52 lines
6.7 KiB
Markdown
52 lines
6.7 KiB
Markdown
# The model machine against compiled Mojo
|
|
|
|
"Open in Hardware" puts a function from the real compiler's listing on the model machine (`src/engines/asm86`), translated from godbolt's AT&T syntax by `src/mojo/att.ts`. The machine implements a teaching subset of x86-64, so the question is how much of what the Mojo compiler actually emits it can take. This is the census: every function in every listing the corpus holds (`library/mojo/golden/*.json` answered with `asm`), sent exactly as the button sends it, and what the assembler said. `node scripts/asm-census.mjs` reruns it (add `--ops` for every mnemonic); `tests/asm-coverage.test.mjs` holds the numbers as a ratchet, so a new corpus item that brings a new instruction fails the build rather than a student's session.
|
|
|
|
## Where it stands
|
|
|
|
| | before | now |
|
|
|---|---|---|
|
|
| distinct instructions in the listings | 97 | 104 |
|
|
| of which outside the model's set | 38 | 6 (all 256-bit AVX2: `vextracti128`, `vinserti128`, `vpblendvb`, `vperm2i128`, `vpalignr`, `vptest`) |
|
|
| the user's own functions that assemble | 3 of 7 (`main` never did) | 17 of 17 |
|
|
| standard-library and runtime functions that assemble | — | 698 of 733 |
|
|
|
|
The "before" column is the census of the listings the corpus held when this work began; the "now" column is today's census of today's listings, and `tests/documents.test.mjs` fails when it no longer matches `node scripts/asm-census.mjs`. Every listing is built for `--target-cpu x86-64-v3` (the pin's build arguments, [mojo-corpus.md](mojo-corpus.md#how-every-program-is-built)), so it holds AVX2 at most and never AVX-512, whichever of godbolt's machines answered; `tests/build-args.test.mjs` fails on a listing with a `zmm` or mask register. Asked again under those arguments, every listing the corpus held came back with the same instructions; `vptest` and four modeled ones (`adc`, `cmovle`, `jns`, `tzcnt`) came with `probes/godbolt-target-cpu`, String's `==` at the default optimization level.
|
|
|
|
`main()` now steps up to its first call into `print` and stops there with "stopped: std_io_io_print: standard library, not on the model machine", which is the honest answer: the model has no standard library, and says exactly where the real program would enter it.
|
|
|
|
## What was wrong, and what changed
|
|
|
|
**The translator dropped size suffixes only for the mnemonics it knew.** AT&T writes `andnq`, `mulxq`, `shlxq`, `xaddq`, `cmpxchgq`, `btsq`, `bswapq`; the Intel pane reads `andn`, `mulx`, … The BMI and atomic mnemonics were missing from the suffix table, so the machine was asked for an instruction called `andnq`, which exists nowhere. They are in the table now, and `lock` (a prefix) is passed through as a prefix rather than treated as a mnemonic with an operand called `xaddq`.
|
|
|
|
**The machine lacked the instructions the optimizer likes.** Added, each with a one-sentence gloss for the datapath view and the micro-op model told what it reads and writes:
|
|
|
|
- BMI1/BMI2: `andn`, `mulx`, `shlx`, `shrx`, `sarx`, `bzhi`, `blsr`, `blsi`, `blsmsk`, `rorx`, `bextr` (`pdep`/`pext` are named as not modeled)
|
|
- the atomics behind reference counts: `xadd`, `cmpxchg`, and the `lock` prefix, accepted on the read-modify-writes the ISA allows it on
|
|
- bit tests that write: `bts`, `btr`, `btc`; `bswap`; `cwd`, `cwde`, `cbw`
|
|
- `ud2`: the trap the compiler plants on paths that must never run; reaching it stops the run with "the processor raised an invalid-opcode fault"
|
|
- the 128-bit AVX spellings of what the subset had: `vmovdqu`, `vmovdqa`, `vmovups`, `vmovaps`, `vmovd`, `vmovq`, `vpxor`, `vxorps`, `vpor`, `vpand`, `vpandn`, `vpaddb`, `vpsubb`, `vpcmpeqb`, `vpmovmskb`, `vzeroupper`; three-operand form (`vop dst, a, b`), sources untouched
|
|
- lanes: `vpinsr{b,w,d,q}`, `vpextr{b,w,d,q}`, `vpshufb`, `vpshufd`, `vpbroadcast{b,d}`, `vpmin/max{ub,ud}`, `vpcmpeq{w,d,q}`, `vpadd{w,d}`, `vpsubd`, `vpsubusb`, `vpsll/vpsrl{w,d,q}`
|
|
|
|
**A call into the standard library refused the whole listing.** The assembler resolves every label up front, so one `call std::io::print` meant the function could not be stepped at all, even to the instruction before the call. The translator now appends a stub for every such symbol (`label:` then `ud2 ; …: standard library, not on the model machine`), so the function assembles, steps up to the call, and the stop says what it called.
|
|
|
|
**Read-only strings were unreachable.** `lea rax, [rip + static_string_…]` named a label that was data, not code, and the machine has no data directives. The translator now finds the `.asciz` behind each such label, places the bytes in memory (`memory 0x6000 "…"`, octal and hex escapes decoded, from 0x6000 up), writes the address in the instruction's place, and hands the lines to the setup block, where the student can see them.
|
|
|
|
## Scalar doubles, parity, shld (added)
|
|
|
|
- `addsd subsd mulsd divsd sqrtsd movsd cvtsi2sd ucomisd comisd` and their `v` forms: IEEE binary64, round to nearest even, default NaN `0xFFF8000000000000`, a NaN operand is quieted and the first operand wins. MXCSR exception flags are not modeled.
|
|
- `ucomisd`/`comisd` set ZF/PF/CF as hardware does (unordered sets all three; OF, SF clear).
|
|
- PF is a real flag now: set by logic, add/sub and shifts, cleared by `popcnt`, untouched by rotates. `jp jnp jpe jpo`, `cmovp…` and `setp…` follow.
|
|
- `shld`/`shrd` on 32- and 64-bit operands; count masked to 5/6 bits; count 0 changes nothing, flags included.
|
|
- Latencies: add/mul 4, div 14, sqrt 18 (unpipelined on port 0), convert 5, compare 3.
|
|
|
|
## What stays outside, and why
|
|
|
|
- **256-bit AVX2 (`ymm`)**: the model keeps sixteen 128-bit `xmm` registers and no `ymm` halves; the six instructions above are used only in that width. A `ymm` operand is refused with that sentence. Modeling it means widening every vector register and every lane helper; worth doing only when a user function needs it, and none in the corpus does.
|
|
- **Symbols the listing addresses but does not define**: `KGEN_…` runtime globals, `…@GOTPCREL` function pointers, a `.zero` constant. The assembler names the symbol in its refusal.
|
|
- **Constant-pool blocks with a symbol in them** (jump tables): not placed; the instruction that loads one is refused by name. Numeric `.LCPI…` blocks (`.quad`, `.long`, `.double`, `.zero`, …) *are* placed, 16-byte aligned from 0x6000, when the code addresses them, and `.LCPI0_0+8(%rip)` works.
|
|
|
|
## Keeping it honest
|
|
|
|
The census runs against whatever the corpus holds: every stored answer that carries a listing (the probes and exercise programs whose header asks for `mode: asm` or `mode: both`). `pixi run mojo-verify` on a new such program adds its listing, and each addition either assembles or fails `tests/asm-coverage.test.mjs` with the instruction named. That test's ratchet (`LIBRARY_AT_LEAST`) is a floor under the table's library count; raise it when the machine learns more, never lower it.
|