feat: add d4r inference engines and Windows parity tooling

Add native K/M/RR inference engines, HIP kernels, replay and validation
harnesses, and Windows DLSS setup and runtime support. Include GPU
profiling tools, build and packaging scripts, platform integration
patches, and implementation documentation.

scripts/run_replay_dlss_surface_store.sh

@@ -0,0 +1,14 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
+ZLUDA_ROOT="${ZLUDA_ROOT:-}"
+ROCM_ROOT="${ROCM_ROOT:-}"
+if [[ -z "$ZLUDA_ROOT" || -z "$ROCM_ROOT" || ! -f "$ZLUDA_ROOT/libcuda.so" || ! -f "$ROCM_ROOT/lib/libamdhip64.so" ]]; then
+  printf 'Set ZLUDA_ROOT and ROCM_ROOT to the ZLUDA and HIP runtimes\n' >&2
+  exit 2
+fi
+
+"$ROOT/scripts/build_replay_dlss_surface_store.sh"
+LD_LIBRARY_PATH="$ZLUDA_ROOT:$ROCM_ROOT/lib:$ROCM_ROOT/lib/llvm/lib:${LD_LIBRARY_PATH:-}" \
+  "$ROOT/build/replay_dlss_surface_store"