engine/rr: native preset F (DLSS 4.5 Ray Reconstruction) and the reference's fused roundings

- engine/compile_rr2.py, runtime_rr2.inc, engine/rr/rr2_m.comp, exposure_f.comp,
  gen_rr2_enc0.py, rr2_pack.py, rr2_ref.py: the rr2_* model (nvngx_dlssd.dll 310.9's
  third network) as d4r's own shaders - exposure, enc0 gather/block split, enc1-5 and
  dec4-0 through one matrix shader, translated output passes; weights packed from the
  DLL, argument blocks from the capture
- ptx2rr: match the driver's fused roundings - opaque-zero OR around cvt.rn.f16.f32
  against v_fma_mix, half-away-from-zero formatted stores, UNORM 10:10:10:2 as RGBA32F
  of q/1023, OCML tanhF with the AMDGPU exp lowering, binary16 fma and fetch roundings;
  --probe for register bisection against ZLUDA
- dec0_m/swin_m/enc0_*: RR_MIX build option (D4R_RR_MIX=1), one v_fma_mix rounding per
  32-deep step, ~5% faster, not bit-exact; default build stays exact
- runtime_rr.inc: RModel/REngine dispatch to the D4RR0002 model; replay_rr: RGBA32F and
  A2B10G10R1010 texel sizes, roughnessPacked bit, larger debug staging
- shim: engine\rr-f model slot, 310.9 version probe so preset F is only claimed when the
  CUDA path has it; d4r.ini / d4r_config.py Model = F; run_rr_engine_compare.sh D4R_RR_DLL
- kernels/rr/swin_native.h + rr_swin_native_test.cpp: HIP port of encoder 1 for the
  FP8-product and rounding cost measurements
- engine/rr/README: preset F's block, options, capture-by-capture results, timings and
  the open camera-matrix difference

engine/rr/rr_inputs.py

@@ -25,6 +25,45 @@ OPTIONAL_OUTPUT = {'particles': 416}                             # output stage
 INPUTS = {'color': 160, 'motion': 168, 'normals': 184, 'roughness': 192, 'diffuse': 232, 'specular': 240, 'depth': 512}
 
 
+# preset F (rr2_enc0_kernel): its textures and argument offsets
+INPUTS_F = {'color': 144, 'motion': 192, 'normals': 224, 'roughness': 240, 'diffuse': 160, 'specular': 176, 'depth': 552}
+
+
+def preset_f(cap, o):
+    lines = []
+    for f in range(1, o.frames + 1):
+        enc0 = cap.find('rr2_enc0', f)
+        a = enc0.args
+        u32 = lambda off: struct.unpack_from('<I', a, off)[0]
+        f32 = lambda off: struct.unpack_from('<f', a, off)[0]
+        mat = lambda off: np.array(struct.unpack_from('<16f', a, off), np.float64).reshape(4, 4)
+        down = cap.find('rr2_downsample', 1).args   # either variant: the sizes are at the same offsets
+        rw, rh, iw, ih = u32(128), u32(132), u32(488), u32(492)
+        ow, oh = struct.unpack_from('<2I', down, 8)
+        if f == 1:
+            lines.append(f'size {rw} {rh} {ow} {oh}')
+        images = {i.offset: i for i in enc0.images}
+        for name, off in INPUTS_F.items():
+            (o.out / f'{f}-{name}.bin').write_bytes(images[off].path.read_bytes())
+        # the optional inputs: encoder 0's textures 272 / 336 / 288, the particle downsample kernel's texture 208
+        for name, off in (('hitdistance', 272), ('disocclusion', 336), ('sss', 288)):
+            if off in images:
+                (o.out / f'{f}-{name}.bin').write_bytes(images[off].path.read_bytes())
+        part = [l for l in cap.launches if l.kernel == 'rr2_downsample_kernel_static_hdr']
+        if part:
+            n = len(part) // len(cap.find('rr2_enc0'))
+            (o.out / f'{f}-particles.bin').write_bytes(part[(f - 1) * n].image(208).path.read_bytes())
+        clip = mat(708)
+        view = mat(644) @ np.linalg.inv(clip)
+        view[3, :3] = 0.0
+        reset = 1 if f == 1 or not o.no_reset else 0
+        values = ' '.join(f'{v:.9g}' for v in list(view.flatten()) + list(clip.flatten()))
+        flags = a[568] | (a[1028] << 1) | (a[466] << 2)   # inverted depth, hardware depth, packed roughness
+        lines.append(f'frame {f} {f32(400):.9g} {f32(404):.9g} {f32(448) * rw / iw:.9g} {f32(452) * rh / ih:.9g} 1 {reset} {flags} {values}')
+    (o.out / 'frames.txt').write_text('\n'.join(lines) + '\n')
+    print(f'{o.frames} preset F frames of {o.capture} in {o.out}')
+
+
 def main():
     ap = argparse.ArgumentParser()
     ap.add_argument('capture')
@@ -35,6 +74,8 @@ def main():
     cap = Capture(o.capture)
     o.out.mkdir(parents=True, exist_ok=True)
     lines = []
+    if any(l.kernel == 'rr2_enc0_kernel' for l in cap.launches):
+        return preset_f(cap, o)
     for f in range(1, o.frames + 1):
         enc0 = cap.find('swin_enc0', f)
         a = enc0.args