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

scripts/package_release.sh
+20 -4
View File
@@ -16,7 +16,8 @@
# D4R_ROCM_RUNTIME ROCm runtime bundled as d4r/rocm (scripts/fetch_rocm_runtime.sh)
# default ~/.cache/d4r-rocm-runtime
# D4R_MAX_GLIBC highest GLIBC ABI the Linux libraries may require default 2.41
# D4R_GPU_ARCHS GPU targets to build kernels for default gfx1030-gfx1036 (K only), gfx1100-gfx1103, gfx1200, gfx1201
# D4R_GPU_ARCHS GPU targets to build kernels for default gfx1030-gfx1036 (K and its hiluma kernels only),
# gfx1100-gfx1103, gfx1200, gfx1201
# (RDNA4 targets also get a <target>-fp8 folder: the kernels for d4r.ini NativeFp8 = on)
# D4R_OPTISCALER_LICENSE OptiScaler's LICENSE (GPL-3.0) text; default: system SPDX or common-licenses copy
# D4R_VKD3D_SRC vkd3d-proton source checkout, for its license files default ~/.cache/d4r-vkd3d-proton
@@ -216,15 +217,30 @@ ensure_rr_textures() {
fi
}
build_target() {
local folder="$1" arch fp8 tex_dir accurate accurate_tex f
local folder="$1" arch fp8 tex_dir tmp_tex accurate accurate_tex f
arch="${folder%-fp8}"
fp8=0
[[ "$folder" == *-fp8 ]] && fp8=1
# RDNA2 (gfx103x): only DLSS 4's layers (preset K) have native kernels there, built with software matrix
# products (kernels/common/wmma_layout.h); M, L, the texture tails and Ray Reconstruction stay translated by ZLUDA
# RDNA2 (gfx103x): DLSS 4's layers (preset K), built with software matrix products
# (kernels/common/wmma_layout.h), and K's hiluma output/input kernels translated from the PTX
# (kernels/native, no WMMA; wave32, byte-identical to ZLUDA's compile). M, L, the texture tails and Ray
# Reconstruction call WMMA and stay translated by ZLUDA. The accuracy set keeps ZLUDA's compile of hiluma.
if [[ "$arch" == gfx103* ]]; then
D4R_PREFER_ACCURACY=0 D4R_ROCM_DIR="$ROCM" D4R_GPU_ARCH="$arch" "$ROOT/kernels/build.sh" k "$STAGE/d4r/kernels/$folder" >/dev/null
D4R_PREFER_ACCURACY=1 D4R_ROCM_DIR="$ROCM" D4R_GPU_ARCH="$arch" "$ROOT/kernels/build.sh" k "$STAGE/d4r/kernels/accuracy/$folder" >/dev/null
if [[ "$VARIANT" != clean ]]; then
tex_dir="$D4R_BUNDLE_TEX/$folder" tmp_tex=""
if [[ ! -d "$tex_dir" ]]; then
tex_dir="$(mktemp -d)" tmp_tex="$tex_dir"
D4R_PREFER_ACCURACY=0 D4R_ROCM_DIR="$ROCM" D4R_GPU_ARCH="$arch" D4R_DLSS_DLL="$D4R_BUNDLE_DLSS" \
"$ROOT/kernels/build.sh" tex "$tex_dir" >/dev/null
fi
# only the kernels validated for RDNA2, whatever else an older bundle folder holds
for f in "$tex_dir"/hiluma_engine_output_*_hdr_max_v2_rel.hsaco "$tex_dir"/hiluma_engine_input_*_v2_rel.hsaco; do
[[ -f "$f" ]] && cp "$f" "$STAGE/d4r/kernels/$folder/"
done
[[ -z "$tmp_tex" ]] || rm -rf "$tmp_tex"
fi
rm -f "$STAGE/d4r/kernels/$folder"/*.resolution.txt "$STAGE/d4r/kernels/accuracy/$folder"/*.resolution.txt
python3 "$ROOT/kernels/tools/kernel_manifest.py" "$STAGE/d4r/kernels/$folder" "${DLLS[@]}" "${RR_DLLS[@]}"
python3 "$ROOT/kernels/tools/kernel_manifest.py" "$STAGE/d4r/kernels/accuracy/$folder" "${DLLS[@]}" "${RR_DLLS[@]}"