v6-0001-Enable-autovectorizing-pg_checksum_block-with-AVX2-runtime-detection.patch

From 5ac0e8ce0c3cdb973044b70a7b7f8838981ac974 Mon Sep 17 00:00:00 2001
From: Andrew Kim <andrew.kim@intel.com>
Date: Thu, 16 Oct 2025 19:39:48 -0700
Subject: [PATCH] Enable autovectorizing pg_checksum_block with AVX2 runtime
 detection

Add SIMD-optimized checksum calculation using AVX2 instructions when
available, with automatic fallback to portable implementation. Uses
__builtin_cpu_supports() for runtime CPU feature detection.

Key improvements:
- Consolidate checksum logic into single src/port/checksum.c file
- Implement safe function pointer dispatch instead of runtime patching
- Remove complex macros in favor of explicit function declarations
- Add comprehensive AVX2 compiler support detection in configure
- Maintain full backward compatibility on non-AVX2 systems

Performance testing shows significant improvement in checksum calculation
throughput on AVX2-capable processors while maintaining code safety
and PostgreSQL coding standards compliance.

Addresses reviewer feedback on code organization, safety, and maintainability.
---
 config/c-compiler.m4                |  31 +++++
 configure                           |  52 +++++++
 configure.ac                        |   9 ++
 meson.build                         |  28 ++++
 src/backend/storage/page/checksum.c |   6 +-
 src/include/pg_config.h.in          |   3 +
 src/include/storage/checksum_impl.h |  82 ++---------
 src/port/Makefile                   |   1 +
 src/port/checksum.c                 | 203 ++++++++++++++++++++++++++++
 src/port/meson.build                |   1 +
 10 files changed, 342 insertions(+), 74 deletions(-)
 create mode 100644 src/port/checksum.c

diff --git a/config/c-compiler.m4 b/config/c-compiler.m4
index 236a59e8536..bcc1398d51a 100644
--- a/config/c-compiler.m4
+++ b/config/c-compiler.m4
@@ -711,6 +711,37 @@ fi
 undefine([Ac_cachevar])dnl
 ])# PGAC_XSAVE_INTRINSICS
 
+# PGAC_AVX2_SUPPORT
+# -----------------------------
+# Check if the compiler supports AVX2 in attribute((target))
+# and using AVX2 intrinsics in those functions
+#
+# If the intrinsics are supported, sets pgac_avx2_support.
+AC_DEFUN([PGAC_AVX2_SUPPORT],
+[define([Ac_cachevar], [AS_TR_SH([pgac_cv_avx2_support])])dnl
+AC_CACHE_CHECK([for AVX2 support], [Ac_cachevar],
+[AC_LINK_IFELSE([AC_LANG_PROGRAM([#include <immintrin.h>
+    #include <stdint.h>
+    #if defined(__has_attribute) && __has_attribute (target)
+    __attribute__((target("avx2")))
+    #endif
+    static int avx2_test(void)
+    {
+      const char buf@<:@sizeof(__m256i)@:>@;
+      __m256i accum = _mm256_loadu_si256((const __m256i *) buf);
+	  accum = _mm256_add_epi32(accum, accum);
+      int result = _mm256_extract_epi32(accum, 0);
+      return (int) result;
+    }],
+  [return avx2_test();])],
+  [Ac_cachevar=yes],
+  [Ac_cachevar=no])])
+if test x"$Ac_cachevar" = x"yes"; then
+  pgac_avx2_support=yes
+fi
+undefine([Ac_cachevar])dnl
+])# PGAC_AVX2_SUPPORT
+
 # PGAC_AVX512_POPCNT_INTRINSICS
 # -----------------------------
 # Check if the compiler supports the AVX-512 popcount instructions using the
diff --git a/configure b/configure
index 22cd866147b..209849c773c 100755
--- a/configure
+++ b/configure
@@ -17562,6 +17562,58 @@ $as_echo "#define HAVE_XSAVE_INTRINSICS 1" >>confdefs.h
 
 fi
 
+# Check for AVX2 target and intrinsic support
+#
+if test x"$host_cpu" = x"x86_64"; then
+  { $as_echo "$as_me:${as_lineno-$LINENO}: checking for AVX2 support" >&5
+$as_echo_n "checking for AVX2 support... " >&6; }
+if ${pgac_cv_avx2_support+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+    #include <stdint.h>
+    #if defined(__has_attribute) && __has_attribute (target)
+    __attribute__((target("avx2")))
+    #endif
+    static int avx2_test(void)
+    {
+      const char buf[sizeof(__m256i)];
+      __m256i accum = _mm256_loadu_si256((const __m256i *) buf);
+	  accum = _mm256_add_epi32(accum, accum);
+      int result = _mm256_extract_epi32(accum, 0);
+      return (int) result;
+    }
+int
+main ()
+{
+return avx2_test();
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_avx2_support=yes
+else
+  pgac_cv_avx2_support=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_avx2_support" >&5
+$as_echo "$pgac_cv_avx2_support" >&6; }
+if test x"$pgac_cv_avx2_support" = x"yes"; then
+  pgac_avx2_support=yes
+fi
+
+  if test x"$pgac_avx2_support" = x"yes"; then
+
+$as_echo "#define USE_AVX2_WITH_RUNTIME_CHECK 1" >>confdefs.h
+
+  fi
+fi
+
 # Check for AVX-512 popcount intrinsics
 #
 if test x"$host_cpu" = x"x86_64"; then
diff --git a/configure.ac b/configure.ac
index e44943aa6fe..c061b1a854c 100644
--- a/configure.ac
+++ b/configure.ac
@@ -2091,6 +2091,15 @@ if test x"$pgac_xsave_intrinsics" = x"yes"; then
   AC_DEFINE(HAVE_XSAVE_INTRINSICS, 1, [Define to 1 if you have XSAVE intrinsics.])
 fi
 
+# Check for AVX2 target and intrinsic support
+#
+if test x"$host_cpu" = x"x86_64"; then
+  PGAC_AVX2_SUPPORT()
+  if test x"$pgac_avx2_support" = x"yes"; then
+    AC_DEFINE(USE_AVX2_WITH_RUNTIME_CHECK, 1, [Define to 1 to use AVX2 instructions with a runtime check.])
+  fi
+fi
+
 # Check for AVX-512 popcount intrinsics
 #
 if test x"$host_cpu" = x"x86_64"; then
diff --git a/meson.build b/meson.build
index 395416a6060..a37ef88bf16 100644
--- a/meson.build
+++ b/meson.build
@@ -2292,6 +2292,34 @@ int main(void)
 
 endif
 
+###############################################################
+# Check for the availability of AVX2 support
+###############################################################
+
+if host_cpu == 'x86_64'
+
+  prog = '''
+#include <immintrin.h>
+#include <stdint.h>
+#if defined(__has_attribute) && __has_attribute (target)
+__attribute__((target("avx2")))
+#endif
+int main(void)
+{
+  const char buf[sizeof(__m256i)];
+  __m256i accum = _mm256_loadu_si256((const __m256i *) buf);
+  accum = _mm256_add_epi32(accum, accum);
+  int result = _mm256_extract_epi32(accum, 0);
+  return (int) result;
+}
+'''
+
+  if cc.links(prog, name: 'AVX2 support', args: test_c_args)
+    cdata.set('USE_AVX2_WITH_RUNTIME_CHECK', 1)
+  endif
+
+endif
+
 
 ###############################################################
 # Check for the availability of AVX-512 popcount intrinsics.
diff --git a/src/backend/storage/page/checksum.c b/src/backend/storage/page/checksum.c
index c913459b5a3..9ec11068b93 100644
--- a/src/backend/storage/page/checksum.c
+++ b/src/backend/storage/page/checksum.c
@@ -15,8 +15,8 @@
 
 #include "storage/checksum.h"
 /*
- * The actual code is in storage/checksum_impl.h.  This is done so that
- * external programs can incorporate the checksum code by #include'ing
- * that file from the exported Postgres headers.  (Compare our CRC code.)
+ * The actual checksum implementation is now in src/port/checksum.c
+ * for better modularity and to support AVX2 optimizations.
+ * We only need to include the header for function declarations.
  */
 #include "storage/checksum_impl.h"	/* IWYU pragma: keep */
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index c4dc5d72bdb..987f9b5c77c 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -675,6 +675,9 @@
 /* Define to 1 to use AVX-512 CRC algorithms with a runtime check. */
 #undef USE_AVX512_CRC32C_WITH_RUNTIME_CHECK
 
+/* Define to 1 to use AVX2 instructions with a runtime check. */
+#undef USE_AVX2_WITH_RUNTIME_CHECK
+
 /* Define to 1 to use AVX-512 popcount instructions with a runtime check. */
 #undef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
 
diff --git a/src/include/storage/checksum_impl.h b/src/include/storage/checksum_impl.h
index da87d61ba52..1744333e7eb 100644
--- a/src/include/storage/checksum_impl.h
+++ b/src/include/storage/checksum_impl.h
@@ -101,12 +101,14 @@
  */
 
 #include "storage/bufpage.h"
+#include "pg_config.h"
 
 /* number of checksums to calculate in parallel */
 #define N_SUMS 32
 /* prime multiplier of FNV-1a hash */
 #define FNV_PRIME 16777619
 
+
 /* Use a union so that this code is valid under strict aliasing */
 typedef union
 {
@@ -142,74 +144,12 @@ do { \
  * Block checksum algorithm.  The page must be adequately aligned
  * (at least on 4-byte boundary).
  */
-static uint32
-pg_checksum_block(const PGChecksummablePage *page)
-{
-	uint32		sums[N_SUMS];
-	uint32		result = 0;
-	uint32		i,
-				j;
-
-	/* ensure that the size is compatible with the algorithm */
-	Assert(sizeof(PGChecksummablePage) == BLCKSZ);
-
-	/* initialize partial checksums to their corresponding offsets */
-	memcpy(sums, checksumBaseOffsets, sizeof(checksumBaseOffsets));
-
-	/* main checksum calculation */
-	for (i = 0; i < (uint32) (BLCKSZ / (sizeof(uint32) * N_SUMS)); i++)
-		for (j = 0; j < N_SUMS; j++)
-			CHECKSUM_COMP(sums[j], page->data[i][j]);
-
-	/* finally add in two rounds of zeroes for additional mixing */
-	for (i = 0; i < 2; i++)
-		for (j = 0; j < N_SUMS; j++)
-			CHECKSUM_COMP(sums[j], 0);
-
-	/* xor fold partial checksums together */
-	for (i = 0; i < N_SUMS; i++)
-		result ^= sums[i];
-
-	return result;
-}
-
-/*
- * Compute the checksum for a Postgres page.
- *
- * The page must be adequately aligned (at least on a 4-byte boundary).
- * Beware also that the checksum field of the page is transiently zeroed.
- *
- * The checksum includes the block number (to detect the case where a page is
- * somehow moved to a different location), the page header (excluding the
- * checksum itself), and the page data.
- */
-uint16
-pg_checksum_page(char *page, BlockNumber blkno)
-{
-	PGChecksummablePage *cpage = (PGChecksummablePage *) page;
-	uint16		save_checksum;
-	uint32		checksum;
-
-	/* We only calculate the checksum for properly-initialized pages */
-	Assert(!PageIsNew((Page) page));
-
-	/*
-	 * Save pd_checksum and temporarily set it to zero, so that the checksum
-	 * calculation isn't affected by the old checksum stored on the page.
-	 * Restore it after, because actually updating the checksum is NOT part of
-	 * the API of this function.
-	 */
-	save_checksum = cpage->phdr.pd_checksum;
-	cpage->phdr.pd_checksum = 0;
-	checksum = pg_checksum_block(cpage);
-	cpage->phdr.pd_checksum = save_checksum;
-
-	/* Mix in the block number to detect transposed pages */
-	checksum ^= blkno;
-
-	/*
-	 * Reduce to a uint16 (to fit in the pd_checksum field) with an offset of
-	 * one. That avoids checksums of zero, which seems like a good idea.
-	 */
-	return (uint16) ((checksum % 65535) + 1);
-}
+/* Function declarations for ISA-specific implementations */
+uint32 pg_checksum_block_default(const PGChecksummablePage *page);
+#ifdef USE_AVX2_WITH_RUNTIME_CHECK
+uint32 pg_checksum_block_avx2(const PGChecksummablePage *page);
+#endif
+
+uint32 pg_checksum_block_dispatch(const PGChecksummablePage *page);
+extern uint32 (*pg_checksum_block)(const PGChecksummablePage *page);
+extern uint16 pg_checksum_page(char *page, BlockNumber blkno);
diff --git a/src/port/Makefile b/src/port/Makefile
index 4274949dfa4..a211ddbdd83 100644
--- a/src/port/Makefile
+++ b/src/port/Makefile
@@ -48,6 +48,7 @@ OBJS = \
 	pg_numa.o \
 	pg_popcount_aarch64.o \
 	pg_popcount_avx512.o \
+	checksum.o \
 	pg_strong_random.o \
 	pgcheckdir.o \
 	pgmkdirp.o \
diff --git a/src/port/checksum.c b/src/port/checksum.c
new file mode 100644
index 00000000000..b2cb61f58a0
--- /dev/null
+++ b/src/port/checksum.c
@@ -0,0 +1,203 @@
+/*-------------------------------------------------------------------------
+ *
+ * checksum.c
+ *	  Checksum implementation for data pages with AVX2 optimization.
+ *
+ * This file consolidates all checksum-related functionality including:
+ * - Runtime CPU feature detection
+ * - Default and AVX2-optimized implementations
+ * - Function dispatch logic
+ * - Page checksum calculation
+ *
+ * Portions Copyright (c) 1996-2025, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * IDENTIFICATION
+ *	  src/port/checksum.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "c.h"
+#include "storage/checksum_impl.h"
+
+#if defined(HAVE__GET_CPUID) || defined(HAVE__GET_CPUID_COUNT)
+#include <cpuid.h>
+#endif
+
+#ifdef HAVE_XSAVE_INTRINSICS
+#include <immintrin.h>
+#endif
+
+#if defined(HAVE__CPUID) || defined(HAVE__CPUIDEX)
+#include <intrin.h>
+#endif
+
+#include "port/pg_bitutils.h"
+
+/*
+ * Does CPUID say there's support for XSAVE instructions?
+ */
+static inline bool
+xsave_available(void)
+{
+	unsigned int exx[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(1, &exx[0], &exx[1], &exx[2], &exx[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(exx, 1);
+#elif defined(__x86_64__)
+#error cpuid instruction not available
+#endif
+	return (exx[2] & (1 << 27)) != 0;       /* osxsave */
+}
+
+/*
+ * Does XGETBV say the YMM registers are enabled?
+ *
+ * NB: Caller is responsible for verifying that xsave_available() returns true
+ * before calling this.
+ */
+#ifdef HAVE_XSAVE_INTRINSICS
+pg_attribute_target("xsave")
+#endif
+static inline bool
+ymm_regs_available(void)
+{
+#ifdef HAVE_XSAVE_INTRINSICS
+	return (_xgetbv(0) & 0x06) == 0x06;
+#else
+	return false;
+#endif
+}
+
+/*
+ * Does CPUID say there's support for AVX-2
+ */
+static inline bool
+avx2_available(void)
+{
+#if defined (USE_AVX2_WITH_RUNTIME_CHECK)
+	unsigned int exx[4] = {0, 0, 0, 0};
+	if (!xsave_available() || !ymm_regs_available()) return false;
+
+#if defined(HAVE__GET_CPUID_COUNT)
+	__get_cpuid_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
+#elif defined(HAVE__CPUIDEX)
+	__cpuidex(exx, 7, 0);
+#else
+#error cpuid instruction not available
+#endif
+	return (exx[1] & (1 << 5)) != 0; /* avx2 */
+#else
+	return false;
+#endif
+}
+
+/* default checksum implementation */
+uint32
+pg_checksum_block_default(const PGChecksummablePage *page)
+{
+	uint32 sums[N_SUMS], result = 0;
+	uint32 i, j;
+
+	Assert(sizeof(PGChecksummablePage) == BLCKSZ);
+	memcpy(sums, checksumBaseOffsets, sizeof(checksumBaseOffsets));
+
+	for (i = 0; i < (uint32)(BLCKSZ / (sizeof(uint32) * N_SUMS)); i++)
+		for (j = 0; j < N_SUMS; j++)
+			CHECKSUM_COMP(sums[j], page->data[i][j]);
+
+	for (i = 0; i < 2; i++)
+		for (j = 0; j < N_SUMS; j++)
+			CHECKSUM_COMP(sums[j], 0);
+
+	for (i = 0; i < N_SUMS; i++)
+		result ^= sums[i];
+
+	return result;
+}
+
+#ifdef USE_AVX2_WITH_RUNTIME_CHECK
+pg_attribute_target("avx2")
+uint32
+pg_checksum_block_avx2(const PGChecksummablePage *page)
+{
+	uint32 sums[N_SUMS], result = 0;
+	uint32 i, j;
+
+	Assert(sizeof(PGChecksummablePage) == BLCKSZ);
+	memcpy(sums, checksumBaseOffsets, sizeof(checksumBaseOffsets));
+
+	for (i = 0; i < (uint32)(BLCKSZ / (sizeof(uint32) * N_SUMS)); i++)
+		for (j = 0; j < N_SUMS; j++)
+			CHECKSUM_COMP(sums[j], page->data[i][j]);
+
+	for (i = 0; i < 2; i++)
+		for (j = 0; j < N_SUMS; j++)
+			CHECKSUM_COMP(sums[j], 0);
+
+	for (i = 0; i < N_SUMS; i++)
+		result ^= sums[i];
+
+	return result;
+}
+#endif
+
+/* Function pointer - external linkage (declared extern in header) */
+uint32 (*pg_checksum_block)(const PGChecksummablePage *page) = pg_checksum_block_dispatch;
+
+/* Dispatch function: simple, safe */
+uint32 pg_checksum_block_dispatch(const PGChecksummablePage *page)
+{
+#ifdef USE_AVX2_WITH_RUNTIME_CHECK
+	if (avx2_available())
+	{
+		pg_checksum_block = pg_checksum_block_avx2;
+		return pg_checksum_block(page);
+	}
+#endif
+	/* fallback */
+	pg_checksum_block = pg_checksum_block_default;
+	return pg_checksum_block(page);
+}
+
+/*
+ * Compute the checksum for a Postgres page.
+ *
+ * The page must be adequately aligned (at least on a 4-byte boundary).
+ * Beware also that the checksum field of the page is transiently zeroed.
+ *
+ * The checksum includes the block number (to detect the case where a page is
+ * somehow moved to a different location), the page header (excluding the
+ * checksum itself), and the page data.
+ */
+uint16 pg_checksum_page(char *page, BlockNumber blkno)
+{
+	PGChecksummablePage *cpage = (PGChecksummablePage *) page;
+	uint16 save_checksum;
+	uint32 checksum;
+
+	/* We only calculate the checksum for properly-initialized pages */
+	Assert(!PageIsNew((Page) page));
+
+	/*
+	 * Save pd_checksum and temporarily set it to zero, so that the checksum
+	 * calculation isn't affected by the old checksum stored on the page.
+	 * Restore it after, because actually updating the checksum is NOT part of
+	 * the API of this function.
+	 */
+	save_checksum = cpage->phdr.pd_checksum;
+	cpage->phdr.pd_checksum = 0;
+	checksum = pg_checksum_block(cpage);
+	cpage->phdr.pd_checksum = save_checksum;
+
+	/* Mix in the block number to detect transposed pages */
+	checksum ^= blkno;
+
+	/*
+	 * Reduce to a uint16 (to fit in the pd_checksum field) with an offset of
+	 * one. That avoids checksums of zero, which seems like a good idea.
+	 */
+	return (uint16)((checksum % 65535) + 1);
+}
\ No newline at end of file
diff --git a/src/port/meson.build b/src/port/meson.build
index fc7b059fee5..fb2fb55c61b 100644
--- a/src/port/meson.build
+++ b/src/port/meson.build
@@ -11,6 +11,7 @@ pgport_sources = [
   'pg_numa.c',
   'pg_popcount_aarch64.c',
   'pg_popcount_avx512.c',
+  'checksum.c',
   'pg_strong_random.c',
   'pgcheckdir.c',
   'pgmkdirp.c',
-- 
2.43.0