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.

packaging/d4r.ini

@@ -3,12 +3,19 @@
 ; that config/d4r.ini.default in the source repository lists for it, e.g. in the game's launch options.
 
 [DLSS]
-; Which DLSS network runs:
-;   K     DLSS 4 transformer (default)
-;   E     DLSS 3 CNN: a little faster, softer image
-;   M     DLSS 4.5 transformer: best image, much slower on RDNA3
-;   game  whatever the game (or OptiScaler's preset override) asks for
-; Frame rates measured on an RX 7700 XT at 2560x1440, Quality mode: see D4R_README.txt.
+; DLSS model recommendations:
+;
+; Model | DLSS  | Recommended modes               | Notes
+; ------+-------+---------------------------------+----------------------------------
+; K     | 4     | DLAA / Quality / Balanced       | Default; faster alternative to M/L
+; M     | 4.5   | Performance                     | More demanding on RDNA3
+; L     | 4.5   | Ultra Performance               | Especially 4K; experimental
+; E     | 3 CNN | Quality / Balanced / Performance | Legacy faster fallback
+; F     | 3 CNN | DLAA / Ultra Performance        | Deprecated; prefer K or L
+;
+; Select the upscaling mode separately in game/OptiScaler. These are recommendations;
+; other modes are allowed. L requires the L texture build.
+; game = use the game/OptiScaler choice. Benchmarks: D4R_README.txt.
 Model = K
 ; NVIDIA's library marks the image "DLSS SDK - DO NOT DISTRIBUTE" in this setup; d4r turns that off.
 ; true shows it.
@@ -25,6 +32,9 @@ FrameAge = 0
 ; intermediate FP8/f16 rounding and denormal handling, and keeps NGX's synchronization calls.
 ; Slower but aims to match RTX DLSS.
 PreferAccuracy = false
+; false reduces L/M motion trails by using original enc1/enc2 layers; other native kernels stay on.
+; Best paired with PreferAccuracy = true; costs some GPU time. Restart after changing this.
+NativeSwinEncoders = true
 ; Hand-written RDNA3 and RDNA4 kernels for the DLSS 4 and 4.5 networks (d4r\kernels). Each one is used
 ; only when your DLSS library's code for that kernel matches the code it was written for; otherwise
 ; that kernel is compiled from NVIDIA's code instead, which is slower but still correct.
@@ -35,10 +45,13 @@ NativeKernels = on
 NativeFp8 = on
 
 [Interop]
-; These keep DLSS's inputs and output in video memory and move the waits between the game and DLSS
-; onto the GPU. Leave them on unless you are chasing a problem.
+; Experimental thin-feature tracking: 0 = off; 1/2 = opaque-surface dilation radius.
+; Both enabled values fill sky gaps from the nearest foreground within 8 render pixels.
+; Requires render- or display-resolution, unjittered motion vectors and same-frame linear VRAM inputs. Restart to change.
+; Unsupported features keep original vectors; larger radii may affect disocclusion edges.
+MotionVectorDilation = 0
+; Keep inputs and output in video memory. Input and output readiness waits use CPU sleeps.
 VramInterop = true
-GpuWait = true
 LinearInputs = true
 ElideNgxSync = true
 ; Lets DLSS's last kernel write straight into the game's output buffer (DLSS 4 / K only). It takes
@@ -59,5 +72,5 @@ Profile = false
 
 [Env]
 ; Extra environment variables for d4r, NAME = value.
-; Use a blocking CUDA event while waiting for DLSS output.
-; D4R_SHIM_BLOCKING_SYNC = 1
+; Sleeping event queries are the default; 0 restores context waits for an A/B comparison.
+; D4R_SHIM_BLOCKING_SYNC = 0