public inbox for [email protected]
help / color / mirror / Atom feedFrom: Andrew Kim <[email protected]>
To: John Naylor <[email protected]>
Cc: [email protected]
Subject: Re: Proposal for enabling auto-vectorization for checksum calculations
Date: Wed, 24 Sep 2025 14:50:44 -0700
Message-ID: <CAK64mnfeWLBRbMfnOsag0vGTDnT84KJzpuei40nG0OHyw4SESw@mail.gmail.com> (raw)
In-Reply-To: <CANWCAZYZQw-nzTXbx3Bk332VtY9_D7ksDsuMZ0A-iDZ53yG7Ng@mail.gmail.com>
References: <[email protected]>
<CANWCAZYZQw-nzTXbx3Bk332VtY9_D7ksDsuMZ0A-iDZ53yG7Ng@mail.gmail.com>
On Tue, Sep 23, 2025 at 11:32 PM John Naylor [email protected] wrote:
There is no attachment in this thread, so it's not showing up in the
commitfest entry (which will need to be moved to next open
commitfest), so it's not getting CI testing:
https://commitfest.postgresql.org/patch/5726/
Note that the whole series must be attached in a single email, or it
won't get automated testing.
Thanks, John. I see the issue now — I’ll attach the entire patch
series in a single email so it shows up properly in the commitfest and
gets CI coverage.
Please find attached v6 of the patchset, updated per your feedback.
Best regards,
Andrew Kim
On Tue, Sep 23, 2025 at 11:32 PM John Naylor <[email protected]> wrote:
>
> On Thu, Sep 11, 2025 at 1:55 PM root <[email protected]> wrote:
> > Thanks for the feedback. This is v5 of the patchset, updated following your comments:
> >
> > - Moved the function pointer definitions out of common headers and
> > into src/port, consistent with existing practice.
>
> There is no attachment in this thread, so it's not showing up in the
> commitfest entry (which will need to be moved to next open
> commitfest), so it's not getting CI testing:
>
> https://commitfest.postgresql.org/patch/5726/
>
> Note that the whole series must be attached in a single email, or it
> won't get automated testing.
>
> --
> John Naylor
> Amazon Web Services
Attachments:
[application/octet-stream] v5-0002-Benchmark-code-for-postgres-checksums.patch (4.7K, 2-v5-0002-Benchmark-code-for-postgres-checksums.patch)
download | inline diff:
From 94160dca5478e713bcaab42389207ee1eac3d553 Mon Sep 17 00:00:00 2001
From: Andrew kim <[email protected]>
Date: Wed, 10 Sep 2025 16:12:44 -0700
Subject: [PATCH 2/2] Benchmark code for postgres checksums
---
contrib/meson.build | 1 +
contrib/pg_checksum_bench/meson.build | 23 +++++++++++++
.../pg_checksum_bench--1.0.sql | 8 +++++
contrib/pg_checksum_bench/pg_checksum_bench.c | 34 +++++++++++++++++++
.../pg_checksum_bench.control | 4 +++
.../sql/pg_checksum_bench.sql | 17 ++++++++++
6 files changed, 87 insertions(+)
create mode 100644 contrib/pg_checksum_bench/meson.build
create mode 100644 contrib/pg_checksum_bench/pg_checksum_bench--1.0.sql
create mode 100644 contrib/pg_checksum_bench/pg_checksum_bench.c
create mode 100644 contrib/pg_checksum_bench/pg_checksum_bench.control
create mode 100644 contrib/pg_checksum_bench/sql/pg_checksum_bench.sql
diff --git a/contrib/meson.build b/contrib/meson.build
index ed30ee7d639..fe5149aadff 100644
--- a/contrib/meson.build
+++ b/contrib/meson.build
@@ -12,6 +12,7 @@ contrib_doc_args = {
'install_dir': contrib_doc_dir,
}
+subdir('pg_checksum_bench')
subdir('amcheck')
subdir('auth_delay')
subdir('auto_explain')
diff --git a/contrib/pg_checksum_bench/meson.build b/contrib/pg_checksum_bench/meson.build
new file mode 100644
index 00000000000..32ccd9efa0f
--- /dev/null
+++ b/contrib/pg_checksum_bench/meson.build
@@ -0,0 +1,23 @@
+# Copyright (c) 2022-2025, PostgreSQL Global Development Group
+
+pg_checksum_bench_sources = files(
+ 'pg_checksum_bench.c',
+)
+
+if host_system == 'windows'
+ pg_checksum_bench_sources += rc_lib_gen.process(win32ver_rc, extra_args: [
+ '--NAME', 'pg_checksum_bench',
+ '--FILEDESC', 'pg_checksum_bench',])
+endif
+
+pg_checksum_bench = shared_module('pg_checksum_bench',
+ pg_checksum_bench_sources,
+ kwargs: contrib_mod_args,
+)
+contrib_targets += pg_checksum_bench
+
+install_data(
+ 'pg_checksum_bench--1.0.sql',
+ 'pg_checksum_bench.control',
+ kwargs: contrib_data_args,
+)
diff --git a/contrib/pg_checksum_bench/pg_checksum_bench--1.0.sql b/contrib/pg_checksum_bench/pg_checksum_bench--1.0.sql
new file mode 100644
index 00000000000..5f13cbe3c5e
--- /dev/null
+++ b/contrib/pg_checksum_bench/pg_checksum_bench--1.0.sql
@@ -0,0 +1,8 @@
+/* contrib/pg_checksum_bench/pg_checksum_bench--1.0.sql */
+
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+-- \echo Use "CREATE EXTENSION pg_checksum_bench" to load this file. \quit
+
+CREATE FUNCTION drive_pg_checksum(page_count int)
+ RETURNS pg_catalog.void
+ AS 'MODULE_PATHNAME' LANGUAGE C;
diff --git a/contrib/pg_checksum_bench/pg_checksum_bench.c b/contrib/pg_checksum_bench/pg_checksum_bench.c
new file mode 100644
index 00000000000..f40f335ff59
--- /dev/null
+++ b/contrib/pg_checksum_bench/pg_checksum_bench.c
@@ -0,0 +1,34 @@
+#include "postgres.h"
+#include "fmgr.h"
+#include "storage/checksum_impl.h"
+
+#include <stdio.h>
+#include <assert.h>
+
+PG_MODULE_MAGIC;
+
+#define REPEATS 1000000
+
+PG_FUNCTION_INFO_V1(drive_pg_checksum);
+Datum
+drive_pg_checksum(PG_FUNCTION_ARGS)
+{
+ int page_count = PG_GETARG_INT32(0);
+
+ PGChecksummablePage * pages = palloc(page_count * sizeof(PGChecksummablePage));
+ srand(0);
+ for (size_t i = 0; i < page_count * sizeof(PGChecksummablePage); i++){
+ char * byte_ptr = (char *) pages;
+ byte_ptr[i] = rand() % 256;
+ }
+
+ for (int i = 0; i < REPEATS; i++){
+ const PGChecksummablePage * test_page = pages + (i % page_count);
+ volatile uint32 result = pg_checksum_block(test_page);
+ (void) result;
+ }
+
+ pfree((void *) pages);
+
+ PG_RETURN_VOID();
+}
diff --git a/contrib/pg_checksum_bench/pg_checksum_bench.control b/contrib/pg_checksum_bench/pg_checksum_bench.control
new file mode 100644
index 00000000000..4a4e2c9363c
--- /dev/null
+++ b/contrib/pg_checksum_bench/pg_checksum_bench.control
@@ -0,0 +1,4 @@
+comment = 'pg_checksum benchmark'
+default_version = '1.0'
+module_pathname = '$libdir/pg_checksum_bench'
+relocatable = true
diff --git a/contrib/pg_checksum_bench/sql/pg_checksum_bench.sql b/contrib/pg_checksum_bench/sql/pg_checksum_bench.sql
new file mode 100644
index 00000000000..4b347699953
--- /dev/null
+++ b/contrib/pg_checksum_bench/sql/pg_checksum_bench.sql
@@ -0,0 +1,17 @@
+CREATE EXTENSION pg_checksum_bench;
+
+SELECT drive_pg_checksum(-1);
+
+\timing on
+
+SELECT drive_pg_checksum(1);
+SELECT drive_pg_checksum(2);
+SELECT drive_pg_checksum(4);
+SELECT drive_pg_checksum(8);
+SELECT drive_pg_checksum(16);
+SELECT drive_pg_checksum(32);
+SELECT drive_pg_checksum(64);
+SELECT drive_pg_checksum(128);
+SELECT drive_pg_checksum(256);
+SELECT drive_pg_checksum(512);
+SELECT drive_pg_checksum(1024);
--
2.43.0
[application/octet-stream] v5-0001-Enable-autovectorizing-pg_checksum_block.patch (15.3K, 3-v5-0001-Enable-autovectorizing-pg_checksum_block.patch)
download | inline diff:
From 982be9006cdb584f0287548da637f41c3f898747 Mon Sep 17 00:00:00 2001
From: Andrew kim <[email protected]>
Date: Tue, 23 Sep 2025 17:44:18 -0700
Subject: [PATCH 1/1] 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 | 90 +++----------
src/port/Makefile | 1 +
src/port/meson.build | 1 +
src/port/pg_checksum_dispatch.c | 195 ++++++++++++++++++++++++++++
9 files changed, 339 insertions(+), 71 deletions(-)
create mode 100644 src/port/pg_checksum_dispatch.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/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..82e525529f4 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 +144,20 @@ 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);
-}
+#define PG_DECLARE_CHECKSUM_ISA(ISANAME) \
+uint32 \
+pg_checksum_block_##ISANAME(const PGChecksummablePage *page);
+
+#define PG_DEFINE_CHECKSUM_ISA(ISANAME) \
+pg_attribute_target(#ISANAME) \
+uint32 pg_checksum_block_##ISANAME(const PGChecksummablePage *page) \
+
+/* Declare ISA implementations (declarations only in header) */
+#ifdef USE_AVX2_WITH_RUNTIME_CHECK
+PG_DECLARE_CHECKSUM_ISA(avx2);
+#endif
+PG_DECLARE_CHECKSUM_ISA(default);
+
+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..27423f1058b 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 \
+ pg_checksum_dispatch.o \
pg_strong_random.o \
pgcheckdir.o \
pgmkdirp.o \
diff --git a/src/port/meson.build b/src/port/meson.build
index fc7b059fee5..c4bbe9f2ece 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',
+ 'pg_checksum_dispatch.c',
'pg_strong_random.c',
'pgcheckdir.c',
'pgmkdirp.c',
diff --git a/src/port/pg_checksum_dispatch.c b/src/port/pg_checksum_dispatch.c
new file mode 100644
index 00000000000..b4b297c831f
--- /dev/null
+++ b/src/port/pg_checksum_dispatch.c
@@ -0,0 +1,195 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_checksum_dispatch.c
+ * Holds the AVX2 pg_popcount() implementation.
+ *
+ * Copyright (c) 2024-2025, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ * src/port/pg_checksum_dispatch.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) && defined(__x86_64__)
+ 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 */
+PG_DEFINE_CHECKSUM_ISA(default)
+{
+ 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_DEFINE_CHECKSUM_ISA(avx2)
+{
+ 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())
+ {
+ /* optional: patch pointer so next call goes directly */
+ pg_checksum_block = pg_checksum_block_avx2;
+ return pg_checksum_block_avx2(page);
+ }
+#endif
+ /* fallback */
+ pg_checksum_block = pg_checksum_block_default;
+ return pg_checksum_block_default(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);
+}
--
2.43.0
view thread (37+ messages) latest in thread
reply
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Reply to all the recipients using the --to and --cc options:
reply via email
To: [email protected]
Cc: [email protected], [email protected], [email protected]
Subject: Re: Proposal for enabling auto-vectorization for checksum calculations
In-Reply-To: <CAK64mnfeWLBRbMfnOsag0vGTDnT84KJzpuei40nG0OHyw4SESw@mail.gmail.com>
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox