After adding -ftree-vectorize and moving the loop boundary computations to outside the loops, popular compilers will auto-vectorize bit_and(), bit_or(), bitxor(), and bitnot(). My testing indicates this produces some nice speedups, but I haven't yet done anything scientific enough to share.
-- nathan
>From 027ed15aa336948445918d85d01fed6eef0df6c0 Mon Sep 17 00:00:00 2001 From: Nathan Bossart <[email protected]> Date: Wed, 2 Sep 2026 13:52:14 -0500 Subject: [PATCH v1 1/1] Auto-vectorize the varbit bitwise operators. Compile varbit.c with -ftree-vectorize where available, and adjust the loops in bit_and(), bit_or(), bitxor(), and bitnot() so that they are amenable to being auto-vectorized. (Mainly, that involves reading the byte count into a local variable before the loop. As written, the bound is recomputed from the varlena header on every iteration, because the compiler must assume that the loop might modify the header.) --- src/backend/utils/adt/Makefile | 3 ++- src/backend/utils/adt/meson.build | 9 ++++----- src/backend/utils/adt/varbit.c | 25 +++++++++++++++++-------- 3 files changed, 23 insertions(+), 14 deletions(-) diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 0c7621957c1..94ac5169940 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -150,8 +150,9 @@ clean: like.o: like.c like_match.c -# Some code in numeric.c benefits from auto-vectorization +# Some code benefits from auto-vectorization numeric.o: CFLAGS += ${CFLAGS_VECTORIZE} +varbit.o: CFLAGS += ${CFLAGS_VECTORIZE} varlena.o: varlena.c levenshtein.c diff --git a/src/backend/utils/adt/meson.build b/src/backend/utils/adt/meson.build index d793f8145f6..04d6f8aa168 100644 --- a/src/backend/utils/adt/meson.build +++ b/src/backend/utils/adt/meson.build @@ -1,14 +1,14 @@ # Copyright (c) 2022-2026, PostgreSQL Global Development Group -# Some code in numeric.c benefits from auto-vectorization -numeric_backend_lib = static_library('numeric_backend_lib', - 'numeric.c', +# Some code benefits from auto-vectorization +vectorize_backend_lib = static_library('vectorize_backend_lib', + ['numeric.c', 'varbit.c'], dependencies: backend_build_deps, kwargs: internal_lib_args, c_args: vectorize_cflags, ) -backend_link_with += numeric_backend_lib +backend_link_with += vectorize_backend_lib backend_sources += files( 'acl.c', @@ -118,7 +118,6 @@ backend_sources += files( 'tsvector_op.c', 'tsvector_parser.c', 'uuid.c', - 'varbit.c', 'varchar.c', 'varlena.c', 'version.c', diff --git a/src/backend/utils/adt/varbit.c b/src/backend/utils/adt/varbit.c index fe49ba851ac..cbb60e68335 100644 --- a/src/backend/utils/adt/varbit.c +++ b/src/backend/utils/adt/varbit.c @@ -1251,6 +1251,7 @@ bit_and(PG_FUNCTION_ARGS) uint8 *p1, *p2, *r; + size_t nbytes; bitlen1 = VARBITLEN(arg1); bitlen2 = VARBITLEN(arg2); @@ -1267,8 +1268,9 @@ bit_and(PG_FUNCTION_ARGS) p1 = VARBITS(arg1); p2 = VARBITS(arg2); r = VARBITS(result); - for (size_t i = 0; i < VARBITBYTES(arg1); i++) - *r++ = *p1++ & *p2++; + nbytes = VARBITBYTES(arg1); + for (size_t i = 0; i < nbytes; i++) + r[i] = p1[i] & p2[i]; /* Padding is not needed as & of 0 pads is 0 */ @@ -1291,6 +1293,7 @@ bit_or(PG_FUNCTION_ARGS) uint8 *p1, *p2, *r; + size_t nbytes; bitlen1 = VARBITLEN(arg1); bitlen2 = VARBITLEN(arg2); @@ -1306,8 +1309,9 @@ bit_or(PG_FUNCTION_ARGS) p1 = VARBITS(arg1); p2 = VARBITS(arg2); r = VARBITS(result); - for (size_t i = 0; i < VARBITBYTES(arg1); i++) - *r++ = *p1++ | *p2++; + nbytes = VARBITBYTES(arg1); + for (size_t i = 0; i < nbytes; i++) + r[i] = p1[i] | p2[i]; /* Padding is not needed as | of 0 pads is 0 */ @@ -1330,6 +1334,7 @@ bitxor(PG_FUNCTION_ARGS) uint8 *p1, *p2, *r; + size_t nbytes; bitlen1 = VARBITLEN(arg1); bitlen2 = VARBITLEN(arg2); @@ -1346,8 +1351,9 @@ bitxor(PG_FUNCTION_ARGS) p1 = VARBITS(arg1); p2 = VARBITS(arg2); r = VARBITS(result); - for (size_t i = 0; i < VARBITBYTES(arg1); i++) - *r++ = *p1++ ^ *p2++; + nbytes = VARBITBYTES(arg1); + for (size_t i = 0; i < nbytes; i++) + r[i] = p1[i] ^ p2[i]; /* Padding is not needed as ^ of 0 pads is 0 */ @@ -1365,6 +1371,7 @@ bitnot(PG_FUNCTION_ARGS) VarBit *result; uint8 *p, *r; + size_t nbytes; result = (VarBit *) palloc(VARSIZE(arg)); SET_VARSIZE(result, VARSIZE(arg)); @@ -1372,8 +1379,10 @@ bitnot(PG_FUNCTION_ARGS) p = VARBITS(arg); r = VARBITS(result); - for (; p < VARBITEND(arg); p++) - *r++ = ~*p; + nbytes = VARBITBYTES(arg); + for (size_t i = 0; i < nbytes; i++) + r[i] = ~p[i]; + r += nbytes; /* Must zero-pad the result, because extra bits are surely 1's here */ VARBIT_PAD_LAST(result, r); -- 2.55.0
