mirror of
https://github.com/postgres/postgres.git
synced 2025-07-30 11:03:19 +03:00
Use ARMv8 CRC instructions where available.
ARMv8 introduced special CPU instructions for calculating CRC-32C. Use them, when available, for speed. Like with the similar Intel CRC instructions, several factors affect whether the instructions can be used. The compiler intrinsics for them must be supported by the compiler, and the instructions must be supported by the target architecture. If the compilation target architecture does not support the instructions, but adding "-march=armv8-a+crc" makes them available, then we compile the code with a runtime check to determine if the host we're running on supports them or not. For the runtime check, use glibc getauxval() function. Unfortunately, that's not very portable, but I couldn't find any more portable way to do it. If getauxval() is not available, the CRC instructions will still be used if the target architecture supports them without any additional compiler flags, but the runtime check will not be available. Original patch by Yuqi Gu, heavily modified by me. Reviewed by Andres Freund, Thomas Munro. Discussion: https://www.postgresql.org/message-id/HE1PR0801MB1323D171938EABC04FFE7FA9E3110%40HE1PR0801MB1323.eurprd08.prod.outlook.com
This commit is contained in:
Heikki Linnakangas
87
configure.in
87
configure.in
@ -2003,28 +2003,73 @@ AC_COMPILE_IFELSE([AC_LANG_PROGRAM([], [
|
||||
#endif
|
||||
])], [SSE4_2_TARGETED=1])
|
||||
|
||||
# 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.
|
||||
# CFLAGS_ARMV8_CRC32C 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])
|
||||
fi
|
||||
AC_SUBST(CFLAGS_ARMV8_CRC32C)
|
||||
|
||||
# In order to detect at runtime, if the ARM CRC Extension is available,
|
||||
# we will do "getauxval(AT_HWCAP) & HWCAP_CRC32". Check if we have
|
||||
# everything we need for that.
|
||||
AC_CHECK_FUNCS([getauxval])
|
||||
AC_COMPILE_IFELSE([AC_LANG_PROGRAM([
|
||||
#include <sys/auxv.h>
|
||||
#include <asm/hwcap.h>
|
||||
], [
|
||||
#ifndef AT_HWCAP
|
||||
#error AT_HWCAP not defined
|
||||
#endif
|
||||
#ifndef HWCAP_CRC32
|
||||
#error HWCAP_CRC32 not defined
|
||||
#endif
|
||||
])], [HAVE_HWCAP_CRC32=1])
|
||||
|
||||
# Select CRC-32C implementation.
|
||||
#
|
||||
# If we are targeting a processor that has SSE 4.2 instructions, we can use the
|
||||
# special CRC instructions for calculating CRC-32C. If we're not targeting such
|
||||
# a processor, but we can nevertheless produce code that uses the SSE
|
||||
# intrinsics, perhaps with some extra CFLAGS, compile both implementations and
|
||||
# select which one to use at runtime, depending on whether SSE 4.2 is supported
|
||||
# by the processor we're running on.
|
||||
# If we are targeting a processor that has Intel SSE 4.2 instructions, we can
|
||||
# use the special CRC instructions for calculating CRC-32C. If we're not
|
||||
# targeting such a processor, but we can nevertheless produce code that uses
|
||||
# the SSE intrinsics, perhaps with some extra CFLAGS, compile both
|
||||
# implementations and select which one to use at runtime, depending on whether
|
||||
# SSE 4.2 is supported by the processor we're running on.
|
||||
#
|
||||
# Similarly, if we are targeting an ARM processor that has the CRC
|
||||
# instructions that are part of the ARMv8 CRC Extension, use them. And if
|
||||
# we're not targeting such a processor, but can nevertheless produce code that
|
||||
# uses the CRC instructions, compile both, and select at runtime.
|
||||
#
|
||||
# You can override this logic by setting the appropriate USE_*_CRC32 flag to 1
|
||||
# in the template or configure command line.
|
||||
if test x"$USE_SSE42_CRC32C" = x"" && test x"$USE_SSE42_CRC32C_WITH_RUNTIME_CHECK" = x"" && test x"$USE_SLICING_BY_8_CRC32C" = x""; then
|
||||
if test x"$USE_SLICING_BY_8_CRC32C" = x"" && test x"$USE_SSE42_CRC32C" = x"" && test x"$USE_SSE42_CRC32C_WITH_RUNTIME_CHECK" = x"" && test x"$USE_ARMV8_CRC32C" = x"" && test x"$USE_ARMV8_CRC32C_WITH_RUNTIME_CHECK" = x""; then
|
||||
# Use Intel SSE 4.2 if available.
|
||||
if test x"$pgac_sse42_crc32_intrinsics" = x"yes" && test x"$SSE4_2_TARGETED" = x"1" ; then
|
||||
USE_SSE42_CRC32C=1
|
||||
else
|
||||
# the CPUID instruction is needed for the runtime check.
|
||||
# Intel SSE 4.2, with runtime check? The CPUID instruction is needed for
|
||||
# the runtime check.
|
||||
if test x"$pgac_sse42_crc32_intrinsics" = x"yes" && (test x"$pgac_cv__get_cpuid" = x"yes" || test x"$pgac_cv__cpuid" = x"yes"); then
|
||||
USE_SSE42_CRC32C_WITH_RUNTIME_CHECK=1
|
||||
else
|
||||
# fall back to slicing-by-8 algorithm which doesn't require any special
|
||||
# CPU support.
|
||||
USE_SLICING_BY_8_CRC32C=1
|
||||
# Use ARM CRC Extension if available.
|
||||
if test x"$pgac_armv8_crc32c_intrinsics" = x"yes" && test x"$CFLAGS_ARMV8_CRC32C" = x""; then
|
||||
USE_ARMV8_CRC32C=1
|
||||
else
|
||||
# ARM CRC Extension, with runtime check? The getauxval() function and
|
||||
# HWCAP_CRC32 are needed for the runtime check.
|
||||
if test x"$pgac_armv8_crc32c_intrinsics" = x"yes" && test x"$ac_cv_func_getauxval" = x"yes" && test x"$HAVE_HWCAP_CRC32" = x"1"; then
|
||||
USE_ARMV8_CRC32C_WITH_RUNTIME_CHECK=1
|
||||
else
|
||||
# fall back to slicing-by-8 algorithm, which doesn't require any
|
||||
# special CPU support.
|
||||
USE_SLICING_BY_8_CRC32C=1
|
||||
fi
|
||||
fi
|
||||
fi
|
||||
fi
|
||||
fi
|
||||
@ -2038,12 +2083,24 @@ if test x"$USE_SSE42_CRC32C" = x"1"; then
|
||||
else
|
||||
if test x"$USE_SSE42_CRC32C_WITH_RUNTIME_CHECK" = x"1"; then
|
||||
AC_DEFINE(USE_SSE42_CRC32C_WITH_RUNTIME_CHECK, 1, [Define to 1 to use Intel SSE 4.2 CRC instructions with a runtime check.])
|
||||
PG_CRC32C_OBJS="pg_crc32c_sse42.o pg_crc32c_sb8.o pg_crc32c_choose.o"
|
||||
PG_CRC32C_OBJS="pg_crc32c_sse42.o pg_crc32c_sb8.o pg_crc32c_sse42_choose.o"
|
||||
AC_MSG_RESULT(SSE 4.2 with runtime check)
|
||||
else
|
||||
AC_DEFINE(USE_SLICING_BY_8_CRC32C, 1, [Define to 1 to use software CRC-32C implementation (slicing-by-8).])
|
||||
PG_CRC32C_OBJS="pg_crc32c_sb8.o"
|
||||
AC_MSG_RESULT(slicing-by-8)
|
||||
if test x"$USE_ARMV8_CRC32C" = x"1"; then
|
||||
AC_DEFINE(USE_ARMV8_CRC32C, 1, [Define to 1 to use ARMv8 CRC Extension.])
|
||||
PG_CRC32C_OBJS="pg_crc32c_armv8.o"
|
||||
AC_MSG_RESULT(ARMv8 CRC instructions)
|
||||
else
|
||||
if test x"$USE_ARMV8_CRC32C_WITH_RUNTIME_CHECK" = x"1"; then
|
||||
AC_DEFINE(USE_ARMV8_CRC32C_WITH_RUNTIME_CHECK, 1, [Define to 1 to use ARMv8 CRC Extension with a runtime check.])
|
||||
PG_CRC32C_OBJS="pg_crc32c_armv8.o pg_crc32c_sb8.o pg_crc32c_armv8_choose.o"
|
||||
AC_MSG_RESULT(ARMv8 CRC instructions with runtime check)
|
||||
else
|
||||
AC_DEFINE(USE_SLICING_BY_8_CRC32C, 1, [Define to 1 to use software CRC-32C implementation (slicing-by-8).])
|
||||
PG_CRC32C_OBJS="pg_crc32c_sb8.o"
|
||||
AC_MSG_RESULT(slicing-by-8)
|
||||
fi
|
||||
fi
|
||||
fi
|
||||
fi
|
||||
AC_SUBST(PG_CRC32C_OBJS)
|
||||
|
||||
Reference in New Issue
Block a user