ayo
ac4ee6c225
Add a native D3D12 FSR Ray Regeneration route for gfx1200/gfx1201, using the game's device and queue with embedded HLSL guide preparation and output composition. Preserve the vkd3d compatibility route for RDNA3 and expose explicit route overrides and diagnostics. Improve Windows runtime compatibility: - Retry rejected application-ID initialization with a project identity. - Defer expensive RR backend creation until feature creation. - Recover from transient submission failures without disabling later frames. - Add shared-buffer export fallbacks through explicit heaps and a private device on the same adapter. - Safely evict old RR descriptor sets when input views change. - Treat requested RR presets as hints when a configured model is available. - Expand SR/RR input formats and handle diffuse/specular hit distances, packed normals, depth-stencil resources, and unused FSR guides. Reduce SR overhead by batching output downloads and format conversion under one completion wait. Optimize strict M enc2/tube attention with bounded FP32 accumulation and the original FP64 fallback for ambiguous rounding cases. Extend RDNA4 tooling with gfx1200/gfx1201 native FP8 RR model builds, capability checks, architecture-aware deployment, and experimental K/M kernel paths. Require matching model and runtime arithmetic families. Add optional embedded FSR shader optimizations keyed by shader hash and exact original SPIR-V contents. Preserve reflected metadata and record optimizer provenance, artifact hashes, and cache identity. Simplify Windows installation with automatic backend dependency downloads, download progress and ETA, backed-up absolute OptiScaler library paths, and recovery from interrupted RR model builds. Add build-kernels.bat and a kernels-only build matrix for all eleven registered RDNA targets, with code-object target validation and SHA256 manifests. Expand conversion probes, numerical stress tests, temporal benchmark tooling, installer/deployment tests, and setup documentation. Document synthetic regression and timing results, experimental build options, and remaining RDNA4 hardware validation requirements.
255 lines
17 KiB
Python
255 lines
17 KiB
Python
"""Run the synthetic production NGX feature-13 harness in a bounded process."""
|
|
import argparse
|
|
import hashlib
|
|
import json
|
|
import os
|
|
import shutil
|
|
from pathlib import Path
|
|
import subprocess
|
|
import struct
|
|
|
|
|
|
def main():
|
|
parser = argparse.ArgumentParser(description=__doc__)
|
|
parser.add_argument('--gpu-arch', choices=('gfx1101', 'gfx1200', 'gfx1201'), default='gfx1101')
|
|
parser.add_argument('--contracts', action='store_true', help='also check capability readiness and negative contracts')
|
|
parser.add_argument('--inherited', action='store_true', help='inherit access from a preceding list in the same submission batch')
|
|
parser.add_argument('--enhanced', action='store_true', help='exercise enhanced texture access and restoration')
|
|
parser.add_argument('--split', action='store_true', help='reject a legacy split barrier, then complete the pair and evaluate')
|
|
parser.add_argument('--unavailable', choices=('disabled', 'missing-model', 'fsr'), help='test unavailable RR configuration without inference')
|
|
parser.add_argument('--without-sr', action='store_true', help='remove SR dependency configuration and require native RR execution')
|
|
parser.add_argument('--float-guides', action='store_true', help='exercise equivalent float32 color/motion/normals and scalar roughness')
|
|
parser.add_argument('--switch-guides', action='store_true', help='alternate canonical and float guide formats without recreating feature')
|
|
parser.add_argument('--auto-exposure', action='store_true', help='also set the public NGX AutoExposure creation flag')
|
|
parser.add_argument('--dynamic-extents', action='store_true', help='read per-frame bounded render dimensions from dynamic-extents.txt')
|
|
parser.add_argument('--two-features', action='store_true', help='evaluate two live independent RR features on each game command list')
|
|
parser.add_argument('--max-resources', action='store_true', help='retain creation-sized textures while dynamic input rectangles change')
|
|
parser.add_argument('--output-float32', action='store_true', help='validate GPU half-to-float32 output conversion against widened standalone output')
|
|
parser.add_argument('--switch-output', action='store_true', help='alternate half/float32 output formats without recreating feature')
|
|
parser.add_argument('--depth-format', choices=('r32', 'r32-typeless', 'd32', 'd32s8', 'd32s8-typeless'), default='r32', help='exercise native depth-plane copy format')
|
|
parser.add_argument('--player-config', action='store_true', help='stage a private player folder and select RR only through d4r.ini')
|
|
parser.add_argument('--use-existing-ini', action='store_true', help='preserve the selected runtime INI when staging player validation')
|
|
for name in ('probe', 'shim', 'runtime', 'core', 'dlss', 'model', 'inputs', 'reference', 'output'):
|
|
parser.add_argument('--' + name, required=True, type=lambda value: Path(value).resolve())
|
|
args = parser.parse_args()
|
|
if args.use_existing_ini and not args.player_config:
|
|
parser.error('--use-existing-ini requires --player-config')
|
|
if args.player_config and (args.without_sr or args.unavailable or not args.contracts):
|
|
parser.error('--player-config requires --contracts, configured SR dependencies and native RR')
|
|
if args.enhanced and args.split:
|
|
parser.error('--split currently covers legacy barriers; use a separate --enhanced run')
|
|
if args.without_sr and (args.unavailable or not args.contracts):
|
|
parser.error('--without-sr requires --contracts and a configured native RR backend')
|
|
if args.switch_guides and not args.float_guides:
|
|
parser.error('--switch-guides requires --float-guides')
|
|
if args.dynamic_extents and (args.float_guides or args.switch_guides or args.depth_format != 'r32'):
|
|
parser.error('--dynamic-extents currently uses canonical guides and R32 depth')
|
|
if args.max_resources and not args.dynamic_extents:
|
|
parser.error('--max-resources requires --dynamic-extents')
|
|
if args.switch_output and (not args.output_float32 or args.max_resources):
|
|
parser.error('--switch-output requires --output-float32 and cannot retain max resources')
|
|
build = Path(__file__).resolve().parents[2] / 'build'
|
|
if not args.output.is_relative_to(build.resolve()):
|
|
parser.error('output must stay under ignored build/')
|
|
args.output.mkdir(parents=True, exist_ok=False)
|
|
env = {key: value for key, value in os.environ.items()
|
|
if not key.startswith('D4R_') and key not in ('ZLUDA_CUDA_LIB', 'ZLUDA_LOG_DIR', 'ZLUDA_CACHE_DIR')}
|
|
runtime = args.runtime
|
|
native = runtime / 'native'
|
|
if (native / args.gpu_arch).is_dir():
|
|
native = native / args.gpu_arch
|
|
env.update(HIP_PATH=str(runtime / 'hip'), D4R_HIP_ROOT=str(runtime / 'hip'), D4R_NVCUDA_DLL=str(runtime / 'zluda/nvcuda.dll'),
|
|
ZLUDA_CUDA_LIB=str(runtime / 'zluda/nvcuda.dll'), D4R_DLSS_DLL=str(args.dlss),
|
|
D4R_NGX_CORE=str(args.core), D4R_NVAPI_DLL=str(runtime / 'nvapi/nvapi64.dll'),
|
|
D4R_NVAPI_BACKEND=str(runtime / 'nvapi/backend/nvapi64.dll'),
|
|
D4R_FORMAT_MODULE=str(runtime / f'pixel_convert_{args.gpu_arch}.hsaco'),
|
|
D4R_ZLUDA_NATIVE_DIR=str(native), D4R_QUIET_API='1',
|
|
D4R_ZLUDA_WMMA='1', D4R_ZLUDA_WMMA_F16_REFERENCE='1',
|
|
D4R_NGX_DATA_DIR=str(args.output / 'ngx-data'), D4R_RR_BACKEND='native', D4R_RR_MODEL_DIR=str(args.model))
|
|
if args.unavailable == 'disabled':
|
|
env.pop('D4R_RR_BACKEND')
|
|
elif args.unavailable == 'missing-model':
|
|
missing = args.output / 'missing-model'
|
|
env['D4R_RR_MODEL_DIR'] = str(missing)
|
|
elif args.unavailable == 'fsr':
|
|
env['D4R_RR_BACKEND'] = 'fsr'
|
|
if args.without_sr:
|
|
for key in ('HIP_PATH', 'D4R_HIP_ROOT', 'D4R_NVCUDA_DLL', 'ZLUDA_CUDA_LIB', 'D4R_DLSS_DLL',
|
|
'D4R_NGX_CORE', 'D4R_NVAPI_DLL', 'D4R_NVAPI_BACKEND', 'D4R_FORMAT_MODULE', 'D4R_ZLUDA_NATIVE_DIR'):
|
|
env.pop(key, None)
|
|
else:
|
|
env['PATH'] = str(runtime / 'hip/bin') + os.pathsep + str(runtime / 'zluda') + os.pathsep + env['PATH']
|
|
command = [str(args.probe), str(args.shim), str(args.inputs), str(args.reference),
|
|
str(args.output / 'frames'), str(args.model)]
|
|
if args.player_config:
|
|
staged = args.output / 'player'
|
|
shutil.copytree(runtime, staged)
|
|
shutil.copy2(args.shim, staged / 'd4r_nvngx.dll')
|
|
for source, relative in ((args.core, 'ngx/_nvngx.dll'), (args.dlss, 'dlss/nvngx_dlss.dll')):
|
|
target = staged / relative
|
|
target.parent.mkdir(parents=True, exist_ok=True)
|
|
shutil.copy2(source, target)
|
|
if not args.use_existing_ini:
|
|
config = (Path(__file__).resolve().parents[2] / 'packaging/windows/d4r.ini').read_text()
|
|
config = config.replace('Backend = off', 'Backend = native').replace('ModelDir = auto', 'ModelDir = ' + str(args.model))
|
|
(staged / 'd4r.ini').write_text(config)
|
|
env = {key: value for key, value in os.environ.items()
|
|
if not key.startswith('D4R_') and key not in ('HIP_PATH', 'ZLUDA_CUDA_LIB', 'ZLUDA_LOG_DIR', 'ZLUDA_CACHE_DIR')}
|
|
command[1] = str(staged / 'd4r_nvngx.dll')
|
|
mode = '-'.join(name for name in ('contracts', 'inherited', 'enhanced', 'split', 'unavailable') if getattr(args, name))
|
|
if args.without_sr:
|
|
mode += '-without-sr'
|
|
if args.float_guides:
|
|
mode += '-float-guides'
|
|
if args.switch_guides:
|
|
mode += '-switch-guides'
|
|
if args.auto_exposure:
|
|
mode += '-auto-exposure'
|
|
if args.dynamic_extents:
|
|
mode += '-dynamic-extents'
|
|
if args.two_features:
|
|
mode += '-two-features'
|
|
if args.max_resources:
|
|
mode += '-max-resources'
|
|
if args.output_float32:
|
|
mode += '-output-float32'
|
|
if args.switch_output:
|
|
mode += '-switch-output'
|
|
if args.depth_format != 'r32':
|
|
mode += '-depth-' + args.depth_format
|
|
if mode:
|
|
command.append(mode)
|
|
report = {'passed': False, 'gameAccessed': False, 'qualityReference': False,
|
|
'artifacts': {str(path): hashlib.sha256(path.read_bytes()).hexdigest()
|
|
for path in (args.probe, args.shim, args.core, args.dlss)}}
|
|
try:
|
|
with (args.output / 'stdout.log').open('wb') as out, (args.output / 'stderr.log').open('wb') as err:
|
|
result = subprocess.run(command, env=env, stdout=out, stderr=err, timeout=180)
|
|
report['exitCode'] = result.returncode
|
|
text = (args.output / 'stdout.log').read_text(errors='replace')
|
|
if args.unavailable:
|
|
if result.returncode or 'PASS RR_NGX_UNAVAILABLE' not in text:
|
|
raise RuntimeError('Unavailable NGX RR checks failed; inspect ' + str(args.output))
|
|
report.update(passed=True, unavailable=args.unavailable, rrAvailable=False, srAvailable=True,
|
|
creationRejected=True, frames=0)
|
|
print('PASS NGX RR unavailable=' + args.unavailable + ' sr_available=1')
|
|
return
|
|
if result.returncode or 'PASS RR_NGX_LIFECYCLE' not in text:
|
|
raise RuntimeError('NGX RR harness failed; inspect ' + str(args.output))
|
|
if args.contracts and 'PASS RR_NGX_CONTRACTS' not in text:
|
|
raise RuntimeError('NGX RR contract checks incomplete')
|
|
if args.inherited and 'PASS RR_NGX_INHERITED' not in text:
|
|
raise RuntimeError('NGX RR inherited access checks incomplete')
|
|
for name in ('enhanced', 'split'):
|
|
if getattr(args, name) and 'PASS RR_NGX_' + name.upper() not in text:
|
|
raise RuntimeError('NGX RR ' + name + ' access checks incomplete')
|
|
if args.without_sr and ('PASS RR_NGX_WITHOUT_SR' not in text or 'D4R_RUNTIME platform=Windows' in text):
|
|
raise RuntimeError('NGX RR did not prove execution without initialized SR runtime')
|
|
if args.float_guides and 'PASS RR_NGX_FLOAT_GUIDES' not in text:
|
|
raise RuntimeError('NGX RR alternate float guide checks incomplete')
|
|
if args.switch_guides and 'PASS RR_NGX_SWITCH_GUIDES' not in text:
|
|
raise RuntimeError('NGX RR temporal guide-format switching checks incomplete')
|
|
if args.auto_exposure and 'PASS RR_NGX_FLAGS' not in text:
|
|
raise RuntimeError('NGX RR creation flag checks incomplete')
|
|
if args.dynamic_extents:
|
|
extents = [tuple(map(int, line.split())) for line in (args.inputs / 'dynamic-extents.txt').read_text().splitlines()]
|
|
if 'PASS RR_NGX_DYNAMIC_EXTENTS' not in text:
|
|
raise RuntimeError('NGX RR dynamic extent checks incomplete')
|
|
for index, (width, height) in enumerate(extents):
|
|
if f'RR_NGX_EXTENT index={index} render={width}x{height} exact=1' not in text:
|
|
raise RuntimeError('Incomplete NGX RR dynamic extent output')
|
|
creation = tuple(map(int, (args.inputs / 'frames.txt').read_text().splitlines()[0].split()[1:3]))
|
|
previous, expected_resizes = creation, []
|
|
for size in extents:
|
|
if size != previous:
|
|
expected_resizes.extend([f'D4R_RR_RESIZE render={size[0]}x{size[1]} history_reset=1 model_reused=1 packet_reused=1'] * (2 if args.two_features else 1))
|
|
previous = size
|
|
diagnostics = args.output / ('player/d4r_nvngx.log' if args.player_config else 'stderr.log')
|
|
actual_resizes = [line for line in diagnostics.read_text().splitlines() if line.startswith('D4R_RR_RESIZE ')]
|
|
if actual_resizes != expected_resizes:
|
|
raise RuntimeError('NGX RR resize operations differ from requested sequence')
|
|
if args.contracts and 'RR_NGX_EXTENT_BOUNDS' not in text:
|
|
raise RuntimeError('NGX RR extent bounds checks missing')
|
|
report['dynamicExtents'] = extents
|
|
report.update(geometryChanges=len(expected_resizes), modelReusedAcrossResize=True,
|
|
packetReusedAcrossResize=True, historyResetOnResize=True)
|
|
if args.max_resources:
|
|
if 'PASS RR_NGX_MAX_RESOURCES' not in text:
|
|
raise RuntimeError('NGX RR creation-sized dynamic input checks missing')
|
|
report['creationSizedInputResourcesRetained'] = True
|
|
depth_values = {'r32-typeless': 39, 'd32': 40, 'd32s8': 20, 'd32s8-typeless': 19}
|
|
if args.depth_format != 'r32':
|
|
marker = f'PASS RR_NGX_DEPTH format={depth_values[args.depth_format]} stencil_preserved={int(args.depth_format.startswith("d32s8"))}'
|
|
if marker not in text:
|
|
raise RuntimeError('NGX RR depth-format/stencil checks incomplete')
|
|
if args.contracts and args.depth_format.startswith('d32') and 'RR_NGX_DEPTH_SUBRECT cropped_rejected=1' not in text:
|
|
raise RuntimeError('NGX RR cropped depth-stencil rejection missing')
|
|
expected = [line.split()[1] + '-out.bin' for line in (args.inputs / 'frames.txt').read_text().splitlines()
|
|
if line.startswith('frame ')]
|
|
outputs = sorted(path.name for path in (args.output / 'frames').glob('*-out.bin'))
|
|
if outputs != sorted(expected):
|
|
raise RuntimeError('Incomplete NGX RR output set')
|
|
def reference_bytes(name):
|
|
data = (args.reference / name).read_bytes()
|
|
if args.output_float32 and (not args.switch_output or expected.index(name) % 2):
|
|
return b''.join(struct.pack('<f', value[0]) for value in struct.iter_unpack('<e', data))
|
|
return data
|
|
for name in expected:
|
|
if (args.output / 'frames' / name).read_bytes() != reference_bytes(name):
|
|
raise RuntimeError('NGX RR reference mismatch: ' + name)
|
|
if args.two_features:
|
|
if 'PASS RR_NGX_TWO_FEATURES' not in text:
|
|
raise RuntimeError('NGX RR two-feature lifecycle checks incomplete')
|
|
peer_outputs = sorted(path.name for path in (args.output / 'frames/peer').glob('*-out.bin'))
|
|
if peer_outputs != sorted(expected):
|
|
raise RuntimeError('Incomplete first-feature output set')
|
|
for index, name in enumerate(expected):
|
|
if (args.output / 'frames/peer' / name).read_bytes() != reference_bytes(name):
|
|
raise RuntimeError('NGX RR first-feature reference mismatch: ' + name)
|
|
if f'RR_NGX_PEER_FRAME index={index} exact=1 both_features_live=1' not in text:
|
|
raise RuntimeError('NGX RR first-feature validation incomplete')
|
|
report.update(liveFeatures=2, bothFeaturesStandaloneExact=True, separateVulkanDevices=True,
|
|
twoDelayedBoundariesPerCommandList=True, bothReleasedBeforeFinalSubmit=True)
|
|
if args.output_float32:
|
|
if 'PASS RR_NGX_OUTPUT_FLOAT32' not in text:
|
|
raise RuntimeError('NGX RR float32 output checks missing')
|
|
report.update(outputFormat='RGBA32F', gpuOutputConversion=True, widenedHalfReferenceExact=True)
|
|
if args.switch_output:
|
|
if 'PASS RR_NGX_SWITCH_OUTPUT' not in text:
|
|
raise RuntimeError('NGX RR temporal output format switching checks missing')
|
|
report.update(outputFormat='alternating RGBA16F/RGBA32F', outputFormatSwitchWithoutFeatureRecreation=True)
|
|
optional_names = ('hitdistance', 'disocclusion', 'sss', 'particles')
|
|
optional_frames = {name: sum((args.inputs / (frame.removesuffix('-out.bin') + '-' + name + '.bin')).is_file()
|
|
for frame in expected) for name in optional_names}
|
|
masks = [sum(1 << index for index, name in enumerate(optional_names)
|
|
if (args.inputs / (frame.removesuffix('-out.bin') + '-' + name + '.bin')).is_file())
|
|
for frame in expected]
|
|
frame_lines = [line.split() for line in (args.inputs / 'frames.txt').read_text().splitlines() if line.startswith('frame ')]
|
|
for index, mask in enumerate(masks):
|
|
depth_mode = int(frame_lines[index][8])
|
|
marker = (f'RR_NGX_FRAME index={index} snapshot_mutated=1 exact=1 optional_mask={mask}'
|
|
f' hardware_depth={int(bool(depth_mode & 2))} depth_inverted={int(bool(depth_mode & 1))}')
|
|
if marker not in text:
|
|
raise RuntimeError('Incomplete NGX optional-guide/depth setting checks')
|
|
report.update(passed=True, frames=len(expected), standaloneExact=True, contracts=args.contracts, inherited=args.inherited,
|
|
enhanced=args.enhanced, split=args.split,
|
|
withoutSr=args.without_sr,
|
|
floatGuides=args.float_guides,
|
|
switchGuides=args.switch_guides,
|
|
creationFlags=int(next(line.split('flags=')[1] for line in text.splitlines()
|
|
if line.startswith('RR_NGX_CREATION flags='))),
|
|
optionalGuideFrames=optional_frames, optionalMasks=masks,
|
|
depthFormat=args.depth_format, stencilPreserved=args.depth_format.startswith('d32s8'),
|
|
hardwareDepthFrames=sum(bool(int(line[8]) & 2) for line in frame_lines),
|
|
playerConfig=args.player_config,
|
|
preservedPlayerIni=args.use_existing_ini,
|
|
invertedDepthFrames=sum(bool(int(line[8]) & 1) for line in frame_lines),
|
|
snapshotMutation=True, releaseBeforeSubmit=True, parameterDestroyBeforeSubmit=True)
|
|
print('PASS NGX RR frames=' + str(len(expected)) + ' standalone_exact=1')
|
|
finally:
|
|
(args.output / 'summary.json').write_text(json.dumps(report, indent=2) + '\n')
|
|
|
|
|
|
if __name__ == '__main__':
|
|
main()
|