fix(asm): read the arm64 move-wide immediate as an unsigned pattern

Assisted-by: GLM 5.3 Flash

asm/arm64_assemble.go

@@ -3069,29 +3069,29 @@ func encodeARM64MoveWide(mnem string, baseOp uint32, ops []*ast.Operand) ([]byte
 	// base, so MOVZ and MOVN come along for free.
 	opc := baseOp >> 29 & 3
 	sf := baseOp >> 31 & 1
-	v := arm64Imm64(ops[0])
-	if v < 0 {
-		return nil, fmt.Errorf("%s: negative immediate %d", mnem, v)
+	// The toolchain's optab case 33, shared by the whole family in both
+	// widths: the immediate is one unsigned 64-bit pattern (a high-lane
+	// constant such as $(40000<<48) arrives negative through int64
+	// folding), it must occupy exactly one 16-bit lane, zero is rejected,
+	// and the W forms cannot reach the top half.
+	u := uint64(arm64Imm64(ops[0]))
+	if u == 0 {
+		return nil, fmt.Errorf("%s: zero immediate cannot be handled", mnem)
 	}
 	hw := -1
-	for i := range 4 {
-		if v>>(uint(i)*16)&0xFFFF != 0 {
-			hw = i
+	for lane := range 4 {
+		if u&^(uint64(0xFFFF)<<(lane*16)) == 0 {
+			hw = lane
 			break
 		}
 	}
 	if hw < 0 {
-		hw = 0 // zero: every chunk is zero, hw = 0 carries it
-	}
-	for i := hw + 1; i < 4; i++ {
-		if v>>(uint(i)*16)&0xFFFF != 0 {
-			return nil, fmt.Errorf("%s: immediate %d does not fit one 16-bit chunk", mnem, v)
-		}
+		return nil, fmt.Errorf("%s: immediate %#x does not fit one 16-bit chunk", mnem, u)
 	}
 	if sf == 0 && hw > 1 {
-		return nil, fmt.Errorf("%s: immediate %d out of range for the 32-bit form", mnem, v)
+		return nil, fmt.Errorf("%s: immediate %#x out of range for the 32-bit form", mnem, u)
 	}
-	return a64wordLE(a64MoveWide(sf, opc, uint32(hw), uint32(v>>uint(hw*16)&0xFFFF), uint32(rd))), nil
+	return a64wordLE(a64MoveWide(sf, opc, uint32(hw), uint32(u>>uint(hw*16)&0xFFFF), uint32(rd))), nil
 }
 
 // ---- Bitfield/EXTR encoding ----