engine/rr: native Ray Reconstruction stages with capture/replay and shim integration

- engine/rr: d4r's own shaders for the denoiser frame (exposure, six encoders,
  five decoders, hkpn output stage) at NGX layouts, plus PTX->GLSL/HIP packing
  scripts, reference implementations and weight extraction
- runtime.h/runtime_rr.inc, game_rr.{h,cpp}: GameDenoiser wired into the engine
  build (d4r-rr replay binary) and the D3D12 shim's feature-13 path
- shim: answer GetFeatureRequirements from d4r's own state only (the old
  cross-binary CUDA handoff crashed OptiScaler's scan); drop the core's
  CUDA GetFeatureRequirements import
- shim/harness: exact guide capture/replay of a frame's RR inputs
- kernels/rr: expanded enc0/engine prototypes; kernels/tools: ptxsim rewrite
  plus rrsim and an engine test; vulkan: ptx2glsl FP8/cooperative-matrix
  support, kvk inout buffers and KVK_DISABLE_OPTIMIZATION
- bridge: report the surface array in cuSurfObjectCreate traces
- packaging: RR settings and the ICU launch overrides in D4R_README

engine/rr/dec1_pack.py

@@ -0,0 +1,60 @@
+#!/usr/bin/env python3
+"""Pack decoder 1's extracted weights (engine/rr/dec1_ref.py --extract) for engine/rr/dec1_m.comp.
+
+usage: dec1_pack.py WEIGHTS.npz OUT.bin OUT.h
+
+enc1_pack.py's layout (transposed products, columns in the consumer's k order) plus the expand (dec0_pack.py): 256
+columns, four sub-positions of 64 channels each permuted to slot order.
+"""
+import os
+import sys
+
+import numpy as np
+
+sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
+from enc1_ref import inter  # noqa: E402
+from enc1_pack import a_tiles, b_tiles, cubic_table  # noqa: E402
+
+I32, I64, I96 = inter(32), inter(64), inter(96)
+I256 = [64 * (j // 64) + I64[j % 64] for j in range(256)]
+
+
+def main():
+    src, out_bin, out_h = sys.argv[1:4]
+    w = dict(np.load(src))
+    e = {'we': ('A', w['we'][:, I256]), 'be': ('H', w['be'][I256])}
+    for h in range(2):
+        e[f'wk{h}'] = ('A', np.vstack([w[f'wk{h}a'], w[f'wk{h}b']])[:, I32])
+        e[f'wv{h}'] = ('B', np.vstack([w[f'wv{h}a'], w[f'wv{h}b']])[:, I32])
+        e[f'wo{h}'] = ('A', w[f'wo{h}'][:, I64])
+        e[f'bias{h}'] = ('H', w[f'bias{h}'][np.ix_(I64, I96)].T)
+    for b in range(8):
+        e[f'w1_{b}'] = ('A', w[f'w1_{b}'][:, I32])
+        e[f'b1_{b}'] = ('H', w[f'b1_{b}'][I32])
+        e[f'w2_{b}'] = ('A', w[f'w2_{b}'][:, I64])
+    e['wh'], e['bh'] = ('A', w['wh']), ('H', w['bh'])
+    e['gain0'] = ('H', w['gain0'])
+    for k in ('table7', 'gain14', 'table16'):
+        e[k] = ('H', w[k][I64])
+    e['cubic'] = ('U', cubic_table())
+    blob, defines = bytearray(), []
+    for name, (kind, a) in e.items():
+        while len(blob) % 256:
+            blob.append(0)
+        off = len(blob)
+        if kind == 'A':
+            blob += a_tiles(a).tobytes()
+        elif kind == 'B':
+            blob += b_tiles(a).tobytes()
+        elif kind == 'U':
+            blob += np.ascontiguousarray(a, np.uint16).tobytes()
+        else:
+            blob += np.ascontiguousarray(a, np.float16).tobytes()
+        defines.append(f'#define W_{name.upper()} {off}u   // {kind} {a.shape}')
+    open(out_bin, 'wb').write(bytes(blob))
+    open(out_h, 'w').write('// generated by engine/rr/dec1_pack.py\n' + '\n'.join(defines) + '\n')
+    print(f'{len(blob)} bytes, {len(e)} entries')
+
+
+if __name__ == '__main__':
+    main()