Files
sim f3c512f2ab docs(ppc-manual): check every xenia-rs claim against Canary's source
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Checking them turned up claims that were wrong, not just outdated: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>
2026-09-16 21:52:38 +02:00

10 KiB
Raw Permalink Blame History

stfd — Store Floating-Point Double

Category: Memory · Form: D · Opcode: 0xd8000000

Assembler Mnemonics

Mnemonic XML entry Flags Description
stfd stfd Store Floating-Point Double
stfdu stfdu Store Floating-Point Double with Update
stfdux stfdux Store Floating-Point Double with Update Indexed
stfdx stfdx Store Floating-Point Double Indexed

Syntax

stfd [FS], [d]([RA0])
stfdu [FS], [d]([RA])
stfdux [FS], [RA], [RB]
stfdx [FS], [RA0], [RB]

Encoding

stfd — form D

  • Opcode word: 0xd8000000
  • Primary opcode (bits 05): 54
  • Extended opcode:
  • Synchronising: no
Bits Field Meaning
05 OPCD primary opcode
610 RT destination GPR (or RS when storing)
1115 RA source GPR (0 ⇒ literal 0 for RA0 forms)
1631 D/SI/UI 16-bit signed or unsigned immediate

stfdu — form D

  • Opcode word: 0xdc000000
  • Primary opcode (bits 05): 55
  • Extended opcode:
  • Synchronising: no
Bits Field Meaning
05 OPCD primary opcode
610 RT destination GPR (or RS when storing)
1115 RA source GPR (0 ⇒ literal 0 for RA0 forms)
1631 D/SI/UI 16-bit signed or unsigned immediate

stfdux — form X

  • Opcode word: 0x7c0005ee
  • Primary opcode (bits 05): 31
  • Extended opcode: 759
  • Synchronising: no
Bits Field Meaning
05 OPCD primary opcode
610 RT/FRT/VRT destination
1115 RA/FRA/VRA source A
1620 RB/FRB/VRB source B
2130 XO extended opcode (10 bits)
31 Rc record-form flag

stfdx — form X

  • Opcode word: 0x7c0005ae
  • Primary opcode (bits 05): 31
  • Extended opcode: 727
  • Synchronising: no
Bits Field Meaning
05 OPCD primary opcode
610 RT/FRT/VRT destination
1115 RA/FRA/VRA source A
1620 RB/FRB/VRB source B
2130 XO extended opcode (10 bits)
31 Rc record-form flag

Operands

Field Role Description
FS stfd: read; stfdu: read; stfdux: read; stfdx: read Source floating-point register.
RA0 stfd: read; stfdx: read Source GPR; when the encoded register number is 0 the operand is the literal 64-bit zero, not r0.
d stfd: read; stfdu: read 16-bit signed displacement (d) added to the base address register.
RA stfdu: read; stfdu: write; stfdux: read; stfdux: write Source GPR (r0r31).
RB stfdux: read; stfdx: read Source GPR.

Register Effects

stfd

  • Reads (always): FS, RA0, d
  • Reads (conditional): none
  • Writes (always): none
  • Writes (conditional): none

stfdu

  • Reads (always): FS, RA, d
  • Reads (conditional): none
  • Writes (always): RA
  • Writes (conditional): none

stfdux

  • Reads (always): FS, RA, RB
  • Reads (conditional): none
  • Writes (always): RA
  • Writes (conditional): none

stfdx

  • Reads (always): FS, 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) + EXTS(d)
MEM(EA, 8) <- (FRS)

C Translation Example

/* 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

stfd

Canary emitter (frozen snapshot @ f21ebd49e9)
int InstrEmit_stfd(PPCHIRBuilder& f, const InstrData& i) {
  // if RA = 0 then
  //   b <- 0
  // else
  //   b <- (RA)
  // EA <- b + EXTS(D)
  // MEM(EA, 8) <- (FRS)
  Value* ea = CalculateEA_0_i(f, i.D.RA, XEEXTS16(i.D.DS));
  f.Store(ea, f.ByteSwap(f.Cast(f.LoadFPR(i.D.RT), INT64_TYPE)));
  return 0;
}

stfdu

Canary emitter (frozen snapshot @ f21ebd49e9)
int InstrEmit_stfdu(PPCHIRBuilder& f, const InstrData& i) {
  // EA <- (RA) + EXTS(D)
  // MEM(EA, 8) <- (FRS)
  // RA <- EA
  Value* ea = CalculateEA_i(f, i.D.RA, XEEXTS16(i.D.DS));
  f.Store(ea, f.ByteSwap(f.Cast(f.LoadFPR(i.D.RT), INT64_TYPE)));
  StoreEA(f, i.D.RA, ea);
  return 0;
}

stfdux

Canary emitter (frozen snapshot @ f21ebd49e9)
int InstrEmit_stfdux(PPCHIRBuilder& f, const InstrData& i) {
  // EA <- (RA) + (RB)
  // MEM(EA, 8) <- (FRS)
  // RA <- EA
  Value* ea = CalculateEA(f, i.X.RA, i.X.RB);
  f.Store(ea, f.ByteSwap(f.Cast(f.LoadFPR(i.X.RT), INT64_TYPE)));
  StoreEA(f, i.X.RA, ea);
  return 0;
}

stfdx

Canary emitter (frozen snapshot @ f21ebd49e9)
int InstrEmit_stfdx(PPCHIRBuilder& f, const InstrData& i) {
  // if RA = 0 then
  //   b <- 0
  // else
  //   b <- (RA)
  // EA <- b + (RB)
  // MEM(EA, 8) <- (FRS)
  Value* ea = CalculateEA_0(f, i.X.RA, i.X.RB);
  f.Store(ea, f.ByteSwap(f.Cast(f.LoadFPR(i.X.RT), INT64_TYPE)));
  return 0;
}

Special Cases & Edge Conditions

  • Bit-exact double store. Writes the 64-bit IEEE binary64 contents of FRS directly to memory; no rounding, no format conversion. Canary reinterprets the FPR as a 64-bit integer (Cast) and stores it byte-swapped, which preserves the exact bit pattern (including signalling NaNs).
  • No FPSCR side effects. Like lfd, stfd cannot raise IEEE exceptions: there is no rounding step. Contrast stfs, where double→single rounding can raise inexact / overflow / underflow.
  • RA0 (non-update forms). RA = 0 in stfd and stfdx selects literal zero. Update forms stfdu / stfdux invoke RA = 0 as an invalid form.
  • Update-form post-write. stfdu / stfdux write the computed EA back to RA after the store. No FRS / RA collision possible — RS is an FPR, RA is a GPR.
  • Big-endian write. Byte at EA is the FPR's most-significant byte (sign + part of exponent), byte at EA+7 is the least-significant mantissa byte. Canary byte-swaps before the host store.
  • Alignment. Xenon tolerates unaligned 8-byte FP stores. PowerISA permits implementations to raise alignment exceptions on cache-inhibited storage.
  • MSR[FP] required. Disabled FP unit raises Floating-Point Unavailable.
  • lfd, lfdu, lfdx, lfdux — corresponding loads.
  • stfs — single-precision store with format conversion (can raise FPSCR).
  • stfiwx — store low 32 bits of FPR as integer word.
  • std — integer doubleword store (same width, GPR source).

IBM Reference