xenia-rs/migration/project-root/ppc-manual/alu/mulhwx.md

# `mulhwx` — Multiply High Word

> **Category:** [Integer ALU](../categories/alu.md) · **Form:** [XO](../forms/XO.md) · **Opcode:** `0x7c000096`

<!-- GENERATED: BEGIN -->

## Assembler Mnemonics

| Mnemonic | XML entry | Flags | Description |
| --- | --- | --- | --- |
| `mulhw` | `mulhwx` | — | Multiply High Word |
| `mulhw.` | `mulhwx` | Rc=1 | Multiply High Word |

## Syntax

```asm
mulhw[Rc] [RD], [RA], [RB]
```

## Encoding

### `mulhwx` — form `XO`

- **Opcode word:** `0x7c000096`
- **Primary opcode (bits 0–5):** `31`
- **Extended opcode:** `75`
- **Synchronising:** no

| Bits | Field | Meaning |
| --- | --- | --- |
| 0–5 | `OPCD` | primary opcode (31) |
| 6–10 | `RT` | destination GPR |
| 11–15 | `RA` | source A |
| 16–20 | `RB` | source B |
| 21 | `OE` | overflow-enable flag |
| 22–30 | `XO` | extended opcode (9 bits) |
| 31 | `Rc` | record-form flag |

## Operands

| Field | Role | Description |
| --- | --- | --- |
| `RA` | mulhwx: read | Source GPR (`r0`–`r31`). |
| `RB` | mulhwx: read | Source GPR. |
| `RD` | mulhwx: write | Destination GPR. |
| `CR` | mulhwx: write (conditional) | Condition-register update. When `Rc=1`, CR field 0 (or CR6 for vector compares, CR1 for FPU) is updated from the result. |

## Register Effects

### `mulhwx`

- **Reads (always):** `RA`, `RB`
- **Reads (conditional):** _none_
- **Writes (always):** `RD`
- **Writes (conditional):** `CR`

## Status-Register Effects

- `mulhwx`: **CR0** ← signed-compare(result, 0) with `SO ← XER[SO]`, when `Rc=1`.

## Operation (pseudocode)

```
RT <- high_32_of_signed_multiply((RA)[32:63], (RB)[32:63]) sign-extended to 64
```

## C Translation Example

```c
/* C translation: the xenia-rs interpreter arm below in           */
/* Implementation References is the authoritative semantic        */
/* snapshot. Translate it line-by-line:                            */
/*   - ctx.gpr[N]  -> r[N]       (or f[]/v[] for FPRs/VRs)        */
/*   - mem.read_u*/write_u* -> mem_read_u*_be / mem_write_u*_be   */
/*   - ctx.update_cr_signed(fld, v) -> update_cr_signed(fld, v)   */
/*   - ctx.xer_ca / xer_ov / xer_so -> xer.CA / xer.OV / xer.SO   */
/* The Register Effects and Status-Register Effects tables above  */
/* enumerate every side effect a faithful translation must emit.  */
```

## Implementation References

**`mulhwx`**
- xenia-canary XML: [`tools/ppc-instructions.xml` — search for `mnem="mulhwx"`](../../xenia-canary/tools/ppc-instructions.xml)
- xenia-canary emit: [`src/xenia/cpu/ppc/ppc_emit_alu.cc:326`](../../xenia-canary/src/xenia/cpu/ppc/ppc_emit_alu.cc#L326)
- xenia-rs opcode: [`crates/xenia-cpu/src/opcode.rs:57`](../../xenia-rs/crates/xenia-cpu/src/opcode.rs#L57)
- xenia-rs decoder: [`crates/xenia-cpu/src/decoder.rs:865`](../../xenia-rs/crates/xenia-cpu/src/decoder.rs#L865)
- xenia-rs interpreter: [`crates/xenia-cpu/src/interpreter.rs:372-382`](../../xenia-rs/crates/xenia-cpu/src/interpreter.rs#L372-L382)
<details><summary>xenia-rs interpreter body (frozen snapshot)</summary>

```rust
        PpcOpcode::mulhwx => {
            // PPCBUG-020: 32-bit ABI CR0 view.
            let ra = ctx.gpr[instr.ra()] as i32 as i64;
            let rb = ctx.gpr[instr.rb()] as i32 as i64;
            let result = ra.wrapping_mul(rb);
            ctx.gpr[instr.rd()] = ((result >> 32) as u32) as u64;
            if instr.rc_bit() {
                ctx.update_cr_signed(0, ctx.gpr[instr.rd()] as u32 as i32 as i64);
            }
            ctx.pc += 4;
        }
```
</details>

<!-- GENERATED: END -->

## Special Cases & Edge Conditions

- **Inputs are the low 32 bits, signed-extended.** `RA[32:63]` and `RB[32:63]` are sign-extended to 64-bit signed values, multiplied, and the *high* 32 bits of the 64-bit product are returned in `RT[32:63]`. The high 32 bits of `RT` are *implementation-defined* per spec but xenia masks them to zero ([`interpreter.rs:222`](../../xenia-rs/crates/xenia-cpu/src/interpreter.rs#L222) `& 0xFFFF_FFFF`).
- **Pair with [`mullwx`](mullwx.md) for the full 64-bit product.** Both can issue independently — no fused 32×32→64 instruction.
- **No `OE` bit.** Like all `mulh*` instructions, no overflow flag is produced; the high half is by definition defined.
- **Xenia-rs quirk: high 32 bits zeroed.** Because spec says they're "undefined", legitimately matching either zero, sign-extension, or garbage. Xenia chooses zero, which differs from the literal Xenon behaviour (which sign-extends in some microarchitecture cases). For game code that doesn't read those bits, the difference is invisible.
- **`Rc=1` CR0 update.** [`interpreter.rs:225`](../../xenia-rs/crates/xenia-cpu/src/interpreter.rs#L225) uses `as i32 as i64` — operates on the truncated low 32 bits, which is correct for the *defined* portion of the result.
- **Multi-cycle latency.** Multiply is the slowest pipelined ALU op; `mulhw` shares the divider/multiplier unit.

## Related Instructions

- [`mullwx`](mullwx.md) — low 32 bits of a signed 32×32 product.
- [`mulhwux`](mulhwux.md) — high 32 bits, unsigned interpretation.
- [`mulhdx`](mulhdx.md), [`mulhdux`](mulhdux.md), [`mulldx`](mulldx.md) — 64-bit family.
- [`divwx`](divwx.md) — sometimes replaced by reciprocal-mul-then-shift in compiled code.

## IBM Reference

- [AIX 7.3 — `mulhw` (Multiply High Word)](https://www.ibm.com/docs/en/aix/7.3.0?topic=set-mulhw-multiply-high-word-instruction)