From 40f9d989df2c1ff2f567656ccbdbfc0d97e34a77 Mon Sep 17 00:00:00 2001 From: Michael Smith Date: Sat, 13 Dec 2025 18:26:51 +0000 Subject: Switch cmeta from chibicc to a new homegrown lexer This lexer is being written as a chunklet, not quite quite complete yet as it lacks some functionality to make it generally useful for things, but good enough for the gluegen use case now. So it's in the repo now and we can go ahead and use it for this instead of having this hacked-to-pieces third party thing that's nowhere near as efficient. In the future the goal is to have a decently usable library for any sort of C metaprogramming needs, not just within this project. This design does the data-oriented thing of storing as little about each token as possible (just 5 bytes), and re-lexing specific pieces only when necessary. In some cases, full validation of correct syntax is only possible through this secondary step. Since the use case is metaprogramming and code-generation rather than the reimplementation of Clang, this slight sloppiness in validation doesn't seem too bad. It's been a while since I did a proper performance measurement of this code but in some crude tests I did in the past the primary tokenisation step was running at well over 500MB/s, which is fast enough for me. It's possible that this version is a tiny bit slower due to the added complexity of making UCNs work. UCNs, incidentally, are one of the dumbest features of C by far. However, unlike trigraphs - which this lexer does not handle - UCNs are still in the language, so it's kind of sort of necessary to support them. It's probably still possible to come up with a faster design with some SIMD trickery, but the main loop is currently branchless and the lookup tables are too big for the SIMD lookup things, so that seems kind of hard. A separate SIMD path for whitespace or comment runs seems dubious as it would introduce branch mispredictions everywhere. I also made previous attempts to unroll the main loop and every attempt just made it slower, so I guess code size is a significant factor. Optimising the secondary tokenisation of identifiers (and later numerals and string/character literals once those are handled) is still on the cards, but since that happens less often, I don't know how much difference it'll make. At any rate, in a multithreaded context this thing would already come pretty close to SSD speeds, if open-read-close syscall overhead doesn't get in the way first. I imagine it's fast enough for anyone who hasn't *already* written something faster. --- src/build/cmeta.h | 49 ++++++++++++++++++++++++------------------------- 1 file changed, 24 insertions(+), 25 deletions(-) (limited to 'src/build/cmeta.h') diff --git a/src/build/cmeta.h b/src/build/cmeta.h index e7c275d..c18adbb 100644 --- a/src/build/cmeta.h +++ b/src/build/cmeta.h @@ -17,33 +17,23 @@ #ifndef INC_CMETA_H #define INC_CMETA_H +#include "../chunklets/clex.h" /* XXX: only need this for struct, kinda leaky */ #include "../intdefs.h" #include "../os.h" -// XXX: leaking chibicc internals. won't matter after we do away with that -typedef struct Token Token; - -enum cmeta_item { - CMETA_ITEM_DEF_CVAR, // includes all min/max/unreg variants - CMETA_ITEM_DEF_CCMD, // includes plusminus/unreg variants - CMETA_ITEM_DEF_EVENT, // includes predicates +enum cmeta_itemtype { + CMETA_ITEM_DEF_CVAR, /* includes all min/max/unreg variants */ + CMETA_ITEM_DEF_CCMD, /* includes plusminus/unreg variants */ + CMETA_ITEM_DEF_EVENT, /* includes predicates */ CMETA_ITEM_HANDLE_EVENT, CMETA_ITEM_FEATURE, - CMETA_ITEM_REQUIRE, // includes all REQUIRE_*/REQUEST variants + CMETA_ITEM_REQUIRE, /* includes all REQUIRE_* and REQUEST variants */ CMETA_ITEM_GAMESPECIFIC, CMETA_ITEM_PREINIT, CMETA_ITEM_INIT, CMETA_ITEM_END }; -struct cmeta { - char *sbase; - u32 nitems; // number of interesting macros - //u32 *itemoffs; // file offsets of interesting macros (ONE DAY!) - Token **itemtoks; // crappy linked token structures, for the time being - u8 *itemtypes; // CMETA_ITEM_* enum values -}; - enum cmeta_flag_cvar { CMETA_CVAR_UNREG = 1, CMETA_CVAR_FEAT = 2, @@ -57,28 +47,37 @@ enum cmeta_flag_event { CMETA_EVENT_ISPREDICATE = 1 }; enum cmeta_flag_require { - CMETA_REQUIRE_OPTIONAL = 1, // i.e. REQUEST() macro, could be extended + CMETA_REQUIRE_OPTIONAL = 1, /* i.e. REQUEST() macro, could be extended */ CMETA_REQUIRE_GAMEDATA = 2, CMETA_REQUIRE_GLOBAL = 4 }; +struct cmeta { + char *sbase; + u32 nitems; /* number of interesting macros */ + //char pad[4]; + struct cmeta_item { + u8 type : 4; /* CMETA_ITEM_* enum value */ + u8 flags : 4; /* relevant flags (see above) */ + } *items; + u32 *itemtoks; /* internal */ + struct clex lexer; /* internal */ +}; + struct cmeta_slice { const char *s; int len; }; struct cmeta cmeta_loadfile(const os_char *path); -int cmeta_flags_cvar(const struct cmeta *cm, u32 i); -int cmeta_flags_ccmd(const struct cmeta *cm, u32 i); -int cmeta_flags_event(const struct cmeta *cm, u32 i); -int cmeta_flags_require(const struct cmeta *cm, u32 i); int cmeta_nparams(const struct cmeta *cm, u32 i); -struct cmeta_param_iter { Token *cur; }; +struct cmeta_param_iter { u32 i; }; struct cmeta_param_iter cmeta_param_iter_init(const struct cmeta *cm, u32 i); -struct cmeta_slice cmeta_param_iter(struct cmeta_param_iter *it); +struct cmeta_slice cmeta_param_iter(const struct cmeta *cm, + struct cmeta_param_iter *it); -#define cmeta_param_foreach(varname, cm, u32) \ +#define cmeta_param_foreach(varname, cm, i) \ switch (0) for (struct cmeta_slice varname; 0;) default: \ for (struct cmeta_param_iter _it = cmeta_param_iter_init(cm, i); \ - varname = cmeta_param_iter(&_it), varname.s;) \ + varname = cmeta_param_iter(cm, &_it), varname.s;) \ /* {...} */ u32 cmeta_line(const struct cmeta *cm, u32 i); -- cgit v1.2.3-54-g00ecf