diff --git a/AGENTS.md b/AGENTS.md index ba22b76..6a99046 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -142,25 +142,25 @@ void rot8_rnz(rot8_iter *iter) { if ((*(iter->mem_now) & 1) == 1) { ... } } 两个默认值集中在 **`include/r8forge/geometry.hh`**,现在是 **11 位 / 259 格**: ```cpp -inline constexpr size_t kDefaultCellBits = 11; +inline constexpr size_t kDefaultCellSize = 11; inline constexpr size_t kDefaultMemoryCells = 259; -inline constexpr uint32_t kDefaultCellMask = (1u << kDefaultCellBits) - 1u; +inline constexpr uint32_t kDefaultCellMask = (1u << kDefaultCellSize) - 1u; ``` 位宽和长度**都不在指令集里**(`ROR` 只是在一个 cell 里转圈,纸带是环),所以它们只以 "参数 + 常量"的形式存在,落在三处。改位宽时照这个清单走: 1. **汇编器**:`import_file(path, cell_size)` 的第二个参数就是位宽,6 个调用点都传 - `kDefaultCellBits`。`set_cell_size` 顺手把三个名字注入程序作用域: + `kDefaultCellSize`。`set_cell_size` 顺手把三个名字注入程序作用域: `_CELL_SIZE`(位宽)、`_CELL_MAX = (1 << 位宽) - 1`、`_ROL_STEP = 位宽 - 1`。 宏里写 `%rep _CELL_SIZE { … }` 就自动跟着位宽走(`erase`、`rol`、所有字节级驱动都这么写), 所以**位级宏、`%synth` 切片、位运算天然与位宽无关** —— 实测 `r8forge_synth_test` 在 11 位下照样 8/8 全过。 2. **四份虚拟机**(`tests/synth_test.cc`、`tests/byte_op_test.cc`、`src/derive.cc`、 `tests/tape_run.cc`):cell 存 `uint16_t`、数组长 `kDefaultMemoryCells`、 - 旋转必须是 `(v >> 1) | ((v & 1) << (kDefaultCellBits - 1))`、输入输出掩码用 + 旋转必须是 `(v >> 1) | ((v & 1) << (kDefaultCellSize - 1))`、输入输出掩码用 `kDefaultCellMask`。**四份要一起改**,少改一份就会出现"两个实现不一致"的假象。 -3. **测试期望**:一律用 `kCellMask` / `kBits` 写,不要出现 `0xff`、`>> 8`、`256 - a`。 +3. **测试期望**:一律用 `kCellMask` / `kCellSize` 写,不要出现 `0xff`、`>> 8`、`256 - a`。 **注意 2048 % 256 == 0**,所以不少 8 位期望在 11 位下碰巧还成立(and/or/xor/not/dec/sub 就是),别把"没报错"当成"不用改" —— `neg`、`add`、`inc`、`mul` 一改位宽当场就错。 @@ -173,12 +173,12 @@ inline constexpr uint32_t kDefaultCellMask = (1u << kDefaultCellBits) - 1u; * **`output` 打印整个 cell 的值**,不再是一个字节;`out` 里出现 257、1088 这种数是对的 (`127+130 = 257`、`200*200 = 19*2048 + 1088`)。 * **交叉验证要先对齐几何**:几何一致时同一条纸带输出完全相同(`asm/test.r8asm` 两边都是 - `1322 1786 1600 5 94 127`);不一致时不是谁错了,是两台不同的机器。作者那份 `ROT-8-viz` - (`C:\Users\peng0\git\ROT-8-viz`)默认 11 位 / 259 格,`--cell` / `--mem` 可改; - **workspace 里另有一份 `ROT-8-viz/`,那是 upstream `starcells/ROT-8` 的 `feat/memory-viz` - 分支**,几何是编译期常量(`cell_size` / `mem_size`,在 `include/rot8/rot8.h`),现在也是 - **11 位 / 259 格**。对答案的办法:`ROT-8-viz/build/Release/rot8_test.exe ` 把每个 - `OUT` 按行打出来,和 `r8forge_derive -1` 的 `out` 逐位比即可。 + `1322 1786 1600 5 94 127`);不一致时不是谁错了,是两台不同的机器。workspace 里的 + `ROT-8-viz/` 是 upstream `starcells/ROT-8` 的 fork(`origin` = `dsh/ROT-8-viz`,`main`), + 默认 **11 位 x 259 格**,几何还能运行期改(`--cell` / `--mem`;默认值与字段在 + `include/rot8/rot8.h`,名字就是 `cell_size` / `mem_size`)。对答案的办法: + `ROT-8-viz/build/Release/rot8_test.exe ` 把每个 `OUT` 按行打出来, + 和 `r8forge_derive -1` 的 `out` 逐位比即可。 * 位宽变大还有个正面效果:`fibonacci` 不再在 256 处回绕,现在跑出 **13 项**(到 233)。 * **旧 tape 换到新位宽上不只是算错,还可能永远跑不完**:按 8 位写死的程序里 `%rep 8` 只转了 8 圈,在 11 位下 cell 没转回原位,"循环到某位清零"的条件于是永远不成立。 diff --git a/README.md b/README.md index 5e31e89..c3d428b 100644 --- a/README.md +++ b/README.md @@ -190,7 +190,7 @@ build/Release/r8forge_derive drv/bit_raw_add.r8asm 6 ## 字节级运算:一个 cell 一个机器字 > 机械字默认 **11 位、纸带 259 格**,都定义在 `include/r8forge/geometry.hh` -> (`kDefaultCellBits` / `kDefaultMemoryCells`)。指令集本身不规定位宽,宏里用 +> (`kDefaultCellSize` / `kDefaultMemoryCells`)。指令集本身不规定位宽,宏里用 > `%rep _CELL_SIZE` 的地方会自动跟着变,所以下面说的"字节级"其实是"机器字级"; > 下面引用的纸带长度是 8 位时代的实测值,11 位下这些宏会长一些(`raw_add` 2199 字符、 > `fibonacci` 11959 字符,完整数字见 `AGENTS.md`)。 diff --git a/include/r8forge/geometry.hh b/include/r8forge/geometry.hh index 69a5a40..fba67d3 100644 --- a/include/r8forge/geometry.hh +++ b/include/r8forge/geometry.hh @@ -7,6 +7,6 @@ // cell is in bits, and how many cells the tape holds. The instruction set does // not fix either (ROR just rotates inside a cell and the tape is a ring), so // these are the only places the old 8 bit / 256 cell assumptions live. -inline constexpr size_t kDefaultCellBits = 11; +inline constexpr size_t kDefaultCellSize = 11; inline constexpr size_t kDefaultMemoryCells = 259; -inline constexpr uint32_t kDefaultCellMask = (1u << kDefaultCellBits) - 1u; +inline constexpr uint32_t kDefaultCellMask = (1u << kDefaultCellSize) - 1u; diff --git a/src/derive.cc b/src/derive.cc index d92d08e..a014e1a 100644 --- a/src/derive.cc +++ b/src/derive.cc @@ -21,7 +21,7 @@ struct machine { size_t dp = 0; static uint16_t ror(uint16_t v) { - return uint16_t((v >> 1) | ((v & 1u) << (kDefaultCellBits - 1))); + return uint16_t((v >> 1) | ((v & 1u) << (kDefaultCellSize - 1))); } void run(const std::string &tape, size_t limit = 5'000'000) { @@ -90,7 +90,7 @@ int main(int argc, char **argv) { 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, kDefaultCellBits)) { + if (!a.import_file(file, kDefaultCellSize)) { std::cerr << "could not assemble " << file << "\n"; return 1; } @@ -105,7 +105,7 @@ int main(int argc, char **argv) { // params == -2: same as -1 but dumps every non zero cell afterwards if (params == -2) { r8asm a; - if (!a.import_file(file, kDefaultCellBits)) { + if (!a.import_file(file, kDefaultCellSize)) { std::cerr << "could not assemble " << file << "\n"; return 1; } @@ -135,7 +135,7 @@ int main(int argc, char **argv) { // params == -1: the rest of argv is addr=value; set those cells, run, dump OUT if (params == -1) { r8asm a; - if (!a.import_file(file, kDefaultCellBits)) { + if (!a.import_file(file, kDefaultCellSize)) { std::cerr << "could not assemble " << file << "\n"; return 1; } @@ -165,7 +165,7 @@ int main(int argc, char **argv) { addr[static_cast(i)] = argc > 3 + i ? std::atoi(argv[3 + i]) : i; r8asm assembler; - if (!assembler.import_file(file, kDefaultCellBits)) { + if (!assembler.import_file(file, kDefaultCellSize)) { std::cerr << "could not assemble " << file << "\n"; return 1; } diff --git a/tests/asm_test.cc b/tests/asm_test.cc index 4fed1d8..a007598 100644 --- a/tests/asm_test.cc +++ b/tests/asm_test.cc @@ -8,7 +8,7 @@ int main(int argc, char **argv) { return (2); } r8asm a; - if (!a.import_file(argv[1], kDefaultCellBits)) + if (!a.import_file(argv[1], kDefaultCellSize)) return (1); std::string tape = a.export_rot8(); if (a.failed()) diff --git a/tests/byte_op_test.cc b/tests/byte_op_test.cc index b2235f8..136184e 100644 --- a/tests/byte_op_test.cc +++ b/tests/byte_op_test.cc @@ -21,8 +21,8 @@ namespace { // written in terms of it instead of in terms of a byte: kCellMod is one past // the largest value a cell holds. The sweeps walk the first 256 values, which // is a sample of the cell range rather than all of it. -constexpr int kBits = int(kDefaultCellBits); -constexpr int kCellMod = 1 << kBits; +constexpr int kCellSize = int(kDefaultCellSize); +constexpr int kCellMod = 1 << kCellSize; constexpr int kCellMask = int(kDefaultCellMask); struct machine { @@ -33,7 +33,7 @@ struct machine { bool finished = true; // false: the step limit ran out static uint16_t ror(uint16_t v) { - return uint16_t((v >> 1) | ((v & 1u) << (kDefaultCellBits - 1))); + return uint16_t((v >> 1) | ((v & 1u) << (kDefaultCellSize - 1))); } void run(const std::string &tape, size_t limit) { @@ -91,7 +91,7 @@ struct machine { std::string assemble(const std::string &file) { r8asm assembler; - if (!assembler.import_file(file, kDefaultCellBits) || assembler.failed()) { + if (!assembler.import_file(file, kDefaultCellSize) || assembler.failed()) { std::cerr << "could not assemble " << file << "\n"; std::exit(1); } @@ -152,14 +152,14 @@ int test_add(const std::string &file) { const int sum = a + b; const bool ok = m.finished && m.out.size() == 5 && m.out[0] == a && m.out[1] == b && m.out[2] == 0 && - m.out[3] == (sum & kCellMask) && m.out[4] == (sum >> kBits); + m.out[3] == (sum & kCellMask) && m.out[4] == (sum >> kCellSize); if (!ok) { bad++; if (bad <= 3) report("raw_add", a, b, m, std::to_string(a) + " " + std::to_string(b) + " 0 " + std::to_string(sum & kCellMask) + " " + - std::to_string(sum >> kBits)); + std::to_string(sum >> kCellSize)); } } std::cout << " " << (bad ? "FAILED" : "all 65536 combinations ok") @@ -181,14 +181,14 @@ int test_inc(const std::string &file) { const int sum = a + ci; const bool ok = m.finished && m.out.size() == 4 && m.out[0] == a && m.out[1] == ci && m.out[2] == (sum & kCellMask) && - m.out[3] == (sum >> kBits); + m.out[3] == (sum >> kCellSize); if (!ok) { bad++; if (bad <= 3) report("raw_inc", a, ci, m, std::to_string(a) + " " + std::to_string(ci) + " " + std::to_string(sum & kCellMask) + " " + - std::to_string(sum >> kBits)); + std::to_string(sum >> kCellSize)); } } std::cout << " " << (bad ? "FAILED" : "all 512 combinations ok") @@ -211,13 +211,13 @@ int test_add_nc(const std::string &file) { const int sum = a + b; const bool ok = m.finished && m.out.size() == 4 && m.out[0] == 0 && m.out[1] == 0 && m.out[2] == (sum & kCellMask) && - m.out[3] == (sum >> kBits); + m.out[3] == (sum >> kCellSize); if (!ok) { bad++; if (bad <= 3) report("clb_add_nc", a, b, m, "0 0 " + std::to_string(sum & kCellMask) + " " + - std::to_string(sum >> kBits)); + std::to_string(sum >> kCellSize)); } } std::cout << " " << (bad ? "FAILED" : "all 65536 combinations ok") @@ -236,13 +236,13 @@ int test_inc_nc(const std::string &file) { m.run(tape, 100'000); const int sum = a + 1; const bool ok = m.finished && m.out.size() == 3 && m.out[0] == 0 && - m.out[1] == (sum & kCellMask) && m.out[2] == (sum >> kBits); + m.out[1] == (sum & kCellMask) && m.out[2] == (sum >> kCellSize); if (!ok) { bad++; if (bad <= 3) report("clb_inc_nc", a, 1, m, "0 " + std::to_string(sum & kCellMask) + " " + - std::to_string(sum >> kBits)); + std::to_string(sum >> kCellSize)); } } std::cout << " " << (bad ? "FAILED" : "all 256 combinations ok") @@ -485,13 +485,13 @@ int test_mul(const std::string &file) { n++; const int p = mc * mu; const bool ok = m.finished && m.out.size() == 3 && - m.out[0] == (p & kCellMask) && m.out[1] == ((p >> kBits) & kCellMask) && + m.out[0] == (p & kCellMask) && m.out[1] == ((p >> kCellSize) & kCellMask) && m.out[2] == mc; if (!ok) { bad++; if (bad <= 3) report("clb_mul", mc, mu, m, - std::to_string(p & kCellMask) + " " + std::to_string((p >> kBits) & kCellMask) + + std::to_string(p & kCellMask) + " " + std::to_string((p >> kCellSize) & kCellMask) + " " + std::to_string(mc)); } } diff --git a/tests/synth_test.cc b/tests/synth_test.cc index 038bf37..af697a3 100644 --- a/tests/synth_test.cc +++ b/tests/synth_test.cc @@ -20,7 +20,7 @@ struct machine { size_t dp = 0; static uint16_t ror(uint16_t v) { - return uint16_t((v >> 1) | ((v & 1u) << (kDefaultCellBits - 1))); + return uint16_t((v >> 1) | ((v & 1u) << (kDefaultCellSize - 1))); } void run(const std::string &tape) { @@ -82,7 +82,7 @@ struct machine { int main(int argc, char **argv) { const char *file = argc > 1 ? argv[1] : "examples/full_add.r8asm"; r8asm assembler; - if (!assembler.import_file(file, kDefaultCellBits)) { + if (!assembler.import_file(file, kDefaultCellSize)) { std::cerr << "could not assemble " << file << "\n"; return 1; } diff --git a/tests/tape_run.cc b/tests/tape_run.cc index e3b691b..f3a04b3 100644 --- a/tests/tape_run.cc +++ b/tests/tape_run.cc @@ -75,7 +75,7 @@ int main(int argc, char **argv) { cells[dp] ^= 1; break; case '+': // ror - cells[dp] = uint16_t((cells[dp] >> 1) | ((cells[dp] & 1u) << (kDefaultCellBits - 1))); + cells[dp] = uint16_t((cells[dp] >> 1) | ((cells[dp] & 1u) << (kDefaultCellSize - 1))); break; // biz / rnz test the LOW BIT, not "is the cell zero" -- see ROT-8-viz // src/rot8.c. Reading them as a Brainfuck style zero test makes every // byte level program in the library look like an endless loop.