v2-0001-Enable-autovectorizing-pg_checksum_block.patch

From a6288a4e73d97f3e76e4dabc1e6e6a86478ddbcd Mon Sep 17 00:00:00 2001
From: Matthew Sterrett <matthew.sterrett@intel.com>
Date: Fri, 7 Mar 2025 11:33:45 -0800
Subject: [PATCH v2 1/4] Enable autovectorizing pg_checksum_block

---
 config/c-compiler.m4                |  31 ++++++
 configure                           |  52 ++++++++++
 configure.ac                        |   9 ++
 meson.build                         |  28 ++++++
 src/include/pg_config.h.in          |   3 +
 src/include/storage/checksum_impl.h | 150 +++++++++++++++++++++++-----
 6 files changed, 250 insertions(+), 23 deletions(-)

diff --git a/config/c-compiler.m4 b/config/c-compiler.m4
index 5f3e1d1faf9..4d5bceafe9e 100644
--- a/config/c-compiler.m4
+++ b/config/c-compiler.m4
@@ -710,6 +710,37 @@ 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 275c67ee67c..5ae2dc00d33 100755
--- a/configure
+++ b/configure
@@ -17711,6 +17711,58 @@ $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"$host_cpu" = x"x86_64"; then
diff --git a/configure.ac b/configure.ac
index 7ea91d56adb..a1f5eb8021a 100644
--- a/configure.ac
+++ b/configure.ac
@@ -2088,6 +2088,15 @@ if test x"$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 12de5e80c31..513d30a93ff 100644
--- a/meson.build
+++ b/meson.build
@@ -2301,6 +2301,34 @@ 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/include/pg_config.h.in b/src/include/pg_config.h.in
index c3cc9fa856d..b174bcc5f79 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -671,6 +671,9 @@
 /* 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..5ea1f698b57 100644
--- a/src/include/storage/checksum_impl.h
+++ b/src/include/storage/checksum_impl.h
@@ -101,12 +101,83 @@
  */
 
 #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
 
+#if defined(HAVE__GET_CPUID) || defined(HAVE__GET_CPUID_COUNT)
+#include <cpuid.h>
+#endif
+
+#include <immintrin.h>
+
+#if defined(HAVE__CPUID) || defined(HAVE__CPUIDEX)
+#include <intrin.h>
+#endif
+
+/*
+ * 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);
+#else
+#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)
+{
+#ifdef 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
+}
+
 /* Use a union so that this code is valid under strict aliasing */
 typedef union
 {
@@ -142,35 +213,68 @@ 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;
+ 
+#define PG_DECLARE_CHECKSUM_ISA(ISANAME) \
+static uint32 \
+pg_checksum_block_##ISANAME(const PGChecksummablePage *page);
+
+#define PG_DEFINE_CHECKSUM_ISA(ISANAME) \
+pg_attribute_target(#ISANAME) \
+static uint32 \
+pg_checksum_block_##ISANAME(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 */ \
+	/* this is the main place that autovectorization occurs */ \
+	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; \
+}
 
-	/* ensure that the size is compatible with the algorithm */
-	Assert(sizeof(PGChecksummablePage) == BLCKSZ);
+/* Declarations are always defined to make dynamic dispatch code simpler */
 
-	/* initialize partial checksums to their corresponding offsets */
-	memcpy(sums, checksumBaseOffsets, sizeof(checksumBaseOffsets));
+PG_DECLARE_CHECKSUM_ISA(default);
+PG_DECLARE_CHECKSUM_ISA(avx2);
 
-	/* 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]);
+PG_DEFINE_CHECKSUM_ISA(default);
+#ifdef USE_AVX2_WITH_RUNTIME_CHECK
+PG_DEFINE_CHECKSUM_ISA(avx2);
+#endif
 
-	/* 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);
+static uint32
+pg_checksum_block_dispatch(const PGChecksummablePage *page);
 
-	/* xor fold partial checksums together */
-	for (i = 0; i < N_SUMS; i++)
-		result ^= sums[i];
+static uint32 (*pg_checksum_block)(const PGChecksummablePage *page) = pg_checksum_block_dispatch;
 
-	return result;
+static uint32
+pg_checksum_block_dispatch(const PGChecksummablePage *page){
+	if (avx2_available()){
+		pg_checksum_block = pg_checksum_block_avx2;
+	}else{
+		pg_checksum_block = pg_checksum_block_default;
+	}
+	return pg_checksum_block(page);
 }
 
 /*
-- 
2.43.0