#define POPCNT_AARCH64 1
#endif
+extern int pg_popcount32_slow(uint32 word);
+extern int pg_popcount64_slow(uint64 word);
+extern uint64 pg_popcount_slow(const char *buf, int bytes);
+extern uint64 pg_popcount_masked_slow(const char *buf, int bytes, bits8 mask);
+
#ifdef TRY_POPCNT_X86_64
-/* Attempt to use the POPCNT instruction, but perform a runtime check first */
+/*
+ * Attempt to use SSE4.2 or AVX-512 instructions, but perform a runtime check
+ * first.
+ */
extern PGDLLIMPORT int (*pg_popcount32) (uint32 word);
extern PGDLLIMPORT int (*pg_popcount64) (uint64 word);
extern PGDLLIMPORT uint64 (*pg_popcount_optimized) (const char *buf, int bytes);
extern PGDLLIMPORT uint64 (*pg_popcount_masked_optimized) (const char *buf, int bytes, bits8 mask);
-/*
- * We can also try to use the AVX-512 popcount instruction on some systems.
- * The implementation of that is located in its own file.
- */
-#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
-extern bool pg_popcount_avx512_available(void);
-extern uint64 pg_popcount_avx512(const char *buf, int bytes);
-extern uint64 pg_popcount_masked_avx512(const char *buf, int bytes, bits8 mask);
-#endif
-
#elif POPCNT_AARCH64
/* Use the Neon version of pg_popcount{32,64} without function pointer. */
extern int pg_popcount32(uint32 word);
*/
#include "c.h"
-#ifdef HAVE__GET_CPUID
-#include <cpuid.h>
-#endif
-#ifdef HAVE__CPUID
-#include <intrin.h>
-#endif
-
#include "port/pg_bitutils.h"
4, 5, 5, 6, 5, 6, 6, 7, 5, 6, 6, 7, 6, 7, 7, 8
};
-/*
- * If we are building the Neon versions, we don't need the "slow" fallbacks.
- */
-#ifndef POPCNT_AARCH64
-static inline int pg_popcount32_slow(uint32 word);
-static inline int pg_popcount64_slow(uint64 word);
-static uint64 pg_popcount_slow(const char *buf, int bytes);
-static uint64 pg_popcount_masked_slow(const char *buf, int bytes, bits8 mask);
-#endif
-
-#ifdef TRY_POPCNT_X86_64
-static bool pg_popcount_available(void);
-static int pg_popcount32_choose(uint32 word);
-static int pg_popcount64_choose(uint64 word);
-static uint64 pg_popcount_choose(const char *buf, int bytes);
-static uint64 pg_popcount_masked_choose(const char *buf, int bytes, bits8 mask);
-static inline int pg_popcount32_fast(uint32 word);
-static inline int pg_popcount64_fast(uint64 word);
-static uint64 pg_popcount_fast(const char *buf, int bytes);
-static uint64 pg_popcount_masked_fast(const char *buf, int bytes, bits8 mask);
-
-int (*pg_popcount32) (uint32 word) = pg_popcount32_choose;
-int (*pg_popcount64) (uint64 word) = pg_popcount64_choose;
-uint64 (*pg_popcount_optimized) (const char *buf, int bytes) = pg_popcount_choose;
-uint64 (*pg_popcount_masked_optimized) (const char *buf, int bytes, bits8 mask) = pg_popcount_masked_choose;
-#endif /* TRY_POPCNT_X86_64 */
-
-#ifdef TRY_POPCNT_X86_64
-
-/*
- * 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 inline void
-choose_popcount_functions(void)
-{
- if (pg_popcount_available())
- {
- pg_popcount32 = pg_popcount32_fast;
- pg_popcount64 = pg_popcount64_fast;
- pg_popcount_optimized = pg_popcount_fast;
- pg_popcount_masked_optimized = pg_popcount_masked_fast;
- }
- else
- {
- pg_popcount32 = pg_popcount32_slow;
- pg_popcount64 = pg_popcount64_slow;
- pg_popcount_optimized = pg_popcount_slow;
- pg_popcount_masked_optimized = pg_popcount_masked_slow;
- }
-
-#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
- if (pg_popcount_avx512_available())
- {
- pg_popcount_optimized = pg_popcount_avx512;
- pg_popcount_masked_optimized = pg_popcount_masked_avx512;
- }
-#endif
-}
-
-static int
-pg_popcount32_choose(uint32 word)
-{
- choose_popcount_functions();
- return pg_popcount32(word);
-}
-
-static int
-pg_popcount64_choose(uint64 word)
-{
- choose_popcount_functions();
- return pg_popcount64(word);
-}
-
-static uint64
-pg_popcount_choose(const char *buf, int bytes)
-{
- choose_popcount_functions();
- return pg_popcount_optimized(buf, bytes);
-}
-
-static uint64
-pg_popcount_masked_choose(const char *buf, int bytes, bits8 mask)
-{
- choose_popcount_functions();
- return pg_popcount_masked(buf, bytes, mask);
-}
-
-/*
- * pg_popcount32_fast
- * Return the number of 1 bits set in word
- */
-static inline 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 inline 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
-}
-
-/*
- * pg_popcount_fast
- * Returns the number of 1-bits in buf
- */
-static uint64
-pg_popcount_fast(const char *buf, int bytes)
-{
- uint64 popcnt = 0;
-
-#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;
-
- while (bytes >= 8)
- {
- popcnt += pg_popcount64_fast(*words++);
- bytes -= 8;
- }
-
- buf = (const char *) words;
- }
-#else
- /* Process in 32-bit chunks if the buffer is aligned. */
- if (buf == (const char *) TYPEALIGN(4, buf))
- {
- const uint32 *words = (const uint32 *) buf;
-
- while (bytes >= 4)
- {
- popcnt += pg_popcount32_fast(*words++);
- bytes -= 4;
- }
-
- buf = (const char *) words;
- }
-#endif
-
- /* Process any remaining bytes */
- while (bytes--)
- popcnt += pg_number_of_ones[(unsigned char) *buf++];
-
- return popcnt;
-}
-
-/*
- * pg_popcount_masked_fast
- * Returns the number of 1-bits in buf after applying the mask to each byte
- */
-static uint64
-pg_popcount_masked_fast(const char *buf, int bytes, bits8 mask)
-{
- uint64 popcnt = 0;
-
-#if SIZEOF_VOID_P >= 8
- /* Process in 64-bit chunks if the buffer is aligned */
- uint64 maskv = ~UINT64CONST(0) / 0xFF * mask;
-
- if (buf == (const char *) TYPEALIGN(8, buf))
- {
- const uint64 *words = (const uint64 *) buf;
-
- while (bytes >= 8)
- {
- popcnt += pg_popcount64_fast(*words++ & maskv);
- bytes -= 8;
- }
-
- buf = (const char *) words;
- }
-#else
- /* Process in 32-bit chunks if the buffer is aligned. */
- uint32 maskv = ~((uint32) 0) / 0xFF * mask;
-
- if (buf == (const char *) TYPEALIGN(4, buf))
- {
- const uint32 *words = (const uint32 *) buf;
-
- while (bytes >= 4)
- {
- popcnt += pg_popcount32_fast(*words++ & maskv);
- bytes -= 4;
- }
-
- buf = (const char *) words;
- }
-#endif
-
- /* Process any remaining bytes */
- while (bytes--)
- popcnt += pg_number_of_ones[(unsigned char) *buf++ & mask];
-
- return popcnt;
-}
-
-#endif /* TRY_POPCNT_X86_64 */
-
-/*
- * If we are building the Neon versions, we don't need the "slow" fallbacks.
- */
-#ifndef POPCNT_AARCH64
-
/*
* pg_popcount32_slow
* Return the number of 1 bits set in word
*/
-static inline int
+int
pg_popcount32_slow(uint32 word)
{
#ifdef HAVE__BUILTIN_POPCOUNT
* pg_popcount64_slow
* Return the number of 1 bits set in word
*/
-static inline int
+int
pg_popcount64_slow(uint64 word)
{
#ifdef HAVE__BUILTIN_POPCOUNT
* pg_popcount_slow
* Returns the number of 1-bits in buf
*/
-static uint64
+uint64
pg_popcount_slow(const char *buf, int bytes)
{
uint64 popcnt = 0;
* pg_popcount_masked_slow
* Returns the number of 1-bits in buf after applying the mask to each byte
*/
-static uint64
+uint64
pg_popcount_masked_slow(const char *buf, int bytes, bits8 mask)
{
uint64 popcnt = 0;
return popcnt;
}
-#endif /* ! POPCNT_AARCH64 */
-
#if !defined(TRY_POPCNT_X86_64) && !defined(POPCNT_AARCH64)
/*
*/
#include "c.h"
-#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+#include "port/pg_bitutils.h"
+
+#ifdef TRY_POPCNT_X86_64
#if defined(HAVE__GET_CPUID) || defined(HAVE__GET_CPUID_COUNT)
#include <cpuid.h>
#endif
+#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
#include <immintrin.h>
+#endif
#if defined(HAVE__CPUID) || defined(HAVE__CPUIDEX)
#include <intrin.h>
#endif
-#include "port/pg_bitutils.h"
+/*
+ * The SSE4.2 versions are built regardless of whether we are building the
+ * AVX-512 versions.
+ */
+static inline int pg_popcount32_fast(uint32 word);
+static inline int pg_popcount64_fast(uint64 word);
+static uint64 pg_popcount_fast(const char *buf, int bytes);
+static uint64 pg_popcount_masked_fast(const char *buf, int bytes, bits8 mask);
/*
- * It's probably unlikely that TRY_POPCNT_X86_64 won't be set if we are able to
- * use AVX-512 intrinsics, but we check it anyway to be sure. We piggy-back on
- * the function pointers that are only used when TRY_POPCNT_X86_64 is set.
+ * These are the AVX-512 implementations of the popcount functions.
*/
-#ifdef TRY_POPCNT_X86_64
+#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+static uint64 pg_popcount_avx512(const char *buf, int bytes);
+static uint64 pg_popcount_masked_avx512(const char *buf, int bytes, bits8 mask);
+#endif /* USE_AVX512_POPCNT_WITH_RUNTIME_CHECK */
+
+/*
+ * The function pointers are initially set to "choose" functions. These
+ * functions will first set the pointers to the right implementations (base on
+ * what the current CPU supports) and then will call the pointer to fulfill the
+ * caller's request.
+ */
+static int pg_popcount32_choose(uint32 word);
+static int pg_popcount64_choose(uint64 word);
+static uint64 pg_popcount_choose(const char *buf, int bytes);
+static uint64 pg_popcount_masked_choose(const char *buf, int bytes, bits8 mask);
+int (*pg_popcount32) (uint32 word) = pg_popcount32_choose;
+int (*pg_popcount64) (uint64 word) = pg_popcount64_choose;
+uint64 (*pg_popcount_optimized) (const char *buf, int bytes) = pg_popcount_choose;
+uint64 (*pg_popcount_masked_optimized) (const char *buf, int bytes, bits8 mask) = pg_popcount_masked_choose;
+
+/*
+ * 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 */
+}
+
+#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
/*
* Does CPUID say there's support for XSAVE instructions?
* Returns true if the CPU supports the instructions required for the AVX-512
* pg_popcount() implementation.
*/
-bool
+static bool
pg_popcount_avx512_available(void)
{
return xsave_available() &&
avx512_popcnt_available();
}
+#endif /* USE_AVX512_POPCNT_WITH_RUNTIME_CHECK */
+
+/*
+ * 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 inline void
+choose_popcount_functions(void)
+{
+ if (pg_popcount_available())
+ {
+ pg_popcount32 = pg_popcount32_fast;
+ pg_popcount64 = pg_popcount64_fast;
+ pg_popcount_optimized = pg_popcount_fast;
+ pg_popcount_masked_optimized = pg_popcount_masked_fast;
+ }
+ else
+ {
+ pg_popcount32 = pg_popcount32_slow;
+ pg_popcount64 = pg_popcount64_slow;
+ pg_popcount_optimized = pg_popcount_slow;
+ pg_popcount_masked_optimized = pg_popcount_masked_slow;
+ }
+
+#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+ if (pg_popcount_avx512_available())
+ {
+ pg_popcount_optimized = pg_popcount_avx512;
+ pg_popcount_masked_optimized = pg_popcount_masked_avx512;
+ }
+#endif
+}
+
+static int
+pg_popcount32_choose(uint32 word)
+{
+ choose_popcount_functions();
+ return pg_popcount32(word);
+}
+
+static int
+pg_popcount64_choose(uint64 word)
+{
+ choose_popcount_functions();
+ return pg_popcount64(word);
+}
+
+static uint64
+pg_popcount_choose(const char *buf, int bytes)
+{
+ choose_popcount_functions();
+ return pg_popcount_optimized(buf, bytes);
+}
+
+static uint64
+pg_popcount_masked_choose(const char *buf, int bytes, bits8 mask)
+{
+ choose_popcount_functions();
+ return pg_popcount_masked(buf, bytes, mask);
+}
+
+#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+
/*
* pg_popcount_avx512
* Returns the number of 1-bits in buf
*/
pg_attribute_target("avx512vpopcntdq,avx512bw")
-uint64
+static uint64
pg_popcount_avx512(const char *buf, int bytes)
{
__m512i val,
* Returns the number of 1-bits in buf after applying the mask to each byte
*/
pg_attribute_target("avx512vpopcntdq,avx512bw")
-uint64
+static uint64
pg_popcount_masked_avx512(const char *buf, int bytes, bits8 mask)
{
__m512i val,
return _mm512_reduce_add_epi64(accum);
}
-#endif /* TRY_POPCNT_X86_64 */
#endif /* USE_AVX512_POPCNT_WITH_RUNTIME_CHECK */
+
+/*
+ * pg_popcount32_fast
+ * Return the number of 1 bits set in word
+ */
+static inline 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 inline 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
+}
+
+/*
+ * pg_popcount_fast
+ * Returns the number of 1-bits in buf
+ */
+static uint64
+pg_popcount_fast(const char *buf, int bytes)
+{
+ uint64 popcnt = 0;
+
+#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;
+
+ while (bytes >= 8)
+ {
+ popcnt += pg_popcount64_fast(*words++);
+ bytes -= 8;
+ }
+
+ buf = (const char *) words;
+ }
+#else
+ /* Process in 32-bit chunks if the buffer is aligned. */
+ if (buf == (const char *) TYPEALIGN(4, buf))
+ {
+ const uint32 *words = (const uint32 *) buf;
+
+ while (bytes >= 4)
+ {
+ popcnt += pg_popcount32_fast(*words++);
+ bytes -= 4;
+ }
+
+ buf = (const char *) words;
+ }
+#endif
+
+ /* Process any remaining bytes */
+ while (bytes--)
+ popcnt += pg_number_of_ones[(unsigned char) *buf++];
+
+ return popcnt;
+}
+
+/*
+ * pg_popcount_masked_fast
+ * Returns the number of 1-bits in buf after applying the mask to each byte
+ */
+static uint64
+pg_popcount_masked_fast(const char *buf, int bytes, bits8 mask)
+{
+ uint64 popcnt = 0;
+
+#if SIZEOF_VOID_P >= 8
+ /* Process in 64-bit chunks if the buffer is aligned */
+ uint64 maskv = ~UINT64CONST(0) / 0xFF * mask;
+
+ if (buf == (const char *) TYPEALIGN(8, buf))
+ {
+ const uint64 *words = (const uint64 *) buf;
+
+ while (bytes >= 8)
+ {
+ popcnt += pg_popcount64_fast(*words++ & maskv);
+ bytes -= 8;
+ }
+
+ buf = (const char *) words;
+ }
+#else
+ /* Process in 32-bit chunks if the buffer is aligned. */
+ uint32 maskv = ~((uint32) 0) / 0xFF * mask;
+
+ if (buf == (const char *) TYPEALIGN(4, buf))
+ {
+ const uint32 *words = (const uint32 *) buf;
+
+ while (bytes >= 4)
+ {
+ popcnt += pg_popcount32_fast(*words++ & maskv);
+ bytes -= 4;
+ }
+
+ buf = (const char *) words;
+ }
+#endif
+
+ /* Process any remaining bytes */
+ while (bytes--)
+ popcnt += pg_number_of_ones[(unsigned char) *buf++ & mask];
+
+ return popcnt;
+}
+
+#endif /* TRY_POPCNT_X86_64 */
projects / postgresql.git / commitdiff