# `stvx` — Store Vector Indexed > **Category:** [Memory](../categories/memory.md) · **Form:** [X](../forms/X.md) · **Opcode:** `0x7c0001ce` ## Assembler Mnemonics | Mnemonic | XML entry | Flags | Description | | --- | --- | --- | --- | | `stvx` | `stvx` | — | Store Vector Indexed | | `stvx128` | `stvx128` | — | Store Vector Indexed 128 | ## Syntax ```asm stvx [VS], [RA0], [RB] stvx128 [VS], [RA0], [RB] ``` ## Encoding ### `stvx` — form `X` - **Opcode word:** `0x7c0001ce` - **Primary opcode (bits 0–5):** `31` - **Extended opcode:** `231` - **Synchronising:** no | Bits | Field | Meaning | | --- | --- | --- | | 0–5 | `OPCD` | primary opcode | | 6–10 | `RT/FRT/VRT` | destination | | 11–15 | `RA/FRA/VRA` | source A | | 16–20 | `RB/FRB/VRB` | source B | | 21–30 | `XO` | extended opcode (10 bits) | | 31 | `Rc` | record-form flag | ### `stvx128` — form `VX128_1` - **Opcode word:** `0x100001c3` - **Primary opcode (bits 0–5):** `4` - **Extended opcode:** `451` - **Synchronising:** no | Bits | Field | Meaning | | --- | --- | --- | | 0–5 | `OPCD` | primary opcode (4) | | 6–10 | `VD128l` | destination low 5 bits | | 11–15 | `RA` | address register | | 16–20 | `RB` | offset register | | 21–27 | `XO` | extended opcode | | 28–29 | `VD128h` | destination high 2 bits | | 30–31 | `—` | reserved | ## Operands | Field | Role | Description | | --- | --- | --- | | `VS` | stvx: read; stvx128: read | Source vector register (alias for VD on stores). | | `RA0` | stvx: read; stvx128: read | Source GPR; when the encoded register number is 0 the operand is the literal 64-bit zero, **not** `r0`. | | `RB` | stvx: read; stvx128: read | Source GPR. | ## Register Effects ### `stvx` - **Reads (always):** `VS`, `RA0`, `RB` - **Reads (conditional):** _none_ - **Writes (always):** _none_ - **Writes (conditional):** _none_ ### `stvx128` - **Reads (always):** `VS`, `RA0`, `RB` - **Reads (conditional):** _none_ - **Writes (always):** _none_ - **Writes (conditional):** _none_ ## Status-Register Effects _No condition-register or status-register effects._ ## Operation (pseudocode) ``` EA <- ((RA|0) + (RB)) & ~0xF ; align to 16 MEM(EA, 16) <- byteswap(VS) ``` ## C Translation Example ```c /* stvx VS, RA, RB — 16-byte aligned store of a vector register */ uint64_t base = (insn.RA == 0) ? 0 : r[insn.RA]; uint32_t ea = (uint32_t)((base + r[insn.RB]) & ~(uint64_t)0xF); mem_write_vec128_be(ea, v[insn.VS]); ``` ## Implementation References **`stvx`** - xenia-canary XML: [`tools/ppc-instructions.xml` — search for `mnem="stvx"`](../../xenia-canary/tools/ppc-instructions.xml) - xenia-canary emit: [`src/xenia/cpu/ppc/ppc_emit_altivec.cc:193`](../../xenia-canary/src/xenia/cpu/ppc/ppc_emit_altivec.cc#L193) - xenia-rs opcode: [`crates/xenia-cpu/src/opcode.rs:79`](../../xenia-rs/crates/xenia-cpu/src/opcode.rs#L79) - xenia-rs decoder: [`crates/xenia-cpu/src/decoder.rs:791`](../../xenia-rs/crates/xenia-cpu/src/decoder.rs#L791) - xenia-rs interpreter: [`crates/xenia-cpu/src/interpreter.rs:1849-1859`](../../xenia-rs/crates/xenia-cpu/src/interpreter.rs#L1849-L1859)
xenia-rs interpreter body (frozen snapshot) ```rust PpcOpcode::stvx => { let ea = if instr.ra() == 0 { 0u64 } else { ctx.gpr[instr.ra()] }; let ea = (ea.wrapping_add(ctx.gpr[instr.rb()]) & !0xF) as u32; // PPCBUG-511: stvx was missing invalidate_for_write. if let Some(t) = ctx.reservation_table.as_ref().filter(|t| t.is_enabled()) { if t.has_active_reservers() { t.invalidate_for_write(ea); } } let bytes = ctx.vr[instr.rs()].as_bytes(); for i in 0..16 { mem.write_u8(ea + i as u32, bytes[i]); } ctx.pc += 4; } ```
**`stvx128`** - xenia-canary XML: [`tools/ppc-instructions.xml` — search for `mnem="stvx128"`](../../xenia-canary/tools/ppc-instructions.xml) - xenia-canary emit: [`src/xenia/cpu/ppc/ppc_emit_altivec.cc:196`](../../xenia-canary/src/xenia/cpu/ppc/ppc_emit_altivec.cc#L196) - xenia-rs opcode: [`crates/xenia-cpu/src/opcode.rs:79`](../../xenia-rs/crates/xenia-cpu/src/opcode.rs#L79) - xenia-rs decoder: [`crates/xenia-cpu/src/decoder.rs:417`](../../xenia-rs/crates/xenia-cpu/src/decoder.rs#L417) - xenia-rs interpreter: [`crates/xenia-cpu/src/interpreter.rs:1860-1870`](../../xenia-rs/crates/xenia-cpu/src/interpreter.rs#L1860-L1870)
xenia-rs interpreter body (frozen snapshot) ```rust PpcOpcode::stvx128 => { let ea = if instr.ra() == 0 { 0u64 } else { ctx.gpr[instr.ra()] }; let ea = (ea.wrapping_add(ctx.gpr[instr.rb()]) & !0xF) as u32; // PPCBUG-511: stvx128 was missing invalidate_for_write. if let Some(t) = ctx.reservation_table.as_ref().filter(|t| t.is_enabled()) { if t.has_active_reservers() { t.invalidate_for_write(ea); } } let bytes = ctx.vr[instr.vs128()].as_bytes(); for i in 0..16 { mem.write_u8(ea + i as u32, bytes[i]); } ctx.pc += 4; } ```
## Extended Pseudocode ``` EA <- ((RA|0) + (RB)) & ~0xF ; force 16-byte alignment MEM(EA, 16) <- byte_order_adjusted(VS) ; lane 0 at EA, lane 15 at EA+15 ``` ## Special Cases & Edge Conditions - **Alignment is forced, not checked.** The low four bits of the effective address are **cleared** before the store — alignment violations silently corrupt adjacent data rather than trap. This differs from scalar `stw` (no alignment enforcement) and from `stvewx` (which stores only one element and keeps the exact EA). - **Big-endian lane layout.** Vector lane 0 (the most-significant bytes of the 128-bit register) lives at the lowest address; lane 15 at `EA + 15`. On little-endian hosts the whole 16-byte block is byte-swapped at the memory boundary so the PowerPC-visible layout is preserved. Xenia's helper `mem_write_vec128_be` handles this. - **`RA0` semantics.** When `RA = 0` the base is the literal zero — just like scalar loads/stores. Combined with the alignment mask this lets `stvx VS, 0, RB` store to address `RB & ~0xF`. - **No update form.** Unlike scalar stores, VMX stores have no `u` variant that post-writes the base. Use [`stvxl`](stvxl.md) for the cache-hint variant (suggests "last" — the line is not expected to be reused soon). - **VMX128 sibling (`stvx128`).** Identical semantics; the only difference is the operand encoding. VMX128 uses a 7-bit register index split across three non-contiguous bit fields (`VS128l ‖ VS128h`) so it can address `v0..v127` instead of the 32-register Altivec space. All alignment, byte-order and `RA0` rules are the same. - **Read-before-write.** The 16-byte write occurs as one conceptual store; subsequent loads from the same address observe the complete new value. There's no split-transaction window visible to software. ## Related Instructions - [`lvx`](lvx.md), [`lvx128`](lvx.md) — the load counterparts. - [`stvxl`](stvxl.md), [`stvxl128`](stvxl.md) — cache-hint "last-use" variants. - [`stvebx`](stvebx.md) / [`stvehx`](stvehx.md) / [`stvewx`](stvewx.md) — store single element (byte / half / word) at the exact (unaligned) address. - [`stvlx`](stvlx.md) / [`stvrx`](stvrx.md) — store-left / store-right for unaligned vector I/O. - [`dcbz`](dcbz.md) — zero a cache line; often paired with `stvx` in block-fill idioms. ## IBM Reference - [AIX 7.3 — `stvx` (Store Vector Indexed)](https://www.ibm.com/docs/en/aix/7.3.0?topic=set-stvx-store-vector-indexed-instruction) - PowerISA Book II (Altivec / VMX). Xbox 360 VMX128 is Microsoft-documented in the XDK; xenia's `ppc-instructions.xml` captures the deltas.