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

kernels/build.sh
+25 -8
View File
@@ -5,8 +5,10 @@
# usage: kernels/build.sh [all|k|l|m|tex|rr|rrswin] [OUT_DIR] (default: all, kernels/out/native)
#
# D4R_ROCM_DIR ROCm installation with clang and the HIP device libraries (default /opt/rocm)
# D4R_GPU_ARCH target GPU (default gfx1101): an RDNA3 (gfx110x) or RDNA4 (gfx120x) target; the kernels
# need wave32 WMMA, and kernels/common/wmma_layout.h picks the register layout per target
# D4R_GPU_ARCH target GPU (default gfx1101): an RDNA3 (gfx110x) or RDNA4 (gfx120x) target, where
# kernels/common/wmma_layout.h picks the WMMA register layout per target, or an RDNA2 (gfx103x)
# target: there only K's layers (software matrix products) and the texture kernels that
# need no WMMA (tex: K's natively translated hiluma output and input kernels) are built
# D4R_NATIVE_FP8 1 (RDNA4 only): the variant for ZLUDA's native FP8 WMMA (d4r.ini [Kernels] NativeFp8):
# M's layers on FP8 WMMA with NVIDIA's e4m3 activations, texture tails matching ZLUDA's
# D4R_ZLUDA_WMMA_FP8_NATIVE lowering. K is the same in both variants.
@@ -45,6 +47,12 @@ CLANG="$ROCM/lib/llvm/bin/clang++"
[[ -x "$CLANG" ]] || { echo "clang++ not found in $ROCM/lib/llvm/bin (set D4R_ROCM_DIR)" >&2; exit 2; }
mkdir -p "$OUT"
case "$WHAT" in all|k|l|m|tex|rr|rrswin) ;; *) echo "unknown kernel family: $WHAT" >&2; exit 2 ;; esac
# RDNA2 has no WMMA instruction: M/L's Swin layers, their texture tails and Ray Reconstruction call it directly
RDNA2=0
if [[ "$ARCH" == gfx103* ]]; then
RDNA2=1
case "$WHAT" in m|l|rr|rrswin) echo "$WHAT kernels need WMMA, which RDNA2 ($ARCH) does not have" >&2; exit 2 ;; esac
fi
# Never certify a directory containing older fast binaries as an accuracy set.
if [[ "$ACCURACY" == 1 ]] && compgen -G "$OUT/*.hsaco" >/dev/null &&
{ [[ ! -f "$OUT/d4r-accuracy.txt" ]] || [[ "$(cat "$OUT/d4r-accuracy.txt")" != 1 ]]; }; then
@@ -82,14 +90,15 @@ if [[ "$WHAT" == all || "$WHAT" == k ]]; then
echo "== DLSS 4 (preset K) transformer layers"
for src in "$HERE"/k/dltss_pwin_*.hip; do build_hip "$src"; done
fi
if [[ "$WHAT" == all || "$WHAT" == m || "$WHAT" == l ]]; then
if [[ "$RDNA2" == 0 && ( "$WHAT" == all || "$WHAT" == m || "$WHAT" == l ) ]]; then
echo "== DLSS 4.5 (presets L/M) shared Swin layers"
for src in "$HERE"/m/rrlite_*.hip; do build_hip "$src" "$([[ "$FP8" == 1 ]] && echo -DD4R_FP8_WMMA)"; done
fi
if [[ "$WHAT" == all || "$WHAT" == tex || "$WHAT" == l ]]; then
echo "== texture kernels (NVIDIA PTX with native parts)"
: "${D4R_DLSS_DLL:?set D4R_DLSS_DLL to nvngx_dlss.dll (310.7)}"
: "${D4R_ZLUDA_EMIT:?set D4R_ZLUDA_EMIT to d4r_emit from a ZLUDA build with patches/zluda}"
# RDNA2 builds only the PTX-to-HIP translations below, which ZLUDA does not compile
[[ "$RDNA2" == 1 ]] || : "${D4R_ZLUDA_EMIT:?set D4R_ZLUDA_EMIT to d4r_emit from a ZLUDA build with patches/zluda}"
PTX_DIR="${D4R_DLSS_PTX_DIR:-$HERE/extracted/ptx}"
if [[ -z "${D4R_DLSS_PTX_DIR:-}" ]]; then
python3 "$HERE/tools/extract_dlss_ptx.py" "$D4R_DLSS_DLL" "$PTX_DIR"
@@ -152,7 +161,10 @@ if [[ "$WHAT" == all || "$WHAT" == tex || "$WHAT" == l ]]; then
for range in hdr ldr; do native_ins+=("hiluma_engine_input_${depth}_${mv}_${range}_v2_rel"); done
done
done
for spec in "${specs[@]}"; do
# RDNA2: none of the ZLUDA-compiled texture builds above (their tails call WMMA, and the sust_only builds
# are not validated there); only the natively translated hiluma kernels below
[[ "$RDNA2" == 1 ]] && specs=()
for spec in "${specs[@]+"${specs[@]}"}"; do
IFS=: read -r kernel src mode <<< "$spec"
[[ "$ACCURACY" == 0 && " ${native_outs[*]} " == *" $kernel "* ]] && continue
# accuracy sets are wave32, except M's post and downsample kernels on RDNA4: their wave64 builds keep the
@@ -180,8 +192,13 @@ if [[ "$WHAT" == all || "$WHAT" == tex || "$WHAT" == l ]]; then
python3 "$NAT/ptx2hip.py" --ctile --as1 "$ptx" "$native_out" > "$NT/output_translated.hip"
python3 "$NAT/rewrite_output.py" "$NT/output_translated.hip" > "$NT/$native_out.hip"
depth_tile=(); [[ "$native_out" == *_mvhi_* ]] && depth_tile=(-DD4R_K_NO_DEPTH_TILE)
D4R_ROCM_DIR="$ROCM" D4R_GPU_ARCH="$ARCH" "$NAT/build_native.sh" "$NT/$native_out.hip" "$OUT/$native_out.hsaco" \
-DD4R_NATIVE_F2I "${depth_tile[@]}" -DD4R_AS1_STORES
# RDNA3/4: wave64 (FP32 dual issue; 0.49 -> 0.44 ms on an RX 7700 XT, same bytes). RDNA2 issues wave64
# in two passes, so it gets wave32 (no stack frame, 96 VGPRs), and WGP mode: a 256-thread workgroup
# then takes 2 of each SIMD's 10 wave slots instead of 4, so 10 waves fit per SIMD instead of 8
# (measured with RDNA2's occupancy on the RX 7700 XT: 0.596 -> 0.568 ms, same bytes).
wave=(); [[ "$RDNA2" == 1 ]] && wave=(WAVE=32 CUMODE=0)
env "${wave[@]}" D4R_ROCM_DIR="$ROCM" D4R_GPU_ARCH="$ARCH" "$NAT/build_native.sh" "$NT/$native_out.hip" \
"$OUT/$native_out.hsaco" -DD4R_NATIVE_F2I "${depth_tile[@]}" -DD4R_AS1_STORES
done
for native_in in "${native_ins[@]}"; do
ptx="$(ptx_of "$native_in")"; [[ -n "$ptx" ]] || { echo "no PTX defines $native_in" >&2; exit 2; }
@@ -192,7 +209,7 @@ if [[ "$WHAT" == all || "$WHAT" == tex || "$WHAT" == l ]]; then
done
fi
fi
if [[ "$WHAT" == rr || ( "$WHAT" == all && -n "${D4R_DLSSD_DLL:-}" ) ]]; then
if [[ "$WHAT" == rr || ( "$WHAT" == all && "$RDNA2" == 0 && -n "${D4R_DLSSD_DLL:-}" ) ]]; then
echo "== Ray Reconstruction texture kernels"
: "${D4R_DLSSD_DLL:?set D4R_DLSSD_DLL to the CUDA-capable nvngx_dlssd.dll}"
: "${D4R_ZLUDA_EMIT:?set D4R_ZLUDA_EMIT to d4r_emit from a patched ZLUDA build}"