The remote was previously a distribution-only point for pre-built DLLs.
This opens the source.
- LICENSE: Unlicense, with a GPL-3.0 carve-out for src/dpslog/WeirdDPSMate
(a DPSMate fork that keeps its own license)
- README.md replaces the stale internal one with the user-facing docs from
DLL_README.md, swapping the 'Why No Source Code?' section for build and
layout notes. DLL_README.md is dropped; one README now serves both.
- RELEASING.md: drop the trim-the-README-per-release dance and the
remote/WeirdUtils/ distribution clone, both obsolete now
- gitignore agent/editor scratch, build caches, the vendored WSBT addon,
and the WeirdThreat/uwu-logs checkouts (separate upstream repos)
- Commit outstanding module work: superweirdo, clickthrough portal visuals,
transform44 decompiles, worldmarkers demo presets, tools/
Adds bone_sse64.zig as an f64-intermediate port of transformMatrix4x4, used as
the active hook. M2 bone matrices are built and multiplied as [16]f64 and only
narrow to f32 on final store into the bone output buffer -- matching the x87
original's rounding profile (wide intermediates, single f32 store) and keeping
M2 vertex positions aligned with the terrain/projected-texture pipeline.
Also fixes, in both bone_sse (f32) and bone_sse64:
- Pre-billboard tx/ty/tz accumulation order (row 0 = pz+px+py; rows 1/2 = pz+py+px)
- Post-billboard pos_y/pos_z accumulation order (py+pz+px)
- Post-billboard scale-recompute accumulation order (row0 + row2 + row1)
- Billboard types 2/4 normalize using f64 intermediates (load-bearing for camera
basis vectors -- pure f32 drifted from x87 by a ULP per axis and caused
particle emitters to jitter on camera motion)
Additional bone_sse64-specific changes:
- Local attachmentRecursion64 that recurses into transformImpl_SSE64 instead of
bone_sse.transformImpl_SSE, so attached child models stay on the f64 path
- child_padding (this+0x84) computed with f64 intermediates
bone_sse remains the reference f32 implementation; its struct fields, inline
helpers, and section-loop fns are now `pub` so bone_sse64 can share them
(types/interpolation helpers/post-loop loops). Artifact size is unchanged.
build.zig adds bench_bone_sse64 object; src/bench/main.zig runs the new variant
through the same warmup/timing harness and prints SSE vs SSE64 vs BASELINE
cycles plus a parity check.
A/B results: hash_lookup prefetch/cache both regressed (original is
near-optimal at 59 bytes), VM opcode SSE2 patches were break-even.
Only luaS_newlstr hash pre-check shows consistent 40-45% per-call win.
Drop hash_lookup hook, VM jump table patches, and resize hook. Keep
newlstr Detour with per-call A/B rdtsc and OnWorldUpdate periodic dump.
Add GC_WRITE_BARRIER.md documenting the barrier globals at 0xCEEAC0/C4
found in lua_vm_execute (useful for luagc module).
bench: add Detour overhead micro-benchmark. Simulates zhook's
JMP+trampoline mechanism on mmap'd executable pages. Result: 5 cyc/call
overhead -- negligible vs the ~100 cyc/call newlstr savings.
Removed deferred divide from both ray-tri functions -- the det-scaled
epsilon comparisons lose precision for near-parallel rays, potentially
accepting triangles the original rejects. Downstream SetupBoxFrustum
then writes to wrong globals near 0xCE6738 (SGroupPtr), causing
ERROR #124 on exit.
inflate_hook: replaced manual FS:0x24 thread ID pool with Zig native
threadlocal. Fixes potential crash on Wine where FS segment layout
may differ.
Build: switched from GNU to MSVC ABI (4-5K smaller per DLL, no
.eh_frame unwind tables). Added setjmp.h stub for libdeflate MSVC
build. Added noperf build variant (zig build noperf).
FindObjectByGUID (0x464890): 4096-entry direct-mapped cache with
validate-on-hit. 97% hit rate at 10K+ calls/frame, reducing from
0.8% to 0.3% frame time. Validates cached pointers by checking
GUID at obj+0x30/+0x34 on every hit.
AddToSpatialGrid (0x6816F0): SSE rewrite attempted, no measurable
gain (memory-bound linked list ops dominate). Not shipped.
rayTriIntersectIndexedInt (0x7C2C40): SSE Moller-Trumbore with deferred
divide, matching original's epsilon thresholds. Parity-tested against
original for edge hits, backfaces, parallel rays, and per-triangle t/uv.
JMP-patched in weirdperformance.
Added transform44 profiling hooks for ray_tri_indexed_int (0x7C2C40)
and ProcessStaticObjectsCulling (0x683BF0).
Bench: added rayTriIndexedInt bench with exhaustive parity tests.
PerformSpatialCulling (0x6B8C60): Zig rewrite with SSE outcode
computation. 1.4x speedup, JMP-patched in weirdperformance.
performCollisionDetection (0x6B88E0): fully inlined SSE Moller-Trumbore
ray-triangle intersection, eliminating 4 SetVector3 calls and the
ray_tri function pointer call per triangle. ~22 cyc/tri in bench.
Both graduated from transform44 A/B testing to production JMP patches.
entity_sse.zig: reimplementations of UpdateEntityAndChunksPositions and
updateEntitiesInBounds (A/B tested, 1.2x bench, not shipped - memory
bound with negligible real-world gain).
clickthrough: fixed CheckObjectTypePermissions hook from fastcall to
thiscall (ECX preservation), fixed ClntObjMgrObjectPtr from fastcall(4)
to fastcall(5) with correct arg count.
bench: added performCollisionDetection bench with synthetic mesh data
and patched FindOrCreateHashEntry stub.
- Ghidra C decompilation of RenderParticleSprites (422 lines) and 5
helper functions (calculateColorValues, matVec3Transform, etc.)
- particle_sse.zig with calcColorValues_SSE (10.7x bench but cache-miss
bound in-game — needs inlining into full function replacement)
- Bench harness for calcColorValues with correctness check
- build.zig: particle_sse as separate ReleaseFast compilation unit
- colorDetour reverted to pass-through (SSE has no in-game effect due
to L1 cache misses on scattered ColorCtx structs)
- bone_sse: deduplicate findInterpIdx calls in bone loop — rotation's
search result reused for scale/translation when tracks share temporal
structure (canReuseInterp guard). Est. ~23% bone loop cycle reduction.
- silicon: SSE replacement for processLinkedListCollision (0x6ABC40,
1.57% CPU). V4 AABB overlap test replaces 6 x87 FCOMP/FNSTSW.
Benched at 3.2x speedup (378→115 cyc/call, 8 nodes).
- transform44: remove A/B toggle, always use SSE path (teardown guard
kept). A/B infrastructure remains for other hooks.
- bench: add processLinkedListCollision benchmark with fake linked list
test fixture and stubbed addGeometryToBuffer.
si_ftol: 9-byte naked asm using FISTTP (SSE3 truncate-from-x87) replaces
the 39-byte FSTCW/FLDCW/FISTP rounding mode dance. 4 vs 7 cycles (1.7x).
13.2M calls/7.5s in-game -- ~13ms savings per period.
Benchmark: patch-in-place at mapped 0x40A2B0, test parity across 19 values,
best-of-5 timing with varying inputs. Framework for all silicon functions.
Also disabled h67 (ConvertPixelsToScreenAlt) probe -- game passes ECX=0
as valid input, thiscall probe crashes on null this.
mulMat3x4 / mulMat3x4InPlace: translation row had A*B operands swapped.
Original computes A_translation * B_rotation + B_translation, but our
code was doing A_rotation * B_translation + A_translation. Verified by
tracing x87 disassembly: first element loads A[9]*B[col] pattern.
Fixed in both silicon_sse.zig and silicon.zig.
packParticleColor: x87 rounds 127.5 to 128 (round-to-nearest), but SSE
@intFromFloat truncates to 127. Added @round() before @intFromFloat.
42/42 benchmarks now pass correctness. 0 MISMATCHes.
Inlined benchmarks use x87 inline asm vs direct Zig @Vector code with
no CALL/RET on either side. Shows the true instruction-level comparison
that in-place patching would achieve:
dotProduct: x87=3 SSE=1 -> 3.0x (was 0.3x when called)
evalPoly: x87=4 SSE=1 -> 4.0x (was 0.7x when called)
vec3MulScal: x87=3 SSE=2 -> 1.5x (was 0.8x when called)
Every "loser" from the called benchmarks flips to a winner when inlined.
The entire performance gap was function call overhead (~5 cycles), not
instruction quality. Confirms in-place patching as the right strategy.
Also added RADV_TEX_ANISO env var exploration item to release notes and
updated math polyfill section with full benchmark breakdown.
In-place functions (vec3MulAssign, scaleByVec, etc.) were showing fake
speedups (121x, 10x) because repeated application on the same data
caused values to overflow to Inf/NaN. x87 FPU traps on denormals while
SSE handles them in hardware, making the comparison meaningless.
Now each iteration resets from a template copy. Real results show these
functions are ~1.0x (neutral), not 100x wins. The actual winners are
rotMat3x3/4x4 at 2.1x, and several functions where our scalar-through-
pointers approach is slower than the original x87 pipeline (dotProduct
0.3x, evaluatePolynomial 0.4x) — candidates for real SIMD optimization.
Extracts original x87 FPU bytes from WoW.exe via Ghidra, mmaps them
executable, and benchmarks against our SSE replacements. Covers all 17
UnitXP polyfill functions with correctness validation and cycle counts.
Maps a page at 0x7ff000 for the float 1.0 constant referenced by
rotMat3x3/rotMat4x4/planeNormal via absolute address 0x7ff9d8.
Build: zig build bench / zig build run-bench
MarcelineVQ