From e5f721d017e4431a32e2605639afea64bf11f52e Mon Sep 17 00:00:00 2001 From: John Naylor Date: Fri, 28 Feb 2025 16:27:30 +0700 Subject: [PATCH v13 2/3] Inline CRC computation for fixed-length input Use a simplified copy of the loop in pg_crc32c_sse42.c to avoid moving code to a separate header. --- src/include/port/pg_crc32c.h | 33 ++++++++++++++++++++++++++++++++- 1 file changed, 32 insertions(+), 1 deletion(-) diff --git a/src/include/port/pg_crc32c.h b/src/include/port/pg_crc32c.h index 65ebeacf4b1..b9f0a8c7cca 100644 --- a/src/include/port/pg_crc32c.h +++ b/src/include/port/pg_crc32c.h @@ -43,12 +43,43 @@ typedef uint32 pg_crc32c; #if defined(USE_SSE42_CRC32C) /* Use Intel SSE4.2 instructions. */ + +#include + #define COMP_CRC32C(crc, data, len) \ - ((crc) = pg_comp_crc32c_sse42((crc), (data), (len))) + ((crc) = pg_comp_crc32c_dispatch((crc), (data), (len))) #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF) extern pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len); +pg_attribute_no_sanitize_alignment() +static inline +pg_crc32c +pg_comp_crc32c_dispatch(pg_crc32c crc, const void *data, size_t len) +{ + if (__builtin_constant_p(len)) + { + const unsigned char *p = data; + + /* + * For constant inputs, inline the computation to avoid the + * indirect function call. This also allows the compiler to unroll + * loops for small inputs. + */ +#if SIZEOF_VOID_P >= 8 + for (; len >= 8; p += 8, len -= 8) + crc = _mm_crc32_u64(crc, *(const uint64 *) p); +#endif + for (; len >= 4; p += 4, len -= 4) + crc = _mm_crc32_u32(crc, *(const uint32 *) p); + for (; len > 0; --len) + crc = _mm_crc32_u8(crc, *p++); + return crc; + } + else + return pg_comp_crc32c_sse42(crc, data, len); +} + #elif defined(USE_ARMV8_CRC32C) /* Use ARMv8 CRC Extension instructions. */ -- 2.48.1