woutermans
74ce9d8f9a
Ray Reconstruction's eleven DLSS-D Swin layers still run ZLUDA's compile of NVIDIA's PTX; at 1280x720 -> 3840x2160 on gfx1201 they are 30.2 of a 31.6 ms frame. The denoiser's high-fidelity output kernel is the first one with a native replacement: make_ptx.py replaces its whole-texel RGBA16F store (sust.b.2d.v4.b16.zero) through d4r_sust_v4b16, kernels/build.sh builds the pair as the `rr` family, and packaging builds it into every target folder including the RDNA4 FP8 ones. Both libraries define modules named cuda_dldn_engine_*, with different text, so one manifest cannot take the union of their hashes: kernel_manifest.py now takes the denoiser DLL as --rr-dll and lets only its hashes authorize a cuda_dldn_engine_* binary, and package_release.sh passes it when the denoiser is bundled. Verified in the D3D12 harness with Ray Reconstruction at 1280x720 -> 3840x2160: the output kernel drops from 1.44 to 1.00 ms/frame and the 66 MB raw output is byte-identical to the run with every kernel translated. docs/native-kernels.md gains the denoiser family, the per-kernel cost table and the instruction counts that show why the Swin layers are the remaining work.
63 lines
2.9 KiB
Python
63 lines
2.9 KiB
Python
"""Native SR code must never be authorized by a colliding denoiser entry."""
|
|
import importlib.util
|
|
from pathlib import Path
|
|
import struct
|
|
import subprocess
|
|
import sys
|
|
import tempfile
|
|
import unittest
|
|
|
|
ROOT = Path(__file__).resolve().parents[1]
|
|
TOOLS = ROOT / 'kernels/tools'
|
|
sys.path.insert(0, str(TOOLS))
|
|
spec = importlib.util.spec_from_file_location('d4r_kernel_manifest', TOOLS / 'kernel_manifest.py')
|
|
manifest = importlib.util.module_from_spec(spec)
|
|
spec.loader.exec_module(manifest)
|
|
|
|
|
|
def fatbin(ptx):
|
|
entry = bytearray(64)
|
|
struct.pack_into('<HHIQ', entry, 0, 1, 0, 64, len(ptx))
|
|
payload = entry + ptx
|
|
return struct.pack('<IHHQ', 0xBA55ED50, 1, 16, len(payload)) + payload
|
|
|
|
|
|
class KernelManifestTests(unittest.TestCase):
|
|
def test_denoiser_owned_name_comes_only_from_the_denoiser_dll(self):
|
|
# A cuda_dldn_engine_* kernel may only be authorized by the DLL passed as --rr-dll; the
|
|
# Super Resolution libraries define names of that shape too, and their modules differ.
|
|
sr = b'.visible .entry dl4rt_input_kernel() { ret; }\n'
|
|
rr = (b'.visible .entry dl4rt_input_kernel() { mov.u32 %r1, 1; ret; }\n'
|
|
b'.visible .entry cuda_dldn_engine_swin_enc1_kernel() { ret; }\n')
|
|
with tempfile.TemporaryDirectory() as directory:
|
|
root = Path(directory)
|
|
(root / 'sr.dll').write_bytes(fatbin(sr))
|
|
(root / 'rr.dll').write_bytes(fatbin(rr))
|
|
for name in ('dl4rt_input_kernel', 'cuda_dldn_engine_swin_enc1_kernel'):
|
|
(root / (name + '.hsaco')).touch()
|
|
subprocess.run([sys.executable, str(TOOLS / 'kernel_manifest.py'), str(root),
|
|
str(root / 'sr.dll'), '--rr-dll', str(root / 'rr.dll')],
|
|
check=True, capture_output=True)
|
|
rows = [line.split() for line in (root / 'd4r-kernels.txt').read_text().splitlines()
|
|
if line and not line.startswith('#')]
|
|
self.assertEqual(rows, [
|
|
['cuda_dldn_engine_swin_enc1_kernel', f'{manifest.fnv1a64(rr):016x}'],
|
|
['dl4rt_input_kernel', f'{manifest.fnv1a64(sr):016x}'],
|
|
])
|
|
|
|
def test_rr_only_input_refuses_unproven_sr_binary(self):
|
|
rr = b'.visible .entry dl4rt_input_kernel() { ret; }\n'
|
|
with tempfile.TemporaryDirectory() as directory:
|
|
root = Path(directory)
|
|
(root / 'rr.dll').write_bytes(fatbin(rr))
|
|
(root / 'dl4rt_input_kernel.hsaco').touch()
|
|
result = subprocess.run([sys.executable, str(TOOLS / 'kernel_manifest.py'), str(root),
|
|
'--rr-dll', str(root / 'rr.dll')], capture_output=True, text=True)
|
|
self.assertNotEqual(result.returncode, 0)
|
|
self.assertIn('no DLL defines dl4rt_input_kernel', result.stderr)
|
|
self.assertFalse((root / 'd4r-kernels.txt').exists())
|
|
|
|
|
|
if __name__ == '__main__':
|
|
unittest.main()
|