Add experimental preset L and fix DLSS resource lifetimes and waits

- Build L texture variants and complete older release kernel bundles.
- Add selective Swin encoder fallback to reduce L/M motion trails.
- Add opt-in GPU motion-vector dilation for thin geometry and sky gaps.
- Replace GPU input waits with cancellable readiness polling and use
  sleeping event queries for completion.
- Retain recorded resources through command allocator completion, defer
  shutdown until cleanup, and preserve unfinished output synchronization.
- Extend lifecycle harness checks and add event, model and motion tests.
- Update configuration defaults, build scripts and release documentation.

tools/d4r_native_selection.h

@@ -5,6 +5,18 @@
 #include <stdlib.h>
 #include <string.h>
 
+static int d4r_native_swin_encoders_enabled(void)
+{
+    const char* value = getenv("D4R_NATIVE_SWIN_ENCODERS");
+    return value == NULL || strcmp(value, "0") != 0;
+}
+
+static int d4r_native_kernel_allowed(const char* name)
+{
+    return d4r_native_swin_encoders_enabled() ||
+        (strcmp(name, "rrlite_enc1_4x4") != 0 && strcmp(name, "rrlite_enc2_4x4") != 0);
+}
+
 static int d4r_apply_accuracy_policy(void)
 {
     const char* prefer = getenv("D4R_PREFER_ACCURACY");