ayo
0e851b7f90
- Add native preset K kernels for gfx1030–gfx1036 using software matrix products, with fast and accuracy builds and RDNA2 motion kernels. - Follow OptiScaler's DLSS and RR preset overrides, sanitize unsupported values and select the preset matching the feature's quality mode. - Enable FSR 4 under NVIDIA GPU spoofing by exposing real AMD PCI IDs to OptiScaler and FidelityFX modules; bundle AMD's loader and upscaler. - Keep K on native kernels in engine auto mode unless HIP is selected, and fall back to CUDA for M/L when shader_float8 is unavailable. - Add native-engine K GPU timings, preset recreation harness controls and regression coverage; fix the input-wait test's glibc name clash. - Update configuration, installer guidance and release documentation, simplify the README and move gameplay videos to docs/videos.md. RDNA2 kernels remain untested on RDNA2 hardware; software matrix arithmetic was validated against WMMA on RDNA3.
31 lines
1.5 KiB
Bash
Executable File
31 lines
1.5 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# Build d4r-owned motion processing kernels and embed them in the Wine bridge.
|
|
set -euo pipefail
|
|
ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
|
|
OUT="${1:-$ROOT/build/wine-nvcuda/generated}"
|
|
ROCM="${D4R_ROCM_DIR:-/opt/rocm}"
|
|
CLANG="$ROCM/lib/llvm/bin/clang++"
|
|
[[ -x "$CLANG" ]] || { echo "motion kernels need ROCm clang (D4R_ROCM_DIR)" >&2; exit 2; }
|
|
mkdir -p "$OUT"
|
|
for arch in gfx1030 gfx1031 gfx1032 gfx1033 gfx1034 gfx1035 gfx1036 gfx1100 gfx1101 gfx1102 gfx1103 gfx1200 gfx1201; do
|
|
"$CLANG" -x hip -nogpuinc -nogpulib --offload-device-only --offload-arch="$arch" \
|
|
--no-gpu-bundle-output -O3 -mno-wavefrontsize64 -o "$OUT/$arch.hsaco" \
|
|
"$ROOT/kernels/support/motion_dilate.hip"
|
|
done
|
|
python3 - "$OUT" <<'PY'
|
|
from pathlib import Path
|
|
import sys
|
|
root = Path(sys.argv[1])
|
|
lines = ['/* Generated from d4r-owned HIP source; do not edit. */', '#include <string.h>']
|
|
for p in sorted(root.glob('gfx*.hsaco')):
|
|
data = p.read_bytes()
|
|
lines.append(f'static const unsigned char motion_{p.stem}[] __attribute__((aligned(64))) = {{')
|
|
lines.extend(','.join(f'0x{x:02x}' for x in data[i:i+24]) + ',' for i in range(0,len(data),24))
|
|
lines.append('};')
|
|
lines.append('static const void* d4r_motion_image(const char* arch) {')
|
|
for p in sorted(root.glob('gfx*.hsaco')):
|
|
lines.append(f' if (strcmp(arch, "{p.stem}") == 0) return motion_{p.stem};')
|
|
lines.append(' return NULL;\n}')
|
|
(root/'d4r_motion_kernels.h').write_text('\n'.join(lines)+'\n')
|
|
PY
|