diff --git a/AGENTS.md b/AGENTS.md index 6cf728e..549cda8 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -36,6 +36,7 @@ r8forge_examples_test # 18 个 example + asm/test.r8asm, r8forge_macro_docs_test # 53 macros in 23 files r8forge --opt asm/test.r8asm # 纸带窥孔优化 64513 -> 58060(>< 净位移、+ mod W、- mod 2) r8forge_tape_opt in.rot8 out.rot8 # 同一优化,但作用在已有纸带上 +r8forge_tape_run t.rot8 --profile # 剖面:指针移动占 76~80% 步数(实测,见下) r8forge_synth_test examples/full_add.r8asm # all eight combinations ok r8forge_derive verify_loop.r8asm -1 0=5 # out 5 0 powershell -File tests\widths.ps1 # 位宽矩阵:每个位宽一套工具链 + 断言(约 20 分钟) @@ -66,6 +67,7 @@ powershell -File tests\widths.ps1 # 位宽矩阵:每个位宽一 * **交互程序这样测**:`r8forge_tape_run t.rot8 -i "12+34="`(字符喂给 `inp`,低 7 位,读空后为 0), `r8forge_derive 0 -i "..."` 是同一份输入的第二个实现;例程把输入写在头部 `; in ...`,`r8forge_examples_test` 会自动喂。实时终端那一侧在 ROT-8-viz(默认串行)。 +* **代价的大头是"走"不是"算"**:`tape_run --profile` 实测,计算器 79.5%、全家桶 76.4% 的步数是 `>`/`<`,旋转只占 7%、翻转 4~6%。这台机器没有随机寻址,每次访问的代价就是 `|Δ地址|`,所以**布局才是性能旋钮**;`--opt` 省 17% 步数正是因为它砍的是往返移动。 * 一次会话很难把结论留在对话里 —— **落进 commit message 和文件注释**。 ## 语义上会咬人的几条 diff --git a/TODO.md b/TODO.md index faec8ff..cc8a6e0 100644 --- a/TODO.md +++ b/TODO.md @@ -25,8 +25,7 @@ 重复清位…… 要能重算跳转偏移。配套 `r8forge_tape_diff`(比较两条纸带的 OUT 流和步数) 证明等价 —— 一次改动全库受益。 -* **`--profile`**:统计每段宏/每个 cell 的步数占比和 `.tp` 行走距离,用数据决定下一步优化谁 - (现在"`.tp` 行走占七成"还是估的)。 + * **`%synth --verify`**:把 `.r8forge_cache/` 里每条结果按对应表的所有输入重跑一遍, 给"缓存已入库"兜底 —— 一条坏条目会让每次构建静默用错块。 * **CI**:暂时不做。本地 `ctest --test-dir build -j 4`(8 条,9 秒)和 `tests/widths.ps1` diff --git a/tests/tape_run.cc b/tests/tape_run.cc index 260149a..2ee927a 100644 --- a/tests/tape_run.cc +++ b/tests/tape_run.cc @@ -19,6 +19,8 @@ #include #include #include +#include +#include #include int main(int argc, char **argv) { @@ -37,12 +39,17 @@ int main(int argc, char **argv) { std::vector cells(kDefaultMemoryCells, 0); std::deque input; bool trace = false; + bool profile = false; for (int i = 2; i < argc; i++) { const std::string a = argv[i]; if (a == "--trace" || a == "-t") { trace = true; continue; } + if (a == "--profile" || a == "-p") { + profile = true; + continue; + } if (a == "-i" || a == "--input") { if (i + 1 >= argc) { std::cerr << "-i needs a string of input characters\n"; @@ -64,6 +71,9 @@ int main(int argc, char **argv) { const size_t limit = 20'000'000; // same as r8forge_derive size_t pc = 0; size_t steps = 0; + size_t ins_count[256] = {}; + std::vector cell_hits(cells.size(), 0); + size_t walking = 0; for (; pc < tape.size(); pc++) { if (++steps > limit) { std::cout << "HANG after " << limit << " steps (pc " << pc << ", dp " << dp @@ -71,6 +81,12 @@ int main(int argc, char **argv) { << ")\n"; return 3; } + if (profile) { + ins_count[(unsigned char)tape[pc]]++; + cell_hits[dp]++; + if (tape[pc] == 0x3e || tape[pc] == 0x3c) + walking++; + } if (trace) { // cells 0..3 are the interesting ones when debugging a library macro std::cout << "pc " << pc << " " << tape[pc] << " dp " << dp << " ["; @@ -136,6 +152,30 @@ int main(int argc, char **argv) { } } + if (profile) { + const char *kinds = "><+-[].,"; + std::fprintf(stderr, "profile: %zu steps, %zu of them pointer moves (%.1f%%)\n", + steps, walking, 100.0 * double(walking) / double(steps)); + for (const char *k = kinds; *k; k++) { + const size_t n = ins_count[(unsigned char)*k]; + std::fprintf(stderr, " %c %8zu %5.1f%%\n", *k, n, + 100.0 * double(n) / double(steps)); + } + std::vector order(cell_hits.size()); + for (size_t i = 0; i < order.size(); i++) + order[i] = i; + std::sort(order.begin(), order.end(), [&](size_t a, size_t b) { + return cell_hits[a] > cell_hits[b]; + }); + std::fprintf(stderr, " hottest cells (steps spent there):"); + for (size_t i = 0; i < order.size() && i < 10; i++) { + if (cell_hits[order[i]] == 0) + break; + std::fprintf(stderr, " %zu:%zu", order[i], cell_hits[order[i]]); + } + std::fprintf(stderr, "\n"); + } + std::cout << "out"; for (uint32_t v : out) std::cout << " " << int(v);