SHA-1 and SHA-256 instructions with a [rip+disp32] operand, and
instructions with one that a short site absorbs, now move into the
stub. The stub records each displacement as a relocation relative to
the site, and the Linux, guest and Windows placements resolve it once
the stub address is known. Indirect branches through [rip+disp32]
still fail the relink.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
RSQRTPS and RCPPS are approximations whose low bits differ between Intel
and AMD. Intel returns 0x3F7FF000 for 1/sqrt(1.0), and two Newton-Raphson
steps on it settle on 0.99999994 instead of 1.0. PPSA21564 renormalises
its spring quaternions that way: an identity quaternion keeps w at
0.99999994 with a zero axis, its axis-angle conversion then normalises the
zero axis into NaNs, and the NaN bone poses reach keyframed physics bodies.
A NaN body later moves to an invalid broadphase cell and the game crashes
a few seconds into its hub level.
--to-intel now replaces the VEX.128 register forms with an out-of-line stub
that computes 1/sqrt(x) with SQRTPS and DIVPS (1/x with DIVPS), keeping
the upper half of the destination cleared and the scratch register intact.
A site with no room for the jump, including one followed by a branch
target or a RIP-relative instruction, keeps the native instruction and is
reported as kept instead of failing the relink.
In 64-bit mode a REX prefix only takes effect when it immediately
precedes the opcode; a REX followed by a legacy prefix or another REX is
ignored. The instruction decoder, the rewriter's reference classifier,
DecodedInstruction and the SSE4a, SHA-256 and CLZERO operand decoders
read legacy prefixes and then at most one REX. `48 F3 0F 2B 00`
(MOVNTSS) was therefore scanned as `[48 F3][0F 2B 00]` and kept, and
`48 67 0F 01 FC` lost its address-size prefix.
All of them now accept REX bytes among the prefixes and keep only one
that directly precedes the opcode. The converter's guard against
prefix-only fragments is removed, since the decoder no longer produces
them, and the TechnicalDebt entry describing the split is dropped.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Lower CLZERO out of line instead of failing the relink: the 64-byte line
containing rAX (EAX with 67h) is cleared with four MOVNTDQ stores of
zero, the same non-temporal, weakly ordered store. The line address is
masked in xmm0 so RFLAGS stays untouched; xmm0 and rcx are spilled below
the red zone. Short sites share stubs through MatchSequence. CLZERO with
LOCK, an FS/GS override, a 66/F2/F3 prefix or longer than 15 bytes fails
the relink.
The decoder splits a REX followed by another prefix into a separate
instruction, which would hide a prefix that changes what CLZERO or the
next instruction does. The converter now fails the relink when such a
prefix-only fragment directly precedes an AMD-only instruction or would
be moved into a stub as a trailing instruction.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
EXTRQ, INSERTQ, MOVNTSS and MOVNTSD are rewritten at relink time: same-length in-place forms
where they exist, otherwise a jmp rel32 into an appended executable section holding a
scratch-free SSE body and a jump back, so no code shifts and no RIP-relative or jump-table
operand needs adjusting. Decoder fixes for POPCNT and 0F BB (BTC), codegen and elfpatcher
tests, README and technical-debt notes. The runtime illegal-instruction trap stays as a
fallback.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0177gthrWEBBfBu5xJDXgBfo
Hashaam Zafar
Dean Galvin
ljkx
devilismyfriend
boykopovar