harness(llvm/py): fix PHI/dominance via Resolver-only; per-pred localization and constant GEPs; stabilize Main.esc_json/1, dirname/1, node_json/3; docs: add NYASH_LLVM_TRACE_FINAL and Resolver-only invariants
- Resolver-only reads across BBs; remove vmap fallbacks - Create PHIs at block start; insert casts in preds before terminators - Re-materialize int in preds to satisfy dominance (add/zext/trunc) - Use constant GEP for method strings to avoid order dependency - Order non-PHI lowering to preserve producer→consumer dominance - Update docs: RESOLVER_API.md, LLVM_HARNESS.md - compare_harness_on_off: ON/OFF exits match; linking green
This commit is contained in:
Selfhosting Dev
@ -76,81 +76,123 @@ def lower_boxcall(
|
||||
|
||||
# Minimal method bridging for strings and console
|
||||
if method_name in ("length", "len"):
|
||||
# Prefer handle-based len_h
|
||||
# Any.length_h: Array/String/Map に対応
|
||||
recv_h = _ensure_handle(builder, module, recv_val)
|
||||
callee = _declare(module, "nyash.string.len_h", i64, [i64])
|
||||
result = builder.call(callee, [recv_h], name="strlen_h")
|
||||
callee = _declare(module, "nyash.any.length_h", i64, [i64])
|
||||
result = builder.call(callee, [recv_h], name="any_length_h")
|
||||
if dst_vid is not None:
|
||||
vmap[dst_vid] = result
|
||||
return
|
||||
|
||||
if method_name == "substring":
|
||||
# substring(start, end) with pointer-based API
|
||||
# substring(start, end)
|
||||
# If receiver is a handle (i64), use handle-based helper; else pointer-based API
|
||||
if resolver is not None and preds is not None and block_end_values is not None and bb_map is not None:
|
||||
s = resolver.resolve_i64(args[0], builder.block, preds, block_end_values, vmap, bb_map) if args else ir.Constant(i64, 0)
|
||||
e = resolver.resolve_i64(args[1], builder.block, preds, block_end_values, vmap, bb_map) if len(args) > 1 else ir.Constant(i64, 0)
|
||||
else:
|
||||
s = vmap.get(args[0], ir.Constant(i64, 0)) if args else ir.Constant(i64, 0)
|
||||
e = vmap.get(args[1], ir.Constant(i64, 0)) if len(args) > 1 else ir.Constant(i64, 0)
|
||||
# Coerce recv to i8*
|
||||
recv_p = recv_val
|
||||
if hasattr(recv_p, 'type') and isinstance(recv_p.type, ir.IntType):
|
||||
recv_p = builder.inttoptr(recv_p, i8p, name="bc_i2p_recv")
|
||||
elif hasattr(recv_p, 'type') and isinstance(recv_p.type, ir.PointerType):
|
||||
try:
|
||||
if isinstance(recv_p.type.pointee, ir.ArrayType):
|
||||
c0 = ir.Constant(ir.IntType(32), 0)
|
||||
recv_p = builder.gep(recv_p, [c0, c0], name="bc_gep_recv")
|
||||
except Exception:
|
||||
pass
|
||||
if hasattr(recv_val, 'type') and isinstance(recv_val.type, ir.IntType):
|
||||
# handle-based
|
||||
callee = _declare(module, "nyash.string.substring_hii", i64, [i64, i64, i64])
|
||||
h = builder.call(callee, [recv_val, s, e], name="substring_h")
|
||||
if dst_vid is not None:
|
||||
vmap[dst_vid] = h
|
||||
try:
|
||||
if resolver is not None and hasattr(resolver, 'mark_string'):
|
||||
resolver.mark_string(dst_vid)
|
||||
except Exception:
|
||||
pass
|
||||
return
|
||||
else:
|
||||
recv_p = ir.Constant(i8p, None)
|
||||
# Coerce indices
|
||||
if hasattr(s, 'type') and isinstance(s.type, ir.PointerType):
|
||||
s = builder.ptrtoint(s, i64)
|
||||
if hasattr(e, 'type') and isinstance(e.type, ir.PointerType):
|
||||
e = builder.ptrtoint(e, i64)
|
||||
callee = _declare(module, "nyash.string.substring_sii", i8p, [i8p, i64, i64])
|
||||
p = builder.call(callee, [recv_p, s, e], name="substring")
|
||||
# Return as handle across blocks (i8* -> i64 via nyash.box.from_i8_string)
|
||||
conv_fnty = ir.FunctionType(i64, [i8p])
|
||||
conv = _declare(module, "nyash.box.from_i8_string", i64, [i8p])
|
||||
h = builder.call(conv, [p], name="str_ptr2h_sub")
|
||||
if dst_vid is not None:
|
||||
vmap[dst_vid] = h
|
||||
return
|
||||
# pointer-based
|
||||
recv_p = recv_val
|
||||
if hasattr(recv_p, 'type') and isinstance(recv_p.type, ir.PointerType):
|
||||
try:
|
||||
if isinstance(recv_p.type.pointee, ir.ArrayType):
|
||||
c0 = ir.Constant(ir.IntType(32), 0)
|
||||
recv_p = builder.gep(recv_p, [c0, c0], name="bc_gep_recv")
|
||||
except Exception:
|
||||
pass
|
||||
else:
|
||||
recv_p = ir.Constant(i8p, None)
|
||||
# Coerce indices
|
||||
if hasattr(s, 'type') and isinstance(s.type, ir.PointerType):
|
||||
s = builder.ptrtoint(s, i64)
|
||||
if hasattr(e, 'type') and isinstance(e.type, ir.PointerType):
|
||||
e = builder.ptrtoint(e, i64)
|
||||
callee = _declare(module, "nyash.string.substring_sii", i8p, [i8p, i64, i64])
|
||||
p = builder.call(callee, [recv_p, s, e], name="substring")
|
||||
conv = _declare(module, "nyash.box.from_i8_string", i64, [i8p])
|
||||
h = builder.call(conv, [p], name="str_ptr2h_sub")
|
||||
if dst_vid is not None:
|
||||
vmap[dst_vid] = h
|
||||
try:
|
||||
if resolver is not None and hasattr(resolver, 'mark_string'):
|
||||
resolver.mark_string(dst_vid)
|
||||
except Exception:
|
||||
pass
|
||||
return
|
||||
|
||||
if method_name == "lastIndexOf":
|
||||
# lastIndexOf(needle)
|
||||
if resolver is not None and preds is not None and block_end_values is not None and bb_map is not None:
|
||||
needle = resolver.resolve_ptr(args[0], builder.block, preds, block_end_values, vmap) if args else ir.Constant(i8p, None)
|
||||
n_i64 = resolver.resolve_i64(args[0], builder.block, preds, block_end_values, vmap, bb_map) if args else ir.Constant(i64, 0)
|
||||
else:
|
||||
needle = vmap.get(args[0], ir.Constant(i8p, None)) if args else ir.Constant(i8p, None)
|
||||
recv_p = recv_val
|
||||
if hasattr(recv_p, 'type') and isinstance(recv_p.type, ir.IntType):
|
||||
recv_p = builder.inttoptr(recv_p, i8p, name="bc_i2p_recv2")
|
||||
elif hasattr(recv_p, 'type') and isinstance(recv_p.type, ir.PointerType):
|
||||
try:
|
||||
if isinstance(recv_p.type.pointee, ir.ArrayType):
|
||||
c0 = ir.Constant(ir.IntType(32), 0)
|
||||
recv_p = builder.gep(recv_p, [c0, c0], name="bc_gep_recv2")
|
||||
except Exception:
|
||||
pass
|
||||
if hasattr(needle, 'type') and isinstance(needle.type, ir.IntType):
|
||||
needle = builder.inttoptr(needle, i8p, name="bc_i2p_needle")
|
||||
elif hasattr(needle, 'type') and isinstance(needle.type, ir.PointerType):
|
||||
try:
|
||||
if isinstance(needle.type.pointee, ir.ArrayType):
|
||||
c0 = ir.Constant(ir.IntType(32), 0)
|
||||
needle = builder.gep(needle, [c0, c0], name="bc_gep_needle")
|
||||
except Exception:
|
||||
pass
|
||||
elif not hasattr(needle, 'type'):
|
||||
needle = ir.Constant(i8p, None)
|
||||
callee = _declare(module, "nyash.string.lastIndexOf_ss", i64, [i8p, i8p])
|
||||
res = builder.call(callee, [recv_p, needle], name="lastIndexOf")
|
||||
n_i64 = vmap.get(args[0], ir.Constant(i64, 0)) if args else ir.Constant(i64, 0)
|
||||
if hasattr(recv_val, 'type') and isinstance(recv_val.type, ir.IntType):
|
||||
# handle-based
|
||||
callee = _declare(module, "nyash.string.lastIndexOf_hh", i64, [i64, i64])
|
||||
res = builder.call(callee, [recv_val, n_i64], name="lastIndexOf_hh")
|
||||
if dst_vid is not None:
|
||||
vmap[dst_vid] = res
|
||||
return
|
||||
else:
|
||||
# pointer-based
|
||||
recv_p = recv_val
|
||||
if hasattr(recv_p, 'type') and isinstance(recv_p.type, ir.PointerType):
|
||||
try:
|
||||
if isinstance(recv_p.type.pointee, ir.ArrayType):
|
||||
c0 = ir.Constant(ir.IntType(32), 0)
|
||||
recv_p = builder.gep(recv_p, [c0, c0], name="bc_gep_recv2")
|
||||
except Exception:
|
||||
pass
|
||||
else:
|
||||
recv_p = ir.Constant(i8p, None)
|
||||
needle = n_i64
|
||||
if hasattr(needle, 'type') and isinstance(needle.type, ir.IntType):
|
||||
needle = builder.inttoptr(needle, i8p, name="bc_i2p_needle")
|
||||
elif hasattr(needle, 'type') and isinstance(needle.type, ir.PointerType):
|
||||
try:
|
||||
if isinstance(needle.type.pointee, ir.ArrayType):
|
||||
c0 = ir.Constant(ir.IntType(32), 0)
|
||||
needle = builder.gep(needle, [c0, c0], name="bc_gep_needle")
|
||||
except Exception:
|
||||
pass
|
||||
callee = _declare(module, "nyash.string.lastIndexOf_ss", i64, [i8p, i8p])
|
||||
res = builder.call(callee, [recv_p, needle], name="lastIndexOf")
|
||||
if dst_vid is not None:
|
||||
vmap[dst_vid] = res
|
||||
return
|
||||
|
||||
if method_name == "get":
|
||||
# ArrayBox.get(index) → nyash.array.get_h(handle, idx)
|
||||
recv_h = _ensure_handle(builder, module, recv_val)
|
||||
if resolver is not None and preds is not None and block_end_values is not None and bb_map is not None:
|
||||
idx = resolver.resolve_i64(args[0], builder.block, preds, block_end_values, vmap, bb_map) if args else ir.Constant(i64, 0)
|
||||
else:
|
||||
idx = vmap.get(args[0], ir.Constant(i64, 0)) if args else ir.Constant(i64, 0)
|
||||
callee = _declare(module, "nyash.array.get_h", i64, [i64, i64])
|
||||
res = builder.call(callee, [recv_h, idx], name="arr_get_h")
|
||||
if dst_vid is not None:
|
||||
vmap[dst_vid] = res
|
||||
try:
|
||||
if resolver is not None and hasattr(resolver, 'mark_string'):
|
||||
# Heuristic: args array often stores strings for CLI; tag as string-ish
|
||||
resolver.mark_string(dst_vid)
|
||||
except Exception:
|
||||
pass
|
||||
return
|
||||
|
||||
if method_name in ("print", "println", "log"):
|
||||
@ -174,6 +216,48 @@ def lower_boxcall(
|
||||
vmap[dst_vid] = ir.Constant(i64, 0)
|
||||
return
|
||||
|
||||
# Special: method on `me` (self) or static dispatch to Main.* → direct call to `Main.method/arity`
|
||||
try:
|
||||
cur_fn_name = str(builder.block.parent.name)
|
||||
except Exception:
|
||||
cur_fn_name = ''
|
||||
# Heuristic: value-id 0 is often the implicit receiver for `me` in MIR
|
||||
if box_vid == 0 and cur_fn_name.startswith('Main.'):
|
||||
# Build target function name with arity
|
||||
arity = len(args)
|
||||
target = f"Main.{method_name}/{arity}"
|
||||
# If module already has such function, prefer direct call
|
||||
callee = None
|
||||
for f in module.functions:
|
||||
if f.name == target:
|
||||
callee = f
|
||||
break
|
||||
if callee is not None:
|
||||
a = []
|
||||
for i, aid in enumerate(args):
|
||||
raw = vmap.get(aid)
|
||||
if raw is not None and hasattr(raw, 'type') and isinstance(raw.type, ir.PointerType):
|
||||
aval = _ensure_handle(builder, module, raw)
|
||||
else:
|
||||
if resolver is not None and preds is not None and block_end_values is not None and bb_map is not None:
|
||||
aval = resolver.resolve_i64(aid, builder.block, preds, block_end_values, vmap, bb_map)
|
||||
else:
|
||||
aval = vmap.get(aid, ir.Constant(ir.IntType(64), 0))
|
||||
if hasattr(aval, 'type') and isinstance(aval.type, ir.PointerType):
|
||||
aval = _ensure_handle(builder, module, aval)
|
||||
elif hasattr(aval, 'type') and isinstance(aval.type, ir.IntType) and aval.type.width != 64:
|
||||
aval = builder.zext(aval, ir.IntType(64)) if aval.type.width < 64 else builder.trunc(aval, ir.IntType(64))
|
||||
a.append(aval)
|
||||
res = builder.call(callee, a, name=f"call_self_{method_name}")
|
||||
if dst_vid is not None:
|
||||
vmap[dst_vid] = res
|
||||
try:
|
||||
if method_name in ("esc_json", "node_json", "dirname", "join", "read_all") and resolver is not None and hasattr(resolver, 'mark_string'):
|
||||
resolver.mark_string(dst_vid)
|
||||
except Exception:
|
||||
pass
|
||||
return
|
||||
|
||||
# Default: invoke via NyRT by-name shim (runtime resolves method id)
|
||||
recv_h = _ensure_handle(builder, module, recv_val)
|
||||
# Build C string for method name
|
||||
@ -195,7 +279,9 @@ def lower_boxcall(
|
||||
g.global_constant = True
|
||||
g.initializer = ir.Constant(arr_ty, bytearray(mbytes))
|
||||
c0 = ir.Constant(ir.IntType(32), 0)
|
||||
mptr = builder.gep(g, [c0, c0], inbounds=True)
|
||||
# Compute GEP in the current block so it is naturally ordered before the call
|
||||
# Use constant GEP so we don't depend on instruction ordering
|
||||
mptr = ir.Constant.gep(g, (c0, c0))
|
||||
|
||||
# Up to 2 args for minimal path
|
||||
argc = ir.Constant(i64, min(len(args), 2))
|
||||
|
||||
Reference in New Issue
Block a user