From 9d2edad34a1823bab012f5d0593d461a9ec396fb Mon Sep 17 00:00:00 2001 From: Masahiko Sawada Date: Thu, 25 Jun 2026 10:03:44 -0700 Subject: [PATCH v4 1/2] Optimize UUID parse using SIMD. Previously, string_to_uuid() decoded one byte at a time, calling isxdigit() twice and strtoul() once for every pair of hexadecimal digits. That loop dominated the cost of uuid_in(). This commit adds a fast path for the two common shapes: a bare string of 32 hexadecimal digits, and the canonical 8x-4x-4x-4x-12x form (where "nx" means n hexadecimal digits), each optionally wrapped in braces. Both are compacted into 32 contiguous hexadecimal digits and decoded with hex_decode_safe(). Any other shape, or any decoding error, is handed off to the original scalar parser, now string_to_uuid_scalar(), so the accepted grammar and the error messages are unchanged. hex_decode_safe() silently skips whitespace while the UUID grammar does not, so a decode can succeed and still write fewer than UUID_LEN bytes. The fast path therefore treats a short result as a failure, just like an error, and lets the scalar parser reject the input and report the syntax error. The fast path is deliberately not conditional on SIMD support. hex_decode_safe() selects a vectorized or scalar implementation itself, and even its scalar implementation is an order of magnitude faster than decoding a byte at a time, so gating this on USE_NO_SIMD would only penalize platforms that have neither SSE2 nor NEON. Reviewed-by: Bharath Rupireddy Reviewed-by: Haibo Yan Discussion: https://postgr.es/m/CAD21AoCqeR4UQU77Q_yOMNNzJ7AVeiO5QZT+4HnzPm4Wm-e02Q@mail.gmail.com --- src/backend/utils/adt/uuid.c | 94 ++++++++++++++++++++++++++++-- src/test/regress/expected/uuid.out | 55 +++++++++++++++++ src/test/regress/sql/uuid.sql | 16 +++++ 3 files changed, 160 insertions(+), 5 deletions(-) diff --git a/src/backend/utils/adt/uuid.c b/src/backend/utils/adt/uuid.c index 246225a8735..3ecca6d3748 100644 --- a/src/backend/utils/adt/uuid.c +++ b/src/backend/utils/adt/uuid.c @@ -19,7 +19,9 @@ #include "common/hashfn.h" #include "lib/hyperloglog.h" #include "libpq/pqformat.h" +#include "nodes/miscnodes.h" #include "port/pg_bswap.h" +#include "utils/builtins.h" #include "utils/fmgrprotos.h" #include "utils/guc.h" #include "utils/skipsupport.h" @@ -139,13 +141,13 @@ uuid_out(PG_FUNCTION_ARGS) } /* - * We allow UUIDs as a series of 32 hexadecimal digits with an optional dash - * after each group of 4 hexadecimal digits, and optionally surrounded by {}. - * (The canonical format 8x-4x-4x-4x-12x, where "nx" means n hexadecimal - * digits, is the only one used for output.) + * Reference implementation of the UUID grammar, parsing one character at a + * time. string_to_uuid() recognizes the common shapes more cheaply and + * defers to this function for everything else, so this is also the only + * place that reports a syntax error. */ static void -string_to_uuid(const char *source, pg_uuid_t *uuid, Node *escontext) +string_to_uuid_scalar(const char *source, pg_uuid_t *uuid, Node *escontext) { const char *src = source; bool braces = false; @@ -194,6 +196,88 @@ syntax_error: "uuid", source))); } +/* + * We allow UUIDs as a series of 32 hexadecimal digits with an optional dash + * after each group of 4 hexadecimal digits, and optionally surrounded by {}. + * (The canonical format 8x-4x-4x-4x-12x, where "nx" means n hexadecimal + * digits, is the only one used for output.) + * + * The two common shapes -- a bare string of 32 hexadecimal digits and the + * canonical form, each optionally wrapped in braces -- are compacted into 32 + * contiguous hex digits and decoded with hex_decode_safe(), which is much + * faster than the character-at-a-time loop. Any other shape, or any decoding + * error, is handed off to string_to_uuid_scalar() so that the accepted + * grammar and the error messages are unchanged. + * + * Note that this fast path is not conditional on SIMD support: + * hex_decode_safe() picks a vectorized or scalar implementation itself, and + * even its scalar implementation is far faster than string_to_uuid_scalar(). + */ +static void +string_to_uuid(const char *source, pg_uuid_t *uuid, Node *escontext) +{ + const char *body = source; + size_t len = strlen(source); + const char *hexsrc = NULL; + char hexbuf[32]; + uint64 written; + ErrorSaveContext esctx = {T_ErrorSaveContext}; + + /* Strip one optional surrounding brace pair */ + if (len >= 2 && source[0] == '{' && source[len - 1] == '}') + { + body = source + 1; + len -= 2; + } + + if (len == 32) + { + /* + * Body is already 32 contiguous hex digits -- decode straight from + * the input. hex_decode_safe() reads exactly body[0..31], so it never + * touches the trailing NULL or '}'. + */ + hexsrc = body; + } + else if (len == 36 && body[8] == '-' && body[13] == '-' && + body[18] == '-' && body[23] == '-') + { + /* + * Canonical 8x-4x-4x-4x-12x form; compact them into hexbuf with + * fixed-offset copies, dropping the dashes. + */ + memcpy(&hexbuf[0], &body[0], 8); + memcpy(&hexbuf[8], &body[9], 4); + memcpy(&hexbuf[12], &body[14], 4); + memcpy(&hexbuf[16], &body[19], 4); + memcpy(&hexbuf[20], &body[24], 12); + hexsrc = hexbuf; + } + + if (hexsrc == NULL) + { + /* Uncommon shape; let the general parse handle it */ + string_to_uuid_scalar(source, uuid, escontext); + return; + } + + /* + * Decode the UUID hex data using our hex decoder that is SIMD-aware. We + * give it a private error context so that a decode failure is swallowed + * here and reported by the scalar path instead, keeping the error message + * identical. + */ + written = hex_decode_safe(hexsrc, 32, (char *) uuid->data, (Node *) &esctx); + + /* + * Fall back to the scalar path on any error. We must also reject a short + * result: hex_decode_safe() skips whitespace, so it can succeed yet write + * fewer than UUID_LEN bytes, whereas the UUID grammar forbids whitespace. + */ + if (esctx.error_occurred || written != UUID_LEN) + string_to_uuid_scalar(source, uuid, escontext); +} + Datum uuid_recv(PG_FUNCTION_ARGS) { diff --git a/src/test/regress/expected/uuid.out b/src/test/regress/expected/uuid.out index d542eb14b26..b40f50ac8be 100644 --- a/src/test/regress/expected/uuid.out +++ b/src/test/regress/expected/uuid.out @@ -375,5 +375,60 @@ SELECT v = v::bytea::uuid as matched FROM gen_random_uuid() v; t (1 row) +-- Test UUID shapes that the parser uses the SIMD path. +SELECT '5b35380a-7143-4912-9b55-f322699c6770'::uuid; + uuid +-------------------------------------- + 5b35380a-7143-4912-9b55-f322699c6770 +(1 row) + +SELECT '{5b35380a-7143-4912-9b55-f322699c6770}'::uuid; + uuid +-------------------------------------- + 5b35380a-7143-4912-9b55-f322699c6770 +(1 row) + +SELECT '5b35380a714349129b55f322699c6770'::uuid; + uuid +-------------------------------------- + 5b35380a-7143-4912-9b55-f322699c6770 +(1 row) + +SELECT '{5b35380a714349129b55f322699c6770}'::uuid; + uuid +-------------------------------------- + 5b35380a-7143-4912-9b55-f322699c6770 +(1 row) + +-- Test if the UUID parser using SIMD optimization correctly rejects invalid UUID +-- string format. +SELECT '5b35380a714349129b55f32 99c6770'::uuid; +ERROR: invalid input syntax for type uuid: "5b35380a714349129b55f32 99c6770" +LINE 1: SELECT '5b35380a714349129b55f32 99c6770'::uuid; + ^ +SELECT '5b35380a-7143-4912-9b55-f322699c67 '::uuid; +ERROR: invalid input syntax for type uuid: "5b35380a-7143-4912-9b55-f322699c67 " +LINE 1: SELECT '5b35380a-7143-4912-9b55-f322699c67 '::uuid; + ^ +SELECT ' 35380a-7143-4912-9b55-f322699c6770'::uuid; +ERROR: invalid input syntax for type uuid: " 35380a-7143-4912-9b55-f322699c6770" +LINE 1: SELECT ' 35380a-7143-4912-9b55-f322699c6770'::uuid; + ^ +SELECT 'AZ35380a-7143-4912-9b55-f322699c6770'::uuid; +ERROR: invalid input syntax for type uuid: "AZ35380a-7143-4912-9b55-f322699c6770" +LINE 1: SELECT 'AZ35380a-7143-4912-9b55-f322699c6770'::uuid; + ^ +SELECT '{AZ35380a-7143-4912-9b55-f322699c6770}'::uuid; +ERROR: invalid input syntax for type uuid: "{AZ35380a-7143-4912-9b55-f322699c6770}" +LINE 1: SELECT '{AZ35380a-7143-4912-9b55-f322699c6770}'::uuid; + ^ +SELECT '{AZ35380a714349129b55f322699c6770}'::uuid; +ERROR: invalid input syntax for type uuid: "{AZ35380a714349129b55f322699c6770}" +LINE 1: SELECT '{AZ35380a714349129b55f322699c6770}'::uuid; + ^ +SELECT '{AZ35380a714349129b55f322699c67 }'::uuid; +ERROR: invalid input syntax for type uuid: "{AZ35380a714349129b55f322699c67 }" +LINE 1: SELECT '{AZ35380a714349129b55f322699c67 }'::uuid; + ^ -- clean up DROP TABLE guid1, guid2, guid3 CASCADE; diff --git a/src/test/regress/sql/uuid.sql b/src/test/regress/sql/uuid.sql index 54f0d8f8255..bdbeb91fe4c 100644 --- a/src/test/regress/sql/uuid.sql +++ b/src/test/regress/sql/uuid.sql @@ -178,5 +178,21 @@ SELECT '\x019a2f859ced7225b99d9c55044a2563'::bytea::uuid; SELECT '\x1234567890abcdef'::bytea::uuid; -- error SELECT v = v::bytea::uuid as matched FROM gen_random_uuid() v; +-- Test UUID shapes that the parser uses the SIMD path. +SELECT '5b35380a-7143-4912-9b55-f322699c6770'::uuid; +SELECT '{5b35380a-7143-4912-9b55-f322699c6770}'::uuid; +SELECT '5b35380a714349129b55f322699c6770'::uuid; +SELECT '{5b35380a714349129b55f322699c6770}'::uuid; + +-- Test if the UUID parser using SIMD optimization correctly rejects invalid UUID +-- string format. +SELECT '5b35380a714349129b55f32 99c6770'::uuid; +SELECT '5b35380a-7143-4912-9b55-f322699c67 '::uuid; +SELECT ' 35380a-7143-4912-9b55-f322699c6770'::uuid; +SELECT 'AZ35380a-7143-4912-9b55-f322699c6770'::uuid; +SELECT '{AZ35380a-7143-4912-9b55-f322699c6770}'::uuid; +SELECT '{AZ35380a714349129b55f322699c6770}'::uuid; +SELECT '{AZ35380a714349129b55f322699c67 }'::uuid; + -- clean up DROP TABLE guid1, guid2, guid3 CASCADE; -- 2.55.0