Build native Windows packages for both RDNA4 targets

Add explicit gfx1200/gfx1201 builds, runtime selection and per-target
code objects. Guard staging, packaging and installation against mixed
architectures; retain gfx1201 compatibility and strict K/M arithmetic.

Adapt realdody's target configuration and MSVC binary16/BOOL portability
fixes from ae530b0. Do not import its forced gfx12 layout on RDNA3.
Add exhaustive binary16 and C++/PowerShell target contract regressions.

Validation: 20 CTest gates on RX 9070 XT; four software-only gfx1200 gates;
MSVC portability compile checks; exact 4K K async and M control outputs;
isolated package install/restore and mixed-target rejection tests.
No physical gfx1200 validation is claimed.

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

tools/windows/ngx_windows_runtime.h

@@ -42,7 +42,7 @@ inline std::filesystem::path pixel_module_path() {
         reinterpret_cast<LPCWSTR>(&pixel_module_path), &module)) throw std::runtime_error("Locate GPU conversion module directory");
     wchar_t path[32768]{}; const DWORD length = GetModuleFileNameW(module, path, 32768);
     if (!length || length == 32768) throw std::runtime_error("GPU conversion module path is invalid");
-    return std::filesystem::path(path).parent_path() / L"pixel_convert_gfx1201.hsaco";
+    return std::filesystem::path(path).parent_path() / diag::wide(std::string("pixel_convert_") + diag::HipApi::target_arch() + ".hsaco");
 }
 
 struct Runtime {
@@ -94,7 +94,7 @@ struct Runtime {
         if (!d3d) throw std::runtime_error("Null D3D12 device");
         try {
             hipDeviceProp_t props{};
-            hip.select_gfx1201(-1, props);
+            hip.select_architecture(-1, props);
             hip.verbose = cuda.verbose = !std::getenv("D4R_QUIET_API");
             const auto luid = adapter_luid(d3d);
             if (std::memcmp(&luid, props.luid, sizeof(luid))) throw std::runtime_error("D3D12/HIP LUID mismatch");
@@ -155,7 +155,7 @@ struct Runtime {
             ngx_check(destroy(caps), "Destroy capability parameters");
             if (available != 1 || initResult != 1 || needsDriver != 0)
                 throw std::runtime_error("CUDA DLSS is unavailable after capability initialization");
-            std::printf("D4R_RUNTIME platform=Windows architecture=gfx1201 cpu_frame_copies=0 frame_age=0\n");
+            std::printf("D4R_RUNTIME platform=Windows architecture=%s cpu_frame_copies=0 frame_age=0\n", d4r::diag::HipApi::target_arch());
         } catch (...) { cleanup(); throw; }
     }
     Runtime(const Runtime&) = delete;