The hand-written parts of the manual still described how the retired xenia-rs interpreter behaved: its snapshots, Rust casts and helpers. Each of those 490 statements is now either restated as what Canary's emitters and x64 backend actually do (at the pinned canary_experimental commit), or dropped where it only made sense for xenia-rs. Checking them turned up claims that were wrong, not just outdated: - VSCR[SAT] is never modelled in Canary (DID_SATURATE is a stub and mfvscr cannot see it); the pages said saturating ops set it stickily. - Canary does not implement lswi/lswx/stswi/stswx, dcbi, mtfsb0/mtfsb1, vmsum*, vmhaddshs, vupkhpx/vupklpx, and most SPRs; pages described them as working. - Traps evaluate TO in Canary; stvebx/stvehx/stvewx store one element, not 16 bytes; mtmsrd writes only EE; fres/frsqrte/vrsqrtefp precision claims and the stfs "rounds under RN / sets FPSCR" claim contradicted the spec. - Reservations are a 64 KiB block bitmap plus a value compare, not per-address tracking. Claims that neither Canary's source nor a public spec settles are marked unverified (NI at boot, vmaddcfp128 operand order, estimate bit-exactness). Generated regions are untouched; re-running the generator changes nothing. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
267 lines
11 KiB
Markdown
267 lines
11 KiB
Markdown
# `lfd` — Load Floating-Point Double
|
||
|
||
> **Category:** [Memory](../categories/memory.md) · **Form:** [D](../forms/D.md) · **Opcode:** `0xc8000000`
|
||
|
||
<!-- GENERATED: BEGIN -->
|
||
|
||
## Assembler Mnemonics
|
||
|
||
| Mnemonic | XML entry | Flags | Description |
|
||
| --- | --- | --- | --- |
|
||
| `lfd` | `lfd` | — | Load Floating-Point Double |
|
||
| `lfdu` | `lfdu` | — | Load Floating-Point Double with Update |
|
||
| `lfdux` | `lfdux` | — | Load Floating-Point Double with Update Indexed |
|
||
| `lfdx` | `lfdx` | — | Load Floating-Point Double Indexed |
|
||
|
||
## Syntax
|
||
|
||
```asm
|
||
lfd [FD], [d]([RA0])
|
||
lfdu [FD], [d]([RA])
|
||
lfdux [FD], [RA], [RB]
|
||
lfdx [FD], [RA0], [RB]
|
||
```
|
||
|
||
## Encoding
|
||
|
||
### `lfd` — form `D`
|
||
|
||
- **Opcode word:** `0xc8000000`
|
||
- **Primary opcode (bits 0–5):** `50`
|
||
- **Extended opcode:** —
|
||
- **Synchronising:** no
|
||
|
||
| Bits | Field | Meaning |
|
||
| --- | --- | --- |
|
||
| 0–5 | `OPCD` | primary opcode |
|
||
| 6–10 | `RT` | destination GPR (or RS when storing) |
|
||
| 11–15 | `RA` | source GPR (0 ⇒ literal 0 for RA0 forms) |
|
||
| 16–31 | `D/SI/UI` | 16-bit signed or unsigned immediate |
|
||
|
||
### `lfdu` — form `D`
|
||
|
||
- **Opcode word:** `0xcc000000`
|
||
- **Primary opcode (bits 0–5):** `51`
|
||
- **Extended opcode:** —
|
||
- **Synchronising:** no
|
||
|
||
| Bits | Field | Meaning |
|
||
| --- | --- | --- |
|
||
| 0–5 | `OPCD` | primary opcode |
|
||
| 6–10 | `RT` | destination GPR (or RS when storing) |
|
||
| 11–15 | `RA` | source GPR (0 ⇒ literal 0 for RA0 forms) |
|
||
| 16–31 | `D/SI/UI` | 16-bit signed or unsigned immediate |
|
||
|
||
### `lfdux` — form `X`
|
||
|
||
- **Opcode word:** `0x7c0004ee`
|
||
- **Primary opcode (bits 0–5):** `31`
|
||
- **Extended opcode:** `631`
|
||
- **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 |
|
||
|
||
### `lfdx` — form `X`
|
||
|
||
- **Opcode word:** `0x7c0004ae`
|
||
- **Primary opcode (bits 0–5):** `31`
|
||
- **Extended opcode:** `599`
|
||
- **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 |
|
||
|
||
## Operands
|
||
|
||
| Field | Role | Description |
|
||
| --- | --- | --- |
|
||
| `RA0` | lfd: read; lfdx: read | Source GPR; when the encoded register number is 0 the operand is the literal 64-bit zero, **not** `r0`. |
|
||
| `d` | lfd: read; lfdu: read | 16-bit signed displacement (`d`) added to the base address register. |
|
||
| `FD` | lfd: write; lfdu: write; lfdux: write; lfdx: write | Destination floating-point register. |
|
||
| `RA` | lfdu: read; lfdu: write; lfdux: read; lfdux: write | Source GPR (`r0`–`r31`). |
|
||
| `RB` | lfdux: read; lfdx: read | Source GPR. |
|
||
|
||
## Register Effects
|
||
|
||
### `lfd`
|
||
|
||
- **Reads (always):** `RA0`, `d`
|
||
- **Reads (conditional):** _none_
|
||
- **Writes (always):** `FD`
|
||
- **Writes (conditional):** _none_
|
||
|
||
### `lfdu`
|
||
|
||
- **Reads (always):** `RA`, `d`
|
||
- **Reads (conditional):** _none_
|
||
- **Writes (always):** `FD`, `RA`
|
||
- **Writes (conditional):** _none_
|
||
|
||
### `lfdux`
|
||
|
||
- **Reads (always):** `RA`, `RB`
|
||
- **Reads (conditional):** _none_
|
||
- **Writes (always):** `FD`, `RA`
|
||
- **Writes (conditional):** _none_
|
||
|
||
### `lfdx`
|
||
|
||
- **Reads (always):** `RA0`, `RB`
|
||
- **Reads (conditional):** _none_
|
||
- **Writes (always):** `FD`
|
||
- **Writes (conditional):** _none_
|
||
|
||
## Status-Register Effects
|
||
|
||
_No condition-register or status-register effects._
|
||
|
||
## Operation (pseudocode)
|
||
|
||
```
|
||
EA <- (RA|0) + EXTS(d)
|
||
FRT <- MEM(EA, 8)
|
||
```
|
||
|
||
## C Translation Example
|
||
|
||
```c
|
||
/* No hand-written C yet. Translate the Canary emitter snapshot */
|
||
/* under Implementation References; its HIR maps directly: */
|
||
/* f.LoadGPR(n) / f.StoreGPR(n, v) -> r[n] / r[n] = v */
|
||
/* f.LoadFPR / StoreFPR, f.LoadVR / StoreVR -> f[n], v[n] */
|
||
/* f.Load(ea, T), f.Store(ea, v) -> raw read / write; emitters */
|
||
/* wrap them in f.ByteSwap for the big-endian guest value */
|
||
/* f.UpdateCR(n, v) -> CR field n from v's LOW 32 BITS vs 0 */
|
||
/* f.LoadCA / f.StoreCA -> xer.CA; f.StoreSAT -> vscr.SAT */
|
||
/* i.XO.RA, i.D.DS, ... -> the bit-fields listed under Operands */
|
||
/* The Register Effects and Status-Register Effects tables above */
|
||
/* enumerate every side effect a faithful translation must emit. */
|
||
```
|
||
|
||
## Implementation References
|
||
|
||
**`lfd`**
|
||
- Canary XML: [`tools/ppc-instructions.xml` — search for `mnem="lfd"`](https://github.com/xenia-canary/xenia-canary/blob/f21ebd49e979e44f081f474df78c3fbfee9cb3f2/tools/ppc-instructions.xml)
|
||
- Canary emitter: [`src/xenia/cpu/ppc/ppc_emit_memory.cc:912`](https://github.com/xenia-canary/xenia-canary/blob/f21ebd49e979e44f081f474df78c3fbfee9cb3f2/src/xenia/cpu/ppc/ppc_emit_memory.cc#L912)
|
||
- Sylpheed opcode: [`crates/sylpheed-ppc/src/opcode.rs:113`](../../../crates/sylpheed-ppc/src/opcode.rs#L113)
|
||
- Sylpheed decoder: [`crates/sylpheed-ppc/src/decoder.rs:488`](../../../crates/sylpheed-ppc/src/decoder.rs#L488)
|
||
<details><summary>Canary emitter (frozen snapshot @ <code>f21ebd49e9</code>)</summary>
|
||
|
||
```cpp
|
||
int InstrEmit_lfd(PPCHIRBuilder& f, const InstrData& i) {
|
||
// if RA = 0 then
|
||
// b <- 0
|
||
// else
|
||
// b <- (RA)
|
||
// EA <- b + EXTS(D)
|
||
// FRT <- MEM(EA, 8)
|
||
Value* ea = CalculateEA_0_i(f, i.D.RA, XEEXTS16(i.D.DS));
|
||
Value* rt = f.Cast(f.ByteSwap(f.Load(ea, INT64_TYPE)), FLOAT64_TYPE);
|
||
f.StoreFPR(i.D.RT, rt);
|
||
return 0;
|
||
}
|
||
```
|
||
</details>
|
||
|
||
**`lfdu`**
|
||
- Canary XML: [`tools/ppc-instructions.xml` — search for `mnem="lfdu"`](https://github.com/xenia-canary/xenia-canary/blob/f21ebd49e979e44f081f474df78c3fbfee9cb3f2/tools/ppc-instructions.xml)
|
||
- Canary emitter: [`src/xenia/cpu/ppc/ppc_emit_memory.cc:925`](https://github.com/xenia-canary/xenia-canary/blob/f21ebd49e979e44f081f474df78c3fbfee9cb3f2/src/xenia/cpu/ppc/ppc_emit_memory.cc#L925)
|
||
- Sylpheed opcode: [`crates/sylpheed-ppc/src/opcode.rs:114`](../../../crates/sylpheed-ppc/src/opcode.rs#L114)
|
||
- Sylpheed decoder: [`crates/sylpheed-ppc/src/decoder.rs:489`](../../../crates/sylpheed-ppc/src/decoder.rs#L489)
|
||
<details><summary>Canary emitter (frozen snapshot @ <code>f21ebd49e9</code>)</summary>
|
||
|
||
```cpp
|
||
int InstrEmit_lfdu(PPCHIRBuilder& f, const InstrData& i) {
|
||
// EA <- (RA) + EXTS(D)
|
||
// FRT <- MEM(EA, 8)
|
||
// RA <- EA
|
||
Value* ea = CalculateEA_i(f, i.D.RA, XEEXTS16(i.D.DS));
|
||
Value* rt = f.Cast(f.ByteSwap(f.Load(ea, INT64_TYPE)), FLOAT64_TYPE);
|
||
f.StoreFPR(i.D.RT, rt);
|
||
StoreEA(f, i.D.RA, ea);
|
||
return 0;
|
||
}
|
||
```
|
||
</details>
|
||
|
||
**`lfdux`**
|
||
- Canary XML: [`tools/ppc-instructions.xml` — search for `mnem="lfdux"`](https://github.com/xenia-canary/xenia-canary/blob/f21ebd49e979e44f081f474df78c3fbfee9cb3f2/tools/ppc-instructions.xml)
|
||
- Canary emitter: [`src/xenia/cpu/ppc/ppc_emit_memory.cc:936`](https://github.com/xenia-canary/xenia-canary/blob/f21ebd49e979e44f081f474df78c3fbfee9cb3f2/src/xenia/cpu/ppc/ppc_emit_memory.cc#L936)
|
||
- Sylpheed opcode: [`crates/sylpheed-ppc/src/opcode.rs:115`](../../../crates/sylpheed-ppc/src/opcode.rs#L115)
|
||
- Sylpheed decoder: [`crates/sylpheed-ppc/src/decoder.rs:942`](../../../crates/sylpheed-ppc/src/decoder.rs#L942)
|
||
<details><summary>Canary emitter (frozen snapshot @ <code>f21ebd49e9</code>)</summary>
|
||
|
||
```cpp
|
||
int InstrEmit_lfdux(PPCHIRBuilder& f, const InstrData& i) {
|
||
// EA <- (RA) + (RB)
|
||
// FRT <- MEM(EA, 8)
|
||
// RA <- EA
|
||
Value* ea = CalculateEA(f, i.X.RA, i.X.RB);
|
||
Value* rt = f.Cast(f.ByteSwap(f.Load(ea, INT64_TYPE)), FLOAT64_TYPE);
|
||
f.StoreFPR(i.X.RT, rt);
|
||
StoreEA(f, i.X.RA, ea);
|
||
return 0;
|
||
}
|
||
```
|
||
</details>
|
||
|
||
**`lfdx`**
|
||
- Canary XML: [`tools/ppc-instructions.xml` — search for `mnem="lfdx"`](https://github.com/xenia-canary/xenia-canary/blob/f21ebd49e979e44f081f474df78c3fbfee9cb3f2/tools/ppc-instructions.xml)
|
||
- Canary emitter: [`src/xenia/cpu/ppc/ppc_emit_memory.cc:947`](https://github.com/xenia-canary/xenia-canary/blob/f21ebd49e979e44f081f474df78c3fbfee9cb3f2/src/xenia/cpu/ppc/ppc_emit_memory.cc#L947)
|
||
- Sylpheed opcode: [`crates/sylpheed-ppc/src/opcode.rs:116`](../../../crates/sylpheed-ppc/src/opcode.rs#L116)
|
||
- Sylpheed decoder: [`crates/sylpheed-ppc/src/decoder.rs:941`](../../../crates/sylpheed-ppc/src/decoder.rs#L941)
|
||
<details><summary>Canary emitter (frozen snapshot @ <code>f21ebd49e9</code>)</summary>
|
||
|
||
```cpp
|
||
int InstrEmit_lfdx(PPCHIRBuilder& f, const InstrData& i) {
|
||
// if RA = 0 then
|
||
// b <- 0
|
||
// else
|
||
// b <- (RA)
|
||
// EA <- b + (RB)
|
||
// FRT <- MEM(EA, 8)
|
||
Value* ea = CalculateEA_0(f, i.X.RA, i.X.RB);
|
||
Value* rt = f.Cast(f.ByteSwap(f.Load(ea, INT64_TYPE)), FLOAT64_TYPE);
|
||
f.StoreFPR(i.X.RT, rt);
|
||
return 0;
|
||
}
|
||
```
|
||
</details>
|
||
|
||
<!-- GENERATED: END -->
|
||
|
||
## Special Cases & Edge Conditions
|
||
|
||
- **Bit-exact double load.** Reads 8 bytes and places them directly into `FRT` as IEEE-754 binary64. No format conversion is performed (contrast `lfs`, which expands single→double).
|
||
- **No FPSCR side effects.** `lfd` cannot raise IEEE exceptions: it neither rounds nor inspects the value. A signalling NaN read this way stays a signalling NaN until it is consumed by an arithmetic op.
|
||
- **`RA0` semantics.** In the non-update forms (`lfd`, `lfdx`), `RA = 0` selects literal zero — `lfd FT, 0(0)` loads from absolute address 0. Update forms `lfdu` / `lfdux` invoke `RA = 0` and `RA = RT` (here `RA` is GPR; `RT` is FPR, so the latter cannot collide) as invalid forms when `RA = 0`.
|
||
- **Alignment.** Xenon tolerates unaligned 8-byte FP loads; PowerISA technically permits implementations to raise alignment exceptions for FP loads, so portable code uses 8-byte aligned addresses.
|
||
- **Big-endian read.** Bytes are interpreted big-endian: byte at `EA` is bits 0–7 of the IEEE pattern (sign + part of exponent), byte at `EA+7` is bits 56–63 of the mantissa. Canary byte-swaps the loaded doubleword and reinterprets it as binary64 (`Cast`), bit-exact.
|
||
- **MSR[FP] required.** Like all FP-register accesses, `lfd` requires the FP unit be enabled (MSR[FP]=1). Otherwise a Floating-Point Unavailable interrupt is raised. Canary does not check `MSR[FP]`.
|
||
- **Pair with [`stfd`](stfd.md).** Store-double is the symmetric counterpart.
|
||
|
||
## Related Instructions
|
||
|
||
- [`lfs`](lfs.md) — single-precision load with format conversion to double.
|
||
- [`stfd`](stfd.md), [`stfdu`](stfd.md), [`stfdx`](stfd.md), [`stfdux`](stfd.md) — corresponding stores.
|
||
- [`stfiwx`](stfiwx.md) — store-FP-as-integer-word (the asymmetric oddity in the FP load/store family).
|
||
- [`ld`](ld.md) — integer doubleword load (same width, GPR target).
|
||
|
||
## IBM Reference
|
||
|
||
- [AIX 7.3 — `lfd` (Load Floating-Point Double)](https://www.ibm.com/docs/en/aix/7.3.0?topic=set-lfd-load-floating-point-double-instruction)
|
||
- [AIX 7.3 — `lfdu` / `lfdx` / `lfdux`](https://www.ibm.com/docs/en/aix/7.3.0?topic=set-lfdu-load-floating-point-double-update-instruction)
|