Enable experimental native Windows RDNA3 and RDNA4 targets

Share explicit target metadata across build/runtime/package guards, preserve native gfx11 WMMA with a Windows LDS lane exchange, select HIP devices by D3D12 LUID, and reject wrong-target/vkd3d installations before changing game files. Review all issue #10 logs and document compile-only coverage plus RX9070XT regressions.

Co-authored-by: realdody <[email protected]>

tools/windows/k_layer_validate.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-"""Compare RDNA4 K enc1/enc2 launches with the existing numpy reference."""
+"""Compare native K enc1/enc2 launches with the existing numpy reference."""
 import argparse
 import math
 import pathlib
@@ -73,7 +73,7 @@ def main():
     # after each K stage has been compared on captured DLSS weights/activations.
     if full_abs > 0.001 or full_psnr < 60.0 or merged_abs > 0.001 or merged_psnr < 60.0:
         raise RuntimeError(f"K {args.kernel_name} numerical mismatch against pwin_model.py")
-    print(f"PASS K_REFERENCE reference_layout=gfx12 kernel={args.kernel_name} "
+    print(f"PASS K_REFERENCE reference=logical kernel={args.kernel_name} "
           "nonzero_weights=1 transformer_executed=1 nan_inf=0")