feat(asm): Phase F — global (module-scope) asm

A top-level `asm { "tmpl", };` block (template only) lowers to LLVM `module asm`;
a lib-less `extern` declaration calls into the symbols it defines (the import
direction reuses the existing C-FFI extern path — no new surface).

- ast.zig: asm_global node (AsmGlobal { template }).
- parser.zig: parseAsmGlobal, dispatched from parseTopLevel on kw_asm — rejects
  `volatile` and any operands/clobbers (template only). The in-function asm
  expression form stays in parsePrimary.
- module.zig: Module.global_asm list; lower/decl.zig captures each template in
  lowerMainAndComptime (the real top-level pass — lowerDecls is dead for
  top-level); emit_llvm.zig emit() appends each via LLVMAppendModuleInlineAsm in
  source order.
- the new node forced asm_global arms in sema.zig (analyzeNode +
  findNodeAtOffset) and semantic_diagnostics.zig (checkBindingNames).

Verified end-to-end: an aarch64 `_my_add` global routine, called via `extern`,
returns 42 — AOT only (the ORC JIT doesn't link module-asm symbols; global-asm
symbols live in the final linked binary). Locked with 1648-platform-asm-global
({ "aot": true, "target": "macos" } → AOT build+run on aarch64, ir-only else).

zig build test green (656 corpus, 446 unit).

src/ast.zig

@@ -96,6 +96,7 @@ pub const Node = struct {
         runtime_class_decl: RuntimeClassDecl,
         jni_env_block: JniEnvBlock,
         asm_expr: AsmExpr,
+        asm_global: AsmGlobal,
 
         pub fn declName(self: Data) ?[]const u8 {
             return switch (self) {
@@ -259,6 +260,15 @@ pub const AsmOperand = struct {
     };
 };
 
+/// Top-level (module-scope) global assembly: `asm { "tmpl", };` (ASM stream
+/// design §II.2 Deviation 6). Template only — no operands, no `volatile`, no
+/// `clobbers`, no `%` substitution. Lowers to `LLVMAppendModuleInlineAsm`;
+/// multiple blocks concatenate in source order. Symbols it defines are reached
+/// with a lib-less `extern` declaration.
+pub const AsmGlobal = struct {
+    template: *Node, // string-literal / `#string` heredoc node
+};
+
 pub const Identifier = struct {
     name: []const u8,
     /// True when written as a backtick raw identifier (`` `i2 ``). Carried so a

src/ir/emit_llvm.zig

@@ -347,6 +347,14 @@ pub const LLVMEmitter = struct {
         // Must precede any DISubprogram (created per function below).
         self.debugInfo().initDebugInfo();
 
+        // Top-level global asm (ASM stream Phase F): append each block verbatim
+        // to the module. Multiple blocks concatenate in source order; LLVM emits
+        // them as module-level `module asm`. Symbols they define are reached via
+        // lib-less `extern` declarations.
+        for (self.ir_mod.global_asm.items) |asm_text| {
+            c.LLVMAppendModuleInlineAsm(self.llvm_module, asm_text.ptr, asm_text.len);
+        }
+
         // Pass 0: Declare and initialize globals
         self.emitGlobals();
 

src/ir/lower/decl.zig

@@ -1342,6 +1342,17 @@ pub fn lowerMainAndComptime(self: *Lowering, decls: []const *const Node) void {
                     self.lowerMainAndComptime(ns.decls);
                 }
             },
+            // Top-level global asm (Phase F): capture the verbatim template; it
+            // is appended to the LLVM module at emit time (source order). The
+            // template must be a comptime-known string (parser guarantees a
+            // string node here).
+            .asm_global => |ag| {
+                if (ag.template.data == .string_literal) {
+                    self.module.global_asm.append(self.alloc, ag.template.data.string_literal.raw) catch unreachable;
+                } else if (self.diagnostics) |diags| {
+                    diags.addFmt(.err, decl.span, "global asm template must be a compile-time-known string", .{});
+                }
+            },
             else => {},
         }
     }

src/ir/module.zig

@@ -51,6 +51,10 @@ pub const Module = struct {
     /// (trampoline emission, +alloc/-dealloc synthesis) can re-walk
     /// `members` for fields / methods / `#extends` / `#implements`.
     objc_defined_class_cache: std.ArrayList(ObjcDefinedClassEntry),
+    /// Top-level `asm { … }` blocks (ASM stream Phase F), in source order.
+    /// Each is verbatim assembly appended to the LLVM module via
+    /// `LLVMAppendModuleInlineAsm` at emit time; multiple blocks concatenate.
+    global_asm: std.ArrayList([]const u8),
     alloc: Allocator,
     /// Owns the per-instruction operand slices the Builder dupes (aggregate
     /// fields, call args, branch args, switch cases, block params). These live
@@ -100,6 +104,7 @@ pub const Module = struct {
             .objc_selector_cache = std.ArrayList(ObjcSelectorEntry).empty,
             .objc_class_cache = std.ArrayList(ObjcClassEntry).empty,
             .objc_defined_class_cache = std.ArrayList(ObjcDefinedClassEntry).empty,
+            .global_asm = std.ArrayList([]const u8).empty,
             .alloc = alloc,
             .slice_arena = std.heap.ArenaAllocator.init(alloc),
         };
@@ -115,6 +120,7 @@ pub const Module = struct {
         self.objc_selector_cache.deinit(self.alloc);
         self.objc_class_cache.deinit(self.alloc);
         self.objc_defined_class_cache.deinit(self.alloc);
+        self.global_asm.deinit(self.alloc);
         self.types.deinit();
         self.slice_arena.deinit();
     }

src/ir/semantic_diagnostics.zig

@@ -316,6 +316,7 @@ pub const UnknownTypeChecker = struct {
                 self.checkBindingNames(ae.template);
                 for (ae.operands) |op| self.checkBindingNames(op.payload);
             },
+            .asm_global => |ag| self.checkBindingNames(ag.template),
             // ── Named type / alias / import declarations: a bare reserved
             // spelling as the declared name is rejected. These
             //    have no nested binding sites, so only the name is checked. A

src/parser.zig

@@ -104,6 +104,13 @@ pub const Parser = struct {
             return try self.createNode(start, .{ .import_decl = .{ .path = path, .name = null } });
         }
 
+        // Top-level (module-scope) global assembly: `asm { "tmpl", };`
+        // (template only — no operands/volatile/clobbers). The in-function
+        // `asm { … }` expression form is parsed in `parsePrimary` instead.
+        if (self.current.tag == .kw_asm) {
+            return self.parseAsmGlobal(start);
+        }
+
         // Top-level #run directive
         if (self.current.tag == .hash_run) {
             self.advance();
@@ -2801,6 +2808,24 @@ pub const Parser = struct {
         } });
     }
 
+    /// Top-level global assembly `asm { "tmpl", };` — template only. Rejects
+    /// `volatile` and any operands/clobbers (design §II.2 Deviation 6).
+    fn parseAsmGlobal(self: *Parser, start: u32) anyerror!*Node {
+        self.advance(); // consume `asm`
+        if (self.isContextualWord("volatile")) {
+            return self.fail("global (top-level) asm cannot be `volatile`");
+        }
+        try self.expect(.l_brace);
+        const template = try self.parseExpr();
+        if (self.current.tag == .comma) self.advance(); // optional trailing comma
+        if (self.current.tag != .r_brace) {
+            return self.fail("global (top-level) asm takes no operands, inputs, or clobbers — only a template string");
+        }
+        try self.expect(.r_brace);
+        try self.expect(.semicolon);
+        return try self.createNode(start, .{ .asm_global = .{ .template = template } });
+    }
+
     fn parsePrimary(self: *Parser) anyerror!*Node {
         const start = self.current.loc.start;
         // Pack references in expression position:

src/sema.zig

@@ -1367,6 +1367,7 @@ pub const Analyzer = struct {
                 try self.analyzeNode(ae.template);
                 for (ae.operands) |op| try self.analyzeNode(op.payload);
             },
+            .asm_global => |ag| try self.analyzeNode(ag.template),
             .impl_block => |ib| {
                 // Each impl block gets its own scope so methods don't conflict across impls
                 try self.pushScope();
@@ -1843,6 +1844,9 @@ pub fn findNodeAtOffset(node: *Node, offset: u32) ?*Node {
                 if (findNodeAtOffset(op.payload, offset)) |found| return found;
             }
         },
+        .asm_global => |ag| {
+            if (findNodeAtOffset(ag.template, offset)) |found| return found;
+        },
     }
 
     return node;