From 2060f79bd3ee29809788a466700a9dc49459ca8e Mon Sep 17 00:00:00 2001 From: AyoubKAZ Date: Sat, 14 Feb 2026 15:12:42 +0100 Subject: [PATCH] Speed up COPY TO text/CSV using SIMD Use SIMD to scan for special characters in COPY TO, processing 16+ bytes at a time instead of byte-by-byte. This speeds up export of fields that contain few characters requiring escaping, so the code falls back to scalar path when we find a special char. --- src/backend/commands/copyto.c | 159 +++++++++++++++++++++++++++++++++- 1 file changed, 157 insertions(+), 2 deletions(-) diff --git a/src/backend/commands/copyto.c b/src/backend/commands/copyto.c index 9ceeff6d99e..49198137531 100644 --- a/src/backend/commands/copyto.c +++ b/src/backend/commands/copyto.c @@ -31,6 +31,8 @@ #include "mb/pg_wchar.h" #include "miscadmin.h" #include "pgstat.h" +#include "port/pg_bitutils.h" +#include "port/simd.h" #include "storage/fd.h" #include "tcop/tcopprot.h" #include "utils/lsyscache.h" @@ -121,6 +123,142 @@ static void CopyAttributeOutCSV(CopyToState cstate, const char *string, bool use_quote); static void CopyRelationTo(CopyToState cstate, Relation rel, Relation root_rel, uint64 *processed); +static pg_attribute_always_inline void CopySkipTextSIMD(const char **ptr, + size_t len, char delimc); + +static pg_attribute_always_inline void CopyCheckCSVQuoteNeedSIMD(const char **ptr, + size_t len, char delimc, char quotec); + +static pg_attribute_always_inline void CopySkipCSVEscapeSIMD(const char **ptr, + size_t len, char escapec, char quotec); + +/* + * CopySkipTextSIMD - Skip forward past safe characters in TEXT mode using SIMD + * + * Advances ptr as far as possible, stopping at first special character. + */ +static pg_attribute_always_inline void +CopySkipTextSIMD(const char **ptr, size_t len, char delimc) +{ +#ifndef USE_NO_SIMD + const char *p = *ptr; + + const char *end = p + len; + + while (p + sizeof(Vector8) <= end) + { + Vector8 chunk; + Vector8 control_mask; + Vector8 backslash_mask; + Vector8 delim_mask; + Vector8 special_mask; + uint32 mask; + + vector8_load(&chunk, (const uint8 *) p); + control_mask = vector8_gt(vector8_broadcast(0x20), chunk); + backslash_mask = vector8_eq(vector8_broadcast('\\'), chunk); + delim_mask = vector8_eq(vector8_broadcast(delimc), chunk); + + special_mask = vector8_or(control_mask, + vector8_or(backslash_mask, delim_mask)); + + mask = vector8_highbit_mask(special_mask); + if (mask != 0) + { + *ptr = p + pg_rightmost_one_pos32(mask); + return; + } + + p += sizeof(Vector8); + } + + *ptr = p; +#endif +} + +/* + * CopyCheckCSVQuoteNeedSIMD - Check if CSV field needs quoting using SIMD + * + * Advances ptr as far as possible, stopping at first special character. + */ +static pg_attribute_always_inline void +CopyCheckCSVQuoteNeedSIMD(const char **ptr, size_t len, char delimc, char quotec) +{ +#ifndef USE_NO_SIMD + const char *p = *ptr; + const char *end = p + len; + + Vector8 delim_mask = vector8_broadcast(delimc); + Vector8 quote_mask = vector8_broadcast(quotec); + Vector8 newline_mask = vector8_broadcast('\n'); + Vector8 carriage_return_mask = vector8_broadcast('\r'); + + while (p + sizeof(Vector8) <= end) + { + Vector8 chunk; + Vector8 special_mask; + uint32 mask; + + vector8_load(&chunk, (const uint8 *) p); + special_mask = vector8_or( + vector8_or(vector8_eq(chunk, delim_mask), + vector8_eq(chunk, quote_mask)), + vector8_or(vector8_eq(chunk, newline_mask), + vector8_eq(chunk, carriage_return_mask)) + ); + + mask = vector8_highbit_mask(special_mask); + if (mask != 0) + { + *ptr = p + pg_rightmost_one_pos32(mask); + return; + } + + p += sizeof(Vector8); + } + + *ptr = p; +#endif +} + +/* + * CopySkipCSVEscapeSIMD - Skip forward past safe characters in CSV mode using SIMD + * + * Advances ptr as far as possible, stopping at first quote or escape character. + */ +static pg_attribute_always_inline void +CopySkipCSVEscapeSIMD(const char **ptr, size_t len, char escapec, char quotec) +{ +#ifndef USE_NO_SIMD + const char *p = *ptr; + const char *end = p + len; + + Vector8 escape_mask = vector8_broadcast(escapec); + Vector8 quote_mask = vector8_broadcast(quotec); + + while (p + sizeof(Vector8) <= end) + { + Vector8 chunk; + Vector8 special_mask; + uint32 mask; + + vector8_load(&chunk, (const uint8 *) p); + special_mask = vector8_or(vector8_eq(chunk, escape_mask), + vector8_eq(chunk, quote_mask)); + + mask = vector8_highbit_mask(special_mask); + if (mask != 0) + { + *ptr = p + pg_rightmost_one_pos32(mask); + return; + } + + p += sizeof(Vector8); + } + + *ptr = p; +#endif +} /* built-in format-specific routines */ static void CopyToTextLikeStart(CopyToState cstate, TupleDesc tupDesc); @@ -1245,9 +1383,14 @@ CopyAttributeOutText(CopyToState cstate, const char *string) const char *start; char c; char delimc = cstate->opts.delim[0]; + size_t len = strlen(string); if (cstate->need_transcoding) - ptr = pg_server_to_any(string, strlen(string), cstate->file_encoding); + { + ptr = pg_server_to_any(string, len, cstate->file_encoding); + /* We have to recalculate the length after transcoding, because it can change the string length */ + len = strlen(ptr); + } else ptr = string; @@ -1268,6 +1411,8 @@ CopyAttributeOutText(CopyToState cstate, const char *string) if (cstate->encoding_embeds_ascii) { start = ptr; + CopySkipTextSIMD(&ptr, len, delimc); + while ((c = *ptr) != '\0') { if ((unsigned char) c < (unsigned char) 0x20) @@ -1328,6 +1473,8 @@ CopyAttributeOutText(CopyToState cstate, const char *string) else { start = ptr; + CopySkipTextSIMD(&ptr, len, delimc); + while ((c = *ptr) != '\0') { if ((unsigned char) c < (unsigned char) 0x20) @@ -1402,13 +1549,18 @@ CopyAttributeOutCSV(CopyToState cstate, const char *string, char quotec = cstate->opts.quote[0]; char escapec = cstate->opts.escape[0]; bool single_attr = (list_length(cstate->attnumlist) == 1); + size_t len = strlen(string); /* force quoting if it matches null_print (before conversion!) */ if (!use_quote && strcmp(string, cstate->opts.null_print) == 0) use_quote = true; if (cstate->need_transcoding) - ptr = pg_server_to_any(string, strlen(string), cstate->file_encoding); + { + ptr = pg_server_to_any(string, len, cstate->file_encoding); + /* We have to recalculate the length after transcoding, because it can change the string length */ + len = strlen(ptr); + } else ptr = string; @@ -1429,6 +1581,7 @@ CopyAttributeOutCSV(CopyToState cstate, const char *string, else { const char *tptr = ptr; + CopyCheckCSVQuoteNeedSIMD(&tptr, len, delimc, quotec); while ((c = *tptr) != '\0') { @@ -1453,6 +1606,8 @@ CopyAttributeOutCSV(CopyToState cstate, const char *string, * We adopt the same optimization strategy as in CopyAttributeOutText */ start = ptr; + CopySkipCSVEscapeSIMD(&ptr, len, escapec, quotec); + while ((c = *ptr) != '\0') { if (c == quotec || c == escapec) -- 2.34.1