docs(asm): generate the instruction appendices

Assisted-by: GLM 5.3 Flash

_gen/gen.go

@@ -8,6 +8,10 @@
 // names so gasm-devkit supports every instruction the real assembler does,
 // with no hand-maintained (and therefore inevitably incomplete) lists.
 //
+// The same data feeds the generated instruction appendices of the assembly
+// language reference, docs/asm/INSTRUCTIONS-<ARCH>.md, so that the reference
+// cannot drift from the tables it documents.
+//
 // Usage (via the justfile):
 //
 //	just gen
@@ -26,6 +30,9 @@ import (
 	"path/filepath"
 	"sort"
 	"strings"
+
+	"sourcedock.dev/petrbalvin/gasm-devkit/arch"
+	"sourcedock.dev/petrbalvin/gasm-devkit/asm"
 )
 
 // archDirs maps a gasm-devkit architecture name to its obj sub-directory.
@@ -39,11 +46,30 @@ var archDirs = []struct {
 	{"loong64", "loong64"},
 }
 
+// docPages maps an architecture to its generated appendix in the language
+// reference.  The amd64 page carries a per-mnemonic encodability column,
+// decided by asm.Encodable, which mirrors the encoder's own dispatch; the
+// other targets have no single cheap predicate, so their pages carry the
+// inventory and point at the live measurement instead.
+var docPages = []struct {
+	arch      arch.Arch
+	title     string
+	file      string
+	anames    string
+	encodable bool
+}{
+	{arch.AMD64, "AMD64", "INSTRUCTIONS-AMD64.md", "cmd/internal/obj/x86/anames.go", true},
+	{arch.ARM64, "ARM64", "INSTRUCTIONS-ARM64.md", "cmd/internal/obj/arm64/anames.go", false},
+	{arch.RISCV, "RISC-V 64", "INSTRUCTIONS-RISCV64.md", "cmd/internal/obj/riscv/anames.go", false},
+	{arch.LOONG64, "LoongArch 64", "INSTRUCTIONS-LOONG64.md", "cmd/internal/obj/loong64/anames.go", false},
+}
+
 func main() {
 	goroot := strings.TrimSpace(runGoEnvGOROOT())
 	if goroot == "" {
 		fatal("could not determine GOROOT")
 	}
+	version := strings.TrimSpace(runGoEnv("GOVERSION"))
 	// The common opcodes shared by every architecture (RET, JMP, NOP, CALL,
 	// TEXT, FUNCDATA, …) live in cmd/internal/obj/util.go.
 	commonPath := filepath.Join(goroot, "src", "cmd", "internal", "obj", "util.go")
@@ -57,16 +83,24 @@ func main() {
 	}
 	fmt.Printf("%-8s %4d instructions -> arch/common_gen.go\n", "common", len(common))
 
+	names := map[string][]string{}
 	for _, a := range archDirs {
 		path := filepath.Join(goroot, "src", "cmd", "internal", "obj", a.sub, "anames.go")
-		names, err := extractInstrs(path)
+		names[a.arch], err = extractInstrs(path)
 		if err != nil {
 			fatal("extract %s: %v", a.arch, err)
 		}
-		if err := writeGen(a.arch, a.sub, names); err != nil {
+		if err := writeGen(a.arch, a.sub, names[a.arch]); err != nil {
 			fatal("write %s: %v", a.arch, err)
 		}
-		fmt.Printf("%-8s %4d instructions -> arch/%s_gen.go\n", a.arch, len(names), a.arch)
+		fmt.Printf("%-8s %4d instructions -> arch/%s_gen.go\n", a.arch, len(names[a.arch]), a.arch)
+	}
+
+	for _, p := range docPages {
+		if err := writeDocPage(p.arch, p.title, p.file, p.anames, version, p.encodable); err != nil {
+			fatal("write %s: %v", p.file, err)
+		}
+		fmt.Printf("%-8s -> docs/asm/%s\n", p.arch, p.file)
 	}
 }
 
@@ -172,6 +206,61 @@ func writeGen(arch, sub string, names []string) error {
 	return os.WriteFile(filepath.Join("arch", arch+"_gen.go"), []byte(b.String()), 0o644)
 }
 
+// writeDocPage emits docs/asm/<file>, the generated instruction appendix of
+// the language reference for one architecture: every mnemonic the toolchain
+// accepts, with the curated summary where the architecture table carries one
+// and, on amd64, a per-mnemonic encodability column.
+func writeDocPage(a arch.Arch, title, file, anames, version string, encodable bool) error {
+	table := arch.ForArch(a)
+	instrs := table.Instructions()
+
+	var b strings.Builder
+	b.WriteString("# " + title + ": instruction inventory\n\n")
+	b.WriteString("Generated by gasm-devkit's `_gen` from the Go toolchain's instruction table\n")
+	b.WriteString("(`" + anames + "`, " + version + "); DO NOT EDIT. This page lists every mnemonic\n")
+	b.WriteString("`go tool asm` accepts on this target, which is the upper bound of the\n")
+	b.WriteString("language on it: a name absent here is not an instruction of the target,\n")
+	b.WriteString("and a name present here may still be one gasm's encoder cannot emit yet.\n\n")
+
+	encodableCount := 0
+	if encodable {
+		b.WriteString("The `gasm encodes` column reports whether gasm's encoder can emit the\n")
+		b.WriteString("mnemonic today; the gap is the encoder backlog, measured live by\n")
+		b.WriteString("`gasm audit-instructions`.\n\n")
+		b.WriteString("| Mnemonic | gasm encodes | Notes |\n")
+		b.WriteString("|---|---|---|\n")
+		for _, in := range instrs {
+			ok := asm.Encodable(in.Name)
+			if ok {
+				encodableCount++
+			}
+			b.WriteString("| `" + in.Name + "` | " + yesNo(ok) + " | " + in.Summary + " |\n")
+		}
+		b.WriteString("\n")
+		fmt.Fprintf(&b, "Recognised: %d mnemonics. gasm encodes: %d.\n", len(instrs), encodableCount)
+	} else {
+		b.WriteString("The inventory carries no per-mnemonic encoder column: on this target\n")
+		b.WriteString("encodability is decided per operand shape, and the live measured\n")
+		b.WriteString("coverage is reported by `gasm audit-instructions`.\n\n")
+		b.WriteString("| Mnemonic | Notes |\n")
+		b.WriteString("|---|---|\n")
+		for _, in := range instrs {
+			b.WriteString("| `" + in.Name + "` | " + in.Summary + " |\n")
+		}
+		b.WriteString("\n")
+		fmt.Fprintf(&b, "Recognised: %d mnemonics.\n", len(instrs))
+	}
+	return os.WriteFile(filepath.Join("docs", "asm", file), []byte(b.String()), 0o644)
+}
+
+// yesNo renders a boolean as the word the appendix tables use.
+func yesNo(v bool) string {
+	if v {
+		return "yes"
+	}
+	return "no"
+}
+
 func runGoEnvGOROOT() string {
 	out, err := exec.Command("go", "env", "GOROOT").Output()
 	if err != nil {
@@ -180,6 +269,15 @@ func runGoEnvGOROOT() string {
 	return string(out)
 }
 
+// runGoEnv runs `go env` for a single variable.
+func runGoEnv(name string) string {
+	out, err := exec.Command("go", "env", name).Output()
+	if err != nil {
+		return ""
+	}
+	return string(out)
+}
+
 func fatal(format string, args ...any) {
 	fmt.Fprintf(os.Stderr, "gen: "+format+"\n", args...)
 	os.Exit(1)