From 30089af06d6c3a0c4b5f1f4fa6af521309354209 Mon Sep 17 00:00:00 2001 From: dsh Date: Fri, 6 Nov 2026 11:04:29 +0800 Subject: [PATCH] Rewrite the bit macros as %synth blocks The eight bit-level macros in asm/ are now synthesised instead of hand written. Their tables were not typed in by hand: r8forge_derive (new, src/derive.cc) runs the OLD implementation over every input combination and reads the cells back, so the replacement is bit-for-bit identical, quirks included. big two findings: * a synth block assumes the parameters that do not take part in the computation start at 0 (that is what compress_stat_space means). These macros are called repeatedly inside a loop, so S/Co/tmp arrive dirty; each one now has a thin %macro wrapper that clears them and then calls the synthesised body. With that, bit_raw_add derives to exactly the old table (0 9 10 19 12 21 22 31 repeated) and bit_raw_and to 0 1 2 7 repeated. * clb_bit_and stays hand written. Three parameters leave no scratch bit and "and" needs both inputs alive at once, so it needs nested biz; the searcher exhausts nine layers over three planes without finding anything. That is the model's expressive limit, not a shallow search. asm/test.r8asm assembles to 1674 characters, down from 1714, with identical block semantics. %synth results are cached in .r8forge_cache/ keyed by the table, so the twenty minute tape search happens once per table rather than once per build. Note on verification: r8forge_derive validates one block at a time, which is what the tables above are. The little VM inside it is not solid enough to vouch for whole programs (fibonacci prints two numbers instead of ten), so "the whole library still computes the right answer end to end" is NOT verified here -- that needs the real ROT-8 virtual machine. --- .gitignore | 2 + CMakeLists.txt | 3 + README.md | 21 ++++++- asm/raw_add.r8asm | 99 ++++++--------------------------- asm/raw_and.r8asm | 77 +++++++------------------- asm/raw_inc.r8asm | 81 ++++++--------------------- asm/raw_or.r8asm | 102 ++++++++-------------------------- asm/raw_xor.r8asm | 92 ++++++++---------------------- drv/bit_raw_add.r8asm | 8 +++ drv/bit_raw_and.r8asm | 6 ++ drv/bit_raw_inc.r8asm | 7 +++ drv/bit_raw_or.r8asm | 6 ++ drv/bit_raw_xor.r8asm | 6 ++ drv/clb_bit_and.r8asm | 5 ++ drv/clb_bit_or.r8asm | 5 ++ drv/clb_bit_xor.r8asm | 5 ++ src/derive.cc | 126 ++++++++++++++++++++++++++++++++++++++++++ src/synth.cc | 47 ++++++++++++++++ 18 files changed, 347 insertions(+), 351 deletions(-) create mode 100644 drv/bit_raw_add.r8asm create mode 100644 drv/bit_raw_and.r8asm create mode 100644 drv/bit_raw_inc.r8asm create mode 100644 drv/bit_raw_or.r8asm create mode 100644 drv/bit_raw_xor.r8asm create mode 100644 drv/clb_bit_and.r8asm create mode 100644 drv/clb_bit_or.r8asm create mode 100644 drv/clb_bit_xor.r8asm create mode 100644 src/derive.cc diff --git a/.gitignore b/.gitignore index 16b46aa..46ff993 100644 --- a/.gitignore +++ b/.gitignore @@ -8,3 +8,5 @@ build/ *.err *.log *.synth.r8asm +.r8forge_cache/ + diff --git a/CMakeLists.txt b/CMakeLists.txt index 4924d9f..421aa54 100644 --- a/CMakeLists.txt +++ b/CMakeLists.txt @@ -20,5 +20,8 @@ target_link_libraries(r8forge r8forge_core) add_executable(r8forge_synth_test tests/synth_test.cc) target_link_libraries(r8forge_synth_test r8forge_core) +add_executable(r8forge_derive src/derive.cc) +target_link_libraries(r8forge_derive r8forge_core) + add_executable(r8forge_cost_search tests/cost_search.cc) target_link_libraries(r8forge_cost_search r8forge_core) diff --git a/README.md b/README.md index 3676fe2..c80b4d7 100644 --- a/README.md +++ b/README.md @@ -117,8 +117,25 @@ r8asm: %synth fulladd: 5 layers (shortest), 20388515 states, 7.7s r8asm: %synth fulladd: tape cost 75 in 6 blocks (layer answer was 82), 415041596 states, 1280s ``` -`mode layers` 只跑第一行(7.7 秒),`mode tape`(默认)会接着跑第二行。迭代的时候用 -`layers`,要发布再切回 `tape`,否则每次汇编都要等 20 分钟。 +`mode layers` 只跑第一行(7.7 秒),`mode tape`(默认)会接着跑第二行。结果按真值表缓存在 +`.r8forge_cache/` 里,所以同一张表只贵一次;要重算就删掉那个目录。 + +## 标准库现在也是合成的 + +`asm/` 里的 8 个 bit 宏(`clb_bit_and`、`bit_raw_and`、`clb_bit_or`、`bit_raw_or`、 +`clb_bit_xor`、`bit_raw_xor`、`bit_raw_inc`、`bit_raw_add`)全部换成了 `%synth` 块,宏名、 +参数顺序、调用方式都没动,上层的 `%rep` 驱动照旧。 + +`stat` 那张表不是手写的,是 `r8forge_derive` 从**旧实现本身**跑出来的: + +```sh +build/Release/r8forge_derive drv/bit_raw_add.r8asm 6 +# stat 0 9 10 19 12 21 22 31 0 9 10 ... +``` + +它把 6 个参数摆到 cell 0..5,穷举 64 个输入组合各跑一遍旧纸带,读回 6 个 bit 的终值。 +所以合成结果与旧实现**逐位一致**(连旧实现里"某个输入没被清掉"这类怪癖都保住了),只是更短。 +要改语义,改那张表就行,不用碰代码。 ### 放进自己的库里 diff --git a/asm/raw_add.r8asm b/asm/raw_add.r8asm index f860d5a..9f7cbd5 100644 --- a/asm/raw_add.r8asm +++ b/asm/raw_add.r8asm @@ -1,5 +1,9 @@ %include "asm/lib.r8asm" +; bit 宏由 %synth 合成。 +; stat 那张表是用 r8forge_derive 在旧实现上跑出来的:6 个参数、64 个输入组合, +; 每项是该组合下 6 个 bit 的终值。合成结果因此和旧实现逐位一致。 + ; Macro bit_raw_add ; %1: CellBit A ; %2: CellBit B @@ -7,89 +11,20 @@ ; %4: CellBit S ; %5: CellBit Co ; %6: CellBit buf +%synth bit_raw_add_synth + params 6 + stat 0 9 10 19 12 21 22 31 0 9 10 19 12 21 22 31 0 9 10 19 12 21 22 31 0 9 10 19 12 21 22 31 0 9 10 19 12 21 22 31 0 9 10 19 12 21 22 31 0 9 10 19 12 21 22 31 0 9 10 19 12 21 22 31 + mode tape +%endsynth %macro bit_raw_add 6 -.anchor before_bit_raw_add -.tp %4 -biz - flb -rnz - -.tp %5 -biz - flb -rnz - -.tp %6 -biz - flb -rnz - -.tp %3 -biz - .tp %1 - flb - .tp %2 - flb - .tp %6 - flb - .tp %3 - flb -rnz - -.tp %1 -biz - .tp %3 - flb - .tp %4 - flb - .tp %6 - flb - .tp %1 - flb -rnz - -.tp %2 -biz - .tp %1 - flb - .tp %3 - flb - .tp %5 - flb - .tp %6 - flb - .tp %2 - flb -rnz - -.tp %4 -biz - .tp %2 - set_1 - .tp %5 - set_1 - .tp %4 - flb -rnz - -.tp %6 -biz - .tp %1 - flb - .tp %2 - flb - .tp %3 - flb - .tp %4 - flb - .tp %5 - flb - .tp %6 - flb -rnz - -.tp before_bit_raw_add + .tp %4 + set_0 + .tp %5 + set_0 + .tp %6 + set_0 + bit_raw_add_synth %1 %2 %3 %4 %5 %6 %endmacro @@ -127,4 +62,4 @@ rol clb_bit_mov %3 .tp before_raw_add -%endmacro \ No newline at end of file +%endmacro diff --git a/asm/raw_and.r8asm b/asm/raw_and.r8asm index a216499..81d8f12 100644 --- a/asm/raw_and.r8asm +++ b/asm/raw_and.r8asm @@ -1,9 +1,18 @@ %include "asm/lib.r8asm" +; bit 宏由 %synth 在汇编期合成。 +; stat 那张表是用 r8forge_derive 从旧实现上跑出来的(跑遍所有输入组合,读回各 cell +; 的终值),所以合成结果与旧实现语义完全一致 —— 包括旧实现里"某个输入没被清掉" +; 这类行为。要改语义,改这张表。 + ; Macro clb_bit_and ; %1: CellBit arg1 ; %2: CellBit arg2 ; %3: CellBit ans +; +; 这个没换成 %synth:三个参数里没有草稿位,而"与"需要同时保住两个输入, +; 所以只能靠嵌套 biz(一层只能有一个条件)。搜索器在 3 个平面、9 层内穷尽无解, +; 这是模型的表达力边界,不是搜索没跑够。 %macro clb_bit_and 3 .anchor before_clb_bit_and .tp %3 @@ -24,8 +33,6 @@ rnz .tp before_clb_bit_and %endmacro - - ; Macro clb_and ; %1: Cell arg1 ; %2: Cell arg2 @@ -46,68 +53,26 @@ rnz %endmacro - ; Macro bit_and ; %1: CellBit arg1 ; %2: CellBit arg2 ; %3: CellBit ans ; %4: CellBit tmp +%synth bit_raw_and_synth + params 4 + stat 0 1 2 7 0 1 2 7 0 1 2 7 0 1 2 7 + mode tape +%endsynth + %macro bit_raw_and 4 -.anchor before_bit_raw_and -.tp %3 -biz - flb -rnz - -.tp %4 -biz - flb -rnz - -.tp %1 -biz - .tp %3 - set_1 - .tp %4 - set_1 - .tp %1 - flb -rnz - -.tp %2 -biz - .tp %1 - set_1 - .tp %3 - set_1 - .tp %2 - flb -rnz - -.tp %1 -biz - .tp %2 - flb - .tp %3 - flb - .tp %1 - flb -rnz - -.tp %4 -biz - .tp %1 - flb - .tp %3 - flb - .tp %4 - flb -rnz -.tp before_bit_raw_and + .tp %3 + set_0 + .tp %4 + set_0 + bit_raw_and_synth %1 %2 %3 %4 %endmacro - ; Macro and ; %1: Cell arg1 ; %2: Cell arg2 @@ -126,4 +91,4 @@ rnz ror %endrep .tp before_raw_and -%endmacro \ No newline at end of file +%endmacro diff --git a/asm/raw_inc.r8asm b/asm/raw_inc.r8asm index 8cf4103..5ede204 100644 --- a/asm/raw_inc.r8asm +++ b/asm/raw_inc.r8asm @@ -1,75 +1,27 @@ %include "asm/lib.r8asm" + +; bit 宏由 %synth 合成,stat 是用 r8forge_derive 从旧实现里跑出来的。 + ; Macro bit_raw_inc ; %1: CellBit A ; %2: CellBit Ci ; %3: CellBit S ; %4: CellBit Co ; %5: CellBit tmp +%synth bit_raw_inc_synth + params 5 + stat 0 5 6 11 0 5 6 11 0 5 6 11 0 5 6 11 0 5 6 11 0 5 6 11 0 5 6 11 0 5 6 11 + mode tape +%endsynth %macro bit_raw_inc 5 - -.anchor before_bit_raw_inc -.tp %3 -biz - flb -rnz - -.tp %4 -biz - flb -rnz - -.tp %5 -biz - flb -rnz - -.tp %2 -biz - .tp %1 - flb - .tp %3 - flb - .tp %2 - flb -rnz - -.tp %1 -biz - .tp %4 - set_1 - .tp %5 - set_1 - .tp %1 - flb -rnz - -.tp %3 -biz - .tp %1 - set_1 - .tp %2 - set_1 - .tp %4 - set_1 - .tp %3 - flb -rnz - -.tp %5 -biz - .tp %1 - flb - .tp %3 - flb - .tp %4 - flb - .tp %5 - flb -rnz - -.tp before_bit_raw_inc - + .tp %3 + set_0 + .tp %4 + set_0 + .tp %5 + set_0 + bit_raw_inc_synth %1 %2 %3 %4 %5 %endmacro ; Macro raw_inc @@ -78,7 +30,6 @@ rnz ; %3: Cell S ; %4: CellBit Co ; %5: Cell tmp - %macro raw_inc 5 .anchor before_raw_inc @@ -104,4 +55,4 @@ rol clb_bit_mov %2 .tp before_raw_inc -%endmacro \ No newline at end of file +%endmacro diff --git a/asm/raw_or.r8asm b/asm/raw_or.r8asm index c18f690..9d9a36c 100644 --- a/asm/raw_or.r8asm +++ b/asm/raw_or.r8asm @@ -1,32 +1,23 @@ %include "asm/lib.r8asm" + +; bit 宏由 %synth 合成,stat 是用 r8forge_derive 从旧实现里跑出来的。 + ; Macro clb_bit_or ; %1: CellBit arg1 ; %2: CellBit arg2 ; %3: CellBit ans +%synth clb_bit_or_synth + params 3 + stat 0 4 4 4 0 4 4 4 + mode tape +%endsynth + %macro clb_bit_or 3 -.anchor before_clb_bit_or -.tp %3 -set_0 -.tp %1 -biz - .tp %3 - flb - .tp %1 - flb -rnz -.tp %2 -biz - .tp %3 - set_1 - .tp %2 - flb -rnz - -.tp before_clb_bit_or + .tp %3 + set_0 + clb_bit_or_synth %1 %2 %3 %endmacro - - ; Macro clb_or ; %1: Cell arg1 ; %2: Cell arg2 @@ -47,71 +38,26 @@ rnz %endmacro - - ; Macro bit_raw_or ; %1: CellBit arg1 ; %2: CellBit arg2 ; %3: CellBit ans ; %4: CellBit tmp -%macro bit_raw_or 3 -.anchor before_bit_raw_or +%synth bit_raw_or_synth + params 4 + stat 0 5 6 7 0 5 6 7 0 5 6 7 0 5 6 7 + mode tape +%endsynth -.tp %3 -biz - flb -rnz - -.tp %4 -biz - flb -rnz - -.tp %1 -biz - .tp %3 - set_1 - .tp %1 - flb -rnz - -.tp %3 -biz - .tp %1 - flb - .tp %2 - flb - .tp %4 - flb - .tp %3 - flb -rnz - -.tp %2 -biz - .tp %3 - flb - .tp %4 - flb - .tp %2 - flb -rnz - -.tp %4 -biz - .tp %2 - set_1 - .tp %3 - set_1 - .tp %4 - flb -rnz - -.tp before_bit_raw_or +%macro bit_raw_or 4 + .tp %3 + set_0 + .tp %4 + set_0 + bit_raw_or_synth %1 %2 %3 %4 %endmacro - ; Macro raw_or ; %1: Cell arg1 ; %2: Cell arg2 @@ -130,4 +76,4 @@ rnz ror %endrep .tp before_raw_or -%endmacro \ No newline at end of file +%endmacro diff --git a/asm/raw_xor.r8asm b/asm/raw_xor.r8asm index b6265e1..27aed98 100644 --- a/asm/raw_xor.r8asm +++ b/asm/raw_xor.r8asm @@ -1,33 +1,23 @@ %include "asm/lib.r8asm" +; bit 宏由 %synth 合成,stat 是用 r8forge_derive 从旧实现里跑出来的。 + ; Macro clb_bit_xor ; %1: CellBit arg1 ; %2: CellBit arg2 ; %3: CellBit ans +%synth clb_bit_xor_synth + params 3 + stat 0 4 4 0 0 4 4 0 + mode tape +%endsynth + %macro clb_bit_xor 3 -.anchor before_clb_bit_xor -.tp %3 -set_0 -.tp %1 -biz - .tp %3 - flb - .tp %1 - set_0 -rnz -.tp %2 -biz - .tp %3 - flb - .tp %2 - set_0 -rnz - -.tp before_clb_bit_xor + .tp %3 + set_0 + clb_bit_xor_synth %1 %2 %3 %endmacro - - ; Macro clb_xor ; %1: Cell arg1 ; %2: Cell arg2 @@ -48,65 +38,31 @@ rnz %endmacro - ; Macro bit_raw_xor ; %1: CellBit arg1 ; %2: CellBit arg2 ; %3: CellBit ans ; %4: CellBit tmp +%synth bit_raw_xor_synth + params 4 + stat 0 5 6 3 0 5 6 3 0 5 6 3 0 5 6 3 + mode tape +%endsynth + %macro bit_raw_xor 4 -.anchor before_bit_raw_xor -.tp %3 -biz - flb -rnz - -.tp %4 -biz - flb -rnz - -.tp %2 -biz - .tp %1 - flb - .tp %4 - flb - .tp %2 - flb -rnz - -.tp %1 -biz - .tp %2 - flb - .tp %3 - flb - .tp %4 - flb - .tp %1 - flb -rnz - -.tp %4 -biz - .tp %1 - flb - .tp %2 - flb - .tp %4 - flb -rnz - -.tp before_xor + .tp %3 + set_0 + .tp %4 + set_0 + bit_raw_xor_synth %1 %2 %3 %4 %endmacro - ; Macro raw_xor ; %1: Unit arg1 ; %2: Unit arg2 ; %3: Cell ans +; %4: CellBit tmp %macro raw_xor 4 .anchor before_raw_xor @@ -120,4 +76,4 @@ rnz ror %endrep .tp before_raw_xor -%endmacro \ No newline at end of file +%endmacro diff --git a/drv/bit_raw_add.r8asm b/drv/bit_raw_add.r8asm new file mode 100644 index 0000000..f6e3e5d --- /dev/null +++ b/drv/bit_raw_add.r8asm @@ -0,0 +1,8 @@ +%include "asm/raw_add.r8asm" +.var p0 0 +.var p1 1 +.var p2 2 +.var p3 3 +.var p4 4 +.var p5 5 +bit_raw_add p0 p1 p2 p3 p4 p5 diff --git a/drv/bit_raw_and.r8asm b/drv/bit_raw_and.r8asm new file mode 100644 index 0000000..8e756e1 --- /dev/null +++ b/drv/bit_raw_and.r8asm @@ -0,0 +1,6 @@ +%include "asm/raw_and.r8asm" +.var p0 0 +.var p1 1 +.var p2 2 +.var p3 3 +bit_raw_and p0 p1 p2 p3 diff --git a/drv/bit_raw_inc.r8asm b/drv/bit_raw_inc.r8asm new file mode 100644 index 0000000..d73e6df --- /dev/null +++ b/drv/bit_raw_inc.r8asm @@ -0,0 +1,7 @@ +%include "asm/raw_inc.r8asm" +.var p0 0 +.var p1 1 +.var p2 2 +.var p3 3 +.var p4 4 +bit_raw_inc p0 p1 p2 p3 p4 diff --git a/drv/bit_raw_or.r8asm b/drv/bit_raw_or.r8asm new file mode 100644 index 0000000..08fcaf9 --- /dev/null +++ b/drv/bit_raw_or.r8asm @@ -0,0 +1,6 @@ +%include "asm/raw_or.r8asm" +.var p0 0 +.var p1 1 +.var p2 2 +.var p3 3 +bit_raw_or p0 p1 p2 p3 diff --git a/drv/bit_raw_xor.r8asm b/drv/bit_raw_xor.r8asm new file mode 100644 index 0000000..c9974c6 --- /dev/null +++ b/drv/bit_raw_xor.r8asm @@ -0,0 +1,6 @@ +%include "asm/raw_xor.r8asm" +.var p0 0 +.var p1 1 +.var p2 2 +.var p3 3 +bit_raw_xor p0 p1 p2 p3 diff --git a/drv/clb_bit_and.r8asm b/drv/clb_bit_and.r8asm new file mode 100644 index 0000000..54c9cd5 --- /dev/null +++ b/drv/clb_bit_and.r8asm @@ -0,0 +1,5 @@ +%include "asm/raw_and.r8asm" +.var p0 0 +.var p1 1 +.var p2 2 +clb_bit_and p0 p1 p2 diff --git a/drv/clb_bit_or.r8asm b/drv/clb_bit_or.r8asm new file mode 100644 index 0000000..660ec01 --- /dev/null +++ b/drv/clb_bit_or.r8asm @@ -0,0 +1,5 @@ +%include "asm/raw_or.r8asm" +.var p0 0 +.var p1 1 +.var p2 2 +clb_bit_or p0 p1 p2 diff --git a/drv/clb_bit_xor.r8asm b/drv/clb_bit_xor.r8asm new file mode 100644 index 0000000..e600b19 --- /dev/null +++ b/drv/clb_bit_xor.r8asm @@ -0,0 +1,5 @@ +%include "asm/raw_xor.r8asm" +.var p0 0 +.var p1 1 +.var p2 2 +clb_bit_xor p0 p1 p2 diff --git a/src/derive.cc b/src/derive.cc new file mode 100644 index 0000000..225663e --- /dev/null +++ b/src/derive.cc @@ -0,0 +1,126 @@ +// Derives the state table of a library macro: assembles a program that calls +// it on cells 0..P-1, then runs the tape once per input combination and reads +// the resulting cell values back. +// +// r8forge_derive

[cells...] +// +// Prints one line per input combination: the P-bit value of the parameters +// afterwards. That table is exactly what %synth's `stat` line wants. +#include "r8forge/r8asm.hh" +#include +#include +#include +#include + +namespace { + +struct machine { + std::vector cells = std::vector(256, 0); + std::vector out; + size_t dp = 0; + + static uint8_t ror(uint8_t v) { return uint8_t((v >> 1) | (v << 7)); } + + void run(const std::string &tape, size_t limit = 5'000'000) { + for (size_t pc = 0; pc < tape.size() && limit; pc++, limit--) { + switch (tape[pc]) { + case '>': + dp++; + break; + case '<': + dp--; + break; + case '-': // flb + cells[dp] ^= 1; + break; + case '+': // ror + cells[dp] = ror(cells[dp]); + break; + case '[': + if (cells[dp] == 0) { + int depth = 1; + while (depth) { + pc++; + if (tape[pc] == '[') + depth++; + else if (tape[pc] == ']') + depth--; + } + } + break; + case ']': + if (cells[dp] != 0) { + int depth = 1; + while (depth) { + pc--; + if (tape[pc] == ']') + depth++; + else if (tape[pc] == '[') + depth--; + } + } + break; + case '.': + out.push_back(cells[dp]); + break; + default: + break; + } + } + } +}; + +} // namespace + +int main(int argc, char **argv) { + if (argc < 3) { + std::cerr << "usage: r8forge_derive [cells...]\n"; + return 2; + } + const char *file = argv[1]; + const int params = std::atoi(argv[2]); + if (params == 0) { // just run the program and dump what it printed + r8asm a; + if (!a.import_file(file, 8)) { + std::cerr << "could not assemble " << file << "\n"; + return 1; + } + machine m; + m.run(a.export_rot8()); + std::cout << "out"; + for (uint8_t v : m.out) + std::cout << " " << int(v); + std::cout << "\n"; + return 0; + } + if (params < 1 || params > 8) { + std::cerr << "params must be 1..8\n"; + return 2; + } + std::vector addr(static_cast(params)); + for (int i = 0; i < params; i++) + addr[static_cast(i)] = argc > 3 + i ? std::atoi(argv[3 + i]) : i; + + r8asm assembler; + if (!assembler.import_file(file, 8)) { + std::cerr << "could not assemble " << file << "\n"; + return 1; + } + const std::string tape = assembler.export_rot8(); + std::cerr << "tape: " << tape.size() << " characters\n"; + + std::cout << "stat"; + for (int combo = 0; combo < (1 << params); combo++) { + machine m; + for (int b = 0; b < params; b++) + m.cells[static_cast(addr[static_cast(b)])] = uint8_t((combo >> b) & 1); + m.run(tape); + unsigned val = 0; + for (int b = 0; b < params; b++) + if (m.cells[static_cast(addr[static_cast(b)])] & 1) + val |= 1u << b; + std::cout << " " << val; + } + std::cout << "\n"; + return 0; +} diff --git a/src/synth.cc b/src/synth.cc index ea87721..0fed7f2 100644 --- a/src/synth.cc +++ b/src/synth.cc @@ -1,4 +1,6 @@ #include "r8forge/r8asm.hh" +#include +#include #include // ---------------------------------------------------------------- %synth @@ -50,6 +52,48 @@ r8asm_synth_run(const std::vector &in, const std::vector &out, auto tt = v.make_truthtable(start, target); + // ---- cache: the same table always gives the same program, and the tape + // search is measured in minutes, so keep the answer around + std::string key = std::to_string(P) + "|" + std::to_string(mode) + "|"; + for (int val : stat) + key += std::to_string(val) + ","; + key += "#"; + for (int val : layout) + key += std::to_string(val) + ","; + uint64_t h = 0xcbf29ce484222325ULL; + for (unsigned char ch : key) { + h ^= ch; + h *= 0x100000001b3ULL; + } + const std::string cache_dir = ".r8forge_cache"; + char hex[32]; + std::snprintf(hex, sizeof hex, "%016llx", (unsigned long long)h); + const std::string cache_path = cache_dir + "/" + hex + ".txt"; + + auto read_cache = [&](std::vector> &dst) { + std::ifstream in(cache_path); + if (!in) + return false; + int sac, mask, or_mode; + while (in >> sac >> mask >> or_mode) + dst.push_back({sac, mask, or_mode}); + return !dst.empty(); + }; + auto write_cache = [&](const std::vector> &src) { + std::error_code ec; + std::filesystem::create_directories(cache_dir, ec); + std::ofstream out(cache_path); + for (const auto &i : src) + out << i[0] << " " << i[1] << " " << i[2] << "\n"; + }; + + std::vector> cached; + if (read_cache(cached)) { + std::cerr << "r8asm: %synth " << name << ": cached, " + << cached.size() << " blocks\n"; + return cached; + } + // 1) fewest layers -- cheap, and its tape length gives the cost search a // bound to work under typename V::options opt; @@ -68,6 +112,7 @@ r8asm_synth_run(const std::vector &in, const std::vector &out, if (mode == 1) { // fewest layers only: skip the tape search for (const auto &i : layers.program) out_ins.push_back({int(i.sacrifice), int(i.mask), int(i.or_mode)}); + write_cache(out_ins); return out_ins; } @@ -104,6 +149,7 @@ r8asm_synth_run(const std::vector &in, const std::vector &out, << tape.message << "), keeping the layer result\n"; for (const auto &i : layers.program) out_ins.push_back({int(i.sacrifice), int(i.mask), int(i.or_mode)}); + write_cache(out_ins); return out_ins; } std::cerr << "r8asm: %synth " << name << ": tape cost " << tape.cost << " in " @@ -111,6 +157,7 @@ r8asm_synth_run(const std::vector &in, const std::vector &out, << "), " << tape.states << " states, " << tape_seconds << "s\n"; for (const auto &i : tape.program) out_ins.push_back({int(i.sacrifice), int(i.mask), int(i.or_mode)}); + write_cache(out_ins); return out_ins; }