson.build +++ b/meson.build @@ -2284,6 +2284,13 @@ int main(void) # Use ARM CRC Extension unconditionally cdata.set('USE_ARMV8_CRC32C', 1) have_optimized_crc = true + elif cc.links(prog, name: '__crc32cb, __crc32ch, __crc32cw, and __crc32cd with -march=armv8-a+crc+simd', + args: test_c_args + ['-march=armv8-a+crc+simd']) + # Use ARM CRC Extension, with runtime check + cflags_crc += '-march=armv8-a+crc+simd' + cdata.set('USE_ARMV8_CRC32C', false) + cdata.set('USE_ARMV8_CRC32C_WITH_RUNTIME_CHECK', 1) + have_optimized_crc = true elif cc.links(prog, name: '__crc32cb, __crc32ch, __crc32cw, and __crc32cd with -march=armv8-a+crc', args: test_c_args + ['-march=armv8-a+crc']) # Use ARM CRC Extension, with runtime check