wouter/d4r
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

engine/rr: build the Ray Reconstruction models from nvngx_dlssd.dll alone, without a capture

Browse Source 
Models built from nvngx_dlssd.dll 310.9.1 are byte-identical to the capture-built ones (every file, plus
d4r-rr's outputs on capF, capF4K, capF900, capFXparticles and capDT). 310.9.1 contains 310.7's D/E kernels
and weights.
This commit is contained in:
woutermans committed 2026-10-14 20:09:08 +02:00
1 parent e3606cedf9
commit 5f520a186d
7 files changed
+508 -45
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

engine/rr/build_native_model.sh
+32 -8
View File
@@ -5,6 +5,11 @@ set -euo pipefail
# for the preset the capture was taken with (D or E).
#
# usage: build_native_model.sh CAPTURE_DIR OUT_DIR [NVNGX_DLSSD_DLL]
# build_native_model.sh --dll NVNGX_DLSSD_DLL D|E OUT_DIR
#
# With --dll no capture is needed: everything comes from the DLL (its PTX: kernels/tools/extract_dlss_ptx.py; the
# argument-block templates: engine/rr/rr_templates.py; the weights: dll_weights.py, model 0 = D, model 1 = E in 310.7's
# file order) and step 3's checks against a captured frame are skipped. This is what install.sh runs.
#
# CAPTURE_DIR is a bridge capture of a few denoiser frames (engine/rr/rr_capture.py); the DLL is the one it was taken
# with (default: CAPTURE_DIR/run/app/nvngx_dlssd.dll, then $D4R_RR_DLL). The steps:
@@ -23,19 +28,38 @@ set -euo pipefail
#
# GPU jobs run one at a time, each in a memory-capped scope (a translated stage's pipeline compile can take tens of GB).
ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)"
CAP="$(realpath "${1:?usage: build_native_model.sh CAPTURE_DIR OUT_DIR}")"
OUT="$(realpath -m "${2:?usage: build_native_model.sh CAPTURE_DIR OUT_DIR}")"
USAGE="usage: build_native_model.sh CAPTURE_DIR OUT_DIR [NVNGX_DLSSD_DLL] | --dll NVNGX_DLSSD_DLL D|E OUT_DIR"
CAP=""
if [[ "${1:-}" == --dll ]]; then
DLL="$(realpath "${2:?$USAGE}")"; WANT="${3:?$USAGE}"; OUT="$(realpath -m "${4:?$USAGE}")"
[[ "$WANT" == D || "$WANT" == E ]] || { echo "$USAGE" >&2; exit 2; }
else
CAP="$(realpath "${1:?$USAGE}")"
OUT="$(realpath -m "${2:?$USAGE}")"
DLL="${3:-${D4R_RR_DLL:-$CAP/run/app/nvngx_dlssd.dll}}"
fi
RR="$ROOT/engine/rr"
WORK="$OUT/native-work"
DLL="${3:-${D4R_RR_DLL:-$CAP/run/app/nvngx_dlssd.dll}}"
[[ -f "$DLL" ]] || { echo "no nvngx_dlssd.dll at $DLL: pass the DLL the capture was taken with" >&2; exit 1; }
FRAME="${D4R_RR_MODEL_FRAME:-2}"
CAPPED=(systemd-run --user --scope -q -p MemoryMax=24G -p MemorySwapMax=0)
# each GPU / compiler job in a memory-capped scope where systemd provides one (D4R_NO_SCOPE=1: none)
CAPPED=()
if [[ "${D4R_NO_SCOPE:-0}" != 1 ]] && command -v systemd-run > /dev/null && systemd-run --user --scope -q true 2> /dev/null; then
CAPPED=(systemd-run --user --scope -q -p MemoryMax=24G -p MemorySwapMax=0)
fi
mkdir -p "$OUT" "$WORK"
cd "$ROOT"
python3 engine/compile_rr.py "$CAP" "$OUT" > "$WORK/compile_rr.log" 2>&1 || { tail -5 "$WORK/compile_rr.log"; exit 1; }
python3 "$RR/dll_weights.py" "$DLL" "$WORK/dll" --capture "$CAP" ${D4R_RR_ANY_KERNELS:+--any-kernels}
if [[ -n "$CAP" ]]; then
python3 engine/compile_rr.py "$CAP" "$OUT" > "$WORK/compile_rr.log" 2>&1 || { tail -5 "$WORK/compile_rr.log"; exit 1; }
python3 "$RR/dll_weights.py" "$DLL" "$WORK/dll" --capture "$CAP" ${D4R_RR_ANY_KERNELS:+--any-kernels}
else
python3 kernels/tools/extract_dlss_ptx.py "$DLL" "$WORK/ptx" > /dev/null
python3 engine/compile_rr.py --dll "$DLL" --preset "$WANT" "$OUT" --ptx-dir "$WORK/ptx" --network-bindings-only \
> "$WORK/compile_rr.log" 2>&1 || { tail -5 "$WORK/compile_rr.log"; exit 1; }
python3 "$RR/dll_weights.py" "$DLL" "$WORK/dll" --model "$([[ "$WANT" == D ]] && echo 0 || echo 1)" \
${D4R_RR_ANY_KERNELS:+--any-kernels} > /dev/null
fi
PRESET="$(awk '$1 == "preset" { print $2 }' "$OUT/rr.txt")"
# RR_EXACT_CONVERT: the compiled module's float conversions are decorated NoContraction (spv_exact_convert.py), which
# keeps the driver from folding a binary16 rounding away without the opaque OR the shaders otherwise need
@@ -68,7 +92,7 @@ for s in enc1 enc2 enc3 enc4 enc5 dec4 dec3 dec2 dec1; do
b=1,1; case $s in enc1|enc2|dec1|dec2) b=5,5 ;; esac
d="$WORK/$s"; mkdir -p "$d"
cp "$WORK/dll/$s.npz" "$d/weights.npz"
python3 "$RR/swin_ref.py" "$CAP" "$s" "$FRAME" "$d/weights.npz" --blocks "$b" 0,0 | tail -2 | sed "s/^/$s: /"
[[ -z "$CAP" ]] || python3 "$RR/swin_ref.py" "$CAP" "$s" "$FRAME" "$d/weights.npz" --blocks "$b" 0,0 | tail -2 | sed "s/^/$s: /"
python3 "$RR/swin_pack.py" "$s" "$d/weights.npz" "$OUT/weights-${s}m.bin" "$d/swin_stage.h" > /dev/null
glsl "$OUT/${s}_m.spv" "$RR/swin_m.comp" "$d" "$RR"
native "$s" "weights-${s}m.bin"
@@ -77,7 +101,7 @@ done
# decoder 0
d="$WORK/dec0"; mkdir -p "$d"
cp "$WORK/dll/dec0.npz" "$d/weights.npz"
python3 "$RR/dec0_ref.py" "$CAP" "$FRAME" "$d/weights.npz" --blocks 5,5 0,0 | tail -2 | sed 's/^/dec0: /'
[[ -z "$CAP" ]] || python3 "$RR/dec0_ref.py" "$CAP" "$FRAME" "$d/weights.npz" --blocks 5,5 0,0 | tail -2 | sed 's/^/dec0: /'
python3 "$RR/dec0_pack.py" "$d/weights.npz" "$OUT/weights-dec0m.bin" "$d/dec0_m_w.h" > /dev/null
glsl "$OUT/dec0_m.spv" "$RR/dec0_m.comp" "$d" "$RR"
native dec0 weights-dec0m.bin