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

Improve GPU compatibility, RDNA2 kernels and startup diagnostics

Browse Source 
- Match render/compute adapters and gate RR models by GPU capabilities
- Add RDNA2 native texture kernels and fix FP16 rounding
- Harden model builds, cache validation and packaging
- Add startup tracing, timeouts, documentation and regression tests
This commit is contained in:
ayo committed 2026-10-19 11:36:40 -04:00
1 parent ca93d0fbf7
commit 2558fcbd39
32 files changed
+1131 -81
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

packaging/build_engine_models.sh
+39 -12
View File
@@ -61,8 +61,27 @@ export PATH="$KIT/bin:$PATH" # the bundled glslangValidator
glslangValidator --version > /dev/null 2>&1 || fail "glslangValidator ($KIT/bin) does not run on this system"
sha() { sha256sum -- "$1" | cut -d' ' -f1; }
WORK="$(mktemp -d "${TMPDIR:-/tmp}/d4r-models.XXXXXX")"
trap 'rm -rf -- "$WORK"' EXIT
LOG_ROOT="${D4R_MODEL_LOG_DIR:-${XDG_CACHE_HOME:-$HOME/.cache}/d4r/model-builds}"
mkdir -p -- "$LOG_ROOT"
BUILD_LOGS="$(mktemp -d "$LOG_ROOT/build.XXXXXX")"
WORK="$BUILD_LOGS/work"; mkdir -p "$WORK"
MODEL_TOOLS="$KIT/model_tools.py"
[[ -f "$MODEL_TOOLS" ]] || fail "missing $MODEL_TOOLS; update the model builder tools"
cleanup() {
local status=$?
if (( status == 0 )); then
while IFS= read -r -d '' log; do
relative="${log#"$WORK/"}"
mkdir -p -- "$BUILD_LOGS/$(dirname -- "$relative")"
cp -- "$log" "$BUILD_LOGS/$relative"
done < <(find "$WORK" -name '*.log' -type f -print0)
rm -rf -- "$WORK"
else
printf 'build-engine-models: failed build and captures preserved at %s\n' "$WORK" >&2
fi
printf 'Model build diagnostics: %s\n' "$BUILD_LOGS"
}
trap cleanup EXIT
trap 'exit 130' INT
trap 'exit 143' TERM
@@ -72,6 +91,7 @@ place() { # place NAME DIR FILE...
shift 2
mkdir -p "$RUNTIME/engine" "$WORK/place/$name"
for f in "$@"; do cp -- "$src/$f" "$WORK/place/$name/"; done
python3 "$MODEL_TOOLS" manifest "$WORK/place/$name"
rm -rf -- "$dst.new"; mv -- "$WORK/place/$name" "$dst.new"
rm -rf -- "$dst.old"; [[ ! -e "$dst" ]] || mv -- "$dst" "$dst.old"
mv -- "$dst.new" "$dst"; rm -rf -- "$dst.old"
@@ -83,18 +103,24 @@ model_files() { # rr.txt and the files it names, for model directory $1
}
run() { # run LOG COMMAND...: the command's output in WORK/LOG, shown when it fails
local log="$WORK/$1"; shift
"$@" > "$log" 2>&1 || { tail -n 20 "$log" >&2; fail "failed: $(basename -- "$2") (log above)"; }
python3 "$MODEL_TOOLS" run --log "$log" --timeout "${D4R_MODEL_TIMEOUT:-900}" -- "$@" ||
fail "failed: $1 (see $log)"
}
if (( DO_RR )); then
DLL="$RUNTIME/nvngx_dlssd.dll"
[[ -f "$DLL" && "$(sha "$DLL")" == "$DLSSD_SHA256" ]] || fail "Ray Reconstruction models need nvngx_dlssd.dll 310.9.1 in $RUNTIME (run install.sh)"
echo 'Building the Ray Reconstruction models (presets D, E and F) from nvngx_dlssd.dll...'
# Build both portable arithmetic variants; runtime selects by device capabilities. Do not let the build
# host (or an inherited developer switch) silently determine what another game/GPU receives from the cache.
for p in D E; do
l=$(tr DE de <<< "$p")
bash "$KIT/engine/rr/build_native_model.sh" --dll "$DLL" "$p" "$WORK/rr-$l" > "$WORK/rr-$l.log" 2>&1 ||
{ tail -n 20 "$WORK/rr-$l.log" >&2; fail "preset $p model failed"; }
place "rr-$l" "$WORK/rr-$l" $(model_files "$WORK/rr-$l") exposure_rr0.spv exposure_rr1.spv
for arithmetic in fp8 gfx11; do
l=$(tr DE de <<< "$p"); name="rr-$l"; gfx11=0
if [[ "$arithmetic" == gfx11 ]]; then name+="-gfx11"; gfx11=1; fi
run "$name.log" env D4R_RR_GFX11="$gfx11" bash "$KIT/engine/rr/build_native_model.sh" \
--dll "$DLL" "$p" "$WORK/$name"
place "$name" "$WORK/$name" $(model_files "$WORK/$name") exposure_rr0.spv exposure_rr1.spv
done
done
run ptx-f.log python3 "$KIT/kernels/tools/extract_dlss_ptx.py" "$DLL" "$WORK/ptx-f"
run rr-f.log python3 "$KIT/engine/compile_rr2.py" --dll "$DLL" "$WORK/rr-f" --ptx-dir "$WORK/ptx-f"
@@ -125,16 +151,17 @@ if (( DO_SR )); then
local w="$WORK/$1"
mkdir -p "$w/replay"
printf ' rendering one frame with model %s through d4r (GE-Proton %s)...\n' "$1" "$(basename "$PROTON")"
(cd "$APP" && env STEAM_COMPAT_CLIENT_INSTALL_PATH="$STEAM_ROOT" STEAM_COMPAT_DATA_PATH="$WORK/prefix" \
(cd "$APP" && python3 "$MODEL_TOOLS" run --log "$w/run.log" --timeout "${D4R_MODEL_TIMEOUT:-900}" -- \
env STEAM_COMPAT_CLIENT_INSTALL_PATH="$STEAM_ROOT" STEAM_COMPAT_DATA_PATH="$WORK/prefix" \
PROTON_FORCE_NVAPI=1 DXVK_NVAPI_GPU_ARCH=AD100 WINEDLLOVERRIDES='d3d12=n,b;d3d12core=n,b;d4r12core=n,b' \
D4R_ENGINE=0 D4R_DLSS_PRESET="$2" D4R_HARNESS_CREATE_FLAGS=0x4B D4R_SHIM_LOG="$(winpath "$w/shim.log")" \
D4R_CUDA_TRACE="$(winpath "$w/cuda.log")" D4R_CUDA_VERBOSE=1 \
D4R_CUDA_REPLAY_DUMP_DIR="$w/replay" D4R_CUDA_REPLAY_DUMP_LIMIT=60 \
"$PROTON/proton" run "$APP/d3d12_dlss_harness.exe" "$(winpath "$RUNTIME/nvngx.dll")" "$(winpath "$w/out.raw")" \
1 640 360 1280 720) > "$w/run.log" 2>&1 || true
if ! ls "$w/replay" | grep -q "$3"; then
tail -n 15 "$w/run.log" >&2
1 640 360 1280 720) || fail "model $1: capture process failed; diagnostics in $w"
if ! python3 "$MODEL_TOOLS" capture "$w" "$1"; then
[[ ! -f "$w/shim.log" ]] || tail -n 15 "$w/shim.log" >&2
fail "model $1: the test frame did not run through DLSS (logs above)"
fail "model $1: incomplete or invalid test frame (diagnostics in $w)"
fi
}
echo 'Building the Super Resolution models (K, M and L) from what NGX uploads...'