public inbox for [email protected]
help / color / mirror / Atom feedFrom: Andrew Kim <[email protected]>
To: Oleg Tselebrovskiy <[email protected]>
Cc: John Naylor <[email protected]>
Cc: [email protected]
Subject: Re: Proposal for enabling auto-vectorization for checksum calculations
Date: Sat, 18 Oct 2025 14:30:21 -0700
Message-ID: <CAK64mnd6VAtTbar=QS4sbWJpfFxjksjg2ERNkGw1tRwh_kc6mw@mail.gmail.com> (raw)
In-Reply-To: <[email protected]>
References: <[email protected]>
<CANWCAZYZQw-nzTXbx3Bk332VtY9_D7ksDsuMZ0A-iDZ53yG7Ng@mail.gmail.com>
<CAK64mnfeWLBRbMfnOsag0vGTDnT84KJzpuei40nG0OHyw4SESw@mail.gmail.com>
<CANWCAZa1b2rcvoK657SmcKwh2P2cgASQ1D-0JPj5d3LbfaAVgA@mail.gmail.com>
<CAK64mneN20+sW5WhV+r7hMVo4Rd0z11B6=3L039rWMt1wK3nPg@mail.gmail.com>
<[email protected]>
Hi Oleg,
Thank you very much for the detailed and constructive feedback on v6 patch.
It was extremely helpful in refining the architecture and ensuring
compliance with PostgreSQL coding standards.
I have updated the patch to V7, which I believe addresses all of your
points, including the critical architectural concerns regarding file
organization and linking.
Key Changes and Feedback Resolution in V7
The architecture is now consolidated in the src/port module.
1. Compiler Flags (Unroll/Vectorize)Resolved: Compiler flags
(CFLAGS_UNROLL_LOOPS) are now correctly placed and applied to
checksum.c in src/port/Makefile and src/port/meson.
2. Header OrganizationResolved: checksum.h and checksum_impl.h have
been moved from src/include/storage/ to src/include/port/ for
consistent module organization.
3. External Program CompatibilityResolved: checksum_impl.h is now
fully self-contained. It provides the static inline implementations
(pg_checksum_block_default, pg_checksum_block_avx2) and all required
constants, ensuring external tools can calculate checksums without
linking to the backend library.
4. Duplicate FilesResolved: The redundant
src/backend/storage/page/checksum.c file has been removed,
consolidating all implementation logic into src/port/checksum.c.
5. Function NamingResolved: The dispatch pattern now uses
pg_checksum_block_choose, aligning with the established naming
conventions (e.g., CRC32C module). The implementations use the clear
names pg_checksum_block_default and pg_checksum_block_avx2.
7. Documentation/CommentsResolved: Comprehensive documentation,
including the detailed FNV-1a algorithm comments, has been restored to
the portable implementation (pg_checksum_block_default).
Best regards,
Andrew Kim
On Fri, Oct 17, 2025 at 3:53 AM Oleg Tselebrovskiy
<[email protected]> wrote:
>
> Greetings!
>
> I've also tried to use AVX2 to speedup checksums and I've found your
> approach quite interesting
>
> But I see some issues with v6 patch
>
> 1) checksum.c was moved to src/port, but special meson rules are left in
> src/backend/storage/page/meson.build. As a result, assembly code for
> moved src/port/checksum.c doesn't use -funroll-loops and
> -ftree-vectorize (latter isn't probably needed now, due to the nature of
> the patch). The same is true for src/port/Makefile, there are no
> instructions to use CFLAGS_UNROLL_LOOPS and CFLAGS_VECTORIZE
>
> 2) checksum.c was moved to src/port, but checksum.h and checksum_impl.h
> are left in src/include/storage. I think they both should be moved to
> src/include/port, as John Naylor suggested in his review of v5
>
> 3) checksum_impl.h now doesn't provide any code, so including it in
> external programs won't allow checksum calculation. I think that all
> code should be in checksum_impl.h, and external programs could just
> define USE_AVX2_WITH_RUNTIME_CHECK (probably using similar checks as we
> are) to use AVX2 implementation. If not - then they will default to
> default realisation
>
> 4) I don't understand why do we need to check for AVX2 intrinsics if we
> don't use those in code (at least I don't see them directly)? As in
> review of v5, couldn't test functions in configure, config/c-compiler.m4
> and ./meson.build just be {return 0;} or {return 1;}?
>
> 5) Why do we need both src/backend/storage/page/checksum.c and
> src/port/checksum.c?
>
> 6)
> > +/* Function declarations for ISA-specific implementations */
> > +uint32 pg_checksum_block_default(const PGChecksummablePage *page);
> > +#ifdef USE_AVX2_WITH_RUNTIME_CHECK
> > +uint32 pg_checksum_block_avx2(const PGChecksummablePage *page);
> > +#endif
>
> What is "ISA-specific implementations" in this comment? Maybe I'm just
> not familiar with the term? Or is it an artifact from macro
> implementation?
>
> 7) Why remove all comments from code of pg_checksum_block_default? I
> could understand if you just removed comments from
> pg_checksum_block_avx2, since it just duplicates code (though I
> personally would leave all the comments even when duplicating code), but
> I don't understand removing comments from pg_checksum_block_default
>
> 8) It might be a personal taste, but pg_checksum_block_dispatch looks
> more like "choose" function from src/port/pg_crc32c_sse42_choose.c and
> alike. "dispatch" from src/include/port/pg_crc32c looks a little
> different - we don't choose function pointer once there, we choose
> between inlined computation and calling a function with runtime check.
> So I'd suggest changing name of pg_checksum_block_dispatch to
> pg_checksum_block_choose
>
> Other than those, I think the core of this patch is good
>
> Oleg Tselebrovskiy, PostgresPro
Attachments:
[application/octet-stream] v7-0001-Enable-autovectorizing-pg_checksum_block-with-AVX2-runtime-detection.patch (23.3K, 2-v7-0001-Enable-autovectorizing-pg_checksum_block-with-AVX2-runtime-detection.patch)
download | inline diff:
From fe7d2e4061042c4fd30c9c7095889fcf777be105 Mon Sep 17 00:00:00 2001
From: Andrew kim <[email protected]>
Date: Sat, 18 Oct 2025 12:13:50 -0700
Subject: [PATCH 1/2] Enable autovectorizing pg_checksum_block with AVX2
runtime-detection
1. Compiler flags: Moved CFLAGS_UNROLL_LOOPS and CFLAGS_VECTORIZE to
proper port module build files
2. Header organization: Relocated headers from src/include/storage/
to src/include/port/ for correct module classification
3. External compatibility: Made checksum_impl.h fully self-contained with
inline implementations, required constants, and external interface
4. Simplified AVX2 detection: Replaced complex CPUID logic with
__builtin_cpu_supports('avx2')
5. File consolidation: Removed duplicate backend/storage/page/checksum.c,
moved pg_checksum_page to unified port implementation
6. Documentation: Restored comprehensive algorithm comments
7. Comment clarity: Replaced confusing ISA-specific references
---
config/c-compiler.m4 | 31 +++++
configure | 52 ++++++++
configure.ac | 9 ++
meson.build | 28 +++++
src/backend/backup/basebackup.c | 2 +-
src/backend/storage/page/Makefile | 4 -
src/backend/storage/page/bufpage.c | 2 +-
src/backend/storage/page/checksum.c | 22 ----
src/backend/storage/page/meson.build | 9 --
src/bin/pg_checksums/pg_checksums.c | 4 +-
src/bin/pg_upgrade/file.c | 4 +-
src/include/pg_config.h.in | 3 +
src/include/{storage => port}/checksum.h | 2 +-
src/include/{storage => port}/checksum_impl.h | 104 ++++++++--------
src/port/Makefile | 6 +
src/port/checksum.c | 116 ++++++++++++++++++
src/port/meson.build | 5 +-
src/test/modules/test_aio/test_aio.c | 2 +-
src/tools/pginclude/headerscheck | 2 +-
19 files changed, 310 insertions(+), 97 deletions(-)
delete mode 100644 src/backend/storage/page/checksum.c
rename src/include/{storage => port}/checksum.h (94%)
rename src/include/{storage => port}/checksum_impl.h (77%)
create mode 100644 src/port/checksum.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/backend/backup/basebackup.c b/src/backend/backup/basebackup.c
index bb7d90aa5d9..d84ced4b47c 100644
--- a/src/backend/backup/basebackup.c
+++ b/src/backend/backup/basebackup.c
@@ -39,7 +39,7 @@
#include "replication/walsender.h"
#include "replication/walsender_private.h"
#include "storage/bufpage.h"
-#include "storage/checksum.h"
+#include "port/checksum.h"
#include "storage/dsm_impl.h"
#include "storage/ipc.h"
#include "storage/reinit.h"
diff --git a/src/backend/storage/page/Makefile b/src/backend/storage/page/Makefile
index da539b113a6..5d8a3d2f5ac 100644
--- a/src/backend/storage/page/Makefile
+++ b/src/backend/storage/page/Makefile
@@ -14,10 +14,6 @@ include $(top_builddir)/src/Makefile.global
OBJS = \
bufpage.o \
- checksum.o \
itemptr.o
include $(top_srcdir)/src/backend/common.mk
-
-# Provide special optimization flags for checksum.c
-checksum.o: CFLAGS += ${CFLAGS_UNROLL_LOOPS} ${CFLAGS_VECTORIZE}
diff --git a/src/backend/storage/page/bufpage.c b/src/backend/storage/page/bufpage.c
index dbb49ed9197..b8f889efb88 100644
--- a/src/backend/storage/page/bufpage.c
+++ b/src/backend/storage/page/bufpage.c
@@ -18,7 +18,7 @@
#include "access/itup.h"
#include "access/xlog.h"
#include "pgstat.h"
-#include "storage/checksum.h"
+#include "port/checksum.h"
#include "utils/memdebug.h"
#include "utils/memutils.h"
diff --git a/src/backend/storage/page/checksum.c b/src/backend/storage/page/checksum.c
deleted file mode 100644
index c913459b5a3..00000000000
--- a/src/backend/storage/page/checksum.c
+++ /dev/null
@@ -1,22 +0,0 @@
-/*-------------------------------------------------------------------------
- *
- * checksum.c
- * Checksum implementation for data pages.
- *
- * Portions Copyright (c) 1996-2025, PostgreSQL Global Development Group
- * Portions Copyright (c) 1994, Regents of the University of California
- *
- * IDENTIFICATION
- * src/backend/storage/page/checksum.c
- *
- *-------------------------------------------------------------------------
- */
-#include "postgres.h"
-
-#include "storage/checksum.h"
-/*
- * The actual code is in storage/checksum_impl.h. This is done so that
- * external programs can incorporate the checksum code by #include'ing
- * that file from the exported Postgres headers. (Compare our CRC code.)
- */
-#include "storage/checksum_impl.h" /* IWYU pragma: keep */
diff --git a/src/backend/storage/page/meson.build b/src/backend/storage/page/meson.build
index 112f00ff365..cf92a8f55f0 100644
--- a/src/backend/storage/page/meson.build
+++ b/src/backend/storage/page/meson.build
@@ -1,14 +1,5 @@
# Copyright (c) 2022-2025, PostgreSQL Global Development Group
-checksum_backend_lib = static_library('checksum_backend_lib',
- 'checksum.c',
- dependencies: backend_build_deps,
- kwargs: internal_lib_args,
- c_args: vectorize_cflags + unroll_loops_cflags,
-)
-
-backend_link_with += checksum_backend_lib
-
backend_sources += files(
'bufpage.c',
'itemptr.c',
diff --git a/src/bin/pg_checksums/pg_checksums.c b/src/bin/pg_checksums/pg_checksums.c
index f20be82862a..5231eb33207 100644
--- a/src/bin/pg_checksums/pg_checksums.c
+++ b/src/bin/pg_checksums/pg_checksums.c
@@ -28,8 +28,8 @@
#include "getopt_long.h"
#include "pg_getopt.h"
#include "storage/bufpage.h"
-#include "storage/checksum.h"
-#include "storage/checksum_impl.h"
+#include "port/checksum.h"
+#include "port/checksum_impl.h"
static int64 files_scanned = 0;
diff --git a/src/bin/pg_upgrade/file.c b/src/bin/pg_upgrade/file.c
index 91ed16acb08..084392ae54d 100644
--- a/src/bin/pg_upgrade/file.c
+++ b/src/bin/pg_upgrade/file.c
@@ -24,8 +24,8 @@
#include "common/file_perm.h"
#include "pg_upgrade.h"
#include "storage/bufpage.h"
-#include "storage/checksum.h"
-#include "storage/checksum_impl.h"
+#include "port/checksum.h"
+#include "port/checksum_impl.h"
/*
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.h b/src/include/port/checksum.h
similarity index 94%
rename from src/include/storage/checksum.h
rename to src/include/port/checksum.h
index 25d13a798d1..c2faed83ede 100644
--- a/src/include/storage/checksum.h
+++ b/src/include/port/checksum.h
@@ -6,7 +6,7 @@
* Portions Copyright (c) 1996-2025, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
- * src/include/storage/checksum.h
+ * src/include/port/checksum.h
*
*-------------------------------------------------------------------------
*/
diff --git a/src/include/storage/checksum_impl.h b/src/include/port/checksum_impl.h
similarity index 77%
rename from src/include/storage/checksum_impl.h
rename to src/include/port/checksum_impl.h
index da87d61ba52..357b2089f01 100644
--- a/src/include/storage/checksum_impl.h
+++ b/src/include/port/checksum_impl.h
@@ -5,13 +5,13 @@
*
* This file exists for the benefit of external programs that may wish to
* check Postgres page checksums. They can #include this to get the code
- * referenced by storage/checksum.h. (Note: you may need to redefine
+ * referenced by port/checksum.h. (Note: you may need to redefine
* Assert() as empty to compile this successfully externally.)
*
* Portions Copyright (c) 1996-2025, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
- * src/include/storage/checksum_impl.h
+ * src/include/port/checksum_impl.h
*
*-------------------------------------------------------------------------
*/
@@ -101,12 +101,15 @@
*/
#include "storage/bufpage.h"
+#include "pg_config.h"
+#include <string.h> /* for memcpy */
/* 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
{
@@ -139,77 +142,76 @@ do { \
} while (0)
/*
- * Block checksum algorithm. The page must be adequately aligned
- * (at least on 4-byte boundary).
+ * Default checksum implementation (always available)
*/
-static uint32
-pg_checksum_block(const PGChecksummablePage *page)
+static inline uint32
+pg_checksum_block_default_impl(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);
+ uint32 sums[N_SUMS], result = 0;
+ uint32 i, j;
- /* initialize partial checksums to their corresponding offsets */
+ /* Initialize each parallel checksum with different base offsets */
memcpy(sums, checksumBaseOffsets, sizeof(checksumBaseOffsets));
- /* main checksum calculation */
- for (i = 0; i < (uint32) (BLCKSZ / (sizeof(uint32) * N_SUMS)); i++)
+ /* Main checksum calculation loop - process page data in parallel */
+ 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 */
+ /* Two final rounds with zero to mix remaining bits */
for (i = 0; i < 2; i++)
for (j = 0; j < N_SUMS; j++)
CHECKSUM_COMP(sums[j], 0);
- /* xor fold partial checksums together */
+ /* Combine all parallel checksums with XOR to get final result */
for (i = 0; i < N_SUMS; i++)
result ^= sums[i];
return result;
}
+#ifdef USE_AVX2_WITH_RUNTIME_CHECK
/*
- * 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.
+ * AVX2 optimized implementation (may not be available on all systems)
*/
-uint16
-pg_checksum_page(char *page, BlockNumber blkno)
+pg_attribute_target("avx2")
+static inline uint32
+pg_checksum_block_avx2_impl(const PGChecksummablePage *page)
{
- 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.
+ /* For now, AVX2 implementation is identical to default
+ * The compiler will auto-vectorize this with proper flags
+ * Future versions could use explicit AVX2 intrinsics here
*/
- save_checksum = cpage->phdr.pd_checksum;
- cpage->phdr.pd_checksum = 0;
- checksum = pg_checksum_block(cpage);
- cpage->phdr.pd_checksum = save_checksum;
+ return pg_checksum_block_default_impl(page);
+}
+#endif
- /* Mix in the block number to detect transposed pages */
- checksum ^= blkno;
+/* Function declarations for checksum implementations */
+uint32 pg_checksum_block_default(const PGChecksummablePage *page);
+#ifdef USE_AVX2_WITH_RUNTIME_CHECK
+uint32 pg_checksum_block_avx2(const PGChecksummablePage *page);
+#endif
- /*
- * 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);
+uint32 pg_checksum_block_choose(const PGChecksummablePage *page);
+extern uint32 (*pg_checksum_block)(const PGChecksummablePage *page);
+
+/*
+ * Simple interface for external programs
+ * Define USE_AVX2_WITH_RUNTIME_CHECK before including to enable AVX2 if available
+ */
+#ifndef PG_CHECKSUM_EXTERNAL_INTERFACE
+#define PG_CHECKSUM_EXTERNAL_INTERFACE
+
+static inline uint32
+pg_checksum_block_simple(const PGChecksummablePage *page)
+{
+#ifdef USE_AVX2_WITH_RUNTIME_CHECK
+ /* External programs can use AVX2 if they define the macro and have CPU support */
+ if (__builtin_cpu_supports("avx2"))
+ return pg_checksum_block_avx2_impl(page);
+ else
+#endif
+ return pg_checksum_block_default_impl(page);
}
+
+#endif /* PG_CHECKSUM_EXTERNAL_INTERFACE */
diff --git a/src/port/Makefile b/src/port/Makefile
index 4274949dfa4..430b7bbbcb6 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 \
+ checksum.o \
pg_strong_random.o \
pgcheckdir.o \
pgmkdirp.o \
@@ -90,6 +91,11 @@ pg_crc32c_armv8.o: CFLAGS+=$(CFLAGS_CRC)
pg_crc32c_armv8_shlib.o: CFLAGS+=$(CFLAGS_CRC)
pg_crc32c_armv8_srv.o: CFLAGS+=$(CFLAGS_CRC)
+# all versions of checksum.o need vectorization and unroll-loops flags
+checksum.o: CFLAGS+=$(CFLAGS_VECTORIZE) $(CFLAGS_UNROLL_LOOPS)
+checksum_shlib.o: CFLAGS+=$(CFLAGS_VECTORIZE) $(CFLAGS_UNROLL_LOOPS)
+checksum_srv.o: CFLAGS+=$(CFLAGS_VECTORIZE) $(CFLAGS_UNROLL_LOOPS)
+
#
# Shared library versions of object files
#
diff --git a/src/port/checksum.c b/src/port/checksum.c
new file mode 100644
index 00000000000..df1a1b4ce83
--- /dev/null
+++ b/src/port/checksum.c
@@ -0,0 +1,116 @@
+/*-------------------------------------------------------------------------
+ *
+ * checksum.c
+ * Checksum implementation for data pages with AVX2 optimization.
+ *
+ * This file consolidates all checksum-related functionality including:
+ * - Runtime CPU feature detection
+ * - Default and AVX2-optimized implementations
+ * - Function dispatch logic
+ * - Page checksum calculation
+ *
+ * Portions Copyright (c) 1996-2025, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * IDENTIFICATION
+ * src/port/checksum.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "c.h"
+#include "port/checksum_impl.h"
+
+#ifndef FRONTEND
+#include "postgres.h"
+#include "storage/bufpage.h"
+#endif
+
+
+
+/*
+ * Check for AVX2 support using GCC builtin
+ */
+static inline bool
+avx2_available(void)
+{
+#ifdef USE_AVX2_WITH_RUNTIME_CHECK
+ return __builtin_cpu_supports("avx2");
+#else
+ return false;
+#endif
+}
+
+/* default checksum implementation */
+uint32
+pg_checksum_block_default(const PGChecksummablePage *page)
+{
+ return pg_checksum_block_default_impl(page);
+}
+
+#ifdef USE_AVX2_WITH_RUNTIME_CHECK
+pg_attribute_target("avx2")
+uint32
+pg_checksum_block_avx2(const PGChecksummablePage *page)
+{
+ return pg_checksum_block_avx2_impl(page);
+}
+#endif
+
+/* Function pointer - external linkage (declared extern in header) */
+uint32 (*pg_checksum_block)(const PGChecksummablePage *page) = pg_checksum_block_choose;
+
+/* Choose the best available checksum implementation */
+uint32 pg_checksum_block_choose(const PGChecksummablePage *page)
+{
+#ifdef USE_AVX2_WITH_RUNTIME_CHECK
+ if (avx2_available())
+ {
+ pg_checksum_block = pg_checksum_block_avx2;
+ return pg_checksum_block(page);
+ }
+#endif
+ /* fallback */
+ pg_checksum_block = pg_checksum_block_default;
+ return pg_checksum_block(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);
+}
diff --git a/src/port/meson.build b/src/port/meson.build
index fc7b059fee5..2074553f9a5 100644
--- a/src/port/meson.build
+++ b/src/port/meson.build
@@ -102,10 +102,11 @@ replace_funcs_pos = [
# generic fallback
['pg_crc32c_sb8', 'USE_SLICING_BY_8_CRC32C'],
+
]
-pgport_cflags = {'crc': cflags_crc}
-pgport_sources_cflags = {'crc': []}
+pgport_cflags = {'crc': cflags_crc, 'checksum': unroll_loops_cflags + vectorize_cflags}
+pgport_sources_cflags = {'crc': [], 'checksum': [files('checksum.c')]}
foreach f : replace_funcs_neg
func = f.get(0)
diff --git a/src/test/modules/test_aio/test_aio.c b/src/test/modules/test_aio/test_aio.c
index c55cf6c0aac..175e491c0bc 100644
--- a/src/test/modules/test_aio/test_aio.c
+++ b/src/test/modules/test_aio/test_aio.c
@@ -24,7 +24,7 @@
#include "storage/aio_internal.h"
#include "storage/buf_internals.h"
#include "storage/bufmgr.h"
-#include "storage/checksum.h"
+#include "port/checksum.h"
#include "storage/ipc.h"
#include "storage/lwlock.h"
#include "utils/builtins.h"
diff --git a/src/tools/pginclude/headerscheck b/src/tools/pginclude/headerscheck
index a52a5580bdc..35ac0caaa43 100755
--- a/src/tools/pginclude/headerscheck
+++ b/src/tools/pginclude/headerscheck
@@ -167,7 +167,7 @@ do
test "$f" = src/test/isolation/specparse.h && continue
# This produces a "no previous prototype" warning.
- ! $cplusplus && test "$f" = src/include/storage/checksum_impl.h && continue
+ ! $cplusplus && test "$f" = src/include/port/checksum_impl.h && continue
# SectionMemoryManager.h is C++
test "$f" = src/include/jit/SectionMemoryManager.h && continue
--
2.43.0
[application/octet-stream] v7-0002-Benchmark-code-for-postgres-checksums.patch (5.2K, 3-v7-0002-Benchmark-code-for-postgres-checksums.patch)
download | inline diff:
From 2fbafd83f0133b5737a47c9226dd72f86c2eb999 Mon Sep 17 00:00:00 2001
From: Andrew kim <[email protected]>
Date: Sat, 18 Oct 2025 13:13:05 -0700
Subject: [PATCH 2/2] Benchmark code for postgres checksums
---
contrib/meson.build | 1 +
contrib/pageinspect/rawpage.c | 2 +-
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 ++++++++++
7 files changed, 88 insertions(+), 1 deletion(-)
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/pageinspect/rawpage.c b/contrib/pageinspect/rawpage.c
index aef442b5db3..7beb7765da9 100644
--- a/contrib/pageinspect/rawpage.c
+++ b/contrib/pageinspect/rawpage.c
@@ -23,7 +23,7 @@
#include "miscadmin.h"
#include "pageinspect.h"
#include "storage/bufmgr.h"
-#include "storage/checksum.h"
+#include "port/checksum.h"
#include "utils/builtins.h"
#include "utils/pg_lsn.h"
#include "utils/rel.h"
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..e5b150e6b13
--- /dev/null
+++ b/contrib/pg_checksum_bench/pg_checksum_bench.c
@@ -0,0 +1,34 @@
+#include "postgres.h"
+#include "fmgr.h"
+#include "port/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
view thread (35+ 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], [email protected]
Subject: Re: Proposal for enabling auto-vectorization for checksum calculations
In-Reply-To: <CAK64mnd6VAtTbar=QS4sbWJpfFxjksjg2ERNkGw1tRwh_kc6mw@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