Add DLSS accuracy mode and GLIBC 2.41 release builds
- Add default-off PreferAccuracy for all native kernel families, including RDNA4 FP8 variants. - Restore intermediate FP8 quantization, per-MMA FP16 rounding, denormal handling and NGX synchronization in accuracy mode. - Select separately marked accuracy kernels and use a separate JIT cache; reject mixed sets and never silently substitute fast kernels. - Add a pinned GLIBC 2.41 build environment for ZLUDA/LLVM, the DLLs and both kernel sets, with ABI checks and toolchain provenance. - Support parallel target builds and pre-extracted PTX; correct ROCm header paths and Clang-CL input handling. - Bump to 0.1.3 and update release notes, documentation and tests. Validation: 11 tests passed; all 912 kernels built; E/K/M GPU harness runs completed with accuracy off/on. Packaged libraries loaded under GLIBC 2.41 and require no GLIBC version newer than 2.38. RTX image-quality parity remains unverified. Fixes #6 Refs #6
This commit is contained in:
ayo committed
1 parent
b2b3781aca
commit
b645ef9096
25 files changed
+641
-105
No files matched your search
@@ -16,7 +16,7 @@ ln -sfn "$VULKAN_INCLUDE/vulkan" "$ROOT/build/vulkan-include/vulkan"
|
||||
ln -sfn "$VULKAN_INCLUDE/vk_video" "$ROOT/build/vulkan-include/vk_video"
|
||||
PARAM_OBJECT="$ROOT/build/d4r_ngx_param_msvc.obj"
|
||||
"$CLANG_CL" --target=x86_64-pc-windows-msvc /nologo /std:c++20 /O2 /c /GS- /GR- /EHs-c- /Zl \
|
||||
"/Fo$PARAM_OBJECT" "$ROOT/tools/d4r_ngx_param_msvc.cpp"
|
||||
"/Fo$PARAM_OBJECT" -- "$ROOT/tools/d4r_ngx_param_msvc.cpp"
|
||||
"$MINGW_CXX" -std=c++20 -O2 -Wall -Wextra -Wno-missing-field-initializers -I"$ROOT/build/vulkan-include" -shared -static -static-libgcc -static-libstdc++ \
|
||||
"$ROOT/tools/d4r_nvngx_shim.cpp" "$ROOT/tools/d4r_ngx_param_host.cpp" "$PARAM_OBJECT" \
|
||||
-o "$ROOT/build/d4r_nvngx.dll"
|
||||
|
||||
Executable
+111
@@ -0,0 +1,111 @@
|
||||
#!/usr/bin/env bash
|
||||
# Run inside packaging/build/Dockerfile.glibc241 with a recent official Rust toolchain and ROCm mounted.
|
||||
# Supply isolated, patched ZLUDA/vkd3d checkouts and the usual package_release.sh inputs.
|
||||
set -euo pipefail
|
||||
ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
|
||||
: "${D4R_RELEASE_BUILD_ROOT:?set the build output directory}"
|
||||
: "${D4R_ZLUDA_SRC:?set a build-local ZLUDA checkout with patches 0002-0007 applied}"
|
||||
: "${D4R_VKD3D_SRC:?set a build-local vkd3d-proton checkout with patch 0001 applied}"
|
||||
: "${D4R_ROCM_DIR:?set ROCm with clang and device libraries}"
|
||||
BUILD="$(realpath -m "$D4R_RELEASE_BUILD_ROOT")"
|
||||
[[ "$(getconf GNU_LIBC_VERSION)" == 'glibc 2.41' ]] || {
|
||||
echo "This release build requires GLIBC 2.41; use the pinned Debian build image" >&2; exit 2;
|
||||
}
|
||||
# Helper generation modifies its source checkout. Refuse the external source-cache directory.
|
||||
case "$(realpath "$D4R_ZLUDA_SRC")" in "$BUILD"/*) ;; *) echo "ZLUDA source must be inside $BUILD" >&2; exit 2 ;; esac
|
||||
case "$(realpath "$D4R_VKD3D_SRC")" in "$BUILD"/*) ;; *) echo "vkd3d source must be inside $BUILD" >&2; exit 2 ;; esac
|
||||
mkdir -p "$BUILD/logs"
|
||||
for source in "$D4R_ZLUDA_SRC/ext/llvm-project/llvm/CMakeLists.txt" "$D4R_ZLUDA_SRC/ext/HiGHS/CMakeLists.txt"; do
|
||||
[[ -f "$source" ]] || { echo "missing pinned source submodule: $source" >&2; exit 2; }
|
||||
done
|
||||
export CARGO_TARGET_DIR="$BUILD/zluda-target"
|
||||
export CARGO_BUILD_JOBS="${CARGO_BUILD_JOBS:-8}"
|
||||
export CMAKE_BUILD_PARALLEL_LEVEL="$CARGO_BUILD_JOBS"
|
||||
export LIBRARY_PATH="$D4R_ROCM_DIR/lib${D4R_ROCM_LINK_STUBS:+:$D4R_ROCM_LINK_STUBS}"
|
||||
export LD_LIBRARY_PATH="$D4R_ROCM_DIR/lib"
|
||||
export HIP_PATH="$D4R_ROCM_DIR"
|
||||
export ROCM_PATH="$D4R_ROCM_DIR"
|
||||
export HIP_CLANG_PATH="$D4R_ROCM_DIR/lib/llvm/bin"
|
||||
{
|
||||
getconf GNU_LIBC_VERSION
|
||||
rustc --version
|
||||
cargo --version
|
||||
gcc --version | head -1
|
||||
winegcc --version | head -1
|
||||
"$D4R_ROCM_DIR/lib/llvm/bin/clang++" --version | head -1
|
||||
} > "$BUILD/toolchain.txt"
|
||||
|
||||
ZLUDA_SOURCE_ROOT="$D4R_ZLUDA_SRC" ROCM_ROOT="$D4R_ROCM_DIR" \
|
||||
D4R_ZLUDA_PTX_HELPER_WORK="$BUILD/helpers" "$ROOT/scripts/build_zluda_ptx_helpers.sh" \
|
||||
> "$BUILD/logs/helpers.log" 2>&1
|
||||
echo 'Device helpers rebuilt'
|
||||
(cd "$D4R_ZLUDA_SRC" && cargo build --offline --locked --release -p zluda \
|
||||
&& cargo build --offline --locked --release -p ptx --example d4r_emit) \
|
||||
> "$BUILD/logs/zluda.log" 2>&1
|
||||
export D4R_ZLUDA_DIR="$CARGO_TARGET_DIR/release"
|
||||
export D4R_ZLUDA_EMIT="$D4R_ZLUDA_DIR/examples/d4r_emit"
|
||||
"$ROOT/scripts/check_glibc_compat.sh" 2.41 "$D4R_ZLUDA_DIR/libnvcuda.so"
|
||||
echo 'ZLUDA and the offline emitter rebuilt; GLIBC check passed'
|
||||
# A minimal ROCm compiler extraction may omit lld. Use the matching LLVM built above so
|
||||
# all GPU targets link with the same AMDGPU/ELF support, inside the compatible environment.
|
||||
for llvm_build in "$CARGO_TARGET_DIR"/release/build/llvm_zluda-*/out/build; do
|
||||
[[ -f "$llvm_build/build.ninja" ]] || continue
|
||||
ninja -j "$CARGO_BUILD_JOBS" -C "$llvm_build" lld > "$BUILD/logs/lld.log" 2>&1
|
||||
export PATH="$llvm_build/bin:$PATH"
|
||||
break
|
||||
done
|
||||
command -v lld >/dev/null || { echo 'missing AMDGPU linker' >&2; exit 2; }
|
||||
|
||||
"$ROOT/scripts/build_d4r_nvngx_shim.sh" > "$BUILD/logs/shim.log" 2>&1
|
||||
"$ROOT/scripts/build_wine_nvcuda_bridge.sh" > "$BUILD/logs/bridge.log" 2>&1
|
||||
"$ROOT/scripts/check_glibc_compat.sh" 2.41 "$ROOT/build/wine-nvcuda/x86_64-unix/nvcuda.dll.so"
|
||||
if [[ ! -f "$BUILD/vkd3d-build/build.ninja" ]]; then
|
||||
meson setup --cross-file "$D4R_VKD3D_SRC/build-win64.txt" --buildtype release \
|
||||
-Denable_tests=false "$BUILD/vkd3d-build" "$D4R_VKD3D_SRC" > "$BUILD/logs/vkd3d.log" 2>&1
|
||||
fi
|
||||
ninja -j "$CARGO_BUILD_JOBS" -C "$BUILD/vkd3d-build" >> "$BUILD/logs/vkd3d.log" 2>&1
|
||||
export D4R_VKD3D_DIR="$BUILD/vkd3d"
|
||||
mkdir -p "$D4R_VKD3D_DIR"
|
||||
x86_64-w64-mingw32-strip -o "$D4R_VKD3D_DIR/d3d12.dll" "$BUILD/vkd3d-build/libs/d3d12/d3d12.dll"
|
||||
x86_64-w64-mingw32-strip -o "$D4R_VKD3D_DIR/d3d12core.dll" "$BUILD/vkd3d-build/libs/d3d12core/d3d12core.dll"
|
||||
echo 'Shim, bridge and vkd3d-proton rebuilt'
|
||||
|
||||
export D4R_BUNDLE_TEX="$BUILD/kernels"
|
||||
export D4R_DLSS_PTX_DIR="$BUILD/ptx"
|
||||
python3 "$ROOT/kernels/tools/extract_dlss_ptx.py" "$D4R_BUNDLE_DLSS" "$D4R_DLSS_PTX_DIR" > "$BUILD/logs/extract.log"
|
||||
build_textures() {
|
||||
local arch="$1" folder fp8 accuracy out
|
||||
folders=("$arch")
|
||||
[[ "$arch" == gfx12* ]] && folders+=("$arch-fp8")
|
||||
for folder in "${folders[@]}"; do
|
||||
fp8=0
|
||||
[[ "$folder" == *-fp8 ]] && fp8=1
|
||||
for accuracy in 0 1; do
|
||||
out="$D4R_BUNDLE_TEX/$folder"
|
||||
[[ "$accuracy" == 1 ]] && out="$D4R_BUNDLE_TEX/accuracy/$folder"
|
||||
D4R_PREFER_ACCURACY="$accuracy" D4R_GPU_ARCH="$arch" D4R_NATIVE_FP8="$fp8" \
|
||||
D4R_DLSS_DLL="$D4R_BUNDLE_DLSS" "$ROOT/kernels/build.sh" tex "$out" \
|
||||
> "$BUILD/logs/tex-$folder-$accuracy.log" 2>&1
|
||||
echo "Texture kernels rebuilt: $folder accuracy=$accuracy"
|
||||
done
|
||||
done
|
||||
}
|
||||
pending=()
|
||||
failed=0
|
||||
for arch in ${D4R_GPU_ARCHS:-gfx1100 gfx1101 gfx1102 gfx1103 gfx1200 gfx1201}; do
|
||||
build_textures "$arch" &
|
||||
pending+=("$!")
|
||||
if (( ${#pending[@]} >= 4 )); then
|
||||
wait "${pending[0]}" || failed=1
|
||||
pending=("${pending[@]:1}")
|
||||
fi
|
||||
done
|
||||
for pid in "${pending[@]}"; do wait "$pid" || failed=1; done
|
||||
[[ "$failed" == 0 ]] || { echo 'Texture target build failed' >&2; exit 1; }
|
||||
python3 -m unittest discover -s "$ROOT/tests" -v > "$BUILD/logs/tests.log" 2>&1
|
||||
export D4R_SKIP_BUILD=1
|
||||
export D4R_MAX_GLIBC=2.41
|
||||
export D4R_BUILD_INFO="$BUILD/toolchain.txt"
|
||||
export D4R_PACKAGE_KERNEL_JOBS=4
|
||||
"$ROOT/scripts/package_release.sh" "$BUILD/dist" > "$BUILD/logs/package.log" 2>&1
|
||||
echo "Release packaged in $BUILD/dist"
|
||||
@@ -28,6 +28,7 @@ mkdir -p "$WORK_ROOT"
|
||||
SOURCE="$ZLUDA_SOURCE_ROOT/ptx/lib/zluda_ptx_impl.cpp"
|
||||
PTX_LIB="$ZLUDA_SOURCE_ROOT/ptx/lib"
|
||||
COMMON_FLAGS=(-DHIP_ENABLE_WARP_SYNC_BUILTINS -std=c++20 -Xclang -fdenormal-fp-math=dynamic
|
||||
--rocm-path="$ROCM_ROOT" -I"$ROCM_ROOT/include"
|
||||
-Wall -Wextra -Wsign-compare -Wconversion -x hip "$SOURCE" -nogpulib -O3
|
||||
-mno-wavefrontsize64 --offload-device-only --offload-arch=gfx1030 -emit-llvm -c
|
||||
-Xclang -mlink-bitcode-file -Xclang "$OCML" "${EXTRA_FLAGS[@]}")
|
||||
|
||||
@@ -75,6 +75,7 @@ def main(argv):
|
||||
return
|
||||
|
||||
env = {}
|
||||
env["D4R_PREFER_ACCURACY"] = "1" if flag("Kernels", "PreferAccuracy") else "0"
|
||||
|
||||
model = get("DLSS", "Model")
|
||||
if model is not None:
|
||||
|
||||
@@ -20,12 +20,17 @@
|
||||
# D4R_VKD3D_SRC vkd3d-proton source checkout, for its license files default ~/.cache/d4r-vkd3d-proton
|
||||
# D4R_ZLUDA_SRC ZLUDA source checkout, for its license files default: D4R_ZLUDA_DIR's ../d4r-zluda-upstream
|
||||
# SOURCE_DATE_EPOCH timestamp given to every packaged file default: the last commit's
|
||||
# D4R_BUILD_INFO optional build-toolchain/provenance text to include in d4r/source/
|
||||
# D4R_PACKAGE_KERNEL_JOBS independent target builds at once (default 1)
|
||||
# The zip also contains NVIDIA's files and the texture kernels built from NVIDIA's PTX; redistributing
|
||||
# those is up to whoever publishes it (they are not covered by d4r's license):
|
||||
# D4R_BUNDLE_DLSS nvngx_dlss.dll to include D4R_BUNDLE_NGX _nvngx.dll to include
|
||||
# D4R_BUNDLE_TEX directory with texture-kernel code objects (kernels/build.sh tex), one subdirectory
|
||||
# per target folder (gfx1101, gfx1201, gfx1201-fp8, ...), or a flat gfx1101 directory for
|
||||
# older builds
|
||||
# Accuracy texture sets go in accuracy/<target>/, built with D4R_PREFER_ACCURACY=1.
|
||||
# D4R_ZLUDA_EMIT d4r_emit from the patched ZLUDA build; required in full builds when an accuracy
|
||||
# texture set is not supplied in D4R_BUNDLE_TEX/accuracy/<target>.
|
||||
# D4R_BUNDLE_NVIDIA=0 leaves them out (d4r-VERSION-nonvidia.zip; users then add the two DLLs themselves).
|
||||
set -euo pipefail
|
||||
|
||||
@@ -121,12 +126,13 @@ for arch in $ARCHS; do
|
||||
folders+=("$arch")
|
||||
[[ "$arch" == gfx12* ]] && folders+=("$arch-fp8")
|
||||
done
|
||||
for folder in "${folders[@]}"; do
|
||||
build_target() {
|
||||
local folder="$1" arch fp8 tex_dir accurate accurate_tex f
|
||||
arch="${folder%-fp8}"
|
||||
fp8=0
|
||||
[[ "$folder" == *-fp8 ]] && fp8=1
|
||||
D4R_ROCM_DIR="$ROCM" D4R_GPU_ARCH="$arch" D4R_NATIVE_FP8="$fp8" "$ROOT/kernels/build.sh" k "$STAGE/d4r/kernels/$folder" >/dev/null
|
||||
D4R_ROCM_DIR="$ROCM" D4R_GPU_ARCH="$arch" D4R_NATIVE_FP8="$fp8" "$ROOT/kernels/build.sh" m "$STAGE/d4r/kernels/$folder" >/dev/null
|
||||
D4R_PREFER_ACCURACY=0 D4R_ROCM_DIR="$ROCM" D4R_GPU_ARCH="$arch" D4R_NATIVE_FP8="$fp8" "$ROOT/kernels/build.sh" k "$STAGE/d4r/kernels/$folder" >/dev/null
|
||||
D4R_PREFER_ACCURACY=0 D4R_ROCM_DIR="$ROCM" D4R_GPU_ARCH="$arch" D4R_NATIVE_FP8="$fp8" "$ROOT/kernels/build.sh" m "$STAGE/d4r/kernels/$folder" >/dev/null
|
||||
rm -f "$STAGE/d4r/kernels/$folder"/*.resolution.txt # empty LTO notes from clang's -save-temps
|
||||
if [[ "$VARIANT" == full ]]; then
|
||||
tex_dir=""
|
||||
@@ -143,7 +149,49 @@ for folder in "${folders[@]}"; do
|
||||
fi
|
||||
fi
|
||||
python3 "$ROOT/kernels/tools/kernel_manifest.py" "$STAGE/d4r/kernels/$folder" "${DLLS[@]}"
|
||||
|
||||
# Every release target also gets conservative network and texture variants. Do not copy fast
|
||||
# texture objects into this set: their compiler policy is fixed inside the binary.
|
||||
accurate="$STAGE/d4r/kernels/accuracy/$folder"
|
||||
D4R_PREFER_ACCURACY=1 D4R_ROCM_DIR="$ROCM" D4R_GPU_ARCH="$arch" D4R_NATIVE_FP8="$fp8" "$ROOT/kernels/build.sh" k "$accurate" >/dev/null
|
||||
D4R_PREFER_ACCURACY=1 D4R_ROCM_DIR="$ROCM" D4R_GPU_ARCH="$arch" D4R_NATIVE_FP8="$fp8" "$ROOT/kernels/build.sh" m "$accurate" >/dev/null
|
||||
if [[ "$VARIANT" == full ]]; then
|
||||
accurate_tex="$D4R_BUNDLE_TEX/accuracy/$folder"
|
||||
if [[ -f "$accurate_tex/d4r-accuracy.txt" && "$(cat "$accurate_tex/d4r-accuracy.txt")" == 1 ]]; then
|
||||
for f in "$accurate_tex"/*.hsaco; do
|
||||
[[ -f "$f" ]] || continue
|
||||
[[ -e "$accurate/$(basename "$f")" ]] || cp "$f" "$accurate/"
|
||||
done
|
||||
else
|
||||
: "${D4R_ZLUDA_EMIT:?set D4R_ZLUDA_EMIT or supply D4R_BUNDLE_TEX/accuracy/$folder}"
|
||||
D4R_PREFER_ACCURACY=1 D4R_ROCM_DIR="$ROCM" D4R_GPU_ARCH="$arch" D4R_NATIVE_FP8="$fp8" \
|
||||
D4R_DLSS_DLL="$D4R_BUNDLE_DLSS" "$ROOT/kernels/build.sh" tex "$accurate" >/dev/null
|
||||
fi
|
||||
fi
|
||||
if [[ "$VARIANT" == full ]]; then
|
||||
for f in "$STAGE/d4r/kernels/$folder"/*.hsaco; do
|
||||
[[ -f "$accurate/$(basename "$f")" ]] || {
|
||||
echo "missing accuracy variant of $(basename "$f") for $folder" >&2; exit 2;
|
||||
}
|
||||
done
|
||||
fi
|
||||
rm -f "$accurate"/*.resolution.txt
|
||||
python3 "$ROOT/kernels/tools/kernel_manifest.py" "$accurate" "${DLLS[@]}"
|
||||
}
|
||||
kernel_jobs="${D4R_PACKAGE_KERNEL_JOBS:-1}"
|
||||
[[ "$kernel_jobs" =~ ^[1-9][0-9]*$ ]] || { echo "D4R_PACKAGE_KERNEL_JOBS must be positive" >&2; exit 2; }
|
||||
pending=()
|
||||
kernel_failed=0
|
||||
for folder in "${folders[@]}"; do
|
||||
build_target "$folder" &
|
||||
pending+=("$!")
|
||||
if (( ${#pending[@]} >= kernel_jobs )); then
|
||||
wait "${pending[0]}" || kernel_failed=1
|
||||
pending=("${pending[@]:1}")
|
||||
fi
|
||||
done
|
||||
for pid in "${pending[@]}"; do wait "$pid" || kernel_failed=1; done
|
||||
[[ "$kernel_failed" == 0 ]] || { echo "native target build failed; no release ZIP created" >&2; exit 1; }
|
||||
|
||||
# licenses and sources
|
||||
ZLUDA_SRC="${D4R_ZLUDA_SRC:-$(dirname "$ZLUDA")/d4r-zluda-upstream}"
|
||||
@@ -168,6 +216,9 @@ file_version() { [[ -f "$1" ]] && strings -el "$1" | grep -A1 '^FileVersion$' |
|
||||
sed -e "s/@VERSION@/$VERSION/g" -e "s/@ZLUDA_COMMIT@/$ZLUDA_COMMIT/g" -e "s/@VKD3D_COMMIT@/$VKD3D_COMMIT/g" \
|
||||
-e "s/@DLSS_VERSION@/$(file_version "$STAGE/d4r/nvngx_dlss.dll")/g" -e "s/@NGX_VERSION@/$(file_version "$STAGE/d4r/ngx/_nvngx.dll")/g" \
|
||||
"$ROOT/packaging/SOURCES.txt" | variant > "$STAGE/d4r/source/SOURCES.txt"
|
||||
if [[ -n "${D4R_BUILD_INFO:-}" ]]; then
|
||||
cp "$D4R_BUILD_INFO" "$STAGE/d4r/source/BUILD_INFO.txt"
|
||||
fi
|
||||
sed -e "s/@VERSION@/$VERSION/g" "$ROOT/packaging/D4R_README.txt" | variant | sed 's/$/\r/' > "$STAGE/D4R_README.txt"
|
||||
|
||||
# One timestamp for every file (SOURCE_DATE_EPOCH, default the last commit): ZLUDA's kernel cache is keyed on
|
||||
|
||||
Reference in new issue
Block a user