From fe5999dfbff619ae5422cfad28430fd1588b75be Mon Sep 17 00:00:00 2001
From: itchyfeetleech <169226071+itchyfeetleech@users.noreply.github.com>
Date: Mon, 19 Oct 2026 21:03:34 +1300
Subject: [PATCH] engine: README: the opt-in M_RESIDUAL_F32, D4R_RR2_UNGUARDED
 and D4R_RR2_POOLED builds measured

Signed-off-by: itchyfeetleech <169226071+itchyfeetleech@users.noreply.github.com>
---
 engine/README.md      |  9 +++++++++
 engine/compile_rr2.py |  5 +++--
 engine/rr/README.md   | 13 +++++++++++++
 3 files changed, 25 insertions(+), 2 deletions(-)

diff --git a/engine/README.md b/engine/README.md
index adf16b1..6ce22c0 100644
--- a/engine/README.md
+++ b/engine/README.md
@@ -1110,6 +1110,15 @@ reconstruction tile tiers and the stress inputs).
 The network layers are separated by an execution-only barrier (`emptyStage`). A memory barrier there gives the same
 output and costs about 60 us (M 1520 -> 1592), so it stays.
 
+### `M_RESIDUAL_F32` (opt-in, 2026-10-19)
+
+`M_RESIDUAL_F32=1 python3 engine/compile_m.py ...` keeps the residual stream in f32 across the MLP's 32-channel chunks
+and rounds it to binary16 once after them, instead of after every chunk. It needs the relaxed build (not
+`M_EXACT=1`) and is off by default. 1280x720 -> 1440p: M 1521 -> 1410 us, L 2195 -> 2077. Against the default build,
+final RGB, peak 1: 43 - 46 dB (L 45 - 49) on smooth frames, 17 - 18 dB on noise. The exact build is as far from the
+default, so this moves no further from NVIDIA's arithmetic than `M_RELAXED` already does. Not checked against an
+NVIDIA card.
+
 ## Preset L (runtime and shim path exist; experimental)
 
 Preset L (render preset 12, NVIDIA's model for Ultra Performance) is M's pipeline with its own input, expansion and
diff --git a/engine/compile_rr2.py b/engine/compile_rr2.py
index 7fcfef7..0d8fed8 100644
--- a/engine/compile_rr2.py
+++ b/engine/compile_rr2.py
@@ -80,8 +80,9 @@ GROUP = int(os.environ.get('D4R_RR2_GROUP', '1'))
 # D4R_RR2_SPLIT=1 / 0 forces the gather pass / the single shader.
 SPLIT = os.environ.get('D4R_RR2_SPLIT', '0' if RELAXED >= 3 and 'enc0' in ONE_WAVE else '1') != '0'
 # The pooled histories as RGBA32F holding q / 1023, as ZLUDA backs them (16 bytes a pixel). D4R_RR2_POOLED=rgb10_a2
-# makes them real UNORM 10:10:10:2 images (0.1 ms faster at 4K), but the hardware's bilinear filter then rounds
-# differently: identical at 3x and 2x scaling, 44 - 51 dB on temporal frames at 1.5x (capFQ, 2026-10-13)
+# makes them real UNORM 10:10:10:2 images (0.1 ms faster at 4K, 70 MB less), but the hardware's bilinear filter then
+# rounds differently: identical at 3x and 2x scaling, 44 - 51 dB on temporal frames at 1.5x (capFQ, 2026-10-13); on
+# random-motion noise also at 2x (29 dB on the history frames, engine/rr/README.md)
 POOLED = os.environ.get('D4R_RR2_POOLED', 'rgba32f')
 SURFACES = {'dec0_1': {176: 'rgba8_snorm', 184: 'rgba8', 192: 'rgba8'}, 'post': {120: POOLED}, 'pooled': {8: POOLED}}
 # D4R_RR2_UNGUARDED=1 (opt-in, D4R_RR_RELAXED=3 only): the translated code (encoder 0's and decoder 0's per-pixel parts,
diff --git a/engine/rr/README.md b/engine/rr/README.md
index e0ac464..3e1f6a9 100644
--- a/engine/rr/README.md
+++ b/engine/rr/README.md
@@ -629,3 +629,16 @@ byte-identical to the previous model on the replay and stress inputs, at levels
   total with an atomic add and the last block finishing. It needs `shaderBufferInt64Atomics`, which vkd3d-proton
   enables; the shim reads the device's features through `GetDeviceFeatures`. Without it, or with a model that has no
   `exposure_f2.spv`, the two passes run (`D4R_RR_TEST_NO_INT64_ATOMICS=1` forces them). Exposure 25.2 -> 14.9 us.
+
+### Opt-in builds for preset F (2026-10-19)
+
+Against the default build, presented image, RGB, peak 1, 1280x720 -> 1440p. For scale, the exact build
+(`D4R_RR_RELAXED=0`) is 43.0 - 44.4 dB from the default.
+
+- `D4R_RR2_UNGUARDED=1` (level 3 only): the translated code (encoder 0's and decoder 0's per-pixel parts, the output
+  passes) without its exactness guards: no `precise`, no opaque zero on binary16 stores, no `spv_exact_convert.py`.
+  56.0 dB on the reset frame, then 43.0 - 45.6 dB, as far from the exact build as the default is. Frame 3.526 -> 3.501
+  ms.
+- `D4R_RR2_POOLED=rgb10_a2` (since 2026-10-13): the pooled histories as UNORM 10:10:10:2 images, 31 MB less at 1440p.
+  Identical at 1280x720 -> 1440p and on reset frames; 43.7 - 47.2 dB on the history frames at 1114x626 -> 1080p and
+  28.8 dB with random motion. Frame 3.526 -> 3.484 ms, 3.456 with `D4R_RR2_UNGUARDED=1` as well.