v8-0001-Refactor-POPCNT-code-refactored-for-future-accelerat.patch

From 57256412ce11b006ad383fc689a0fd28716632e0 Mon Sep 17 00:00:00 2001
From: Paul Amonson <paul.d.amonson@intel.com>
Date: Wed, 13 Mar 2024 11:56:44 -0700
Subject: [PATCH 1/2] [Refactor] POPCNT code refactored for future acceleration
 of the function.

Signed-off-by: Paul Amonson <paul.d.amonson@intel.com>
---
 src/port/Makefile                 |   2 +
 src/port/meson.build              |   2 +
 src/port/pg_bitutils.c            | 124 +-----------------------------
 src/port/pg_popcnt_choose.c       |  97 +++++++++++++++++++++++
 src/port/pg_popcnt_x86_64_accel.c |  55 +++++++++++++
 5 files changed, 160 insertions(+), 120 deletions(-)
 create mode 100644 src/port/pg_popcnt_choose.c
 create mode 100644 src/port/pg_popcnt_x86_64_accel.c

diff --git a/src/port/Makefile b/src/port/Makefile
index dcc8737e68..12c56b0ba7 100644
--- a/src/port/Makefile
+++ b/src/port/Makefile
@@ -44,6 +44,8 @@ OBJS = \
 	noblock.o \
 	path.o \
 	pg_bitutils.o \
+	pg_popcnt_choose.o \
+	pg_popcnt_x86_64_accel.o \
 	pg_strong_random.o \
 	pgcheckdir.o \
 	pgmkdirp.o \
diff --git a/src/port/meson.build b/src/port/meson.build
index 92b593e6ef..ed8828c739 100644
--- a/src/port/meson.build
+++ b/src/port/meson.build
@@ -7,6 +7,8 @@ pgport_sources = [
   'noblock.c',
   'path.c',
   'pg_bitutils.c',
+  'pg_popcnt_choose.c',
+  'pg_popcnt_x86_64_accel.c',
   'pg_strong_random.c',
   'pgcheckdir.c',
   'pgmkdirp.c',
diff --git a/src/port/pg_bitutils.c b/src/port/pg_bitutils.c
index 640a89561a..d8b045d0a4 100644
--- a/src/port/pg_bitutils.c
+++ b/src/port/pg_bitutils.c
@@ -12,13 +12,6 @@
  */
 #include "c.h"
 
-#ifdef HAVE__GET_CPUID
-#include <cpuid.h>
-#endif
-#ifdef HAVE__CPUID
-#include <intrin.h>
-#endif
-
 #include "port/pg_bitutils.h"
 
 
@@ -103,123 +96,14 @@ const uint8 pg_number_of_ones[256] = {
 	4, 5, 5, 6, 5, 6, 6, 7, 5, 6, 6, 7, 6, 7, 7, 8
 };
 
-static int	pg_popcount32_slow(uint32 word);
-static int	pg_popcount64_slow(uint64 word);
-
-#ifdef TRY_POPCNT_FAST
-static bool pg_popcount_available(void);
-static int	pg_popcount32_choose(uint32 word);
-static int	pg_popcount64_choose(uint64 word);
-static int	pg_popcount32_fast(uint32 word);
-static int	pg_popcount64_fast(uint64 word);
-
-int			(*pg_popcount32) (uint32 word) = pg_popcount32_choose;
-int			(*pg_popcount64) (uint64 word) = pg_popcount64_choose;
-#endif							/* TRY_POPCNT_FAST */
-
-#ifdef TRY_POPCNT_FAST
-
-/*
- * Return true if CPUID indicates that the POPCNT instruction is available.
- */
-static bool
-pg_popcount_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 << 23)) != 0;	/* POPCNT */
-}
-
-/*
- * These functions get called on the first call to pg_popcount32 etc.
- * They detect whether we can use the asm implementations, and replace
- * the function pointers so that subsequent calls are routed directly to
- * the chosen implementation.
- */
-static int
-pg_popcount32_choose(uint32 word)
-{
-	if (pg_popcount_available())
-	{
-		pg_popcount32 = pg_popcount32_fast;
-		pg_popcount64 = pg_popcount64_fast;
-	}
-	else
-	{
-		pg_popcount32 = pg_popcount32_slow;
-		pg_popcount64 = pg_popcount64_slow;
-	}
-
-	return pg_popcount32(word);
-}
-
-static int
-pg_popcount64_choose(uint64 word)
-{
-	if (pg_popcount_available())
-	{
-		pg_popcount32 = pg_popcount32_fast;
-		pg_popcount64 = pg_popcount64_fast;
-	}
-	else
-	{
-		pg_popcount32 = pg_popcount32_slow;
-		pg_popcount64 = pg_popcount64_slow;
-	}
-
-	return pg_popcount64(word);
-}
-
-/*
- * pg_popcount32_fast
- *		Return the number of 1 bits set in word
- */
-static int
-pg_popcount32_fast(uint32 word)
-{
-#ifdef _MSC_VER
-	return __popcnt(word);
-#else
-	uint32		res;
-
-__asm__ __volatile__(" popcntl %1,%0\n":"=q"(res):"rm"(word):"cc");
-	return (int) res;
-#endif
-}
-
-/*
- * pg_popcount64_fast
- *		Return the number of 1 bits set in word
- */
-static int
-pg_popcount64_fast(uint64 word)
-{
-#ifdef _MSC_VER
-	return __popcnt64(word);
-#else
-	uint64		res;
-
-__asm__ __volatile__(" popcntq %1,%0\n":"=q"(res):"rm"(word):"cc");
-	return (int) res;
-#endif
-}
-
-#endif							/* TRY_POPCNT_FAST */
-
+int	pg_popcount32_slow(uint32 word);
+int	pg_popcount64_slow(uint64 word);
 
 /*
  * pg_popcount32_slow
  *		Return the number of 1 bits set in word
  */
-static int
+int
 pg_popcount32_slow(uint32 word)
 {
 #ifdef HAVE__BUILTIN_POPCOUNT
@@ -241,7 +125,7 @@ pg_popcount32_slow(uint32 word)
  * pg_popcount64_slow
  *		Return the number of 1 bits set in word
  */
-static int
+int
 pg_popcount64_slow(uint64 word)
 {
 #ifdef HAVE__BUILTIN_POPCOUNT
diff --git a/src/port/pg_popcnt_choose.c b/src/port/pg_popcnt_choose.c
new file mode 100644
index 0000000000..89fcf2609c
--- /dev/null
+++ b/src/port/pg_popcnt_choose.c
@@ -0,0 +1,97 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_popcnt_choose.c
+ *	  For FAST operations, these methods do runtime checks and set the
+ *    appropriate function pointers.
+ *
+ * Copyright (c) 2019-2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *	  src/port/pg_popcnt_choose.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "c.h"
+
+#ifdef HAVE__GET_CPUID
+#include <cpuid.h>
+#endif
+#ifdef HAVE__CPUID
+#include <intrin.h>
+#endif
+
+#include "port/pg_bitutils.h"
+
+
+/* In pg_bitutils.c file */
+int	pg_popcount32_slow(uint32 word);
+int	pg_popcount64_slow(uint64 word);
+
+#ifdef TRY_POPCNT_FAST
+static bool pg_popcount_available(void);
+static int	pg_popcount32_choose(uint32 word);
+static int	pg_popcount64_choose(uint64 word);
+
+/* In pg_popcnt_*_accel source file. */
+int	pg_popcount32_fast(uint32 word);
+int	pg_popcount64_fast(uint64 word);
+
+int			(*pg_popcount32) (uint32 word) = pg_popcount32_choose;
+int			(*pg_popcount64) (uint64 word) = pg_popcount64_choose;
+#endif							/* TRY_POPCNT_FAST */
+
+#ifdef TRY_POPCNT_FAST
+
+/*
+ * Return true if CPUID indicates that the POPCNT instruction is available.
+ */
+static bool
+pg_popcount_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 << 23)) != 0;	/* POPCNT */
+}
+
+/*
+ * These functions get called on the first call to pg_popcount32 etc.
+ * They detect whether we can use the asm implementations, and replace
+ * the function pointers so that subsequent calls are routed directly to
+ * the chosen implementation.
+ */
+static void setup_function_pointers()
+{
+	if (pg_popcount_available())
+	{
+		pg_popcount32 = pg_popcount32_fast;
+		pg_popcount64 = pg_popcount64_fast;
+	}
+	else
+	{
+		pg_popcount32 = pg_popcount32_slow;
+		pg_popcount64 = pg_popcount64_slow;
+	}
+}
+
+static int
+pg_popcount32_choose(uint32 word)
+{
+	setup_function_pointers();
+	return pg_popcount32(word);
+}
+
+static int
+pg_popcount64_choose(uint64 word)
+{
+	setup_function_pointers();
+	return pg_popcount64(word);
+}
+#endif							/* TRY_POPCNT_FAST */
diff --git a/src/port/pg_popcnt_x86_64_accel.c b/src/port/pg_popcnt_x86_64_accel.c
new file mode 100644
index 0000000000..2e9b2ee774
--- /dev/null
+++ b/src/port/pg_popcnt_x86_64_accel.c
@@ -0,0 +1,55 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_popcnt_x86_64_accel.c
+ *	  Fast POPCNT methods for x86_64.
+ *
+ * Copyright (c) 2019-2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *	  src/port/pg_popcnt_x86_64_accel.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "c.h"
+
+#include "port/pg_bitutils.h"
+
+int pg_popcount32_fast(uint32 word);
+int pg_popcount64_fast(uint64 word);
+
+#ifdef TRY_POPCNT_FAST
+/*
+ * pg_popcount32_fast
+ *		Return the number of 1 bits set in word
+ */
+int
+pg_popcount32_fast(uint32 word)
+{
+#ifdef _MSC_VER
+	return __popcnt(word);
+#else
+	uint32		res;
+
+__asm__ __volatile__(" popcntl %1,%0\n":"=q"(res):"rm"(word):"cc");
+	return (int) res;
+#endif
+}
+
+/*
+ * pg_popcount64_fast
+ *		Return the number of 1 bits set in word
+ */
+int
+pg_popcount64_fast(uint64 word)
+{
+#ifdef _MSC_VER
+	return __popcnt64(word);
+#else
+	uint64		res;
+
+__asm__ __volatile__(" popcntq %1,%0\n":"=q"(res):"rm"(word):"cc");
+	return (int) res;
+#endif
+}
+
+#endif							/* TRY_POPCNT_FAST */
-- 
2.34.1