proposed_popcnt.patch

diff --git a/src/port/Makefile b/src/port/Makefile
index 4320dee0d1..1f6cbe362f 100644
--- a/src/port/Makefile
+++ b/src/port/Makefile
@@ -93,6 +93,7 @@ pg_crc32c_sse42_srv.o: CFLAGS+=$(CFLAGS_CRC)
 pg_crc32c_armv8.o: CFLAGS+=$(CFLAGS_CRC)
 pg_crc32c_armv8_shlib.o: CFLAGS+=$(CFLAGS_CRC)
 pg_crc32c_armv8_srv.o: CFLAGS+=$(CFLAGS_CRC)
+pg_bitutils.o: CFLAGS+=$(CFLAGS_AVX512)
 
 #
 # Shared library versions of object files
diff --git a/src/port/pg_bitutils.c b/src/port/pg_bitutils.c
index 1f3dea2d4b..443b8b63ce 100644
--- a/src/port/pg_bitutils.c
+++ b/src/port/pg_bitutils.c
@@ -21,6 +21,21 @@
 
 #include "port/pg_bitutils.h"
 
+#if (defined(__linux__) || defined(__linux) || defined(linux))
+#if defined(__x86_64) && defined(AVX512_POPCNT)
+/* Set macro for AVX-512 inclusion in the binary. */
+#define NEED_AVX512_POPCNTDQ 1
+
+#include <immintrin.h>
+
+/* Forward ref for AVX-512 private implementation */
+uint64 popcount_512_impl_unaligned(const char *buf, int bytes);
+#endif /* Platform and Flag for AVX-512 */
+#endif /* Linux */
+
+/* Forward refs for private refactor of 64-bit implementation */
+uint64 popcount_64_impl(const char *buf, int bytes);
+uint64 popcount_impl(const char *buf, int bytes);
 
 /*
  * Array giving the position of the left-most set bit for each possible
@@ -288,48 +303,99 @@ pg_popcount64(uint64 word)
 
 #endif							/* !TRY_POPCNT_FAST */
 
+inline uint64
+pg_popcnt_software(const char *buf, int bytes)
+{
+	uint64 popcnt = 0;
+	while (bytes--)
+		popcnt += pg_number_of_ones[(unsigned char)*buf++];
+	return popcnt;
+}
+
 /*
  * pg_popcount
  *		Returns the number of 1-bits in buf
  */
-uint64
+inline uint64
 pg_popcount(const char *buf, int bytes)
-{
-	uint64		popcnt = 0;
-
+{ /* Refatored for reuse in AVX-512 implementaitons. */
 #if SIZEOF_VOID_P >= 8
 	/* Process in 64-bit chunks if the buffer is aligned. */
 	if (buf == (const char *) TYPEALIGN(8, buf))
-	{
-		const uint64 *words = (const uint64 *) buf;
+		return popcount_impl(buf, bytes);
+	else /* If not aligned use software only */
+		return pg_popcnt_software(buf, bytes);
+#else
+	return pg_popcnt_software(buf, bytes);
+#endif
+}
 
-		while (bytes >= 8)
-		{
-			popcnt += pg_popcount64(*words++);
-			bytes -= 8;
-		}
+/*
+ * Refatored 64-bit algorithm using the refactored software
+ * algorithm for trailing bytes.
+ */
+inline uint64
+popcount_64_impl(const char *buf, int bytes)
+{
+	uint64 popcnt = 0;
 
-		buf = (const char *) words;
-	}
-#else
-	/* Process in 32-bit chunks if the buffer is aligned. */
-	if (buf == (const char *) TYPEALIGN(4, buf))
+	while (bytes >= sizeof(uint64))
 	{
-		const uint32 *words = (const uint32 *) buf;
+		popcnt += pg_popcount64(*((const uint64 *)buf));
+		buf += sizeof(uint64);
+		bytes -= sizeof(uint64);
+	}
+	
+	/* Process remaining bytes... */
+	popcnt += pg_popcnt_software(buf, bytes);
+	return popcnt;
+}
 
-		while (bytes >= 4)
-		{
-			popcnt += pg_popcount32(*words++);
-			bytes -= 4;
-		}
+#if defined(NEED_AVX512_POPCNTDQ)
 
-		buf = (const char *) words;
+#define LINE_SIZE_LOCAL 8192
+/*
+ * AVX-512 implementation for popcount using 64-bit algorithm
+ * for 512-bit unaligned leading and trailing portions.
+ */
+inline uint64
+popcount_512_impl_unaligned(const char *buf, int bytes)
+{
+	uint64 popcnt = 0;
+	uint64 remainder = ((uint64)buf) % 64;
+	popcnt += popcount_64_impl(buf, remainder);
+	bytes -= remainder;
+	buf += remainder;
+
+	__m512i *vectors = (__m512i *)buf;
+	while (bytes >= 64) {
+		popcnt += (uint64)_mm512_reduce_add_epi64(
+			_mm512_popcnt_epi64(*(vectors++)));
+		bytes -= 64;
 	}
-#endif
-
-	/* Process any remaining bytes */
-	while (bytes--)
-		popcnt += pg_number_of_ones[(unsigned char) *buf++];
+	buf = (const char *)vectors;
 
+	popcnt += popcount_64_impl(buf, bytes);
 	return popcnt;
 }
+#endif
+
+/*
+ * Called by pg_popcount when architecture is 64-bit and aligned.
+ * Will default to the original 64-bit algorithm if conditions for AVX-512
+ * are not met.
+ */
+inline uint64
+popcount_impl(const char *buf, int bytes)
+{
+#if defined(NEED_AVX512_POPCNTDQ)
+	if(bytes >= 25165824) /* 24MiB */
+		/* After testing, this is the threshhold where benefits for AVX-512
+		   starts. */
+		return popcount_512_impl_unaligned(buf, bytes);
+	else
+		return popcount_64_impl(buf, bytes);
+#else
+	return popcount_64_impl(buf, bytes);
+#endif
+}