1
0
mirror of https://github.com/postgres/postgres.git synced 2025-07-27 12:41:57 +03:00

Use native CRC instructions on 64-bit LoongArch

As with the Intel and Arm CRC instructions, compiler intrinsics for
them must be supported by the compiler. In contrast, no runtime check
is needed. Aligned memory access is faster, so use the Arm coding as
a model.

YANG Xudong

Discussion: https://postgr.es/m/b522a0c5-e3b2-99cc-6387-58134fb88cbe%40ymatrix.cn
This commit is contained in:
John Naylor
2023-08-10 11:36:15 +07:00
parent fa2e874946
commit 4d14ccd6af
8 changed files with 240 additions and 17 deletions

View File

@ -2099,6 +2099,12 @@ if test x"$pgac_armv8_crc32c_intrinsics" != x"yes"; then
PGAC_ARMV8_CRC32C_INTRINSICS([-march=armv8-a+crc])
fi
# Check for LoongArch CRC intrinsics to do CRC calculations.
#
# Check if __builtin_loongarch_crcc_* intrinsics can be used
# with the default compiler flags.
PGAC_LOONGARCH_CRC32C_INTRINSICS()
AC_SUBST(CFLAGS_CRC)
# Select CRC-32C implementation.
@ -2115,9 +2121,12 @@ AC_SUBST(CFLAGS_CRC)
# we're not targeting such a processor, but can nevertheless produce code that
# uses the CRC instructions, compile both, and select at runtime.
#
# You can override this logic by setting the appropriate USE_*_CRC32 flag to 1
# You can skip the runtime check by setting the appropriate USE_*_CRC32 flag to 1
# in the template or configure command line.
if test x"$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
#
# If we are targeting a LoongArch processor, CRC instructions are
# always available (at least on 64 bit), so no runtime check is needed.
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"$USE_ARMV8_CRC32C_WITH_RUNTIME_CHECK" = x"" && test x"$USE_LOONGARCH_CRC32C" = 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
@ -2135,10 +2144,15 @@ if test x"$USE_SLICING_BY_8_CRC32C" = x"" && test x"$USE_SSE42_CRC32C" = x"" &&
if test x"$pgac_armv8_crc32c_intrinsics" = x"yes"; then
USE_ARMV8_CRC32C_WITH_RUNTIME_CHECK=1
else
# fall back to slicing-by-8 algorithm, which doesn't require any
# special CPU support.
USE_SLICING_BY_8_CRC32C=1
fi
# LoongArch CRCC instructions.
if test x"$pgac_loongarch_crc32c_intrinsics" = x"yes"; then
USE_LOONGARCH_CRC32C=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
@ -2166,9 +2180,15 @@ else
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)
if test x"$USE_LOONGARCH_CRC32C" = x"1"; then
AC_DEFINE(USE_LOONGARCH_CRC32C, 1, [Define to 1 to use LoongArch CRCC instructions.])
PG_CRC32C_OBJS="pg_crc32c_loongarch.o"
AC_MSG_RESULT(LoongArch CRCC instructions)
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